From e6723f9ae441fefcf0d3f24f8e100e7b05c5b77a Mon Sep 17 00:00:00 2001 From: Pranshu Srivastava Date: Mon, 7 Oct 2024 16:00:18 +0530 Subject: [PATCH] OCPBUGS-35095: sync k-mixin with upstream Also drop redundant KSM selector from KubeCPUOvercommit. Signed-off-by: Pranshu Srivastava --- assets/control-plane/prometheus-rule.yaml | 14 +++++-- jsonnet/jsonnetfile.json | 3 +- jsonnet/jsonnetfile.lock.json | 51 +++++++++++------------ 3 files changed, 36 insertions(+), 32 deletions(-) diff --git a/assets/control-plane/prometheus-rule.yaml b/assets/control-plane/prometheus-rule.yaml index c477f58dbb..f003bb0673 100644 --- a/assets/control-plane/prometheus-rule.yaml +++ b/assets/control-plane/prometheus-rule.yaml @@ -94,7 +94,7 @@ spec: summary: StatefulSet update has not been rolled out. expr: | ( - max without (revision) ( + max by(namespace, statefulset, job, cluster) ( kube_statefulset_status_current_revision{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"} unless kube_statefulset_status_update_revision{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"} @@ -232,7 +232,7 @@ spec: description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure. summary: Cluster has overcommitted CPU resource requests. expr: | - sum(namespace_cpu:kube_pod_container_resource_requests:sum{job="kube-state-metrics",}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 and (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 for: 10m @@ -336,7 +336,7 @@ spec: description: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. expr: | - sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by(cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 for: 5m labels: severity: warning @@ -477,7 +477,7 @@ spec: max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) ) record: node_namespace_pod_container:container_memory_swap - - name: k8s.rules.container_resource + - name: k8s.rules.container_memory_requests rules: - expr: | kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) @@ -496,6 +496,8 @@ spec: ) ) record: namespace_memory:kube_pod_container_resource_requests:sum + - name: k8s.rules.container_cpu_requests + rules: - expr: | kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( @@ -513,6 +515,8 @@ spec: ) ) record: namespace_cpu:kube_pod_container_resource_requests:sum + - name: k8s.rules.container_memory_limits + rules: - expr: | kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( @@ -530,6 +534,8 @@ spec: ) ) record: namespace_memory:kube_pod_container_resource_limits:sum + - name: k8s.rules.container_cpu_limits + rules: - expr: | kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( diff --git a/jsonnet/jsonnetfile.json b/jsonnet/jsonnetfile.json index 0b958450e2..bbbbcb093c 100644 --- a/jsonnet/jsonnetfile.json +++ b/jsonnet/jsonnetfile.json @@ -58,14 +58,13 @@ "version": "main" }, { - "name": "kubernetes-mixin is pinned because newer versions are breaking MON-3837", "source": { "git": { "remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin.git", "subdir": "" } }, - "version": "b247371d1780f530587a8d9dd04ccb19ea970ba0" + "version": "cb72d737459a655e7575c09f7859815ae3690981" } ], "legacyImports": true diff --git a/jsonnet/jsonnetfile.lock.json b/jsonnet/jsonnetfile.lock.json index 8ded37a347..f0baa034fc 100644 --- a/jsonnet/jsonnetfile.lock.json +++ b/jsonnet/jsonnetfile.lock.json @@ -18,7 +18,7 @@ "subdir": "contrib/mixin" } }, - "version": "5704c6148d798ea444db26a966394406d8c10526", + "version": "995027f5c1363404e86f7a858ea2833df01f0954", "sum": "IXI3LQIT9NmTPJAk8WLUJd5+qZfcGpeNCyWIK7oEpws=" }, { @@ -58,8 +58,8 @@ "subdir": "gen/grafonnet-latest" } }, - "version": "733beadbc8dab55c5fe1bcdcf0d8a2d215759a55", - "sum": "eyuJ0jOXeA4MrobbNgU4/v5a7ASDHslHZ0eS6hDdWoI=" + "version": "82a19822e54a0a12a51e24dbd48fcde717dc0864", + "sum": "64fMUPI3frXGj4X1FqFd1t7r04w3CUSmXaDcJ23EYbQ=" }, { "source": { @@ -68,18 +68,18 @@ "subdir": "gen/grafonnet-v10.0.0" } }, - "version": "733beadbc8dab55c5fe1bcdcf0d8a2d215759a55", + "version": "82a19822e54a0a12a51e24dbd48fcde717dc0864", "sum": "xdcrJPJlpkq4+5LpGwN4tPAuheNNLXZjE6tDcyvFjr0=" }, { "source": { "git": { "remote": "https://github.com/grafana/grafonnet.git", - "subdir": "gen/grafonnet-v11.0.0" + "subdir": "gen/grafonnet-v11.1.0" } }, - "version": "733beadbc8dab55c5fe1bcdcf0d8a2d215759a55", - "sum": "0BvzR0i4bS4hc2O3xDv6i9m52z7mPrjvqxtcPrGhynA=" + "version": "82a19822e54a0a12a51e24dbd48fcde717dc0864", + "sum": "41w7p/rwrNsITqNHMXtGSJAfAyKmnflg6rFhKBduUxM=" }, { "source": { @@ -88,7 +88,7 @@ "subdir": "grafana-builder" } }, - "version": "4ad199dab450b829274234b1014ca577649b4557", + "version": "ab84b9f67c7a7f61e0c0a311afb47a1af4f5903f", "sum": "yxqWcq/N3E/a/XreeU6EuE6X7kYPnG0AspAQFKOjASo=" }, { @@ -129,9 +129,8 @@ "subdir": "" } }, - "version": "b247371d1780f530587a8d9dd04ccb19ea970ba0", - "sum": "7M2QHK3WhOc1xT7T7KhL9iKsCYTfsIXpmcItffAcbL0=", - "name": "kubernetes-mixin is pinned because newer versions are breaking MON-3837" + "version": "cb72d737459a655e7575c09f7859815ae3690981", + "sum": "JaPnO5N/KUBgA9v6qE7CYzp8OWDTpzjM0+l/SPqL4m4=" }, { "source": { @@ -140,7 +139,7 @@ "subdir": "jsonnet/kube-state-metrics" } }, - "version": "f50205a4dfc81042bb140f289a3d2bc81a7557d0", + "version": "3c6bc839119b271bf9fa86809d5b3b1421fc1d36", "sum": "lO7jUSzAIy8Yk9pOWJIWgPRhubkWzVh56W6wtYfbVH4=" }, { @@ -150,7 +149,7 @@ "subdir": "jsonnet/kube-state-metrics-mixin" } }, - "version": "f50205a4dfc81042bb140f289a3d2bc81a7557d0", + "version": "3c6bc839119b271bf9fa86809d5b3b1421fc1d36", "sum": "qclI7LwucTjBef3PkGBkKxF0mfZPbHnn4rlNWKGtR4c=" }, { @@ -171,8 +170,8 @@ "subdir": "jsonnet/telemeter" } }, - "version": "ecc16b6a0335b0cd57e0de0a2850763eb9e145fa", - "sum": "n4IkAE4vnL+b2TqSr0c8JDZ7jRhNrnuruUz4MyAKEfU=", + "version": "0453f452b7ca677e3be10faa95bea714733b4830", + "sum": "0m1kvO0SH4YoldGek69nhBGMTPxYz3gYcyNhfrymAOE=", "name": "telemeter-client" }, { @@ -182,8 +181,8 @@ "subdir": "jsonnet/kube-prometheus" } }, - "version": "23db41ce8b6deed1d131444108d4259c901b843d", - "sum": "t+TcSKTyuukf1RRh0y82UixlYD36LCSoxx1CRfqKvYY=" + "version": "69d9636b64192418d64912c032f5437361e88ea5", + "sum": "W4HnSyscMMutOCaDyjNZy1XXcdhRPibYuV1yVgqxXm0=" }, { "source": { @@ -192,7 +191,7 @@ "subdir": "jsonnet/mixin" } }, - "version": "04b0019ca1863ed7b431c58d51889f5aa10fc437", + "version": "f4ecf80bd1051cb62a95a7c49ef228a67e5c2f45", "sum": "gi+knjdxs2T715iIQIntrimbHRgHnpM8IFBJDD1gYfs=", "name": "prometheus-operator-mixin" }, @@ -203,8 +202,8 @@ "subdir": "jsonnet/prometheus-operator" } }, - "version": "3271016a84d9b02b119d8f57cc178db6cb3bc706", - "sum": "viqiCZIsUz+BKJOnwOeHTuk00h2yDaoSenNH6PMuBcQ=" + "version": "37a55955b3abd23cb57af49216b76189b73dca98", + "sum": "fKeI+sfBrJlz74DYDQjZHhUFseDqhcg32mOEQxWZDYA=" }, { "source": { @@ -213,8 +212,8 @@ "subdir": "doc/alertmanager-mixin" } }, - "version": "e1492602209b86e0ca6d7671c7353b62a31b897b", - "sum": "IpF46ZXsm+0wJJAPtAre8+yxTNZA57mBqGpBP/r7/kw=", + "version": "ff8c09d60174f27850830ceed6be38b3cf86974b", + "sum": "Mf4h1BYLle2nrgjf/HXrBbl0Zk8N+xaoEM017o0BC+k=", "name": "alertmanager" }, { @@ -224,8 +223,8 @@ "subdir": "docs/node-mixin" } }, - "version": "71d9b6c06103a440a6590135467bc4c96174c9a1", - "sum": "rhUvbqviGjQ2mwsRhHKMN0TiS3YvnYpUXHew3XlQ+Wg=" + "version": "07ee8efaa4f8e7260eb8611f3f42973cbbf8ce8f", + "sum": "cQCW+1N0Xae5yXecCWDK2oAlN0luBS/5GrwBYSlaFms=" }, { "source": { @@ -234,7 +233,7 @@ "subdir": "documentation/prometheus-mixin" } }, - "version": "5037cf75f2d4f1671ad365ba1e99902fc36808d5", + "version": "4b56af7eb824d8e7dc13994b662b5c5b39928629", "sum": "dYLcLzGH4yF3qB7OGC/7z4nqeTNjv42L7Q3BENU8XJI=", "name": "prometheus" }, @@ -266,7 +265,7 @@ "subdir": "mixin" } }, - "version": "585899439beddde6018d9e8cfacc74d1efb5617f", + "version": "62038110b1bc47b1324b06a0f7d91c8bce680e5e", "sum": "ieCD4eMgGbOlrI8GmckGPHBGQDcLasE1rULYq56W/bs=" } ],