From 15db197a3e7f189a897545aca7fdea32c95ce5ea Mon Sep 17 00:00:00 2001 From: Aki Date: Fri, 18 Oct 2024 12:18:55 +0800 Subject: [PATCH 01/15] update ai landing page to include PaaS section --- .../artificial intelligence/_index.md | 27 ++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/docs/content/patterns/artificial intelligence/_index.md b/docs/content/patterns/artificial intelligence/_index.md index f78bb90fb..a18e0c2cd 100644 --- a/docs/content/patterns/artificial intelligence/_index.md +++ b/docs/content/patterns/artificial intelligence/_index.md @@ -7,6 +7,31 @@ geekdocCollapseSection: true There are numerous ways to implement AI solution on Azure, and each comes with its own monitoring solution. Monitoring AI solutions involves a combination of the infra or paas resources, along with monitoring any utilization metrics that can be exposed through the platform or other tooling. This page will summarize the recommended monitoring solutions for different scenarios. -### AI on Infrastructure (BYOM) +### AI on Azure platforms (PaaS) + +Common AI Ready infrastructure on Azure may include services including Azure AI Hub, Azure AI Services including Azure OpenAI, AI Search etc. Specific workloads like Azure Kubernetes Services, API Management, App Services are also used to build enterprise level AI applications. Below table lists quick links to alert guidelines to most commonly used services, for other Azure service in your architecture, refer to the [Azure Resource](../../../../azure-monitor-baseline-alerts/services/) which provides more comprehensive lists. + +| Services | Resource Type | +| --- | --- | +| Azure AI Studio Hub/Azure Machine Learning Hub | [Microsoft.MachineLearningServices/workspaces](../../../../azure-monitor-baseline-alerts/services/MachineLearningServices/workspaces/) | +| Azure AI Search | [Microsoft.Search/searchServices](../../../../azure-monitor-baseline-alerts/services/Search/searchServices/) | +| Azure AI Services | [Microsoft.CognitiveServices/accounts](../../../../azure-monitor-baseline-alerts/services/CognitiveServices/accounts) | +| Azure Kubernetes Services | [Microsoft.ContainerService/managedClusters](../../../../azure-monitor-baseline-alerts/services/ContainerService/managedClusters/) | +| Azure App Services | [Microsoft.Web/sites](../../../../azure-monitor-baseline-alerts/services/Web/sites/) | +| Azure API Management | [lMicrosoft.ApiManagement/service](../../../../azure-monitor-baseline-alerts/services/ApiManagement/service/) | +| Azure Container Apps | [Microsoft.App/containerApps](../../../../azure-monitor-baseline-alerts/services/App/containerApps//) | +| Azure Functions Apps | [Microsoft.Web/sites](../../../../azure-monitor-baseline-alerts/services/Web/sites/) | +| Azure Cosmos DB | [Microsoft.DocumentDB/databaseAccounts](../../../../azure-monitor-baseline-alerts/services/DocumentDB/databaseAccounts/) | +| Azure SQL Database - managedInstances | [Microsoft.Sql/managedInstances](../../../../azure-monitor-baseline-alerts/services/Sql/managedInstances/) | +| Azure SQL Database - server | [Microsoft.Sql/servers/databases](../../../../azure-monitor-baseline-alerts/services/Sql/servers/) | +| Azure Database for MySQL | [Microsoft.DBforMySQL/servers](../../../../azure-monitor-baseline-alerts/services/DBforMySQL/servers/) | +| Azure Database for PostgreSQL | [Microsoft.DBforPostgreSQL/servers](../../../../azure-monitor-baseline-alerts/services/DBforPostgreSQL/servers//) | + +### AI on Azure infrastructure (IaaS) Running AI workloads on Azure infrastructure involves monitoring each of the components of the solution, including virtual machines, storage, and networking. Refer to the defined metrics in [HPC](../../specialized/hpc/Alerting-and-Monitoring.md). For monitoring the GPU/CPU metrics, use [Moneo](https://github.com/Azure/Moneo) + + +### AI Specialized Workload Patterns + +#### GPT-RAG (coming soon) From d6c6eb229b4b30099c7473346eb32c54f01cdd2d Mon Sep 17 00:00:00 2001 From: Jan Faurskov <22591930+jfaurskov@users.noreply.github.com> Date: Tue, 29 Oct 2024 12:15:48 +0100 Subject: [PATCH 02/15] Initial commit --- .github/ISSUE_TEMPLATE/amba-alz-issue.yml | 42 +++++++++++++++++++ .github/ISSUE_TEMPLATE/amba-avd-issue.yml | 42 +++++++++++++++++++ .github/ISSUE_TEMPLATE/amba-avs-issue.yml | 42 +++++++++++++++++++ .../ISSUE_TEMPLATE/amba-workload-issue.yml | 42 +++++++++++++++++++ .github/ISSUE_TEMPLATE/question_feedback.yml | 24 ----------- 5 files changed, 168 insertions(+), 24 deletions(-) create mode 100644 .github/ISSUE_TEMPLATE/amba-alz-issue.yml create mode 100644 .github/ISSUE_TEMPLATE/amba-avd-issue.yml create mode 100644 .github/ISSUE_TEMPLATE/amba-avs-issue.yml create mode 100644 .github/ISSUE_TEMPLATE/amba-workload-issue.yml delete mode 100644 .github/ISSUE_TEMPLATE/question_feedback.yml diff --git a/.github/ISSUE_TEMPLATE/amba-alz-issue.yml b/.github/ISSUE_TEMPLATE/amba-alz-issue.yml new file mode 100644 index 000000000..106de85eb --- /dev/null +++ b/.github/ISSUE_TEMPLATE/amba-alz-issue.yml @@ -0,0 +1,42 @@ +name: AMBA - ALZ Pattern Issue 🚀 +description: Have an issue, question or suggestion for the AMBA ALZ Pattern? Let us know! +title: "[General workload issue]: " +assignees: + - arjenhuitema +labels: + [ + "Pattern: ALZ" + ] +body: + - type: markdown + attributes: + value: | + Thank you for submitting this issue! + - type: checkboxes + id: existing-checks + attributes: + label: Check for previous/existing GitHub issues + description: By submitting this issue, you confirm that you have [searched for previous/existing GitHub issues](https://github.com/Azure/azure-monitor-baseline-alerts/issues) to avoid creating a duplicate. + options: + - label: I have checked for previous/existing GitHub issues + required: true + - type: dropdown + id: issue-type + attributes: + label: Issue Type? + description: How would you best describe this issue? Is this a... + options: + - "Feature Request" + - "Bug" + - "Question" + - "Other" + validations: + required: true + - type: textarea + id: question-feedback-text + attributes: + label: Description + description: Let us know your question, feedback or suggestion here! + validations: + required: true + diff --git a/.github/ISSUE_TEMPLATE/amba-avd-issue.yml b/.github/ISSUE_TEMPLATE/amba-avd-issue.yml new file mode 100644 index 000000000..2f75c8773 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/amba-avd-issue.yml @@ -0,0 +1,42 @@ +name: AMBA - AVD Pattern Issue 🚀 +description: Have an issue, question or suggestion for the AMBA AVD Pattern? Let us know! +title: "[General workload issue]: " +assignees: + - JCoreMS +labels: + [ + "Pattern: AVD" + ] +body: + - type: markdown + attributes: + value: | + Thank you for submitting this issue! + - type: checkboxes + id: existing-checks + attributes: + label: Check for previous/existing GitHub issues + description: By submitting this issue, you confirm that you have [searched for previous/existing GitHub issues](https://github.com/Azure/azure-monitor-baseline-alerts/issues) to avoid creating a duplicate. + options: + - label: I have checked for previous/existing GitHub issues + required: true + - type: dropdown + id: issue-type + attributes: + label: Issue Type? + description: How would you best describe this issue? Is this a... + options: + - "Feature Request" + - "Bug" + - "Question" + - "Other" + validations: + required: true + - type: textarea + id: question-feedback-text + attributes: + label: Description + description: Let us know your question, feedback or suggestion here! + validations: + required: true + diff --git a/.github/ISSUE_TEMPLATE/amba-avs-issue.yml b/.github/ISSUE_TEMPLATE/amba-avs-issue.yml new file mode 100644 index 000000000..cedb30424 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/amba-avs-issue.yml @@ -0,0 +1,42 @@ +name: AMBA - AVS Pattern Issue 🚀 +description: Have an issue, question or suggestion for the AMBA AVS Pattern? Let us know! +title: "[General workload issue]: " +assignees: + - Mahesh-MSFT +labels: + [ + "Pattern: AVS" + ] +body: + - type: markdown + attributes: + value: | + Thank you for submitting this issue! + - type: checkboxes + id: existing-checks + attributes: + label: Check for previous/existing GitHub issues + description: By submitting this issue, you confirm that you have [searched for previous/existing GitHub issues](https://github.com/Azure/azure-monitor-baseline-alerts/issues) to avoid creating a duplicate. + options: + - label: I have checked for previous/existing GitHub issues + required: true + - type: dropdown + id: issue-type + attributes: + label: Issue Type? + description: How would you best describe this issue? Is this a... + options: + - "Feature Request" + - "Bug" + - "Question" + - "Other" + validations: + required: true + - type: textarea + id: question-feedback-text + attributes: + label: Description + description: Let us know your question, feedback or suggestion here! + validations: + required: true + diff --git a/.github/ISSUE_TEMPLATE/amba-workload-issue.yml b/.github/ISSUE_TEMPLATE/amba-workload-issue.yml new file mode 100644 index 000000000..da3a1d279 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/amba-workload-issue.yml @@ -0,0 +1,42 @@ +name: AMBA - General workload Issue 🚀 +description: Have an issue, question or suggestion for a specific workload alert or for the overall project? Let us know! +title: "[General workload issue]: " +assignees: + - JoeyBarnes +labels: + [ + "AMBA Core" + ] +body: + - type: markdown + attributes: + value: | + Thank you for submitting this issue! + - type: checkboxes + id: existing-checks + attributes: + label: Check for previous/existing GitHub issues + description: By submitting this issue, you confirm that you have [searched for previous/existing GitHub issues](https://github.com/Azure/azure-monitor-baseline-alerts/issues) to avoid creating a duplicate. + options: + - label: I have checked for previous/existing GitHub issues + required: true + - type: dropdown + id: issue-type + attributes: + label: Issue Type? + description: How would you best describe this issue? Is this a... + options: + - "Feature Request" + - "Bug" + - "Question" + - "Other" + validations: + required: true + - type: textarea + id: question-feedback-text + attributes: + label: Description + description: Let us know your question, feedback or suggestion here! + validations: + required: true + diff --git a/.github/ISSUE_TEMPLATE/question_feedback.yml b/.github/ISSUE_TEMPLATE/question_feedback.yml deleted file mode 100644 index c9d72a7f4..000000000 --- a/.github/ISSUE_TEMPLATE/question_feedback.yml +++ /dev/null @@ -1,24 +0,0 @@ -name: General Question/Feedback ❔ -description: Just got a question or some general feedback? Let us know -title: "[Question/Feedback]: " -labels: ["question"] -body: - - type: markdown - attributes: - value: | - Thank you for your question/feedback - - type: checkboxes - id: existing-checks - attributes: - label: Check for previous/existing GitHub issues - description: By submitting this issue, you confirm that you have [searched for previous/existing GitHub issues](https://github.com/Azure/azure-monitor-baseline-alerts/issues?q=is%3Aissue+sort%3Aupdated-desc+) to avoid creating a duplicate. - options: - - label: I have checked for previous/existing GitHub issues - required: true - - type: textarea - id: question-feedback-text - attributes: - label: Description - description: Let us know your question or feedback here - validations: - required: true From 6153eb520058ba71b1db1f4c72e589a2ce83e4f1 Mon Sep 17 00:00:00 2001 From: Cassie Kays <86622587+cassiekays@users.noreply.github.com> Date: Wed, 30 Oct 2024 14:37:47 -0700 Subject: [PATCH 03/15] changed two AOAI alerts to visible with the proper thresholds --- services/CognitiveServices/accounts/alerts.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/services/CognitiveServices/accounts/alerts.yaml b/services/CognitiveServices/accounts/alerts.yaml index 9d8a784db..9a28dcb26 100644 --- a/services/CognitiveServices/accounts/alerts.yaml +++ b/services/CognitiveServices/accounts/alerts.yaml @@ -343,18 +343,18 @@ description: Utilization % for a provisoned-managed deployment, calculated as (PTUs consumed / PTUs deployed) x 100. type: Metric verified: false - visible: false + visible: true tags: manual-ck properties: metricName: AzureOpenAIProvisionedManagedUtilizationV2 metricNamespace: Microsoft.CognitiveServices/accounts - severity: 0 + severity: 2 windowSize: PT5M evaluationFrequency: PT1M timeAggregation: Total operator: GreaterThan criterionType: StaticThresholdCriterion - threshold: 0.0 + threshold: 80 guid: 693a3b37-1e2a-42d1-aaed-b1f374276d1c - name: AzureOpenAIRequests description: Number of calls made to the Azure OpenAI API over a period of time. @@ -377,18 +377,18 @@ description: Recommended latency (responsiveness) measure for streaming requests. type: Metric verified: false - visible: false + visible: true tags: manual-ck properties: metricName: AzureOpenAITimeToResponse metricNamespace: Microsoft.CognitiveServices/accounts - severity: 0 + severity: 2 windowSize: PT5M evaluationFrequency: PT1M timeAggregation: Total operator: GreaterThan criterionType: StaticThresholdCriterion - threshold: 0.0 + threshold: 200ms guid: 995cc12a-1887-4669-92c5-70a6ca8bfe70 - name: BaselineEstimatorOverallReward description: Baseline Estimator Overall Reward. From 9f28447bdaae7ac10067ada4cbbba8793165453a Mon Sep 17 00:00:00 2001 From: Divyadeep Dayal Date: Thu, 31 Oct 2024 09:38:03 +0530 Subject: [PATCH 04/15] adding alert for not responding runs after discussion with ML PG --- .../workspaces/alerts.yaml | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/services/MachineLearningServices/workspaces/alerts.yaml b/services/MachineLearningServices/workspaces/alerts.yaml index d8a39f869..3e6283716 100644 --- a/services/MachineLearningServices/workspaces/alerts.yaml +++ b/services/MachineLearningServices/workspaces/alerts.yaml @@ -81,3 +81,21 @@ - name: Monitor Azure Machine Learning url: https://learn.microsoft.com/en-us/azure/machine-learning/monitor-azure-machine-learning?view=azureml-api-2#machine-learning-alert-rules guid: a171bc0c-676f-464b-a7b5-e50cd6c612a2 +- name: Not Responding Runs + description: Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state. + type: Metric + verified: true + visible: true + tags: + - manual + properties: + metricName: Not Responding Runs + metricNamespace: Microsoft.MachineLearningServices/workspaces + severity: 3 + windowSize: PT5M + evaluationFrequency: PT1M + timeAggregation: Total + operator: GreaterThan + criterionType: StaticThresholdCriterion + threshold: 0.0 + guid: d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a From 1faa1d8dd1bbb17bb36cfc3446175b705b7f7869 Mon Sep 17 00:00:00 2001 From: Aki Date: Thu, 31 Oct 2024 17:31:18 +0800 Subject: [PATCH 05/15] update RAG alert and RAG link --- .../artificial intelligence/_index.md | 50 ++- .../artificial intelligence/rag/_index.md | 20 + docs/layouts/shortcodes/ragMetricAlerts.html | 95 +++++ .../CognitiveServices/accounts/alerts.yaml | 396 +++++++++++++----- .../DocumentDB/databaseAccounts/alerts.yaml | 15 + services/KeyVault/vaults/alerts.yaml | 6 + services/Search/searchServices/alerts.yaml | 3 + services/Storage/storageAccounts/alerts.yaml | 8 + services/Web/sites/alerts.yaml | 28 ++ 9 files changed, 502 insertions(+), 119 deletions(-) create mode 100644 docs/content/patterns/artificial intelligence/rag/_index.md create mode 100644 docs/layouts/shortcodes/ragMetricAlerts.html diff --git a/docs/content/patterns/artificial intelligence/_index.md b/docs/content/patterns/artificial intelligence/_index.md index a18e0c2cd..5f505d814 100644 --- a/docs/content/patterns/artificial intelligence/_index.md +++ b/docs/content/patterns/artificial intelligence/_index.md @@ -7,31 +7,37 @@ geekdocCollapseSection: true There are numerous ways to implement AI solution on Azure, and each comes with its own monitoring solution. Monitoring AI solutions involves a combination of the infra or paas resources, along with monitoring any utilization metrics that can be exposed through the platform or other tooling. This page will summarize the recommended monitoring solutions for different scenarios. -### AI on Azure platforms (PaaS) - -Common AI Ready infrastructure on Azure may include services including Azure AI Hub, Azure AI Services including Azure OpenAI, AI Search etc. Specific workloads like Azure Kubernetes Services, API Management, App Services are also used to build enterprise level AI applications. Below table lists quick links to alert guidelines to most commonly used services, for other Azure service in your architecture, refer to the [Azure Resource](../../../../azure-monitor-baseline-alerts/services/) which provides more comprehensive lists. - -| Services | Resource Type | -| --- | --- | -| Azure AI Studio Hub/Azure Machine Learning Hub | [Microsoft.MachineLearningServices/workspaces](../../../../azure-monitor-baseline-alerts/services/MachineLearningServices/workspaces/) | -| Azure AI Search | [Microsoft.Search/searchServices](../../../../azure-monitor-baseline-alerts/services/Search/searchServices/) | -| Azure AI Services | [Microsoft.CognitiveServices/accounts](../../../../azure-monitor-baseline-alerts/services/CognitiveServices/accounts) | -| Azure Kubernetes Services | [Microsoft.ContainerService/managedClusters](../../../../azure-monitor-baseline-alerts/services/ContainerService/managedClusters/) | -| Azure App Services | [Microsoft.Web/sites](../../../../azure-monitor-baseline-alerts/services/Web/sites/) | -| Azure API Management | [lMicrosoft.ApiManagement/service](../../../../azure-monitor-baseline-alerts/services/ApiManagement/service/) | -| Azure Container Apps | [Microsoft.App/containerApps](../../../../azure-monitor-baseline-alerts/services/App/containerApps//) | -| Azure Functions Apps | [Microsoft.Web/sites](../../../../azure-monitor-baseline-alerts/services/Web/sites/) | -| Azure Cosmos DB | [Microsoft.DocumentDB/databaseAccounts](../../../../azure-monitor-baseline-alerts/services/DocumentDB/databaseAccounts/) | -| Azure SQL Database - managedInstances | [Microsoft.Sql/managedInstances](../../../../azure-monitor-baseline-alerts/services/Sql/managedInstances/) | -| Azure SQL Database - server | [Microsoft.Sql/servers/databases](../../../../azure-monitor-baseline-alerts/services/Sql/servers/) | -| Azure Database for MySQL | [Microsoft.DBforMySQL/servers](../../../../azure-monitor-baseline-alerts/services/DBforMySQL/servers/) | -| Azure Database for PostgreSQL | [Microsoft.DBforPostgreSQL/servers](../../../../azure-monitor-baseline-alerts/services/DBforPostgreSQL/servers//) | - -### AI on Azure infrastructure (IaaS) +### AI on Azure Platforms (PaaS) + +Common AI Ready infrastructures on Azure may contain services such as Azure AI Hub, Azure AI Services (including Azure OpenAI) and AI Search. Specific workloads like Azure Kubernetes services, API Management and App Services are also frequently used to build enterprise-level AI applications. +The table below provides quick links to alert guidelines for the most commonly used services. For other Azure services in your architecture, please refer to the [Azure Resource](../../services/), which offers comprehensive lists. + +|Services|Resource Type| +|--- |--- | +|Azure AI Studio Hub/Azure Machine Learning |[Microsoft.MachineLearningServices/workspaces](../../services/machineLearningServices/workspaces/)| +|Azure AI Search|[Microsoft.Search/searchServices](../../services/Search/searchServices/)| +|Azure AI Services |[Microsoft.CognitiveServices/accounts](../../services/CognitiveServices/accounts/)| +|Azure Kubernetes services |[Microsoft.ContainerService/managedClusters](../../services/ContainerService/managedClusters/)| +|Azure App Services |[Microsoft.Web/sites](../../services/Web/sites/)| +|Azure API Management |[Microsoft.ApiManagement/service](../../services/ApiManagement/service/)| +|Azure Container Apps |[Microsoft.App/containerApps](../../services/App/containerApps/)| +|Azure Functions Apps |[Microsoft.Web/sites](../../services/Web/sites/)| +|Azure Cosmos DB |[Microsoft.DocumentDB/databaseAccounts](../../services/DocumentDB/databaseAccounts/)| +|Azure SQL Database - managedInstances |[Microsoft.Sql/managedInstances](../../services/Sql/managedInstances/)| +|Azure SQL Database - server |[Microsoft.Sql/servers/databases](../../services/Sql/servers/)| +|Azure Database for MySQL - flexibleServers|[Microsoft.DBforMySQL/flexibleServers](../../services/DBforMySQL/flexibleServers/)| +|Azure Database for MySQL - servers |[Microsoft.DBforMySQL/servers](../../services/DBforMySQL/servers/)| +|Azure Database for PostgreSQL - flexibleServers|[Microsoft.DBforPostgreSQL/flexibleServers](../../services/DBforPostgreSQL/flexibleServers/)| +|Azure Database for PostgreSQL - servers|[Microsoft.DBforPostgreSQL/servers](../../services/DBforPostgreSQL/servers/)| + + + +### AI on Infrastructure (IaaS) Running AI workloads on Azure infrastructure involves monitoring each of the components of the solution, including virtual machines, storage, and networking. Refer to the defined metrics in [HPC](../../specialized/hpc/Alerting-and-Monitoring.md). For monitoring the GPU/CPU metrics, use [Moneo](https://github.com/Azure/Moneo) + ### AI Specialized Workload Patterns -#### GPT-RAG (coming soon) +#### [GPT-RAG](./rag/) diff --git a/docs/content/patterns/artificial intelligence/rag/_index.md b/docs/content/patterns/artificial intelligence/rag/_index.md new file mode 100644 index 000000000..53fa562a4 --- /dev/null +++ b/docs/content/patterns/artificial intelligence/rag/_index.md @@ -0,0 +1,20 @@ +--- +title: GPT-RAG +geekdocCollapseSection: true +--- + +## Overview + +The Retrieval-Augmented Generation (RAG) pattern is an industry-standard approach to building applications that use large language models to reason over specific or proprietary data that is not already known to the large language model. + +This page provides the alert settings for AI RAG pattern setup. It contains relevant metrics and threshold recommendations for key services involved in a RAG pattern architecture.For a reference architecture design of RAG, see [GPT-RAG](https://github.com/Azure/GPT-RAG). + +Below is a basic architecture of RAG implementation + +![](https://github.com/Azure/GPT-RAG/blob/main/media/architecture-GPT-RAG-Basic.png?raw=true) + +We may update these settings as we continue to work with a breadth of customers. + +## Alerts + +{{< ragMetricAlerts >}} diff --git a/docs/layouts/shortcodes/ragMetricAlerts.html b/docs/layouts/shortcodes/ragMetricAlerts.html new file mode 100644 index 000000000..3bc9f6ab3 --- /dev/null +++ b/docs/layouts/shortcodes/ragMetricAlerts.html @@ -0,0 +1,95 @@ +
+ + + + + + + + + + + + + + + + +{{ range $category, $types := $.Site.Data }} + {{ range $type, $rules := $types }} + {{ range $rules.alerts }} + {{ if or (eq .visible true) (eq $.Site.Params.ambaDevMode true) }} + {{ if and (eq .type "Metric") (in .tags "rag") }} + {{ $data := newScratch }} + {{ if isset . "deployments" }} + {{ range where .deployments "type" "Policy" }} + {{ if and (in .tags "rag") }} + {{ $data.Set "name" .name }} + {{ $data.Set "url" (relURL (path.Join "services" $category $type .template)) }} + {{ $data.Set "scope" .properties.scope }} + {{ $data.Set "multiResource" .properties.multiResource }} + {{ end }} + {{ end }} + {{ end }} + + + + + + + + + + + + + + + + {{ end }} + {{ end }} + {{ end }} + {{ end }} +{{ end }} + +
Alert NameComponentMetricAggregationOperatorThresholdWindowFrequencySeverityScopeSupport for Multiple ResourcesVerifiedReferences
+ {{ $data.Get "name" }} + + {{ .properties.metricNamespace }} + + {{ .properties.metricName }} + + {{ .properties.timeAggregation }} + + {{ .properties.operator }} + + {{ if eq .properties.criterionType "DynamicThresholdCriterion" }} + dynamic + {{ else }} + {{ .properties.threshold }} + {{ end }} + + {{ .properties.windowSize }} + + {{ .properties.evaluationFrequency }} + + {{ .properties.severity }} + + {{ $data.Get "scope" }} + + {{ if ($data.Get "multiResource") }} + Yes + {{ else }} + No + {{ end }} + + {{ if .verified }} + Y + {{ else }} + N + {{ end }} + + {{ range .references }} + {{ .name }} + {{ end }} +
diff --git a/services/CognitiveServices/accounts/alerts.yaml b/services/CognitiveServices/accounts/alerts.yaml index 9d8a784db..a8e000b26 100644 --- a/services/CognitiveServices/accounts/alerts.yaml +++ b/services/CognitiveServices/accounts/alerts.yaml @@ -6,6 +6,7 @@ tags: - auto-generated - agc-1205 + - rag properties: metricName: TotalCalls metricNamespace: Microsoft.CognitiveServices/accounts @@ -26,6 +27,7 @@ tags: - auto-generated - agc-1052 + - rag properties: metricName: TotalErrors metricNamespace: Microsoft.CognitiveServices/accounts @@ -45,6 +47,7 @@ tags: - auto-generated - agc-882 + - rag properties: metricName: Latency metricNamespace: Microsoft.CognitiveServices/accounts @@ -65,6 +68,7 @@ tags: - auto-generated - agc-852 + - rag properties: metricName: SuccessRate metricNamespace: Microsoft.CognitiveServices/accounts @@ -84,6 +88,7 @@ tags: - auto-generated - agc-606 + - rag properties: metricName: ServerErrors metricNamespace: Microsoft.CognitiveServices/accounts @@ -103,6 +108,7 @@ tags: - auto-generated - agc-530 + - rag properties: metricName: TokenTransaction metricNamespace: Microsoft.CognitiveServices/accounts @@ -122,6 +128,7 @@ tags: - auto-generated - agc-468 + - rag properties: metricName: BlockedCalls metricNamespace: Microsoft.CognitiveServices/accounts @@ -141,6 +148,7 @@ tags: - auto-generated - agc-420 + - rag properties: metricName: ClientErrors metricNamespace: Microsoft.CognitiveServices/accounts @@ -157,7 +165,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ActionFeaturesIdOccurrences metricNamespace: Microsoft.CognitiveServices/accounts @@ -174,7 +184,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ActionFeaturesPerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -191,7 +203,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ActionIfOccurrence metricNamespace: Microsoft.CognitiveServices/accounts @@ -208,7 +222,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ActionNamespacePerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -225,7 +241,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ActionPerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -242,7 +260,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ActiveTokens metricNamespace: Microsoft.CognitiveServices/accounts @@ -259,7 +279,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AudioSecondsTranscribed metricNamespace: Microsoft.CognitiveServices/accounts @@ -276,7 +298,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AudioSecondsTranslated metricNamespace: Microsoft.CognitiveServices/accounts @@ -293,7 +317,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AvatarModelHostingSeconds metricNamespace: Microsoft.CognitiveServices/accounts @@ -310,7 +336,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AzureOpenAIContextTokensCacheMatchRate metricNamespace: Microsoft.CognitiveServices/accounts @@ -327,7 +355,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AzureOpenAIProvisionedManagedUtilization metricNamespace: Microsoft.CognitiveServices/accounts @@ -344,7 +374,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AzureOpenAIProvisionedManagedUtilizationV2 metricNamespace: Microsoft.CognitiveServices/accounts @@ -361,7 +393,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AzureOpenAIRequests metricNamespace: Microsoft.CognitiveServices/accounts @@ -378,7 +412,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: AzureOpenAITimeToResponse metricNamespace: Microsoft.CognitiveServices/accounts @@ -395,7 +431,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BaselineEstimatorOverallReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -412,7 +450,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BaselineEstimatorSlotReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -429,7 +469,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BaselineRandomEstimatorOverallReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -446,7 +488,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BaselineRandomEstimatorSlotReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -463,7 +507,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BaselineRandomEventCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -480,7 +526,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BaselineRandomReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -497,7 +545,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: BlockedCalls metricNamespace: Microsoft.CognitiveServices/accounts @@ -514,7 +564,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: CarnegieInferenceCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -531,7 +583,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ClientErrors metricNamespace: Microsoft.CognitiveServices/accounts @@ -548,7 +602,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ComputerVisionTransactions metricNamespace: Microsoft.CognitiveServices/accounts @@ -565,7 +621,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ContentSafetyImageAnalyzeRequestCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -582,7 +640,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ContentSafetyTextAnalyzeRequestCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -599,7 +659,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ContextFeatureIdOccurrences metricNamespace: Microsoft.CognitiveServices/accounts @@ -616,7 +678,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ContextFeaturesPerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -633,7 +697,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ContextNamespacesPerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -650,7 +716,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: CustomVisionTrainingTime metricNamespace: Microsoft.CognitiveServices/accounts @@ -667,7 +735,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: CustomVisionTransactions metricNamespace: Microsoft.CognitiveServices/accounts @@ -684,7 +754,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: DataIn metricNamespace: Microsoft.CognitiveServices/accounts @@ -701,7 +773,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: DataOut metricNamespace: Microsoft.CognitiveServices/accounts @@ -718,7 +792,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: DocumentCharactersTranslated metricNamespace: Microsoft.CognitiveServices/accounts @@ -735,7 +811,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: DocumentCustomCharactersTranslated metricNamespace: Microsoft.CognitiveServices/accounts @@ -752,7 +830,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FaceImagesTrained metricNamespace: Microsoft.CognitiveServices/accounts @@ -769,7 +849,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FacesStored metricNamespace: Microsoft.CognitiveServices/accounts @@ -786,7 +868,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FaceTransactions metricNamespace: Microsoft.CognitiveServices/accounts @@ -803,7 +887,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FeatureCardinality_Action metricNamespace: Microsoft.CognitiveServices/accounts @@ -820,7 +906,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FeatureCardinality_Context metricNamespace: Microsoft.CognitiveServices/accounts @@ -837,7 +925,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FeatureCardinality_Slot metricNamespace: Microsoft.CognitiveServices/accounts @@ -854,7 +944,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: FineTunedTrainingHours metricNamespace: Microsoft.CognitiveServices/accounts @@ -871,7 +963,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: GeneratedTokens metricNamespace: Microsoft.CognitiveServices/accounts @@ -888,7 +982,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ImagesStored metricNamespace: Microsoft.CognitiveServices/accounts @@ -905,7 +1001,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: Latency metricNamespace: Microsoft.CognitiveServices/accounts @@ -922,7 +1020,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: LearnedEvents metricNamespace: Microsoft.CognitiveServices/accounts @@ -939,7 +1039,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: LUISSpeechRequests metricNamespace: Microsoft.CognitiveServices/accounts @@ -956,7 +1058,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: LUISTextRequests metricNamespace: Microsoft.CognitiveServices/accounts @@ -973,7 +1077,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: MatchedRewards metricNamespace: Microsoft.CognitiveServices/accounts @@ -990,7 +1096,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: NonActivatedEvents metricNamespace: Microsoft.CognitiveServices/accounts @@ -1007,7 +1115,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: NumberOfSlots metricNamespace: Microsoft.CognitiveServices/accounts @@ -1024,7 +1134,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: NumberofSpeakerProfiles metricNamespace: Microsoft.CognitiveServices/accounts @@ -1041,7 +1153,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ObservedRewards metricNamespace: Microsoft.CognitiveServices/accounts @@ -1058,7 +1172,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: OneDocumentCharactersTranslated metricNamespace: Microsoft.CognitiveServices/accounts @@ -1075,7 +1191,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: OnlineEstimatorOverallReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -1092,7 +1210,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: OnlineEstimatorSlotReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -1109,7 +1229,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: OnlineEventCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -1126,7 +1248,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: OnlineReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -1143,7 +1267,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ProcessedCharacters metricNamespace: Microsoft.CognitiveServices/accounts @@ -1160,7 +1286,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ProcessedHealthTextRecords metricNamespace: Microsoft.CognitiveServices/accounts @@ -1177,7 +1305,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ProcessedImages metricNamespace: Microsoft.CognitiveServices/accounts @@ -1194,7 +1324,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ProcessedPages metricNamespace: Microsoft.CognitiveServices/accounts @@ -1211,7 +1343,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ProcessedPromptTokens metricNamespace: Microsoft.CognitiveServices/accounts @@ -1228,7 +1362,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ProcessedTextRecords metricNamespace: Microsoft.CognitiveServices/accounts @@ -1245,7 +1381,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: QuestionAnsweringTextRecords metricNamespace: Microsoft.CognitiveServices/accounts @@ -1262,7 +1400,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: RAIAbusiveUsersCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -1279,7 +1419,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: RAIHarmfulRequests metricNamespace: Microsoft.CognitiveServices/accounts @@ -1296,7 +1438,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: RAIRejectedRequests metricNamespace: Microsoft.CognitiveServices/accounts @@ -1313,7 +1457,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: RAISystemEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -1330,7 +1476,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: RAITotalRequests metricNamespace: Microsoft.CognitiveServices/accounts @@ -1347,7 +1495,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: Ratelimit metricNamespace: Microsoft.CognitiveServices/accounts @@ -1364,7 +1514,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: Reward metricNamespace: Microsoft.CognitiveServices/accounts @@ -1381,7 +1533,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: ServerErrors metricNamespace: Microsoft.CognitiveServices/accounts @@ -1398,7 +1552,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SlotFeatureIdOccurrences metricNamespace: Microsoft.CognitiveServices/accounts @@ -1415,7 +1571,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SlotFeaturesPerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -1432,7 +1590,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SlotIdOccurrences metricNamespace: Microsoft.CognitiveServices/accounts @@ -1449,7 +1609,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SlotNamespacesPerEvent metricNamespace: Microsoft.CognitiveServices/accounts @@ -1466,7 +1628,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SlotRewards metricNamespace: Microsoft.CognitiveServices/accounts @@ -1483,7 +1647,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SpeakerRecognitionTransactions metricNamespace: Microsoft.CognitiveServices/accounts @@ -1500,7 +1666,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SpeechModelHostingHours metricNamespace: Microsoft.CognitiveServices/accounts @@ -1517,7 +1685,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SpeechModelHostingHours metricNamespace: Microsoft.CognitiveServices/accounts @@ -1534,7 +1704,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SuccessfulCalls metricNamespace: Microsoft.CognitiveServices/accounts @@ -1551,7 +1723,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SuccessRate metricNamespace: Microsoft.CognitiveServices/accounts @@ -1568,7 +1742,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: SynthesizedCharacters metricNamespace: Microsoft.CognitiveServices/accounts @@ -1585,7 +1761,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TextCharactersTranslated metricNamespace: Microsoft.CognitiveServices/accounts @@ -1602,7 +1780,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TextCustomCharactersTranslated metricNamespace: Microsoft.CognitiveServices/accounts @@ -1619,7 +1799,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TextTrainedCharacters metricNamespace: Microsoft.CognitiveServices/accounts @@ -1636,7 +1818,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TokenTransaction metricNamespace: Microsoft.CognitiveServices/accounts @@ -1653,7 +1837,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TotalCalls metricNamespace: Microsoft.CognitiveServices/accounts @@ -1670,7 +1856,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TotalErrors metricNamespace: Microsoft.CognitiveServices/accounts @@ -1687,7 +1875,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TotalEvents metricNamespace: Microsoft.CognitiveServices/accounts @@ -1704,7 +1894,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: TotalTokenCalls metricNamespace: Microsoft.CognitiveServices/accounts @@ -1721,7 +1913,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: UserBaselineEventCount metricNamespace: Microsoft.CognitiveServices/accounts @@ -1738,7 +1932,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: UserBaselineReward metricNamespace: Microsoft.CognitiveServices/accounts @@ -1755,7 +1951,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: VideoSecondsSynthesized metricNamespace: Microsoft.CognitiveServices/accounts @@ -1772,7 +1970,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: VoiceModelHostingHours metricNamespace: Microsoft.CognitiveServices/accounts @@ -1789,7 +1989,9 @@ type: Metric verified: false visible: false - tags: manual-ck + tags: + - manual-ck + - rag properties: metricName: VoiceModelTrainingMinutes metricNamespace: Microsoft.CognitiveServices/accounts diff --git a/services/DocumentDB/databaseAccounts/alerts.yaml b/services/DocumentDB/databaseAccounts/alerts.yaml index 1333a6ffd..643c94eef 100644 --- a/services/DocumentDB/databaseAccounts/alerts.yaml +++ b/services/DocumentDB/databaseAccounts/alerts.yaml @@ -6,6 +6,7 @@ tags: - auto-generated - agc-10210 + - rag properties: metricName: TotalRequests metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -39,6 +40,7 @@ tags: - auto-generated - agc-7686 + - rag properties: metricName: NormalizedRUConsumption metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -65,6 +67,7 @@ tags: - auto-generated - agc-5578 + - rag properties: metricName: ServiceAvailability metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -91,6 +94,7 @@ tags: - auto-generated - agc-3381 + - rag properties: metricName: TotalRequestUnits metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -125,6 +129,7 @@ tags: - auto-generated - agc-2201 + - rag properties: metricName: ServerSideLatency metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -151,6 +156,7 @@ tags: - auto-generated - agc-1906 + - rag properties: metricName: ProvisionedThroughput metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -177,6 +183,7 @@ tags: - auto-generated - agc-1531 + - rag properties: metricName: RegionFailover metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -201,6 +208,7 @@ tags: - auto-generated - agc-1232 + - rag properties: metricName: UpdateAccountKeys metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -232,6 +240,7 @@ tags: - auto-generated - agc-707 + - rag properties: metricName: DataUsage metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -251,6 +260,7 @@ tags: - auto-generated - agc-518 + - rag properties: metricName: MongoRequests metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -277,6 +287,7 @@ tags: - auto-generated - agc-448 + - rag properties: metricName: RemoveRegion metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -302,6 +313,7 @@ tags: - auto-generated - agc-390 + - rag properties: metricName: ReplicationLatency metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -321,6 +333,7 @@ tags: - auto-generated - agc-364 + - rag properties: metricName: SqlContainerDelete metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -345,6 +358,7 @@ tags: - auto-generated - agc-304 + - rag properties: metricName: OfflineRegion metricNamespace: Microsoft.DocumentDB/databaseAccounts @@ -364,6 +378,7 @@ tags: - auto-generated - agc-297 + - rag properties: metricName: SqlDatabaseDelete metricNamespace: Microsoft.DocumentDB/databaseAccounts diff --git a/services/KeyVault/vaults/alerts.yaml b/services/KeyVault/vaults/alerts.yaml index 67672f590..79ce8b14a 100644 --- a/services/KeyVault/vaults/alerts.yaml +++ b/services/KeyVault/vaults/alerts.yaml @@ -5,6 +5,7 @@ visible: true tags: - alz + - rag properties: category: Administrative operationName: Microsoft.KeyVault/vaults/delete @@ -34,6 +35,7 @@ visible: true tags: - alz + - rag properties: metricName: Availability metricNamespace: Microsoft.KeyVault/vaults @@ -69,6 +71,7 @@ visible: true tags: - alz + - rag properties: metricName: SaturationShoebox metricNamespace: Microsoft.KeyVault/vaults @@ -104,6 +107,7 @@ visible: true tags: - alz + - rag properties: metricName: ServiceApiLatency metricNamespace: Microsoft.KeyVault/vaults @@ -139,6 +143,7 @@ visible: true tags: - alz + - rag properties: metricName: ServiceApiResult metricNamespace: Microsoft.KeyVault/vaults @@ -178,6 +183,7 @@ tags: - auto-generated - agc-1137 + - rag properties: metricName: ServiceApiHit metricNamespace: Microsoft.KeyVault/vaults diff --git a/services/Search/searchServices/alerts.yaml b/services/Search/searchServices/alerts.yaml index 5b1c86551..1be6e9df6 100644 --- a/services/Search/searchServices/alerts.yaml +++ b/services/Search/searchServices/alerts.yaml @@ -6,6 +6,7 @@ tags: - auto-generated - agc-636 + - rag properties: metricName: SearchLatency metricNamespace: Microsoft.Search/searchServices @@ -25,6 +26,7 @@ tags: - auto-generated - agc-613 + - rag properties: metricName: ThrottledSearchQueriesPercentage metricNamespace: Microsoft.Search/searchServices @@ -43,6 +45,7 @@ visible: true tags: - manual + - rag properties: category: Administrative operationName: Microsoft.Search/searchServices/delete diff --git a/services/Storage/storageAccounts/alerts.yaml b/services/Storage/storageAccounts/alerts.yaml index 2272508ba..cd832d654 100644 --- a/services/Storage/storageAccounts/alerts.yaml +++ b/services/Storage/storageAccounts/alerts.yaml @@ -11,6 +11,7 @@ - alz - hpc - alz + - rag properties: metricName: Availability metricNamespace: Microsoft.Storage/storageAccounts @@ -47,6 +48,7 @@ - alz - hpc - alz + - rag properties: metricName: Transactions dimensions: @@ -140,6 +142,7 @@ - hpc - auto-generated - agc-35128 + - rag properties: metricName: UsedCapacity metricNamespace: Microsoft.Storage/storageAccounts @@ -169,6 +172,7 @@ - hpc - auto-generated - agc-2980 + - rag properties: metricName: Egress metricNamespace: Microsoft.Storage/storageAccounts @@ -197,6 +201,7 @@ - hpc - auto-generated - agc-2078 + - rag properties: metricName: Ingress metricNamespace: Microsoft.Storage/storageAccounts @@ -252,6 +257,7 @@ - hpc - auto-generated - agc-496 + - rag properties: metricName: SuccessE2ELatency metricNamespace: Microsoft.Storage/storageAccounts/blobServices @@ -280,6 +286,7 @@ - hpc - auto-generated - agc-297 + - rag properties: metricName: SuccessServerLatency metricNamespace: Microsoft.Storage/storageAccounts/blobServices @@ -406,6 +413,7 @@ - hpc - auto-generated - agc-1507 + - rag properties: metricName: Transactions metricNamespace: Microsoft.Storage/storageAccounts/fileServices diff --git a/services/Web/sites/alerts.yaml b/services/Web/sites/alerts.yaml index 009487124..582ed5aa1 100644 --- a/services/Web/sites/alerts.yaml +++ b/services/Web/sites/alerts.yaml @@ -7,6 +7,7 @@ tags: - auto-generated - agc-15815 + - rag properties: metricName: AverageResponseTime metricNamespace: Microsoft.Web/sites @@ -28,6 +29,7 @@ tags: - auto-generated - agc-11669 + - rag properties: metricName: CpuTime metricNamespace: Microsoft.Web/sites @@ -61,6 +63,7 @@ tags: - auto-generated - agc-10341 + - rag properties: metricName: AppConnections metricNamespace: Microsoft.Web/sites @@ -95,6 +98,7 @@ tags: - auto-generated - agc-10057 + - rag properties: metricName: RequestsInApplicationQueue metricNamespace: Microsoft.Web/sites @@ -126,6 +130,7 @@ tags: - auto-generated - agc-7758 + - rag properties: metricName: PrivateBytes metricNamespace: Microsoft.Web/sites @@ -151,6 +156,7 @@ tags: - auto-generated - agc-7042 + - rag properties: metricName: FileSystemUsage metricNamespace: Microsoft.Web/sites @@ -178,6 +184,7 @@ tags: - auto-generated - agc-5187 + - rag properties: metricName: MemoryWorkingSet metricNamespace: Microsoft.Web/sites @@ -205,6 +212,7 @@ tags: - auto-generated - agc-4574 + - rag properties: metricName: Threads metricNamespace: Microsoft.Web/sites @@ -230,6 +238,7 @@ tags: - auto-generated - agc-4499 + - rag properties: metricName: Http401 metricNamespace: Microsoft.Web/sites @@ -259,6 +268,7 @@ tags: - auto-generated - agc-4292 + - rag properties: metricName: Requests metricNamespace: Microsoft.Web/sites @@ -278,6 +288,7 @@ tags: - auto-generated - agc-3568 + - rag properties: metricName: FunctionExecutionCount metricNamespace: Microsoft.Web/sites @@ -305,6 +316,7 @@ tags: - auto-generated - agc-1448 + - rag properties: metricName: BytesSent metricNamespace: Microsoft.Web/sites @@ -333,6 +345,7 @@ tags: - auto-generated - agc-992 + - rag properties: metricName: Http406 metricNamespace: Microsoft.Web/sites @@ -358,6 +371,7 @@ tags: - auto-generated - agc-988 + - rag properties: metricName: Http3xx metricNamespace: Microsoft.Web/sites @@ -386,6 +400,7 @@ tags: - auto-generated - agc-865 + - rag properties: metricName: WorkflowRunsFailureRate metricNamespace: Microsoft.Web/sites @@ -406,6 +421,7 @@ tags: - auto-generated - agc-836 + - rag properties: metricName: BytesReceived metricNamespace: Microsoft.Web/sites @@ -431,6 +447,7 @@ tags: - auto-generated - agc-778 + - rag properties: metricName: Handles metricNamespace: Microsoft.Web/sites @@ -458,6 +475,7 @@ tags: - auto-generated - agc-463 + - rag properties: metricName: FunctionExecutionUnits metricNamespace: Microsoft.Web/sites @@ -480,6 +498,7 @@ tags: - auto-generated - agc-412 + - rag properties: metricName: WorkflowTriggersFailureRate metricNamespace: Microsoft.Web/sites @@ -500,6 +519,7 @@ tags: - auto-generated - agc-357 + - rag properties: metricName: Http2xx metricNamespace: Microsoft.Web/sites @@ -520,6 +540,7 @@ tags: - auto-generated - agc-252 + - rag properties: metricName: CurrentAssemblies metricNamespace: Microsoft.Web/sites @@ -540,6 +561,7 @@ tags: - auto-generated - agc-1692 + - rag properties: metricName: Http5xx metricNamespace: Microsoft.Web/sites/slots @@ -568,6 +590,7 @@ tags: - auto-generated - agc-662 + - rag properties: metricName: HttpResponseTime metricNamespace: Microsoft.Web/sites/slots @@ -595,6 +618,7 @@ tags: - auto-generated - agc-486 + - rag properties: metricName: Http4xx metricNamespace: Microsoft.Web/sites/slots @@ -619,6 +643,7 @@ tags: - auto-generated - agc-381 + - rag properties: metricName: AverageMemoryWorkingSet metricNamespace: Microsoft.Web/sites/slots @@ -638,6 +663,7 @@ tags: - auto-generated - agc-291 + - rag properties: metricName: HealthCheckStatus metricNamespace: Microsoft.Web/sites/slots @@ -664,6 +690,7 @@ tags: - auto-generated - agc-270 + - rag properties: metricName: Http403 metricNamespace: Microsoft.Web/sites/slots @@ -683,6 +710,7 @@ tags: - auto-generated - agc-258 + - rag properties: metricName: Http404 metricNamespace: Microsoft.Web/sites/slots From 52683eecb69eb62d36a7f6dd67a5dcb2378544dd Mon Sep 17 00:00:00 2001 From: Joseph Barnes Date: Thu, 31 Oct 2024 13:11:22 -0500 Subject: [PATCH 06/15] Updated version for Microsoft.Resources/deployments --- tooling/generate-templates/arm/activity-administrative.json | 2 +- tooling/generate-templates/arm/activity-resourcehealth.json | 2 +- tooling/generate-templates/arm/activity-servicehealth.json | 2 +- tooling/generate-templates/arm/log.json | 2 +- tooling/generate-templates/arm/metric-dynamic.json | 2 +- tooling/generate-templates/arm/metric-static.json | 2 +- tooling/generate-templates/bicep/activity-administrative.bicep | 2 +- tooling/generate-templates/bicep/activity-resourcehealth.bicep | 2 +- tooling/generate-templates/bicep/activity-servicehealth.bicep | 2 +- tooling/generate-templates/bicep/log.bicep | 2 +- tooling/generate-templates/bicep/metric-dynamic.bicep | 2 +- tooling/generate-templates/bicep/metric-static.bicep | 2 +- 12 files changed, 12 insertions(+), 12 deletions(-) diff --git a/tooling/generate-templates/arm/activity-administrative.json b/tooling/generate-templates/arm/activity-administrative.json index a48293408..093e567a2 100644 --- a/tooling/generate-templates/arm/activity-administrative.json +++ b/tooling/generate-templates/arm/activity-administrative.json @@ -79,7 +79,7 @@ }, { "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", + "apiVersion": "2023-07-01", "name": "[variables('pidDeploymentName')]", "type": "Microsoft.Resources/deployments", "properties": { diff --git a/tooling/generate-templates/arm/activity-resourcehealth.json b/tooling/generate-templates/arm/activity-resourcehealth.json index a25574c0f..9cb698f59 100644 --- a/tooling/generate-templates/arm/activity-resourcehealth.json +++ b/tooling/generate-templates/arm/activity-resourcehealth.json @@ -79,7 +79,7 @@ }, { "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", + "apiVersion": "2023-07-01", "name": "[variables('pidDeploymentName')]", "type": "Microsoft.Resources/deployments", "properties": { diff --git a/tooling/generate-templates/arm/activity-servicehealth.json b/tooling/generate-templates/arm/activity-servicehealth.json index 796bd3784..22f75d9d9 100644 --- a/tooling/generate-templates/arm/activity-servicehealth.json +++ b/tooling/generate-templates/arm/activity-servicehealth.json @@ -75,7 +75,7 @@ }, { "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", + "apiVersion": "2023-07-01", "name": "[variables('pidDeploymentName')]", "type": "Microsoft.Resources/deployments", "properties": { diff --git a/tooling/generate-templates/arm/log.json b/tooling/generate-templates/arm/log.json index b4e714e00..b3371f4d5 100644 --- a/tooling/generate-templates/arm/log.json +++ b/tooling/generate-templates/arm/log.json @@ -249,7 +249,7 @@ }, { "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", + "apiVersion": "2023-07-01", "name": "[variables('pidDeploymentName')]", "type": "Microsoft.Resources/deployments", "properties": { diff --git a/tooling/generate-templates/arm/metric-dynamic.json b/tooling/generate-templates/arm/metric-dynamic.json index b5ed3681f..28e1cf149 100644 --- a/tooling/generate-templates/arm/metric-dynamic.json +++ b/tooling/generate-templates/arm/metric-dynamic.json @@ -205,7 +205,7 @@ }, { "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", + "apiVersion": "2023-07-01", "name": "[variables('pidDeploymentName')]", "type": "Microsoft.Resources/deployments", "properties": { diff --git a/tooling/generate-templates/arm/metric-static.json b/tooling/generate-templates/arm/metric-static.json index 2e94c860a..73a780eb0 100644 --- a/tooling/generate-templates/arm/metric-static.json +++ b/tooling/generate-templates/arm/metric-static.json @@ -185,7 +185,7 @@ }, { "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", + "apiVersion": "2023-07-01", "name": "[variables('pidDeploymentName')]", "type": "Microsoft.Resources/deployments", "properties": { diff --git a/tooling/generate-templates/bicep/activity-administrative.bicep b/tooling/generate-templates/bicep/activity-administrative.bicep index 53c404616..29dc89f42 100644 --- a/tooling/generate-templates/bicep/activity-administrative.bicep +++ b/tooling/generate-templates/bicep/activity-administrative.bicep @@ -52,7 +52,7 @@ resource symbolicname 'Microsoft.Insights/activityLogAlerts@2023-01-01-preview' } var ambaTelemetryPidName = '##TELEMETRY_PID##-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2023-07-01' = if (telemetryOptOut == 'No') { name: ambaTelemetryPidName tags: { _deployed_by_amba: 'true' diff --git a/tooling/generate-templates/bicep/activity-resourcehealth.bicep b/tooling/generate-templates/bicep/activity-resourcehealth.bicep index e993691b9..24d1c410b 100644 --- a/tooling/generate-templates/bicep/activity-resourcehealth.bicep +++ b/tooling/generate-templates/bicep/activity-resourcehealth.bicep @@ -50,7 +50,7 @@ resource symbolicname 'Microsoft.Insights/activityLogAlerts@2023-01-01-preview' } var ambaTelemetryPidName = '##TELEMETRY_PID##-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2023-07-01' = if (telemetryOptOut == 'No') { name: ambaTelemetryPidName tags: { _deployed_by_amba: 'true' diff --git a/tooling/generate-templates/bicep/activity-servicehealth.bicep b/tooling/generate-templates/bicep/activity-servicehealth.bicep index 36e9470f7..5943c7f90 100644 --- a/tooling/generate-templates/bicep/activity-servicehealth.bicep +++ b/tooling/generate-templates/bicep/activity-servicehealth.bicep @@ -48,7 +48,7 @@ resource symbolicname 'Microsoft.Insights/activityLogAlerts@2023-01-01-preview' } var ambaTelemetryPidName = '##TELEMETRY_PID##-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2023-07-01' = if (telemetryOptOut == 'No') { name: ambaTelemetryPidName tags: { _deployed_by_amba: 'true' diff --git a/tooling/generate-templates/bicep/log.bicep b/tooling/generate-templates/bicep/log.bicep index c1227dd63..e154f11bc 100644 --- a/tooling/generate-templates/bicep/log.bicep +++ b/tooling/generate-templates/bicep/log.bicep @@ -157,7 +157,7 @@ resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { } var ambaTelemetryPidName = '##TELEMETRY_PID##-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2023-07-01' = if (telemetryOptOut == 'No') { name: ambaTelemetryPidName tags: { _deployed_by_amba: 'true' diff --git a/tooling/generate-templates/bicep/metric-dynamic.bicep b/tooling/generate-templates/bicep/metric-dynamic.bicep index 7279764ba..fb68bd096 100644 --- a/tooling/generate-templates/bicep/metric-dynamic.bicep +++ b/tooling/generate-templates/bicep/metric-dynamic.bicep @@ -131,7 +131,7 @@ resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { } var ambaTelemetryPidName = '##TELEMETRY_PID##-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2023-07-01' = if (telemetryOptOut == 'No') { name: ambaTelemetryPidName tags: { _deployed_by_amba: 'true' diff --git a/tooling/generate-templates/bicep/metric-static.bicep b/tooling/generate-templates/bicep/metric-static.bicep index 10bb85a0c..1258b56af 100644 --- a/tooling/generate-templates/bicep/metric-static.bicep +++ b/tooling/generate-templates/bicep/metric-static.bicep @@ -119,7 +119,7 @@ resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { } var ambaTelemetryPidName = '##TELEMETRY_PID##-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2023-07-01' = if (telemetryOptOut == 'No') { name: ambaTelemetryPidName tags: { _deployed_by_amba: 'true' From befb971dfe3f4830a2c1c9f3d64bf1ddda9cd370 Mon Sep 17 00:00:00 2001 From: Cassie Kays <86622587+cassiekays@users.noreply.github.com> Date: Thu, 31 Oct 2024 11:33:19 -0700 Subject: [PATCH 07/15] changed PG verified to true; added token cache threshold : visible and verified --- services/CognitiveServices/accounts/alerts.yaml | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/services/CognitiveServices/accounts/alerts.yaml b/services/CognitiveServices/accounts/alerts.yaml index 9a28dcb26..da9fa66c6 100644 --- a/services/CognitiveServices/accounts/alerts.yaml +++ b/services/CognitiveServices/accounts/alerts.yaml @@ -308,19 +308,19 @@ - name: AzureOpenAIContextTokensCacheMatchRate description: Percentage of the prompt tokens hit the cache, avaiable for PTU-managed. type: Metric - verified: false - visible: false + verified: true + visible: true tags: manual-ck properties: metricName: AzureOpenAIContextTokensCacheMatchRate metricNamespace: Microsoft.CognitiveServices/accounts - severity: 0 + severity: 2 windowSize: PT5M evaluationFrequency: PT1M timeAggregation: Total operator: GreaterThan criterionType: StaticThresholdCriterion - threshold: 0.0 + threshold: 75 guid: 81f8369c-65bf-4194-bfd2-ffdfa2470577 - name: AzureOpenAIProvisionedManagedUtilization description: Utilization % for a provisoned-managed deployment, calculated as (PTUs consumed / PTUs deployed) x 100. @@ -342,7 +342,7 @@ - name: AzureOpenAIProvisionedManagedUtilizationV2 description: Utilization % for a provisoned-managed deployment, calculated as (PTUs consumed / PTUs deployed) x 100. type: Metric - verified: false + verified: true visible: true tags: manual-ck properties: @@ -376,7 +376,7 @@ - name: AzureOpenAITimeToResponse description: Recommended latency (responsiveness) measure for streaming requests. type: Metric - verified: false + verified: true visible: true tags: manual-ck properties: From c77f3422ca0f9eb1e000ba0bd0ab6d4a90b5ea22 Mon Sep 17 00:00:00 2001 From: Cassie Kays <86622587+cassiekays@users.noreply.github.com> Date: Thu, 31 Oct 2024 12:04:17 -0700 Subject: [PATCH 08/15] fixed text in threshold for time to respond metric --- services/CognitiveServices/accounts/alerts.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/services/CognitiveServices/accounts/alerts.yaml b/services/CognitiveServices/accounts/alerts.yaml index da9fa66c6..2105993ce 100644 --- a/services/CognitiveServices/accounts/alerts.yaml +++ b/services/CognitiveServices/accounts/alerts.yaml @@ -374,7 +374,7 @@ threshold: 0.0 guid: a1528d17-f288-46b1-b084-8b8fe3af90fa - name: AzureOpenAITimeToResponse - description: Recommended latency (responsiveness) measure for streaming requests. + description: Recommended latency (responsiveness) measure for streaming requests. Time in milliseconds. type: Metric verified: true visible: true @@ -388,7 +388,7 @@ timeAggregation: Total operator: GreaterThan criterionType: StaticThresholdCriterion - threshold: 200ms + threshold: 200 guid: 995cc12a-1887-4669-92c5-70a6ca8bfe70 - name: BaselineEstimatorOverallReward description: Baseline Estimator Overall Reward. From d483270c591f75dda8ac1783db522fa242000b39 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Thu, 31 Oct 2024 19:12:26 +0000 Subject: [PATCH 09/15] [GitHub Action - Generate Templates] Generate templates for alerts --- ..._bb83ae53-3b91-49ff-a351-9545ea747335.json | 199 ++++++++++++++ ..._282cb835-592b-4e49-89c1-ea1aaefb37c4.json | 199 ++++++++++++++ ..._a2f5e5a3-ec38-4201-970f-971ad4707b93.json | 199 ++++++++++++++ ..._e840c7a9-e070-4dc9-919b-c75a3679f6b7.json | 199 ++++++++++++++ ..._8bafb3d5-d961-49a4-9867-f1cddfd703e0.json | 199 ++++++++++++++ ...bb83ae53-3b91-49ff-a351-9545ea747335.bicep | 140 ++++++++++ ...282cb835-592b-4e49-89c1-ea1aaefb37c4.bicep | 140 ++++++++++ ...a2f5e5a3-ec38-4201-970f-971ad4707b93.bicep | 140 ++++++++++ ...e840c7a9-e070-4dc9-919b-c75a3679f6b7.bicep | 140 ++++++++++ ...8bafb3d5-d961-49a4-9867-f1cddfd703e0.bicep | 140 ++++++++++ ..._81f8369c-65bf-4194-bfd2-ffdfa2470577.json | 199 ++++++++++++++ ..._693a3b37-1e2a-42d1-aaed-b1f374276d1c.json | 199 ++++++++++++++ ..._995cc12a-1887-4669-92c5-70a6ca8bfe70.json | 199 ++++++++++++++ ...81f8369c-65bf-4194-bfd2-ffdfa2470577.bicep | 135 +++++++++ ...693a3b37-1e2a-42d1-aaed-b1f374276d1c.bicep | 135 +++++++++ ...995cc12a-1887-4669-92c5-70a6ca8bfe70.bicep | 135 +++++++++ ..._0337a76f-238e-4d4d-9cd1-48b205874dbb.json | 199 ++++++++++++++ ..._d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.json | 199 ++++++++++++++ ..._be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.json | 199 ++++++++++++++ ..._a171bc0c-676f-464b-a7b5-e50cd6c612a2.json | 199 ++++++++++++++ ...0337a76f-238e-4d4d-9cd1-48b205874dbb.bicep | 135 +++++++++ ...d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.bicep | 135 +++++++++ ...be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.bicep | 135 +++++++++ ...a171bc0c-676f-464b-a7b5-e50cd6c612a2.bicep | 135 +++++++++ ..._5611eb31-51c7-4279-ab8c-97dba0a2c044.json | 95 +++++++ ...5611eb31-51c7-4279-ab8c-97dba0a2c044.bicep | 68 +++++ ..._ebd68fdd-9672-43e8-b7d5-6e479210535d.json | 256 ++++++++++++++++++ ..._ecec6f93-af7e-4071-b35d-cd70b3f16581.json | 256 ++++++++++++++++++ ..._2feba8fd-ff1e-4f48-bc01-6e2996edafa6.json | 256 ++++++++++++++++++ ..._48fc094d-8a00-4d3c-86d3-3230c7e5881a.json | 256 ++++++++++++++++++ ..._4eeca790-a804-4453-b339-73ea425610bc.json | 256 ++++++++++++++++++ ..._59298086-ec77-4f47-b2ef-b853b79e31cb.json | 256 ++++++++++++++++++ ..._8f231351-c123-4e4c-8631-9978e641a3ca.json | 256 ++++++++++++++++++ ..._9d086772-1887-4893-8b9f-7e5169398bae.json | 256 ++++++++++++++++++ ..._7f951991-c6ce-4c72-9f55-7eade2c4f57c.json | 199 ++++++++++++++ ...ebd68fdd-9672-43e8-b7d5-6e479210535d.bicep | 183 +++++++++++++ ...ecec6f93-af7e-4071-b35d-cd70b3f16581.bicep | 183 +++++++++++++ ...2feba8fd-ff1e-4f48-bc01-6e2996edafa6.bicep | 183 +++++++++++++ ...48fc094d-8a00-4d3c-86d3-3230c7e5881a.bicep | 183 +++++++++++++ ...4eeca790-a804-4453-b339-73ea425610bc.bicep | 183 +++++++++++++ ...59298086-ec77-4f47-b2ef-b853b79e31cb.bicep | 183 +++++++++++++ ...8f231351-c123-4e4c-8631-9978e641a3ca.bicep | 183 +++++++++++++ ...9d086772-1887-4893-8b9f-7e5169398bae.bicep | 183 +++++++++++++ ...7f951991-c6ce-4c72-9f55-7eade2c4f57c.bicep | 135 +++++++++ 44 files changed, 8042 insertions(+) create mode 100644 services/AVS/privateClouds/templates/arm/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.json create mode 100644 services/AVS/privateClouds/templates/arm/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.json create mode 100644 services/AVS/privateClouds/templates/arm/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.json create mode 100644 services/AVS/privateClouds/templates/arm/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.json create mode 100644 services/AVS/privateClouds/templates/arm/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.json create mode 100644 services/AVS/privateClouds/templates/bicep/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.bicep create mode 100644 services/AVS/privateClouds/templates/bicep/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.bicep create mode 100644 services/AVS/privateClouds/templates/bicep/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.bicep create mode 100644 services/AVS/privateClouds/templates/bicep/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.bicep create mode 100644 services/AVS/privateClouds/templates/bicep/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.bicep create mode 100644 services/CognitiveServices/accounts/templates/arm/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.json create mode 100644 services/CognitiveServices/accounts/templates/arm/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.json create mode 100644 services/CognitiveServices/accounts/templates/arm/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.json create mode 100644 services/CognitiveServices/accounts/templates/bicep/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.bicep create mode 100644 services/CognitiveServices/accounts/templates/bicep/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.bicep create mode 100644 services/CognitiveServices/accounts/templates/bicep/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.bicep create mode 100644 services/MachineLearningServices/workspaces/templates/arm/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.json create mode 100644 services/MachineLearningServices/workspaces/templates/arm/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.json create mode 100644 services/MachineLearningServices/workspaces/templates/arm/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.json create mode 100644 services/MachineLearningServices/workspaces/templates/arm/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.json create mode 100644 services/MachineLearningServices/workspaces/templates/bicep/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.bicep create mode 100644 services/MachineLearningServices/workspaces/templates/bicep/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.bicep create mode 100644 services/MachineLearningServices/workspaces/templates/bicep/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.bicep create mode 100644 services/MachineLearningServices/workspaces/templates/bicep/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.bicep create mode 100644 services/Search/searchServices/templates/arm/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.json create mode 100644 services/Search/searchServices/templates/bicep/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.json create mode 100644 services/StorageCache/AmlFilesystems/templates/arm/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.json create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.bicep create mode 100644 services/StorageCache/AmlFilesystems/templates/bicep/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.bicep diff --git a/services/AVS/privateClouds/templates/arm/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.json b/services/AVS/privateClouds/templates/arm/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.json new file mode 100644 index 000000000..10fe083d3 --- /dev/null +++ b/services/AVS/privateClouds/templates/arm/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "CPU Usage per Cluster (Critical)", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 0, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "95", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT30M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "EffectiveCpuAverage", + "dimensions": [{"operator": "include", "name": "clustername", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/AVS/privateClouds/templates/arm/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.json b/services/AVS/privateClouds/templates/arm/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.json new file mode 100644 index 000000000..a3252a726 --- /dev/null +++ b/services/AVS/privateClouds/templates/arm/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "CPU Usage per Cluster", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "80", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT30M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "EffectiveCpuAverage", + "dimensions": [{"operator": "include", "name": "clustername", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/AVS/privateClouds/templates/arm/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.json b/services/AVS/privateClouds/templates/arm/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.json new file mode 100644 index 000000000..075c7ee72 --- /dev/null +++ b/services/AVS/privateClouds/templates/arm/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Memory Usage per Cluster (Critical)", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 0, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "95", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT30M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "UsageAverage", + "dimensions": [{"operator": "include", "name": "clustername", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/AVS/privateClouds/templates/arm/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.json b/services/AVS/privateClouds/templates/arm/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.json new file mode 100644 index 000000000..9fdf26bbc --- /dev/null +++ b/services/AVS/privateClouds/templates/arm/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Memory Usage per Cluster", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "80", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT30M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "UsageAverage", + "dimensions": [{"operator": "include", "name": "clustername", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/AVS/privateClouds/templates/arm/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.json b/services/AVS/privateClouds/templates/arm/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.json new file mode 100644 index 000000000..a6bc42e24 --- /dev/null +++ b/services/AVS/privateClouds/templates/arm/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Storage Usage per Datastore", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "70", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT30M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "DiskUsedPercentage", + "dimensions": [{"operator": "include", "name": "dsname", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/AVS/privateClouds/templates/bicep/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.bicep b/services/AVS/privateClouds/templates/bicep/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.bicep new file mode 100644 index 000000000..0fccc44b2 --- /dev/null +++ b/services/AVS/privateClouds/templates/bicep/CPUCritical_bb83ae53-3b91-49ff-a351-9545ea747335.bicep @@ -0,0 +1,140 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'CPU Usage per Cluster (Critical)' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 0 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 95 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT30M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'EffectiveCpuAverage' + dimensions: [ + { + name: 'clustername' + operator: 'include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/AVS/privateClouds/templates/bicep/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.bicep b/services/AVS/privateClouds/templates/bicep/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.bicep new file mode 100644 index 000000000..353e29373 --- /dev/null +++ b/services/AVS/privateClouds/templates/bicep/CPU_282cb835-592b-4e49-89c1-ea1aaefb37c4.bicep @@ -0,0 +1,140 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'CPU Usage per Cluster' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 80 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT30M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'EffectiveCpuAverage' + dimensions: [ + { + name: 'clustername' + operator: 'include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/AVS/privateClouds/templates/bicep/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.bicep b/services/AVS/privateClouds/templates/bicep/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.bicep new file mode 100644 index 000000000..4c970b8b6 --- /dev/null +++ b/services/AVS/privateClouds/templates/bicep/MemoryCritical_a2f5e5a3-ec38-4201-970f-971ad4707b93.bicep @@ -0,0 +1,140 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Memory Usage per Cluster (Critical)' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 0 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 95 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT30M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'UsageAverage' + dimensions: [ + { + name: 'clustername' + operator: 'include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/AVS/privateClouds/templates/bicep/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.bicep b/services/AVS/privateClouds/templates/bicep/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.bicep new file mode 100644 index 000000000..55c85d4bf --- /dev/null +++ b/services/AVS/privateClouds/templates/bicep/Memory_e840c7a9-e070-4dc9-919b-c75a3679f6b7.bicep @@ -0,0 +1,140 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Memory Usage per Cluster' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 80 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT30M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'UsageAverage' + dimensions: [ + { + name: 'clustername' + operator: 'include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/AVS/privateClouds/templates/bicep/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.bicep b/services/AVS/privateClouds/templates/bicep/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.bicep new file mode 100644 index 000000000..d8a5e9640 --- /dev/null +++ b/services/AVS/privateClouds/templates/bicep/Storage_8bafb3d5-d961-49a4-9867-f1cddfd703e0.bicep @@ -0,0 +1,140 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Storage Usage per Datastore' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 70 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT30M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'DiskUsedPercentage' + dimensions: [ + { + name: 'dsname' + operator: 'include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/CognitiveServices/accounts/templates/arm/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.json b/services/CognitiveServices/accounts/templates/arm/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.json new file mode 100644 index 000000000..a08c4b025 --- /dev/null +++ b/services/CognitiveServices/accounts/templates/arm/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Percentage of the prompt tokens hit the cache, avaiable for PTU-managed.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "75", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "AzureOpenAIContextTokensCacheMatchRate", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/CognitiveServices/accounts/templates/arm/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.json b/services/CognitiveServices/accounts/templates/arm/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.json new file mode 100644 index 000000000..f4a66fc03 --- /dev/null +++ b/services/CognitiveServices/accounts/templates/arm/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Utilization % for a provisoned-managed deployment, calculated as (PTUs consumed / PTUs deployed) x 100.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "80", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "AzureOpenAIProvisionedManagedUtilizationV2", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/CognitiveServices/accounts/templates/arm/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.json b/services/CognitiveServices/accounts/templates/arm/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.json new file mode 100644 index 000000000..a3b462e45 --- /dev/null +++ b/services/CognitiveServices/accounts/templates/arm/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Recommended latency (responsiveness) measure for streaming requests. Time in milliseconds.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "200", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "AzureOpenAITimeToResponse", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/CognitiveServices/accounts/templates/bicep/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.bicep b/services/CognitiveServices/accounts/templates/bicep/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.bicep new file mode 100644 index 000000000..393addddd --- /dev/null +++ b/services/CognitiveServices/accounts/templates/bicep/AzureOpenAIContextTokensCacheMatchRate_81f8369c-65bf-4194-bfd2-ffdfa2470577.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Percentage of the prompt tokens hit the cache, avaiable for PTU-managed.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 75 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'AzureOpenAIContextTokensCacheMatchRate' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/CognitiveServices/accounts/templates/bicep/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.bicep b/services/CognitiveServices/accounts/templates/bicep/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.bicep new file mode 100644 index 000000000..c425de20b --- /dev/null +++ b/services/CognitiveServices/accounts/templates/bicep/AzureOpenAIProvisionedManagedUtilizationV2_693a3b37-1e2a-42d1-aaed-b1f374276d1c.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Utilization % for a provisoned-managed deployment, calculated as (PTUs consumed / PTUs deployed) x 100.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 80 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'AzureOpenAIProvisionedManagedUtilizationV2' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/CognitiveServices/accounts/templates/bicep/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.bicep b/services/CognitiveServices/accounts/templates/bicep/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.bicep new file mode 100644 index 000000000..74758b96b --- /dev/null +++ b/services/CognitiveServices/accounts/templates/bicep/AzureOpenAITimeToResponse_995cc12a-1887-4669-92c5-70a6ca8bfe70.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Recommended latency (responsiveness) measure for streaming requests. Time in milliseconds.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 200 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'AzureOpenAITimeToResponse' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/MachineLearningServices/workspaces/templates/arm/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.json b/services/MachineLearningServices/workspaces/templates/arm/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.json new file mode 100644 index 000000000..c0e7f0473 --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/arm/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Number of model deployments that failed in this workspace.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 3, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "0", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "Model Deploy Failed", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/MachineLearningServices/workspaces/templates/arm/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.json b/services/MachineLearningServices/workspaces/templates/arm/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.json new file mode 100644 index 000000000..3928d116b --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/arm/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 3, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "0", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "Not Responding Runs", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/MachineLearningServices/workspaces/templates/arm/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.json b/services/MachineLearningServices/workspaces/templates/arm/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.json new file mode 100644 index 000000000..d2b2f5e8d --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/arm/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Percent of quota utilized.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 3, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "90", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "Quota Utilization Percentage", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/MachineLearningServices/workspaces/templates/arm/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.json b/services/MachineLearningServices/workspaces/templates/arm/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.json new file mode 100644 index 000000000..bda61d6bb --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/arm/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Number of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 3, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "0", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "Unusable Nodes", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/MachineLearningServices/workspaces/templates/bicep/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.bicep b/services/MachineLearningServices/workspaces/templates/bicep/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.bicep new file mode 100644 index 000000000..04325f934 --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/bicep/ModelDeployFailed_0337a76f-238e-4d4d-9cd1-48b205874dbb.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Number of model deployments that failed in this workspace.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 3 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 0 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'Model Deploy Failed' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/MachineLearningServices/workspaces/templates/bicep/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.bicep b/services/MachineLearningServices/workspaces/templates/bicep/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.bicep new file mode 100644 index 000000000..2e81b12d2 --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/bicep/NotRespondingRuns_d3b80f22-9f1d-3038-86ff-c4dd5ba02d7a.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Number of runs not responding for this workspace. Count is updated when a run enters Not Responding state.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 3 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 0 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'Not Responding Runs' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/MachineLearningServices/workspaces/templates/bicep/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.bicep b/services/MachineLearningServices/workspaces/templates/bicep/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.bicep new file mode 100644 index 000000000..8fff070e3 --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/bicep/QuotaUtilizationPercentage_be3f1bfc-c21a-4399-9b9f-a33ebdc470cb.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Percent of quota utilized.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 3 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 90 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'Quota Utilization Percentage' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/MachineLearningServices/workspaces/templates/bicep/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.bicep b/services/MachineLearningServices/workspaces/templates/bicep/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.bicep new file mode 100644 index 000000000..93dd546a6 --- /dev/null +++ b/services/MachineLearningServices/workspaces/templates/bicep/UnusableNodes_a171bc0c-676f-464b-a7b5-e50cd6c612a2.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Number of unusable nodes. Unusable nodes are not functional due to some unresolvable issue. Azure will recycle these nodes.' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 3 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 0 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'Unusable Nodes' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/Search/searchServices/templates/arm/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.json b/services/Search/searchServices/templates/arm/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.json new file mode 100644 index 000000000..1a057c27b --- /dev/null +++ b/services/Search/searchServices/templates/arm/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.json @@ -0,0 +1,95 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "metadata": { + "description": "Unique name (within the Resource Group) for the Activity log alert." + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Activity Log Alert for Search Service Delete", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Indicates whether or not the alert is enabled." + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/activityLogAlerts", + "apiVersion": "2017-04-01", + "name": "[parameters('alertName')]", + "location": "Global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": [ + "[subscription().id]" + ], + "enabled": "[parameters('isEnabled')]", + "condition": { + "allOf": [ + { + "field": "category", + "equals": "Administrative" + }, + { + "field": "operationName", + "equals": "Microsoft.Search/searchServices/delete" + }, + { + "field": "status", + "containsAny": ["succeeded"] + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/Search/searchServices/templates/bicep/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.bicep b/services/Search/searchServices/templates/bicep/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.bicep new file mode 100644 index 000000000..e9da93e1e --- /dev/null +++ b/services/Search/searchServices/templates/bicep/ActivityLogSearchServiceDelete_5611eb31-51c7-4279-ab8c-97dba0a2c044.bicep @@ -0,0 +1,68 @@ +@description('Unique name (within the Resource Group) for the Activity log alert.') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Activity Log Alert for Search Service Delete' + +@description('Indicates whether or not the alert is enabled.') +param isEnabled bool = true + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource symbolicname 'Microsoft.Insights/activityLogAlerts@2023-01-01-preview' = { + name: alertName + location: 'Global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: [ + subscription().id + ] + enabled: isEnabled + condition: { + allOf: [ + { + { + field: 'category' + equals: 'Administrative' + } + { + field: 'operationName' + equals: 'Microsoft.Search/searchServices/delete' + } + { + field: 'status' + containsAny: ['succeeded'] + } + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.json b/services/StorageCache/AmlFilesystems/templates/arm/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.json new file mode 100644 index 000000000..37f0174e6 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if MDTBytesUsed is above 85%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_used = 0.85; AzureMetrics | where MetricName == \"MDTBytesTotal\" or MetricName == \"MDTBytesUsed\" | summarize MDTBytesTotal = maxif(Total, MetricName == \"MDTBytesTotal\"), MDTBytesUsed = maxif(Total, MetricName == \"MDTBytesUsed\") | extend UsedRatio = MDTBytesUsed / MDTBytesTotal | where UsedRatio > threshold_used | project UsedRatio, MDTBytesUsed, MDTBytesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "85", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "UsedRatio", "operator": "Include", "values": ["*"]}, {"name": "MDTBytesUsed", "operator": "Include", "values": ["*"]}, {"name": "MDTBytesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.json b/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.json new file mode 100644 index 000000000..d59cb95d5 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if MDTBytesAvailable is below 15%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_used = 0.15; AzureMetrics | where MetricName == \"MDTBytesAvailable\" or MetricName == \"MDTBytesTotal\" | summarize MDTBytesAvailable = maxif(Total, MetricName == \"MDTBytesAvailable\"), MDTBytesTotal = maxif(Total, MetricName == \"MDTBytesTotal\") | extend AvailableRatio = MDTBytesAvailable / MDTBytesTotal | where AvailableRatio < threshold_available | project AvailableRatio, MDTBytesAvailable, MDTBytesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "LessThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "15", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "AvailableRatio", "operator": "Include", "values": ["*"]}, {"name": "MDTBytesAvailable", "operator": "Include", "values": ["*"]}, {"name": "MDTBytesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.json b/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.json new file mode 100644 index 000000000..c36818c6a --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if MDTFilesFree is below 15%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_used = 0.15; AzureMetrics | where MetricName == \"MDTFilesFree\" or MetricName == \"MDTFilesTotal\" | summarize MDTFilesFree = maxif(Total, MetricName == \"MDTFilesFree\"), MDTFilesTotal = maxif(Total, MetricName == \"MDTFilesTotal\") | extend FreeRatio = MDTFilesFree / MDTFilesTotal | where FreeRatio < threshold_free | project FreeRatio, MDTFilesFree, MDTFilesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "LessThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "15", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "FreeRatio", "operator": "Include", "values": ["*"]}, {"name": "MDTFilesFree", "operator": "Include", "values": ["*"]}, {"name": "MDTFilesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.json b/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.json new file mode 100644 index 000000000..83bbe912d --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if MDTFilesUsed is above 85%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_used = 0.85; AzureMetrics | where MetricName == \"MDTFilesTotal\" or MetricName == \"MDTFilesUsed\" | summarize MDTFilesTotal = maxif(Total, MetricName == \"MDTFilesTotal\"), MDTFilesUsed = maxif(Total, MetricName == \"MDTFilesUsed\") | extend FreeRatio = MDTFilesFree / MDTFilesTotal | where UsedRatio > threshold_used | project UsedRatio, MDTFilesUsed, MDTFilesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "85", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "UsedRatio", "operator": "Include", "values": ["*"]}, {"name": "MDTFilesUsed", "operator": "Include", "values": ["*"]}, {"name": "MDTFilesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.json b/services/StorageCache/AmlFilesystems/templates/arm/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.json new file mode 100644 index 000000000..3e3a9d50f --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if OSTBytesAvailable is below 15%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_free = 0.15; AzureMetrics | where MetricName == \"OSTBytesAvailable\" or MetricName == \"OSTBytesTotal\" | summarize OSTBytesAvailable = maxif(Total, MetricName == \"OSTBytesAvailable\"), OSTBytesTotal = maxif(Total, MetricName == \"OSTBytesTotal\") | extend AvailableRatio = OSTBytesAvailable / OSTBytesTotal | where AvailableRatio < threshold_available | project AvailableRatio, OSTBytesAvailable, OSTBytesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "LessThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "15", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "AvailableRatio", "operator": "Include", "values": ["*"]}, {"name": "OSTBytesAvailable", "operator": "Include", "values": ["*"]}, {"name": "OSTBytesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.json b/services/StorageCache/AmlFilesystems/templates/arm/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.json new file mode 100644 index 000000000..42cff46fb --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if OSTByteUsed is above 85%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_used = 0.85; AzureMetrics | where MetricName == \"OSTBytesTotal\" or MetricName == \"OSTBytesUsed\" | summarize OSTBytesTotal = maxif(Total, MetricName == \"OSTBytesTotal\"), OSTBytesUsed = maxif(Total, MetricName == \"OSTBytesUsed\") | extend UsedRatio = OSTBytesUsed / OSTBytesTotal | where UsedRatio > threshold_used | project UsedRatio, OSTBytesUsed, OSTBytesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "85", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "UsedRatio", "operator": "Include", "values": ["*"]}, {"name": "OSTBytesUsed", "operator": "Include", "values": ["*"]}, {"name": "OSTBytesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.json b/services/StorageCache/AmlFilesystems/templates/arm/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.json new file mode 100644 index 000000000..b5e4bca1a --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if OSTFilesFree is below 15%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_free = 0.15; AzureMetrics | where MetricName == \"OSTFilesFree\" or MetricName == \"OSTFilesTotal\" | summarize OSTFilesFree = maxif(Total, MetricName == \"OSTFilesFree\"), OSTFilesTotal = maxif(Total, MetricName == \"OSTFilesTotal\") | extend FreeRatio = OSTFilesFree / OSTFilesTotal | where FreeRatio < threshold_free | project FreeRatio, OSTFilesFree, OSTFilesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "LessThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "15", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "FreeRatio", "operator": "Include", "values": ["*"]}, {"name": "OSTFilesFree", "operator": "Include", "values": ["*"]}, {"name": "OSTFilesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.json b/services/StorageCache/AmlFilesystems/templates/arm/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.json new file mode 100644 index 000000000..3c699685d --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.json @@ -0,0 +1,256 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Log an alert if OSTFilesUsed is above 85%", + "metadata": { + "description": "Description of alert" + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "checkWorkspaceAlertsStorageConfigured": { + "type": "bool", + "defaultValue": false, + "metadata": { + "description": "Specifies whether to check linked storage and fail creation if the storage was not found" + } + }, + "resourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz" + } + }, + "muteActionsDuration": { + "type": "string", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H" + ], + "metadata": { + "description": "Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired." + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "autoMitigate": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert will automatically resolve" + } + }, + "query": { + "type": "string", + "minLength": 1, + "defaultValue": " let threshold_used = 0.85; AzureMetrics | where MetricName == \"OSTFilesTotal\" or MetricName == \"OSTFilesUsed\" | summarize OSTFilesTotal = maxif(Total, MetricName == \"OSTFilesTotal\"), OSTFilesUsed = maxif(Total, MetricName == \"OSTFilesUsed\") | extend UsedRatio = OSTFilesUsed / OSTFilesTotal | where UsedRatio > threshold_used | project UsedRatio, OSTFilesUsed, OSTFilesTotal ", + "metadata": { + "description": "Name of the metric used in the comparison to activate the alert." + } + }, + "metricMeasureColumn": { + "type": "string", + "defaultValue": "AggregatedValue", + "metadata": { + "description": "Name of the measure column used in the alert evaluation." + } + }, + "resourceIdColumn": { + "type": "string", + "defaultValue": "", + "metadata": { + "description": "Name of the resource ID column used in the alert targeting the alerts." + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "85", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "numberOfEvaluationPeriods": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of periods to check in the alert evaluation." + } + }, + "minFailingPeriodsToAlert": { + "type": "int", + "defaultValue": 1, + "metadata": { + "description": "The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods)." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Average", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]" + }, + "resources": [ + { + "type": "Microsoft.Insights/scheduledQueryRules", + "apiVersion": "2021-08-01", + "name": "[parameters('alertName')]", + "location": "[resourceGroup().location]", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "scopes": [ + "[parameters('resourceId')]" + ], + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "allOf": [ + { + "query": "[parameters('query')]", + "metricMeasureColumn": "[parameters('metricMeasureColumn')]", + "resourceIdColumn": "[parameters('resourceIdColumn')]", + "dimensions": [{"name": "UsedRatio", "operator": "Include", "values": ["*"]}, {"name": "OSTFilesUsed", "operator": "Include", "values": ["*"]}, {"name": "OSTFilesTotal", "operator": "Include", "values": ["*"]}], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "failingPeriods": { + "numberOfEvaluationPeriods": "[parameters('numberOfEvaluationPeriods')]", + "minFailingPeriodsToAlert": "[parameters('minFailingPeriodsToAlert')]" + } + } + ] + }, + "muteActionsDuration": "[parameters('muteActionsDuration')]", + "autoMitigate": "[parameters('autoMitigate')]", + "checkWorkspaceAlertsStorageConfigured": "[parameters('checkWorkspaceAlertsStorageConfigured')]" + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/arm/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.json b/services/StorageCache/AmlFilesystems/templates/arm/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.json new file mode 100644 index 000000000..c174a96c2 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/arm/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Total number of client input/output operations per second", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 1, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "LessThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "99", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "Uptime", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.bicep new file mode 100644 index 000000000..3dde5a525 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/MDTBytesUsed_ebd68fdd-9672-43e8-b7d5-6e479210535d.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if MDTBytesUsed is above 85%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_used = 0.85; AzureMetrics | where MetricName == "MDTBytesTotal" or MetricName == "MDTBytesUsed" | summarize MDTBytesTotal = maxif(Total, MetricName == "MDTBytesTotal"), MDTBytesUsed = maxif(Total, MetricName == "MDTBytesUsed") | extend UsedRatio = MDTBytesUsed / MDTBytesTotal | where UsedRatio > threshold_used | project UsedRatio, MDTBytesUsed, MDTBytesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 85 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'UsedRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTBytesUsed' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTBytesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.bicep new file mode 100644 index 000000000..41bb9b4f1 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesAvailable_ecec6f93-af7e-4071-b35d-cd70b3f16581.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if MDTBytesAvailable is below 15%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_used = 0.15; AzureMetrics | where MetricName == "MDTBytesAvailable" or MetricName == "MDTBytesTotal" | summarize MDTBytesAvailable = maxif(Total, MetricName == "MDTBytesAvailable"), MDTBytesTotal = maxif(Total, MetricName == "MDTBytesTotal") | extend AvailableRatio = MDTBytesAvailable / MDTBytesTotal | where AvailableRatio < threshold_available | project AvailableRatio, MDTBytesAvailable, MDTBytesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'LessThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 15 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'AvailableRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTBytesAvailable' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTBytesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.bicep new file mode 100644 index 000000000..4822dbdb6 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesFree_2feba8fd-ff1e-4f48-bc01-6e2996edafa6.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if MDTFilesFree is below 15%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_used = 0.15; AzureMetrics | where MetricName == "MDTFilesFree" or MetricName == "MDTFilesTotal" | summarize MDTFilesFree = maxif(Total, MetricName == "MDTFilesFree"), MDTFilesTotal = maxif(Total, MetricName == "MDTFilesTotal") | extend FreeRatio = MDTFilesFree / MDTFilesTotal | where FreeRatio < threshold_free | project FreeRatio, MDTFilesFree, MDTFilesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'LessThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 15 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'FreeRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTFilesFree' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTFilesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.bicep new file mode 100644 index 000000000..e42f3ac6c --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/MDTFilesUsed_48fc094d-8a00-4d3c-86d3-3230c7e5881a.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if MDTFilesUsed is above 85%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_used = 0.85; AzureMetrics | where MetricName == "MDTFilesTotal" or MetricName == "MDTFilesUsed" | summarize MDTFilesTotal = maxif(Total, MetricName == "MDTFilesTotal"), MDTFilesUsed = maxif(Total, MetricName == "MDTFilesUsed") | extend FreeRatio = MDTFilesFree / MDTFilesTotal | where UsedRatio > threshold_used | project UsedRatio, MDTFilesUsed, MDTFilesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 85 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'UsedRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTFilesUsed' + operator: 'Include' + values: ['*'] + } + { + name: 'MDTFilesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.bicep new file mode 100644 index 000000000..f54da1a33 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesAvailable_4eeca790-a804-4453-b339-73ea425610bc.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if OSTBytesAvailable is below 15%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_free = 0.15; AzureMetrics | where MetricName == "OSTBytesAvailable" or MetricName == "OSTBytesTotal" | summarize OSTBytesAvailable = maxif(Total, MetricName == "OSTBytesAvailable"), OSTBytesTotal = maxif(Total, MetricName == "OSTBytesTotal") | extend AvailableRatio = OSTBytesAvailable / OSTBytesTotal | where AvailableRatio < threshold_available | project AvailableRatio, OSTBytesAvailable, OSTBytesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'LessThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 15 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'AvailableRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTBytesAvailable' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTBytesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.bicep new file mode 100644 index 000000000..405f71dd9 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/OSTBytesUsed_59298086-ec77-4f47-b2ef-b853b79e31cb.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if OSTByteUsed is above 85%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_used = 0.85; AzureMetrics | where MetricName == "OSTBytesTotal" or MetricName == "OSTBytesUsed" | summarize OSTBytesTotal = maxif(Total, MetricName == "OSTBytesTotal"), OSTBytesUsed = maxif(Total, MetricName == "OSTBytesUsed") | extend UsedRatio = OSTBytesUsed / OSTBytesTotal | where UsedRatio > threshold_used | project UsedRatio, OSTBytesUsed, OSTBytesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 85 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'UsedRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTBytesUsed' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTBytesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.bicep new file mode 100644 index 000000000..0bdac3e4a --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesFree_8f231351-c123-4e4c-8631-9978e641a3ca.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if OSTFilesFree is below 15%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_free = 0.15; AzureMetrics | where MetricName == "OSTFilesFree" or MetricName == "OSTFilesTotal" | summarize OSTFilesFree = maxif(Total, MetricName == "OSTFilesFree"), OSTFilesTotal = maxif(Total, MetricName == "OSTFilesTotal") | extend FreeRatio = OSTFilesFree / OSTFilesTotal | where FreeRatio < threshold_free | project FreeRatio, OSTFilesFree, OSTFilesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'LessThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 15 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'FreeRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTFilesFree' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTFilesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.bicep new file mode 100644 index 000000000..b9dc8e593 --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/OSTFilesUsed_9d086772-1887-4893-8b9f-7e5169398bae.bicep @@ -0,0 +1,183 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Log an alert if OSTFilesUsed is above 85%' + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Specifies whether to check linked storage and fail creation if the storage was not found') +param checkWorkspaceAlertsStorageConfigured bool = false + +@description('Full Resource ID of the resource emitting the metric that will be used for the comparison. For example /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroups/ResourceGroupName/providers/Microsoft.compute/virtualMachines/VM_xyz') +@minLength(1) +param resourceId string + +@description('Mute actions for the chosen period of time (in ISO 8601 duration format) after the alert is fired.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' +]) +param muteActionsDuration string + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 2 + +@description('Specifies whether the alert will automatically resolve') +param autoMitigate bool = true + +@description('Name of the metric used in the comparison to activate the alert.') +@minLength(1) +param query string = ' let threshold_used = 0.85; AzureMetrics | where MetricName == "OSTFilesTotal" or MetricName == "OSTFilesUsed" | summarize OSTFilesTotal = maxif(Total, MetricName == "OSTFilesTotal"), OSTFilesUsed = maxif(Total, MetricName == "OSTFilesUsed") | extend UsedRatio = OSTFilesUsed / OSTFilesTotal | where UsedRatio > threshold_used | project UsedRatio, OSTFilesUsed, OSTFilesTotal ' + +@description('Name of the measure column used in the alert evaluation.') +param metricMeasureColumn string = 'AggregatedValue' + +@description('Name of the resource ID column used in the alert targeting the alerts.') +param resourceIdColumn string = '' + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'GreaterThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 85 + +@description('The number of periods to check in the alert evaluation.') +param numberOfEvaluationPeriods int = 1 + +@description('The number of unhealthy periods to alert on (must be lower or equal to numberOfEvaluationPeriods).') +param minFailingPeriodsToAlert int = 1 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Average' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT1M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT5M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource alert 'Microsoft.Insights/scheduledQueryRules@2021-08-01' = { + name: alertName + location: resourceGroup().location + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + severity: alertSeverity + enabled: isEnabled + scopes: [ + resourceId + ] + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + allOf: [ + { + query: query + metricMeasureColumn: metricMeasureColumn + resourceIdColumn: resourceIdColumn + dimensions: [ + { + name: 'UsedRatio' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTFilesUsed' + operator: 'Include' + values: ['*'] + } + { + name: 'OSTFilesTotal' + operator: 'Include' + values: ['*'] + }] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + failingPeriods: { + numberOfEvaluationPeriods: numberOfEvaluationPeriods + minFailingPeriodsToAlert: minFailingPeriodsToAlert + } + } + ] + } + muteActionsDuration: muteActionsDuration + autoMitigate: autoMitigate + checkWorkspaceAlertsStorageConfigured: checkWorkspaceAlertsStorageConfigured + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} diff --git a/services/StorageCache/AmlFilesystems/templates/bicep/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.bicep b/services/StorageCache/AmlFilesystems/templates/bicep/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.bicep new file mode 100644 index 000000000..fd041082f --- /dev/null +++ b/services/StorageCache/AmlFilesystems/templates/bicep/Uptime_7f951991-c6ce-4c72-9f55-7eade2c4f57c.bicep @@ -0,0 +1,135 @@ +@description('Name of the alert') +@minLength(1) +param alertName string + +@description('Description of alert') +param alertDescription string = 'Total number of client input/output operations per second' + +@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') +@minLength(1) +param targetResourceId array + +@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') +param targetResourceRegion string + +@description('Resource type of target resources to be monitored.') +@minLength(1) +param targetResourceType string + +@description('Specifies whether the alert is enabled') +param isEnabled bool = true + +@description('Severity of alert {0,1,2,3,4}') +@allowed([ + 0 + 1 + 2 + 3 + 4 +]) +param alertSeverity int = 1 + +@description('Operator comparing the current value with the threshold value.') +@allowed([ + 'Equals' + 'GreaterThan' + 'GreaterThanOrEqual' + 'LessThan' + 'LessThanOrEqual' +]) +param operator string = 'LessThan' + +@description('The threshold value at which the alert is activated.') +param threshold int = 99 + +@description('How the data that is collected should be combined over time.') +@allowed([ + 'Average' + 'Minimum' + 'Maximum' + 'Total' + 'Count' +]) +param timeAggregation string = 'Total' + +@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' + 'PT6H' + 'PT12H' + 'PT24H' + 'P1D' +]) +param windowSize string = 'PT5M' + +@description('how often the metric alert is evaluated represented in ISO 8601 duration format') +@allowed([ + 'PT1M' + 'PT5M' + 'PT15M' + 'PT30M' + 'PT1H' +]) +param evaluationFrequency string = 'PT1M' + +@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') +param currentDateTimeUtcNow string = utcNow() + +@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') +@allowed([ + 'Yes' + 'No' +]) +param telemetryOptOut string = 'No' + +resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { + name: alertName + location: 'global' + tags: { + _deployed_by_amba: 'true' + } + properties: { + description: alertDescription + scopes: targetResourceId + targetResourceType: targetResourceType + targetResourceRegion: targetResourceRegion + severity: alertSeverity + enabled: isEnabled + evaluationFrequency: evaluationFrequency + windowSize: windowSize + criteria: { + 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' + allOf: [ + { + name: '1st criterion' + metricName: 'Uptime' + dimensions: [[]] + operator: operator + threshold: threshold + timeAggregation: timeAggregation + criterionType: 'StaticThresholdCriterion' + } + ] + } + } +} + +var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' +resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { + name: ambaTelemetryPidName + tags: { + _deployed_by_amba: 'true' + } + properties: { + mode: 'Incremental' + template: { + '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' + contentVersion: '1.0.0.0' + resources: [] + } + } +} From 560de78bbc5a03d6df467509e3585349f4c5c3ce Mon Sep 17 00:00:00 2001 From: Cassie Kays <86622587+cassiekays@users.noreply.github.com> Date: Thu, 31 Oct 2024 13:06:26 -0700 Subject: [PATCH 10/15] changed old alerts to visible false. changed index to visible --- services/CognitiveServices/accounts/_index.md | 2 +- services/CognitiveServices/accounts/alerts.yaml | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/services/CognitiveServices/accounts/_index.md b/services/CognitiveServices/accounts/_index.md index c158109b7..3637cac7e 100644 --- a/services/CognitiveServices/accounts/_index.md +++ b/services/CognitiveServices/accounts/_index.md @@ -1,7 +1,7 @@ --- title: accounts geekdocCollapseSection: true -geekdocHidden: true +geekdocHidden: false --- {{< alertList name="alertList" >}} diff --git a/services/CognitiveServices/accounts/alerts.yaml b/services/CognitiveServices/accounts/alerts.yaml index 2105993ce..f99b399b6 100644 --- a/services/CognitiveServices/accounts/alerts.yaml +++ b/services/CognitiveServices/accounts/alerts.yaml @@ -2,7 +2,7 @@ description: Total number of calls. type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-1205 @@ -22,7 +22,7 @@ 5xx). type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-1052 @@ -41,7 +41,7 @@ description: Latency in milliseconds. type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-882 @@ -61,7 +61,7 @@ - Server Errors)/Total Calls. Server Errors include any HTTP responses >=500.' type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-852 @@ -80,7 +80,7 @@ description: Number of calls with service internal error (HTTP response code 5xx). type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-606 @@ -99,7 +99,7 @@ description: Number of Inference Tokens Processed on an OpenAI Model type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-530 @@ -118,7 +118,7 @@ description: Number of calls that exceeded rate or quota limit. type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-468 @@ -137,7 +137,7 @@ description: Number of calls with client side error (HTTP response code 4xx). type: Metric verified: false - visible: true + visible: false tags: - auto-generated - agc-420 From 4a90b89c8c1c60f0c41cfa891304f9d86037f874 Mon Sep 17 00:00:00 2001 From: Akiliu0512 <122460647+Akiliu0512@users.noreply.github.com> Date: Fri, 1 Nov 2024 08:24:19 +0800 Subject: [PATCH 11/15] fix Alt text for image --- docs/content/patterns/artificial intelligence/rag/_index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/content/patterns/artificial intelligence/rag/_index.md b/docs/content/patterns/artificial intelligence/rag/_index.md index 53fa562a4..47325a2da 100644 --- a/docs/content/patterns/artificial intelligence/rag/_index.md +++ b/docs/content/patterns/artificial intelligence/rag/_index.md @@ -11,7 +11,7 @@ This page provides the alert settings for AI RAG pattern setup. It contains rele Below is a basic architecture of RAG implementation -![](https://github.com/Azure/GPT-RAG/blob/main/media/architecture-GPT-RAG-Basic.png?raw=true) +![RAG Basic Architecture](https://github.com/Azure/GPT-RAG/blob/main/media/architecture-GPT-RAG-Basic.png?raw=true) We may update these settings as we continue to work with a breadth of customers. From bc4630bf4996844f9e6852ba5cca5d8a329f4424 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Fri, 1 Nov 2024 03:51:07 +0000 Subject: [PATCH 12/15] [GitHub Action - Generate Templates] Generate templates for alerts --- ..._87fe8679-655d-4acb-a37c-b7faebe26d47.json | 199 ------------------ ..._ec8c928a-5206-4059-8aea-8486004dd30d.json | 199 ------------------ ..._d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.json | 199 ------------------ ..._3c550d9c-8276-4a61-b0cf-ef437a55e299.json | 199 ------------------ ..._80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.json | 199 ------------------ ..._287a29bf-097d-4c4a-9ac5-df70a10f6903.json | 199 ------------------ ..._07f1ae0a-94f3-41da-b3a6-ca9188e416cb.json | 199 ------------------ ..._e228ad2d-7f9f-4843-88e2-57f6d44c59e9.json | 199 ------------------ ...87fe8679-655d-4acb-a37c-b7faebe26d47.bicep | 135 ------------ ...ec8c928a-5206-4059-8aea-8486004dd30d.bicep | 135 ------------ ...d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.bicep | 135 ------------ ...3c550d9c-8276-4a61-b0cf-ef437a55e299.bicep | 135 ------------ ...80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.bicep | 135 ------------ ...287a29bf-097d-4c4a-9ac5-df70a10f6903.bicep | 135 ------------ ...07f1ae0a-94f3-41da-b3a6-ca9188e416cb.bicep | 135 ------------ ...e228ad2d-7f9f-4843-88e2-57f6d44c59e9.bicep | 135 ------------ 16 files changed, 2672 deletions(-) delete mode 100644 services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.json delete mode 100644 services/CognitiveServices/accounts/templates/arm/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.json delete mode 100644 services/CognitiveServices/accounts/templates/bicep/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.bicep delete mode 100644 services/CognitiveServices/accounts/templates/bicep/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.bicep diff --git a/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json b/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json deleted file mode 100644 index eaebbe5c5..000000000 --- a/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Number of calls that exceeded rate or quota limit.", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 2, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "0", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "BlockedCalls", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.json b/services/CognitiveServices/accounts/templates/arm/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.json deleted file mode 100644 index 3707bb0a1..000000000 --- a/services/CognitiveServices/accounts/templates/arm/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Number of calls with client side error (HTTP response code 4xx).", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 1, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "0", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "ClientErrors", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.json b/services/CognitiveServices/accounts/templates/arm/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.json deleted file mode 100644 index 38da92fbd..000000000 --- a/services/CognitiveServices/accounts/templates/arm/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Latency in milliseconds.", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 2, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "90", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Average", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "Latency", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.json b/services/CognitiveServices/accounts/templates/arm/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.json deleted file mode 100644 index bb5ecde96..000000000 --- a/services/CognitiveServices/accounts/templates/arm/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Number of calls with service internal error (HTTP response code 5xx).", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 3, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "0", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "ServerErrors", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.json b/services/CognitiveServices/accounts/templates/arm/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.json deleted file mode 100644 index 21274fb86..000000000 --- a/services/CognitiveServices/accounts/templates/arm/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Availability percentage with the following calculation: (Total Calls - Server Errors)/Total Calls. Server Errors include any HTTP responses >=500.", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 3, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "LessThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "100", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Average", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "SuccessRate", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.json b/services/CognitiveServices/accounts/templates/arm/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.json deleted file mode 100644 index 70a512db0..000000000 --- a/services/CognitiveServices/accounts/templates/arm/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Number of Inference Tokens Processed on an OpenAI Model", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 2, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "180000", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "TokenTransaction", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.json b/services/CognitiveServices/accounts/templates/arm/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.json deleted file mode 100644 index 3ec0bd7ad..000000000 --- a/services/CognitiveServices/accounts/templates/arm/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Total number of calls.", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 3, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "5000", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "TotalCalls", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/arm/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.json b/services/CognitiveServices/accounts/templates/arm/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.json deleted file mode 100644 index 5a2eb0410..000000000 --- a/services/CognitiveServices/accounts/templates/arm/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Total number of calls with error response (HTTP response code 4xx or 5xx).", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 2, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "5", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "TotalErrors", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} diff --git a/services/CognitiveServices/accounts/templates/bicep/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.bicep b/services/CognitiveServices/accounts/templates/bicep/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.bicep deleted file mode 100644 index 24bb27923..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Number of calls that exceeded rate or quota limit.' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 2 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 0 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Total' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'BlockedCalls' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.bicep b/services/CognitiveServices/accounts/templates/bicep/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.bicep deleted file mode 100644 index 8ef3ee774..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/ClientErrors_ec8c928a-5206-4059-8aea-8486004dd30d.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Number of calls with client side error (HTTP response code 4xx).' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 1 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 0 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Total' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'ClientErrors' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.bicep b/services/CognitiveServices/accounts/templates/bicep/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.bicep deleted file mode 100644 index 98204477a..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/Latency_d76ab40a-2831-4fa2-b476-5fdcda3d7c4c.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Latency in milliseconds.' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 2 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 90 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Average' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'Latency' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.bicep b/services/CognitiveServices/accounts/templates/bicep/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.bicep deleted file mode 100644 index 0f7bc916c..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/ServerErrors_3c550d9c-8276-4a61-b0cf-ef437a55e299.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Number of calls with service internal error (HTTP response code 5xx).' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 3 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 0 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Total' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'ServerErrors' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.bicep b/services/CognitiveServices/accounts/templates/bicep/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.bicep deleted file mode 100644 index 19b1a1cda..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/SuccessRate_80f3c9ae-7da9-462f-ab44-2ff80d27c8f1.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Availability percentage with the following calculation: (Total Calls - Server Errors)/Total Calls. Server Errors include any HTTP responses >=500.' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 3 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'LessThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 100 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Average' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'SuccessRate' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.bicep b/services/CognitiveServices/accounts/templates/bicep/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.bicep deleted file mode 100644 index 272a7be66..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/TokenTransaction_287a29bf-097d-4c4a-9ac5-df70a10f6903.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Number of Inference Tokens Processed on an OpenAI Model' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 2 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 180000 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Total' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'TokenTransaction' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.bicep b/services/CognitiveServices/accounts/templates/bicep/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.bicep deleted file mode 100644 index ae0f1040c..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/TotalCalls_07f1ae0a-94f3-41da-b3a6-ca9188e416cb.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Total number of calls.' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 3 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 5000 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Total' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'TotalCalls' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} diff --git a/services/CognitiveServices/accounts/templates/bicep/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.bicep b/services/CognitiveServices/accounts/templates/bicep/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.bicep deleted file mode 100644 index 8e91ce6c8..000000000 --- a/services/CognitiveServices/accounts/templates/bicep/TotalErrors_e228ad2d-7f9f-4843-88e2-57f6d44c59e9.bicep +++ /dev/null @@ -1,135 +0,0 @@ -@description('Name of the alert') -@minLength(1) -param alertName string - -@description('Description of alert') -param alertDescription string = 'Total number of calls with error response (HTTP response code 4xx or 5xx).' - -@description('Array of Azure resource Ids. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name') -@minLength(1) -param targetResourceId array - -@description('Azure region in which target resources to be monitored are in (without spaces). For example: EastUS') -param targetResourceRegion string - -@description('Resource type of target resources to be monitored.') -@minLength(1) -param targetResourceType string - -@description('Specifies whether the alert is enabled') -param isEnabled bool = true - -@description('Severity of alert {0,1,2,3,4}') -@allowed([ - 0 - 1 - 2 - 3 - 4 -]) -param alertSeverity int = 2 - -@description('Operator comparing the current value with the threshold value.') -@allowed([ - 'Equals' - 'GreaterThan' - 'GreaterThanOrEqual' - 'LessThan' - 'LessThanOrEqual' -]) -param operator string = 'GreaterThan' - -@description('The threshold value at which the alert is activated.') -param threshold int = 5 - -@description('How the data that is collected should be combined over time.') -@allowed([ - 'Average' - 'Minimum' - 'Maximum' - 'Total' - 'Count' -]) -param timeAggregation string = 'Total' - -@description('Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format.') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' - 'PT6H' - 'PT12H' - 'PT24H' - 'P1D' -]) -param windowSize string = 'PT5M' - -@description('how often the metric alert is evaluated represented in ISO 8601 duration format') -@allowed([ - 'PT1M' - 'PT5M' - 'PT15M' - 'PT30M' - 'PT1H' -]) -param evaluationFrequency string = 'PT1M' - -@description('"The current date and time using the utcNow function. Used for deployment name uniqueness') -param currentDateTimeUtcNow string = utcNow() - -@description('The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry.') -@allowed([ - 'Yes' - 'No' -]) -param telemetryOptOut string = 'No' - -resource metricAlert 'Microsoft.Insights/metricAlerts@2018-03-01' = { - name: alertName - location: 'global' - tags: { - _deployed_by_amba: 'true' - } - properties: { - description: alertDescription - scopes: targetResourceId - targetResourceType: targetResourceType - targetResourceRegion: targetResourceRegion - severity: alertSeverity - enabled: isEnabled - evaluationFrequency: evaluationFrequency - windowSize: windowSize - criteria: { - 'odata.type': 'Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria' - allOf: [ - { - name: '1st criterion' - metricName: 'TotalErrors' - dimensions: [[]] - operator: operator - threshold: threshold - timeAggregation: timeAggregation - criterionType: 'StaticThresholdCriterion' - } - ] - } - } -} - -var ambaTelemetryPidName = 'pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-${uniqueString(resourceGroup().id, alertName, currentDateTimeUtcNow)}' -resource ambaTelemetryPid 'Microsoft.Resources/deployments@2020-06-01' = if (telemetryOptOut == 'No') { - name: ambaTelemetryPidName - tags: { - _deployed_by_amba: 'true' - } - properties: { - mode: 'Incremental' - template: { - '$schema': 'https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#' - contentVersion: '1.0.0.0' - resources: [] - } - } -} From 109c90944fd5734fb8cb06f4a23ede03d9e4bc3f Mon Sep 17 00:00:00 2001 From: Jan Faurskov <22591930+jfaurskov@users.noreply.github.com> Date: Fri, 1 Nov 2024 08:34:53 +0100 Subject: [PATCH 13/15] run_tests check --- .github/workflows/unit-test-arm-templates.yml | 1 + 1 file changed, 1 insertion(+) diff --git a/.github/workflows/unit-test-arm-templates.yml b/.github/workflows/unit-test-arm-templates.yml index 2d973821f..a15921523 100644 --- a/.github/workflows/unit-test-arm-templates.yml +++ b/.github/workflows/unit-test-arm-templates.yml @@ -81,6 +81,7 @@ jobs: continue-on-error: true - name: Check for failed tests id: check_fail + if: steps.run_tests.conclusion == 'success' shell: pwsh run: | echo "Number of failed tests: ${{ env.failtests }}" From 7339529a773c51b5a2ae194830d5a03e7120dba7 Mon Sep 17 00:00:00 2001 From: Jan Faurskov <22591930+jfaurskov@users.noreply.github.com> Date: Fri, 1 Nov 2024 08:41:46 +0100 Subject: [PATCH 14/15] test --- ..._87fe8679-655d-4acb-a37c-b7faebe26d47.json | 199 ------------------ 1 file changed, 199 deletions(-) delete mode 100644 services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json diff --git a/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json b/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json deleted file mode 100644 index eaebbe5c5..000000000 --- a/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json +++ /dev/null @@ -1,199 +0,0 @@ -{ - "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "parameters": { - "alertName": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Name of the alert" - } - }, - "alertDescription": { - "type": "string", - "defaultValue": "Number of calls that exceeded rate or quota limit.", - "metadata": { - "description": "Description of alert" - } - }, - "targetResourceId": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" - } - }, - "targetResourceRegion": { - "type": "string", - "metadata": { - "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" - } - }, - "targetResourceType": { - "type": "string", - "minLength": 1, - "metadata": { - "description": "Resource type of target resources to be monitored." - } - }, - "isEnabled": { - "type": "bool", - "defaultValue": true, - "metadata": { - "description": "Specifies whether the alert is enabled" - } - }, - "alertSeverity": { - "type": "int", - "defaultValue": 2, - "allowedValues": [ - 0, - 1, - 2, - 3, - 4 - ], - "metadata": { - "description": "Severity of alert {0,1,2,3,4}" - } - }, - "operator": { - "type": "string", - "defaultValue": "GreaterThan", - "allowedValues": [ - "Equals", - "GreaterThan", - "GreaterThanOrEqual", - "LessThan", - "LessThanOrEqual" - ], - "metadata": { - "description": "Operator comparing the current value with the threshold value." - } - }, - "threshold": { - "type": "string", - "defaultValue": "0", - "metadata": { - "description": "The threshold value at which the alert is activated." - } - }, - "timeAggregation": { - "type": "string", - "defaultValue": "Total", - "allowedValues": [ - "Average", - "Minimum", - "Maximum", - "Total", - "Count" - ], - "metadata": { - "description": "How the data that is collected should be combined over time." - } - }, - "windowSize": { - "type": "string", - "defaultValue": "PT5M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H", - "PT6H", - "PT12H", - "PT24H", - "PT1D" - ], - "metadata": { - "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." - } - }, - "evaluationFrequency": { - "type": "string", - "defaultValue": "PT1M", - "allowedValues": [ - "PT1M", - "PT5M", - "PT15M", - "PT30M", - "PT1H" - ], - "metadata": { - "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" - } - }, - "currentDateTimeUtcNow": { - "type": "string", - "defaultValue": "[utcNow()]", - "metadata": { - "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" - } - }, - "telemetryOptOut": { - "type": "string", - "defaultValue": "No", - "allowedValues": [ - "Yes", - "No" - ], - "metadata": { - "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." - } - } - }, - "variables": { - "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", - "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" - }, - "resources": [ - { - "type": "Microsoft.Insights/metricAlerts", - "apiVersion": "2018-03-01", - "name": "[parameters('alertName')]", - "location": "global", - "tags": { - "_deployed_by_amba": true - }, - "properties": { - "description": "[parameters('alertDescription')]", - "scopes": "[variables('varTargetResourceId')]", - "targetResourceType": "[parameters('targetResourceType')]", - "targetResourceRegion": "[parameters('targetResourceRegion')]", - "severity": "[parameters('alertSeverity')]", - "enabled": "[parameters('isEnabled')]", - "evaluationFrequency": "[parameters('evaluationFrequency')]", - "windowSize": "[parameters('windowSize')]", - "criteria": { - "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", - "allOf": [ - { - "name": "1st criterion", - "metricName": "BlockedCalls", - "dimensions": [], - "operator": "[parameters('operator')]", - "threshold": "[parameters('threshold')]", - "timeAggregation": "[parameters('timeAggregation')]", - "criterionType": "StaticThresholdCriterion" - } - ] - } - } - }, - { - "condition": "[equals(parameters('telemetryOptOut'), 'No')]", - "apiVersion": "2020-06-01", - "name": "[variables('pidDeploymentName')]", - "type": "Microsoft.Resources/deployments", - "properties": { - "mode": "Incremental", - "template": { - "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", - "contentVersion": "1.0.0.0", - "resources": [] - } - } - } - ] -} From 21536f82bc5e20a451e5e2a46838e4c7c0f3ce9c Mon Sep 17 00:00:00 2001 From: Jan Faurskov <22591930+jfaurskov@users.noreply.github.com> Date: Fri, 1 Nov 2024 08:43:01 +0100 Subject: [PATCH 15/15] reset test --- ..._87fe8679-655d-4acb-a37c-b7faebe26d47.json | 199 ++++++++++++++++++ 1 file changed, 199 insertions(+) create mode 100644 services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json diff --git a/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json b/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json new file mode 100644 index 000000000..eaebbe5c5 --- /dev/null +++ b/services/CognitiveServices/accounts/templates/arm/BlockedCalls_87fe8679-655d-4acb-a37c-b7faebe26d47.json @@ -0,0 +1,199 @@ +{ + "$schema": "https://schema.management.azure.com/schemas/2019-04-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "parameters": { + "alertName": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Name of the alert" + } + }, + "alertDescription": { + "type": "string", + "defaultValue": "Number of calls that exceeded rate or quota limit.", + "metadata": { + "description": "Description of alert" + } + }, + "targetResourceId": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "List of Azure resource Ids seperated by a comma. For example - /subscriptions/00000000-0000-0000-0000-0000-00000000/resourceGroup/resource-group-name/Microsoft.compute/virtualMachines/vm-name" + } + }, + "targetResourceRegion": { + "type": "string", + "metadata": { + "description": "Azure region in which target resources to be monitored are in (without spaces). For example: EastUS" + } + }, + "targetResourceType": { + "type": "string", + "minLength": 1, + "metadata": { + "description": "Resource type of target resources to be monitored." + } + }, + "isEnabled": { + "type": "bool", + "defaultValue": true, + "metadata": { + "description": "Specifies whether the alert is enabled" + } + }, + "alertSeverity": { + "type": "int", + "defaultValue": 2, + "allowedValues": [ + 0, + 1, + 2, + 3, + 4 + ], + "metadata": { + "description": "Severity of alert {0,1,2,3,4}" + } + }, + "operator": { + "type": "string", + "defaultValue": "GreaterThan", + "allowedValues": [ + "Equals", + "GreaterThan", + "GreaterThanOrEqual", + "LessThan", + "LessThanOrEqual" + ], + "metadata": { + "description": "Operator comparing the current value with the threshold value." + } + }, + "threshold": { + "type": "string", + "defaultValue": "0", + "metadata": { + "description": "The threshold value at which the alert is activated." + } + }, + "timeAggregation": { + "type": "string", + "defaultValue": "Total", + "allowedValues": [ + "Average", + "Minimum", + "Maximum", + "Total", + "Count" + ], + "metadata": { + "description": "How the data that is collected should be combined over time." + } + }, + "windowSize": { + "type": "string", + "defaultValue": "PT5M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H", + "PT6H", + "PT12H", + "PT24H", + "PT1D" + ], + "metadata": { + "description": "Period of time used to monitor alert activity based on the threshold. Must be between one minute and one day. ISO 8601 duration format." + } + }, + "evaluationFrequency": { + "type": "string", + "defaultValue": "PT1M", + "allowedValues": [ + "PT1M", + "PT5M", + "PT15M", + "PT30M", + "PT1H" + ], + "metadata": { + "description": "how often the metric alert is evaluated represented in ISO 8601 duration format" + } + }, + "currentDateTimeUtcNow": { + "type": "string", + "defaultValue": "[utcNow()]", + "metadata": { + "description": "The current date and time using the utcNow function. Used for deployment name uniqueness" + } + }, + "telemetryOptOut": { + "type": "string", + "defaultValue": "No", + "allowedValues": [ + "Yes", + "No" + ], + "metadata": { + "description": "The customer usage identifier used for telemetry purposes. The default value of False enables telemetry. The value of True disables telemetry." + } + } + }, + "variables": { + "pidDeploymentName": "[take(concat('pid-8bb7cf8a-bcf7-4264-abcb-703ace2fc84d-', uniqueString(resourceGroup().id, parameters('alertName'), parameters('currentDateTimeUtcNow'))), 64)]", + "varTargetResourceId": "[split(parameters('targetResourceId'), ',')]" + }, + "resources": [ + { + "type": "Microsoft.Insights/metricAlerts", + "apiVersion": "2018-03-01", + "name": "[parameters('alertName')]", + "location": "global", + "tags": { + "_deployed_by_amba": true + }, + "properties": { + "description": "[parameters('alertDescription')]", + "scopes": "[variables('varTargetResourceId')]", + "targetResourceType": "[parameters('targetResourceType')]", + "targetResourceRegion": "[parameters('targetResourceRegion')]", + "severity": "[parameters('alertSeverity')]", + "enabled": "[parameters('isEnabled')]", + "evaluationFrequency": "[parameters('evaluationFrequency')]", + "windowSize": "[parameters('windowSize')]", + "criteria": { + "odata.type": "Microsoft.Azure.Monitor.MultipleResourceMultipleMetricCriteria", + "allOf": [ + { + "name": "1st criterion", + "metricName": "BlockedCalls", + "dimensions": [], + "operator": "[parameters('operator')]", + "threshold": "[parameters('threshold')]", + "timeAggregation": "[parameters('timeAggregation')]", + "criterionType": "StaticThresholdCriterion" + } + ] + } + } + }, + { + "condition": "[equals(parameters('telemetryOptOut'), 'No')]", + "apiVersion": "2020-06-01", + "name": "[variables('pidDeploymentName')]", + "type": "Microsoft.Resources/deployments", + "properties": { + "mode": "Incremental", + "template": { + "$schema": "https://schema.management.azure.com/schemas/2015-01-01/deploymentTemplate.json#", + "contentVersion": "1.0.0.0", + "resources": [] + } + } + } + ] +}