Updated Datadog agent configuration and added sample dashboard

monitoring/datadog-agent/README.md

@@ -1,9 +1,11 @@
-# Datadog Openmetrics Configuration Example
+# Datadog Openmetrics Configuration and Dashboard Example
 Datadog provides an agent that will scrape metrics across various sources including an Openmetrics endpoint like the one provided by Rockset. You can configure this agent to scrape metrics from your Rockset metrics endpoint using the Openmetrics integration.
+You can also import a sample dashboard that visualizes these metrics to get you started quickly.
 
 ## Dependencies
 1. Datadog Agent version 6.6.0 and above
 2. Enable Rockset metrics endpoint
+3. Access to a Datadog account
 
 ## Instructions
 Copy the [example](./openmetrics.d/conf.yaml) from this repository to your agent's host. The location of this configuration file on your agent host will generally be located at:
@@ -13,6 +15,10 @@ Copy the [example](./openmetrics.d/conf.yaml) from this repository to your agent
 
 The syntax is very specific and please note any differences between your file and the example provided. For exampe, the password must be an empty string in order to be encoded properly.
 
+You can import the sample dashboard into your Datadog account by following the instructions here: https://docs.datadoghq.com/dashboards/#copy-import-or-export-dashboard-json
+
+![image](https://github.com/lukalovosevic/community/assets/62242783/850dd6a2-f9d8-444a-9faa-7ecea01b6268)
+
 ## References
 - https://rockset.com/docs/monitoring-and-alerting/
-- https://docs.datadoghq.com/integrations/openmetrics/
+- https://docs.datadoghq.com/integrations/openmetrics/

monitoring/datadog-agent/openmetrics.d/RocksetMetricsDashboard.json

@@ -0,0 +1 @@
+{"title":"Rockset Metrics Dashboard","description":"","widgets":[{"id":1246456925018978,"definition":{"type":"image","url":"https://rockset-demo-ecommerce.s3.us-west-2.amazonaws.com/rockset.svg","sizing":"scale-down","has_background":false,"has_border":false,"vertical_align":"center","horizontal_align":"center"}},{"id":7186493897479482,"definition":{"title":"Collection Details","background_color":"purple","show_title":true,"type":"group","layout_type":"ordered","widgets":[{"id":6058642202006128,"definition":{"title":"Number of Collections per Workspace","title_size":"16","title_align":"left","type":"query_table","requests":[{"response_format":"scalar","queries":[{"name":"query1","data_source":"metrics","query":"sum:rockset.rockset_collections{*} by {workspace_name}","aggregator":"avg"}],"formulas":[{"cell_display_mode":"number","alias":"# of coll.","formula":"query1","limit":{"count":500,"order":"desc"},"number_format":{"unit":{"type":"canonical_unit","unit_name":"item"}}}]}],"has_search_bar":"auto"}},{"id":11,"definition":{"title":"Number of Documents per Collection","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_collection_documents{$scope} by {collection_name}"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"area"}]}},{"id":8,"definition":{"title":"Collection Size in Bytes","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1","number_format":{"unit":{"type":"canonical_unit","unit_name":"byte"}}}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_collection_size_bytes{$scope} by {collection_name}"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"area"}]}},{"id":8709473059158392,"definition":{"title":"Collection Size in Bytes","type":"query_table","requests":[{"response_format":"scalar","queries":[{"data_source":"metrics","name":"query1","query":"max:rockset.rockset_collection_size_bytes{*} by {collection_name}","aggregator":"avg"}],"formulas":[{"cell_display_mode":"bar","alias":"Coll. size","formula":"query1","limit":{"count":500,"order":"desc"},"number_format":{"unit":{"type":"canonical_unit","unit_name":"byte"}}}]}],"has_search_bar":"auto"}}]}},{"id":4564612793581622,"definition":{"title":"Virtual Instance Details","background_color":"purple","show_title":true,"type":"group","layout_type":"ordered","widgets":[{"id":4,"definition":{"title":"VI CPU Utilization","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"number_format":{"unit":{"type":"canonical_unit","unit_name":"percent"}},"formula":"query1"},{"number_format":{"unit":{"type":"canonical_unit","unit_name":"percent"}},"formula":"100 * query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"avg:rockset.rockset_leaf_cpu_utilization_percentage{$scope} by {virtual_instance_id}"}],"response_format":"timeseries","style":{"palette":"purple","order_reverse":false,"line_type":"solid","line_width":"normal"},"display_type":"line"}],"yaxis":{"include_zero":true,"scale":"linear","min":"0","max":"100"}}},{"id":2168985221699616,"definition":{"title":"VI Memory Utilization","title_size":"16","title_align":"left","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"number_format":{"unit":{"type":"canonical_unit","unit_name":"percent"}},"formula":"query1"},{"number_format":{"unit":{"type":"canonical_unit","unit_name":"percent"}},"formula":"100 * query1"}],"queries":[{"name":"query1","data_source":"metrics","query":"avg:rockset.rockset_leaf_memory_utilization_percentage{*} by {virtual_instance_id}"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"line"}],"yaxis":{"include_zero":true,"min":"0","max":"100"}}}]}},{"id":5479815899399802,"definition":{"title":"Ingestion Details","background_color":"purple","show_title":true,"type":"group","layout_type":"ordered","widgets":[{"id":10,"definition":{"title":"Total Ingested Bytes per Collection","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1","number_format":{"unit":{"type":"canonical_unit","unit_name":"byte"}}}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_collection_total_ingest_bytes.count{$scope} by {collection_name}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"area"}]}},{"id":22,"definition":{"title":"Parse Errors per Collection","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_collection_parse_errors.count{$scope} by {collection_name}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"line"}]}},{"id":18,"definition":{"title":"Ingest Transformation Errors per Collection","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_collection_ingest_transformation_errors.count{$scope}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"line"}]}},{"id":29,"definition":{"title":"Data Discovery Latency per Collection (ms)","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"number_format":{"unit":{"type":"canonical_unit","unit_name":"millisecond"}},"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"avg:rockset.rockset_collection_data_discovery_latency.bucket{$scope} by {collection_name}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}},{"id":14,"definition":{"title":"Data Processing Latency per Collection (ms)","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"number_format":{"unit":{"type":"canonical_unit","unit_name":"millisecond"}},"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"avg:rockset.rockset_collection_data_process_latency.bucket{$scope} by {collection_name}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}}]}},{"id":8525032580543298,"definition":{"title":"Query Metrics","background_color":"purple","show_title":true,"type":"group","layout_type":"ordered","widgets":[{"id":1,"definition":{"title":"Requested Queries","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_queries.count{virtual_instance_id:*} by {virtual_instance_id}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}},{"id":17,"definition":{"title":"Query Queue","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1","number_format":{"unit":{"type":"canonical_unit","unit_name":"item"}}}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_query_queue_size{$scope} by {virtual_instance_id}"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}},{"id":6,"definition":{"title":"Query Errors","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_query_errors.count{$scope} by {virtual_instance_id}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}},{"id":28,"definition":{"title":"Query Admission Control (seconds)","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1","number_format":{"unit":{"type":"canonical_unit","unit_name":"second"}}}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_query_admission_latency_seconds.sum{$scope} by {virtual_instance_id}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}},{"id":0,"definition":{"title":"Query Lambda Latency (ms)","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1","number_format":{"unit":{"type":"custom_unit_label","label":"ms"}}}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_query_lambda_latency_seconds.bucket{*} by {query_lambda}.as_rate()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}],"yaxis":{"include_zero":false}}},{"id":12,"definition":{"title":"Query Lambda Errors","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1"}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_query_lambda_errors.count{$scope} by {query_lambda}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}},{"id":27,"definition":{"title":"Query Lambda Admission Control (seconds)","show_legend":true,"legend_layout":"auto","legend_columns":["avg","min","max","value","sum"],"type":"timeseries","requests":[{"formulas":[{"formula":"query1","number_format":{"unit":{"type":"canonical_unit","unit_name":"second"}}}],"queries":[{"data_source":"metrics","name":"query1","query":"sum:rockset.rockset_query_lambda_admission_latency_seconds.sum{$scope} by {query_lambda}.as_count()"}],"response_format":"timeseries","style":{"palette":"purple","line_type":"solid","line_width":"normal"},"display_type":"bars"}]}}]}}],"template_variables":[{"name":"scope","available_values":[],"default":"*"}],"layout_type":"ordered","notify_list":[],"reflow_type":"auto"}

monitoring/datadog-agent/openmetrics.d/conf.yaml

@@ -2,10 +2,32 @@ init_config:
   service: rockset
 
 instances:
-  - openmetrics_endpoint: https://api.rs2.usw2.rockset.com/v1/orgs/self/metrics
+  - openmetrics_endpoint: https://api.usw2a1.rockset.com/v1/orgs/self/metrics
     ### make sure the api endpoint matches your region's endpoint url
     namespace: rockset
     extra_headers:
-        authorization: Apikey <api_key>
+        authorization: Apikey <your_api_key_here>
+    max_returned_metrics: 50000
     metrics:
-      - .+
+      - rockset_leaf_cpu_utilization_percentage
+      - rockset_leaf_memory_utilization_percentage
+      - rockset_agg_cpu_utilization_percentage
+      - rockset_agg_memory_utilization_percentage
+      - rockset_collections
+      - rockset_collection_size_bytes
+      - rockset_collection_documents
+      - rockset_collection_total_ingest_bytes
+      - rockset_collection_parse_errors
+      - rockset_collection_data_discovery_latency
+      - rockset_collection_data_process_latency
+      - rockset_data_discovery_latency
+      - rockset_data_process_latency
+      - rockset_queries
+      - rockset_query_latency_seconds
+      - rockset_query_admission_latency_seconds
+      - rockset_query_queue_size
+      - rockset_query_errors
+      - rockset_query_lambda_queries
+      - rockset_query_lambda_latency_seconds
+      - rockset_query_lambda_admission_latency_seconds
+      - rockset_query_lambda_errors