From 9ca2595bab8b6d8dc2044477032bf503d3a157fc Mon Sep 17 00:00:00 2001 From: klinch0 <68821526+klinch0@users.noreply.github.com> Date: Tue, 22 Apr 2025 16:35:54 +0300 Subject: [PATCH 1/5] [ci] Fix escaping for gen_versions_map.sh script (#836) Backport of #836 fixes errors like this: ``` make: Entering directory '/home/runner/work/cozystack/cozystack/packages/apps' find . -maxdepth 2 -name Chart.yaml | awk -F/ '{print $2}' | while read i; do sed -i "s/^name: .*/name: $i/" "$i/Chart.yaml"; done ../../hack/gen_versions_map.sh ../../hack/gen_versions_map.sh: 34: [: !=: unexpected operator fatal: Needed a single revision make: *** [Makefile:17: gen-versions-map] Error 128 make: Leaving directory '/home/runner/work/cozystack/cozystack/packages/apps' ``` https://github.com/cozystack/cozystack/actions/runs/14591720553/job/40928276862?pr=835 Improved reliability of version generation by handling empty or special values safely in the process. (cherry picked from commit 7a9a1fcba47cecb3a9f02eb9e3f6b1369a12b279) Signed-off-by: Nick Volynkin --- hack/gen_versions_map.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hack/gen_versions_map.sh b/hack/gen_versions_map.sh index 3b65bb4f..c325cff3 100755 --- a/hack/gen_versions_map.sh +++ b/hack/gen_versions_map.sh @@ -30,7 +30,7 @@ resolved_miss_map=$( fi # if commit is not HEAD, check if it's valid - if [ $commit != "HEAD" ]; then + if [ "x$commit" != "xHEAD" ]; then if [ $(git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') != "${version}" ]; then echo "Commit $commit for $chart $version is not valid" >&2 exit 1 From 4a72cc4fa665885fecbb90e58d651ce3a2f30689 Mon Sep 17 00:00:00 2001 From: Andrei Kvapil Date: Tue, 22 Apr 2025 17:53:36 +0200 Subject: [PATCH 2/5] [ci] Fix escaping for gen_versions_map.sh script (#842) Backport of #842 to release-v0.30 second attept of https://github.com/cozystack/cozystack/pull/836 - Improved reliability of version generation by handling empty or special values safely in the process. (cherry picked from commit e505857832b5ab38a977cff6a3804632a2a56e6a) Signed-off-by: Nick Volynkin --- hack/gen_versions_map.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/hack/gen_versions_map.sh b/hack/gen_versions_map.sh index c325cff3..27664229 100755 --- a/hack/gen_versions_map.sh +++ b/hack/gen_versions_map.sh @@ -24,14 +24,14 @@ search_commits=$(git ls-remote --tags origin | awk -F/ '$3 ~ /v[0-9]+.[0-9]+.[0- resolved_miss_map=$( echo "$miss_map" | while read -r chart version commit; do # if version is found in HEAD, it's HEAD - if [ $(awk '$1 == "version:" {print $2}' ./${chart}/Chart.yaml) = "${version}" ]; then + if [ "$(awk '$1 == "version:" {print $2}' ./${chart}/Chart.yaml)" = "${version}" ]; then echo "$chart $version HEAD" continue fi # if commit is not HEAD, check if it's valid - if [ "x$commit" != "xHEAD" ]; then - if [ $(git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') != "${version}" ]; then + if [ "$commit" != "HEAD" ]; then + if [ "$(git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}')" != "${version}" ]; then echo "Commit $commit for $chart $version is not valid" >&2 exit 1 fi @@ -44,7 +44,7 @@ resolved_miss_map=$( # if commit is HEAD, but version is not found in HEAD, check all tags found_tag="" for tag in $search_commits; do - if [ $(git show "${tag}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') = "${version}" ]; then + if [ "$(git show "${tag}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}')" = "${version}" ]; then found_tag=$(git rev-parse --short "${tag}") break fi From 9257dfe23023999250413ecea684df8436709613 Mon Sep 17 00:00:00 2001 From: Andrei Kvapil Date: Tue, 22 Apr 2025 18:38:08 +0200 Subject: [PATCH 3/5] [ci] Fix checkout and improve error output for gen_versions_map.sh (#845) Backport of #845 to release-v0.30 Third attempt to fix https://github.com/cozystack/cozystack/pull/842 and https://github.com/cozystack/cozystack/pull/836 tested in https://github.com/cozystack/cozystack/actions/runs/14599981710/job/40955508728?pr=808 Signed-off-by: Andrei Kvapil **Chores** - Improved GitHub Actions workflow to fetch full git history and tags during pre-commit checks. **Refactor** - Updated script behavior to display error messages when version extraction from git fails, making troubleshooting easier. (cherry picked from commit a6b02bf3810c2933db783727e319b9646851309c) Signed-off-by: Nick Volynkin --- .github/workflows/pre-commit.yml | 3 +++ hack/gen_versions_map.sh | 4 ++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/.github/workflows/pre-commit.yml b/.github/workflows/pre-commit.yml index 873bd9fc..a33c78e2 100644 --- a/.github/workflows/pre-commit.yml +++ b/.github/workflows/pre-commit.yml @@ -13,6 +13,9 @@ jobs: steps: - name: Checkout code uses: actions/checkout@v3 + with: + fetch-depth: 0 + fetch-tags: true - name: Set up Python uses: actions/setup-python@v4 diff --git a/hack/gen_versions_map.sh b/hack/gen_versions_map.sh index 27664229..5169bc2f 100755 --- a/hack/gen_versions_map.sh +++ b/hack/gen_versions_map.sh @@ -31,7 +31,7 @@ resolved_miss_map=$( # if commit is not HEAD, check if it's valid if [ "$commit" != "HEAD" ]; then - if [ "$(git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}')" != "${version}" ]; then + if [ "$(git show "${commit}:./${chart}/Chart.yaml" | awk '$1 == "version:" {print $2}')" != "${version}" ]; then echo "Commit $commit for $chart $version is not valid" >&2 exit 1 fi @@ -44,7 +44,7 @@ resolved_miss_map=$( # if commit is HEAD, but version is not found in HEAD, check all tags found_tag="" for tag in $search_commits; do - if [ "$(git show "${tag}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}')" = "${version}" ]; then + if [ "$(git show "${tag}:./${chart}/Chart.yaml" | awk '$1 == "version:" {print $2}')" = "${version}" ]; then found_tag=$(git rev-parse --short "${tag}") break fi From b70df68a5d9ac196f9c3ecf3b84ee1d1df5d4c71 Mon Sep 17 00:00:00 2001 From: Andrei Kvapil Date: Tue, 22 Apr 2025 18:55:47 +0200 Subject: [PATCH 4/5] [monitoring] Drop legacy label condition. (#826) Backport of #826 Updated dashboard metrics filters to exclude containers with empty names instead of specifically excluding containers named "POD". This change applies to all relevant CPU, memory, network, and storage metrics across capacity planning, controller, namespace, namespaces, and pod dashboards. No other dashboard functionality or structure was changed. (cherry picked from commit 277b438f688a0e56a9c5eafbe41a4cf4fc464457) Co-authored-by: Denis Seleznev Signed-off-by: Nick Volynkin --- dashboards/flux/flux-control-plane.json | 2 +- dashboards/main/capacity-planning.json | 24 ++++---- dashboards/main/controller.json | 74 +++++++++++----------- dashboards/main/namespace.json | 82 ++++++++++++------------- dashboards/main/namespaces.json | 76 +++++++++++------------ dashboards/main/pod.json | 58 ++++++++--------- 6 files changed, 158 insertions(+), 158 deletions(-) diff --git a/dashboards/flux/flux-control-plane.json b/dashboards/flux/flux-control-plane.json index 391538c7..bebbbdd3 100644 --- a/dashboards/flux/flux-control-plane.json +++ b/dashboards/flux/flux-control-plane.json @@ -626,7 +626,7 @@ "datasource": { "uid": "${DS_PROMETHEUS}" }, - "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",container!=\"POD\",container!=\"\",pod=~\".*-controller-.*\"}) by (pod)", + "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",container!=\"\",pod=~\".*-controller-.*\"}) by (pod)", "hide": false, "interval": "", "legendFormat": "{{pod}}", diff --git a/dashboards/main/capacity-planning.json b/dashboards/main/capacity-planning.json index 47abe1a8..b2a3b966 100644 --- a/dashboards/main/capacity-planning.json +++ b/dashboards/main/capacity-planning.json @@ -450,7 +450,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval])))\n / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))", + "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval])))\n / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))", "hide": false, "legendFormat": "Total", "range": true, @@ -520,7 +520,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"})) / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"memory\",unit=\"byte\",node=~\"$node\"}[$__rate_interval])))", + "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"})) / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"memory\",unit=\"byte\",node=~\"$node\"}[$__rate_interval])))", "hide": false, "legendFormat": "Total", "range": true, @@ -590,7 +590,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval]))) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))", + "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval]))) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))", "hide": false, "legendFormat": "Total", "range": true, @@ -660,7 +660,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"} )) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"}[$__rate_interval])))", + "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"} )) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"}[$__rate_interval])))", "hide": false, "legendFormat": "__auto", "range": true, @@ -1128,7 +1128,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0\n", + "expr": "sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0\n", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -1143,7 +1143,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0)", + "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0)", "hide": false, "legendFormat": "Total", "range": true, @@ -1527,7 +1527,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0\n", + "expr": "(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0\n", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -1542,7 +1542,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum((sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0)", + "expr": "sum((sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0)", "hide": false, "legendFormat": "Total", "range": true, @@ -1909,7 +1909,7 @@ }, "editorMode": "code", "exemplar": false, - "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) * -1 > 0)\n", + "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) * -1 > 0)\n", "format": "table", "instant": true, "range": false, @@ -2037,7 +2037,7 @@ }, "editorMode": "code", "exemplar": false, - "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) * -1 >0)\n", + "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) * -1 >0)\n", "format": "table", "instant": true, "range": false, @@ -2160,7 +2160,7 @@ }, "editorMode": "code", "exemplar": false, - "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) > 0)\n", + "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) > 0)\n", "format": "table", "instant": true, "range": false, @@ -2288,7 +2288,7 @@ }, "editorMode": "code", "exemplar": false, - "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) >0)\n", + "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) >0)\n", "format": "table", "instant": true, "range": false, diff --git a/dashboards/main/controller.json b/dashboards/main/controller.json index f6eaea06..9d0e0f47 100644 --- a/dashboards/main/controller.json +++ b/dashboards/main/controller.json @@ -684,7 +684,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "hide": false, "instant": true, @@ -710,7 +710,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (pod)\n(\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "sum by (pod)\n(\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "hide": false, "instant": true, @@ -723,7 +723,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod)\n (\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n ) > 0\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod)\n (\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n ) > 0\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "hide": false, "instant": true, @@ -736,7 +736,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) \n (\n (\n (\n sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n ) or sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n ) > 0\n )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) \n (\n (\n (\n sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n ) or sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n ) > 0\n )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "hide": false, "instant": true, @@ -762,7 +762,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -786,7 +786,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (pod)\n(\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "sum by (pod)\n(\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -798,7 +798,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod)\n (\n (\n (\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n ) > 0\n )\n )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod)\n (\n (\n (\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n ) > 0\n )\n )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -810,7 +810,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod)\n (\n (\n (\n sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n ) or sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n ) > 0\n )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod)\n (\n (\n (\n sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n -\n sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n ) or sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n ) > 0\n )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -848,7 +848,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -860,7 +860,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", + "expr": "(\n sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n * on (pod)\n sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -1315,7 +1315,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", + "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -1488,7 +1488,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -1502,7 +1502,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -1642,7 +1642,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum by (pod)\n (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n ) > 0\n )", + "expr": "sum by (pod)\n (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n ) > 0\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -1779,7 +1779,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": " (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n )\n or\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n )\n) > 0", + "expr": " (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n )\n or\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n )\n) > 0", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -2095,7 +2095,7 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Usage", @@ -2109,7 +2109,7 @@ "refId": "D" }, { - "expr": "sum by (pod)\n(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n)", + "expr": "sum by (pod)\n(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "VPA Target", @@ -2295,7 +2295,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "System", @@ -2306,7 +2306,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -2468,7 +2468,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", + "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -2653,7 +2653,7 @@ "uid": "${ds_prometheus}" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "RSS", @@ -2666,7 +2666,7 @@ "uid": "${ds_prometheus}" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "Cache", @@ -2679,7 +2679,7 @@ "uid": "${ds_prometheus}" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "Swap", @@ -2692,7 +2692,7 @@ "uid": "${ds_prometheus}" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", @@ -2705,7 +2705,7 @@ "uid": "${ds_prometheus}" }, "editorMode": "code", - "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)", + "expr": "sum (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n * on (pod)\n sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -2837,7 +2837,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (pod) group_left()\n sum by (pod)\n (\n (\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n ) > 0\n )\n)", + "expr": "(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (pod) group_left()\n sum by (pod)\n (\n (\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n ) > 0\n )\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -2974,7 +2974,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (pod) group_left()\n sum by (pod)\n (\n (\n (\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n ) > 0\n )\n)", + "expr": "(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (pod) group_left()\n sum by (pod)\n (\n (\n (\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n ) > 0\n )\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -3290,56 +3290,56 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "RSS", "refId": "A" }, { - "expr": "sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Cache", "refId": "B" }, { - "expr": "sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Swap", "refId": "C" }, { - "expr": "sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum by (pod)\n(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{namespace=\"$namespace\", container!=\"POD\", resource=\"memory\"}[$__rate_interval]))\n)", + "expr": "sum by (pod)\n(\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n * on (controller_type, controller_name) group_left()\n sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{namespace=\"$namespace\", container!=\"\", resource=\"memory\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "VPA Target", "refId": "E" }, { - "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Limits", "refId": "F" }, { - "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Requests", "refId": "G" }, { - "expr": "sum by(pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -3834,7 +3834,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", + "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -3972,7 +3972,7 @@ "uid": "$ds_prometheus" }, "editorMode": "code", - "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", + "expr": "sum by(pod) (\n max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n * on (pod)\n sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", diff --git a/dashboards/main/namespace.json b/dashboards/main/namespace.json index 9a53033c..ebf63517 100644 --- a/dashboards/main/namespace.json +++ b/dashboards/main/namespace.json @@ -656,7 +656,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -680,7 +680,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n ) \nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n ) \nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -692,7 +692,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -704,7 +704,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -728,7 +728,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -740,7 +740,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (pod) group_left()\n sum by (namespace, pod)\n (\n avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])\n )\n )\n or\n count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (pod) group_left()\n sum by (namespace, pod)\n (\n avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])\n )\n )\n or\n count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -752,7 +752,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n ) \n or \ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n ) \n or \ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -764,7 +764,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -776,7 +776,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller)\n (\n avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n ) > 0\n )\n )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -814,7 +814,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -826,7 +826,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -877,7 +877,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", + "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -1475,7 +1475,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))", + "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", @@ -1646,7 +1646,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))))", + "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))))", "format": "time_series", "intervalFactor": 1, "legendFormat": "System", @@ -1657,7 +1657,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))))", + "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -1798,7 +1798,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n ) > 0\n )\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n ) > 0\n )\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", @@ -1939,7 +1939,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n ) > 0\n )\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n ) > 0\n )\n )", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -2257,28 +2257,28 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))", + "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Usage", "refId": "D" }, { - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Requests", "refId": "C" }, { - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Limits", "refId": "E" }, { - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "VPA Target", @@ -2458,7 +2458,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))", + "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2470,7 +2470,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))", + "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -2622,7 +2622,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", @@ -2799,14 +2799,14 @@ "pluginVersion": "8.5.13", "targets": [ { - "expr": "sum\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "RSS", "refId": "A" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2814,7 +2814,7 @@ "refId": "B" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2822,14 +2822,14 @@ "refId": "C" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -2955,7 +2955,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n ) > 0\n )\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n ) > 0\n )\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", @@ -3091,7 +3091,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n )\n or\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n +\n sum by(namespace, pod, container) (avg_over_time(container_memory:kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n )\n ) > 0\n )\n )", + "expr": "sum by (controller)\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n * on (namespace, pod) group_left()\n sum by (namespace, pod)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n )\n or\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n +\n sum by(namespace, pod, container) (avg_over_time(container_memory:kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n )\n ) > 0\n )\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", @@ -3408,14 +3408,14 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left() \n sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left() \n sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "RSS", "refId": "A" }, { - "expr": "sum\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n * on (pod) group_left() \n sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n * on (pod) group_left() \n sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -3423,7 +3423,7 @@ "refId": "B" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left() \n sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left() \n sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -3431,35 +3431,35 @@ "refId": "C" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n ) ", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n ) ", "format": "time_series", "intervalFactor": 1, "legendFormat": "Requests", "refId": "E" }, { - "expr": "sum\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n * on (pod) group_left() \n sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n )", + "expr": "sum\n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n * on (pod) group_left() \n sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Limits", "refId": "F" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (controller_type, controller_name) group_left()\n sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "VPA Target", "refId": "G" }, { - "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n )", + "expr": "sum \n (\n kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n * on (pod) group_left()\n sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -3910,7 +3910,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])))", + "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", @@ -4049,7 +4049,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])))", + "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ controller }}", diff --git a/dashboards/main/namespaces.json b/dashboards/main/namespaces.json index bfbaf781..e05e8265 100644 --- a/dashboards/main/namespaces.json +++ b/dashboards/main/namespaces.json @@ -869,7 +869,7 @@ "refId": "A" }, { - "expr": "100 * count by (namespace) (\n sum by (namespace, verticalpodautoscaler) ( \n count by (namespace, controller_name, verticalpodautoscaler) (avg_over_time(vpa_target_recommendation{namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\n / on (controller_name, namespace) group_left\n count by (namespace, controller_name) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range]))\n )\n) \n/ count by (namespace) (sum by (namespace, controller) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "100 * count by (namespace) (\n sum by (namespace, verticalpodautoscaler) ( \n count by (namespace, controller_name, verticalpodautoscaler) (avg_over_time(vpa_target_recommendation{namespace=~\"$namespace\", container!=\"\"}[$__range]))\n / on (controller_name, namespace) group_left\n count by (namespace, controller_name) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range]))\n )\n) \n/ count by (namespace) (sum by (namespace, controller) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "hide": false, "instant": true, @@ -878,7 +878,7 @@ "refId": "B" }, { - "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "hide": false, "instant": true, @@ -895,7 +895,7 @@ "refId": "D" }, { - "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n ) > 0\n )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n ) > 0\n )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -903,7 +903,7 @@ "refId": "E" }, { - "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n )\n > 0\n )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n )\n > 0\n )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -919,7 +919,7 @@ "refId": "G" }, { - "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -935,7 +935,7 @@ "refId": "I" }, { - "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n ) > 0\n )\nor\ncount(avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n ) > 0\n )\nor\ncount(avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -943,7 +943,7 @@ "refId": "J" }, { - "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n )\n > 0\n )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n )\n > 0\n )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "instant": true, "intervalFactor": 1, @@ -968,7 +968,7 @@ "refId": "M" }, { - "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "hide": false, "instant": true, @@ -977,7 +977,7 @@ "refId": "N" }, { - "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", + "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0", "format": "table", "hide": false, "instant": true, @@ -1449,7 +1449,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -1616,7 +1616,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "System", @@ -1627,7 +1627,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -1764,7 +1764,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) > 0\n )", + "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) > 0\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -1901,7 +1901,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n )\n > 0\n )", + "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n )\n > 0\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -2210,7 +2210,7 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2218,21 +2218,21 @@ "refId": "A" }, { - "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})", + "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})", "format": "time_series", "intervalFactor": 1, "legendFormat": "Requests", "refId": "B" }, { - "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})", + "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})", "format": "time_series", "intervalFactor": 1, "legendFormat": "Limits", "refId": "C" }, { - "expr": "sum by (namespace) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "VPA Target", @@ -2407,7 +2407,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2419,7 +2419,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -2572,7 +2572,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -2754,14 +2754,14 @@ "pluginVersion": "8.5.13", "targets": [ { - "expr": "sum (avg_over_time(container_memory_rss{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (avg_over_time(container_memory_rss{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "RSS", "refId": "A" }, { - "expr": "sum (avg_over_time(container_memory_cache{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (avg_over_time(container_memory_cache{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2769,7 +2769,7 @@ "refId": "B" }, { - "expr": "sum (avg_over_time(container_memory_swap{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (avg_over_time(container_memory_swap{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -2777,14 +2777,14 @@ "refId": "C" }, { - "expr": "sum (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -2910,7 +2910,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) > 0\n )", + "expr": "sum by (namespace)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) > 0\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -3046,7 +3046,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n )\n > 0\n )", + "expr": "sum by (namespace)\n (\n (\n (\n sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n )\n > 0\n )", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -3370,14 +3370,14 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by (namespace) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "RSS", "refId": "A" }, { - "expr": "sum by (namespace) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -3385,7 +3385,7 @@ "refId": "B" }, { - "expr": "sum by (namespace) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -3393,35 +3393,35 @@ "refId": "C" }, { - "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum by(namespace) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))", + "expr": "sum by(namespace) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "VPA Target", "refId": "E" }, { - "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Requests", "refId": "F" }, { - "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Limits", "refId": "G" }, { - "expr": "sum by (namespace) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -3873,7 +3873,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", @@ -4008,7 +4008,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ namespace }}", diff --git a/dashboards/main/pod.json b/dashboards/main/pod.json index fdca7f65..f3201f34 100644 --- a/dashboards/main/pod.json +++ b/dashboards/main/pod.json @@ -686,7 +686,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)", + "expr": "sum by (container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)", "format": "table", "hide": false, "instant": true, @@ -759,7 +759,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)", + "expr": "sum by (container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -847,7 +847,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by(container) (rate(container_fs_reads_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__range]))", + "expr": "sum by(container) (rate(container_fs_reads_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__range]))", "format": "table", "hide": false, "instant": true, @@ -860,7 +860,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by(container) (rate(container_fs_writes_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__range]))", + "expr": "sum by(container) (rate(container_fs_writes_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__range]))", "format": "table", "hide": false, "instant": true, @@ -899,7 +899,7 @@ "type": "prometheus", "uid": "${ds_prometheus}" }, - "expr": "sum by (container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)", + "expr": "sum by (container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)", "format": "table", "instant": true, "intervalFactor": 1, @@ -1503,7 +1503,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -1669,7 +1669,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -1681,7 +1681,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -1820,7 +1820,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (namespace, pod, container)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{container!=\"POD\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n ) > 0\n )", + "expr": "sum by (namespace, pod, container)\n (\n (\n sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n -\n sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{container!=\"\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n ) > 0\n )", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -2269,7 +2269,7 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Usage", @@ -2476,7 +2476,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(container) (rate(container_cpu_system_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (rate(container_cpu_system_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -2488,7 +2488,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(container) (rate(container_cpu_user_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (rate(container_cpu_user_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "User", @@ -2639,7 +2639,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -2816,7 +2816,7 @@ "pluginVersion": "8.5.13", "targets": [ { - "expr": "sum by(pod) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -2824,28 +2824,28 @@ "refId": "A" }, { - "expr": "sum by(pod) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Cache", "refId": "B" }, { - "expr": "sum by(pod) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Swap", "refId": "C" }, { - "expr": "sum by(pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum by(pod) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))", + "expr": "sum by(pod) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -2974,7 +2974,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (container)\n (\n (\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[$__rate_interval]))\n ) > 0\n )", + "expr": "sum by (container)\n (\n (\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"\"}[$__rate_interval]))\n ) > 0\n )", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -3110,7 +3110,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by (container)\n (\n (\n (\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[$__rate_interval]))\n ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[$__rate_interval]))\n ) > 0\n )", + "expr": "sum by (container)\n (\n (\n (\n sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n -\n sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"\"}[$__rate_interval]))\n ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"\"}[$__rate_interval]))\n ) > 0\n )", "format": "time_series", "hide": false, "intervalFactor": 1, @@ -3431,7 +3431,7 @@ "repeatDirection": "h", "targets": [ { - "expr": "sum by(container) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "instant": false, "intervalFactor": 1, @@ -3439,7 +3439,7 @@ "refId": "A" }, { - "expr": "sum by(container) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "interval": "", "intervalFactor": 1, @@ -3447,28 +3447,28 @@ "refId": "B" }, { - "expr": "sum by(container) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Swap", "refId": "C" }, { - "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Working set bytes without kmem", "refId": "D" }, { - "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Limits", "refId": "E" }, { - "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Requests", @@ -3482,7 +3482,7 @@ "refId": "G" }, { - "expr": "sum by(container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))", + "expr": "sum by(container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Kmem", @@ -3930,7 +3930,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ container }}", @@ -4068,7 +4068,7 @@ "type": "prometheus", "uid": "$ds_prometheus" }, - "expr": "sum by(container) (rate(container_fs_writes_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", + "expr": "sum by(container) (rate(container_fs_writes_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ container }}", From 6f3aa9abbe52ee1a1592d6b8fc0a5d93d0ed487a Mon Sep 17 00:00:00 2001 From: klinch0 <68821526+klinch0@users.noreply.github.com> Date: Tue, 22 Apr 2025 16:07:54 +0300 Subject: [PATCH 5/5] [kubernetes] Fix tenant addons removal (#835) Backport of #835 **New Features** - Expanded the pre-delete operation to target additional components, including cert-manager and vertical pod autoscaler resources. **Chores** - Updated chart version to 0.18.1 and revised version mappings for improved tracking. (cherry picked from commit ccedcb7419f0b39649b1853fa7532cfdbc0362bf) Co-authored-by: Andrei Kvapil Signed-off-by: Nick Volynkin --- packages/apps/kubernetes/Chart.yaml | 2 +- packages/apps/kubernetes/templates/helmreleases/delete.yaml | 6 ++++++ packages/apps/versions_map | 3 ++- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/packages/apps/kubernetes/Chart.yaml b/packages/apps/kubernetes/Chart.yaml index 35a41f92..cc8b5a83 100644 --- a/packages/apps/kubernetes/Chart.yaml +++ b/packages/apps/kubernetes/Chart.yaml @@ -16,7 +16,7 @@ type: application # This is the chart version. This version number should be incremented each time you make changes # to the chart and its templates, including the app version. # Versions are expected to follow Semantic Versioning (https://semver.org/) -version: 0.18.0 +version: 0.18.1 # This is the version number of the application being deployed. This version number should be # incremented each time you make changes to the application. Versions are not expected to diff --git a/packages/apps/kubernetes/templates/helmreleases/delete.yaml b/packages/apps/kubernetes/templates/helmreleases/delete.yaml index 30cd5586..35cacedb 100644 --- a/packages/apps/kubernetes/templates/helmreleases/delete.yaml +++ b/packages/apps/kubernetes/templates/helmreleases/delete.yaml @@ -32,6 +32,9 @@ spec: {{ .Release.Name }}-cilium {{ .Release.Name }}-csi {{ .Release.Name }}-cert-manager + {{ .Release.Name }}-cert-manager-crds + {{ .Release.Name }}-vertical-pod-autoscaler + {{ .Release.Name }}-vertical-pod-autoscaler-crds {{ .Release.Name }}-ingress-nginx {{ .Release.Name }}-fluxcd-operator {{ .Release.Name }}-fluxcd @@ -67,6 +70,9 @@ rules: - {{ .Release.Name }}-cilium - {{ .Release.Name }}-csi - {{ .Release.Name }}-cert-manager + - {{ .Release.Name }}-cert-manager-crds + - {{ .Release.Name }}-vertical-pod-autoscaler + - {{ .Release.Name }}-vertical-pod-autoscaler-crds - {{ .Release.Name }}-ingress-nginx - {{ .Release.Name }}-fluxcd-operator - {{ .Release.Name }}-fluxcd diff --git a/packages/apps/versions_map b/packages/apps/versions_map index 8fa9e74e..3d26fa55 100644 --- a/packages/apps/versions_map +++ b/packages/apps/versions_map @@ -58,7 +58,8 @@ kubernetes 0.15.2 8267072d kubernetes 0.16.0 077045b0 kubernetes 0.17.0 1fbbfcd0 kubernetes 0.17.1 fd240701 -kubernetes 0.18.0 HEAD +kubernetes 0.18.0 721c12a7 +kubernetes 0.18.1 HEAD mysql 0.1.0 263e47be mysql 0.2.0 c24a103f mysql 0.3.0 53f2365e