diff --git a/charts/kubernetes-mixin/Chart.yaml b/charts/kubernetes-mixin/Chart.yaml index db8e5a21..2ae42e03 100644 --- a/charts/kubernetes-mixin/Chart.yaml +++ b/charts/kubernetes-mixin/Chart.yaml @@ -31,12 +31,12 @@ keywords: # 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: 1.3.0 +version: 1.4.0 # 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 # follow Semantic Versioning. They should reflect the version the application is using. -appVersion: 0.8.0 +appVersion: master maintainers: - name: nlamirault diff --git a/charts/kubernetes-mixin/dashboards/apiserver.json b/charts/kubernetes-mixin/dashboards/apiserver.json index e7c8743c..391b0dd7 100644 --- a/charts/kubernetes-mixin/dashboards/apiserver.json +++ b/charts/kubernetes-mixin/dashboards/apiserver.json @@ -528,7 +528,7 @@ "steppedLine": false, "targets": [ { - "expr": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}", + "expr": "cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{ resource }}", @@ -893,7 +893,7 @@ "steppedLine": false, "targets": [ { - "expr": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}", + "expr": "cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{ resource }}", @@ -1468,12 +1468,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/cluster-total.json b/charts/kubernetes-mixin/dashboards/cluster-total.json index 3afd2b65..f13807cc 100644 --- a/charts/kubernetes-mixin/dashboards/cluster-total.json +++ b/charts/kubernetes-mixin/dashboards/cluster-total.json @@ -1534,7 +1534,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ @@ -1616,6 +1616,7 @@ }, { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/controller-manager.json b/charts/kubernetes-mixin/dashboards/controller-manager.json index b8d442df..a2d0cc93 100644 --- a/charts/kubernetes-mixin/dashboards/controller-manager.json +++ b/charts/kubernetes-mixin/dashboards/controller-manager.json @@ -938,12 +938,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/k8s-resources-cluster.json b/charts/kubernetes-mixin/dashboards/k8s-resources-cluster.json index c9d35ef4..7c8b9d1e 100644 --- a/charts/kubernetes-mixin/dashboards/k8s-resources-cluster.json +++ b/charts/kubernetes-mixin/dashboards/k8s-resources-cluster.json @@ -538,8 +538,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -769,8 +768,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", @@ -778,8 +776,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)", @@ -787,8 +784,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", @@ -796,8 +792,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", @@ -805,8 +800,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", @@ -814,8 +808,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", @@ -823,8 +816,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "G", - "step": 10 + "refId": "G" } ], "thresholds": [ ], @@ -915,8 +907,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1146,8 +1137,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", @@ -1155,8 +1145,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(container_memory_rss{job=\"kubelet\", cluster=\"$cluster\", container!=\"\"}) by (namespace)", @@ -1164,8 +1153,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", @@ -1173,8 +1161,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(container_memory_rss{job=\"kubelet\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", @@ -1182,8 +1169,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", @@ -1191,8 +1177,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" }, { "expr": "sum(container_memory_rss{job=\"kubelet\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", @@ -1200,8 +1185,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "G", - "step": 10 + "refId": "G" } ], "thresholds": [ ], @@ -1417,8 +1401,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", @@ -1426,8 +1409,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", @@ -1435,8 +1417,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", @@ -1444,8 +1425,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", @@ -1453,8 +1433,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", @@ -1462,8 +1441,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -1554,8 +1532,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1633,8 +1610,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1724,8 +1700,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1803,8 +1778,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1894,8 +1868,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1973,8 +1946,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2064,8 +2036,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2143,8 +2114,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2235,8 +2205,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2314,8 +2283,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{namespace}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2415,7 +2383,7 @@ "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -2423,14 +2391,14 @@ "pattern": "Value #A", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "IOPS(Writes)", "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -2438,14 +2406,14 @@ "pattern": "Value #B", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "IOPS(Reads + Writes)", "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -2453,7 +2421,7 @@ "pattern": "Value #C", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "Throughput(Read)", @@ -2534,8 +2502,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum by(namespace) (rate(container_fs_writes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", @@ -2543,8 +2510,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", @@ -2552,8 +2518,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", @@ -2561,8 +2526,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", @@ -2570,8 +2534,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", @@ -2579,8 +2542,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -2633,7 +2595,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ diff --git a/charts/kubernetes-mixin/dashboards/k8s-resources-namespace.json b/charts/kubernetes-mixin/dashboards/k8s-resources-namespace.json index 3483bafe..727b0ff2 100644 --- a/charts/kubernetes-mixin/dashboards/k8s-resources-namespace.json +++ b/charts/kubernetes-mixin/dashboards/k8s-resources-namespace.json @@ -403,24 +403,21 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - requests", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - limits", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -620,8 +617,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -629,8 +625,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -638,8 +633,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -647,8 +641,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -656,8 +649,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" } ], "thresholds": [ ], @@ -771,24 +763,21 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - requests", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - limits", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1033,8 +1022,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -1042,8 +1030,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -1051,8 +1038,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -1060,8 +1046,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", @@ -1069,8 +1054,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(container_memory_rss{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", @@ -1078,8 +1062,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" }, { "expr": "sum(container_memory_cache{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", @@ -1087,8 +1070,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "G", - "step": 10 + "refId": "G" }, { "expr": "sum(container_memory_swap{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", @@ -1096,8 +1078,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "H", - "step": 10 + "refId": "H" } ], "thresholds": [ ], @@ -1313,8 +1294,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", @@ -1322,8 +1302,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", @@ -1331,8 +1310,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", @@ -1340,8 +1318,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", @@ -1349,8 +1326,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", @@ -1358,8 +1334,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -1450,8 +1425,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1529,8 +1503,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1620,8 +1593,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1699,8 +1671,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1790,8 +1761,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1869,8 +1839,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1961,8 +1930,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2040,8 +2008,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -2141,7 +2108,7 @@ "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -2149,14 +2116,14 @@ "pattern": "Value #A", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "IOPS(Writes)", "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -2164,14 +2131,14 @@ "pattern": "Value #B", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "IOPS(Reads + Writes)", "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -2179,7 +2146,7 @@ "pattern": "Value #C", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "Throughput(Read)", @@ -2260,8 +2227,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", @@ -2269,8 +2235,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", @@ -2278,8 +2243,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", @@ -2287,8 +2251,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", @@ -2296,8 +2259,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", @@ -2305,8 +2267,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -2359,7 +2320,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ diff --git a/charts/kubernetes-mixin/dashboards/k8s-resources-node.json b/charts/kubernetes-mixin/dashboards/k8s-resources-node.json index 7d36698c..944a57f1 100644 --- a/charts/kubernetes-mixin/dashboards/k8s-resources-node.json +++ b/charts/kubernetes-mixin/dashboards/k8s-resources-node.json @@ -64,16 +64,14 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "max capacity", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -273,8 +271,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -282,8 +279,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -291,8 +287,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -300,8 +295,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -309,8 +303,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" } ], "thresholds": [ ], @@ -413,16 +406,14 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "max capacity", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -667,8 +658,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -676,8 +666,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -685,8 +674,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -694,8 +682,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", @@ -703,8 +690,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", @@ -712,8 +698,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" }, { "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", @@ -721,8 +706,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "G", - "step": 10 + "refId": "G" }, { "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", @@ -730,8 +714,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "H", - "step": 10 + "refId": "H" } ], "thresholds": [ ], @@ -784,7 +767,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ diff --git a/charts/kubernetes-mixin/dashboards/k8s-resources-pod.json b/charts/kubernetes-mixin/dashboards/k8s-resources-pod.json index 549d788f..5e81510f 100644 --- a/charts/kubernetes-mixin/dashboards/k8s-resources-pod.json +++ b/charts/kubernetes-mixin/dashboards/k8s-resources-pod.json @@ -71,24 +71,21 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{container}}", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "requests", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "limits", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -178,8 +175,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{container}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ @@ -388,8 +384,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -397,8 +392,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -406,8 +400,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -415,8 +408,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -424,8 +416,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" } ], "thresholds": [ ], @@ -537,24 +528,21 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{container}}", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "requests", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "limits", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -799,8 +787,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -808,8 +795,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -817,8 +803,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -826,8 +811,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", @@ -835,8 +819,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum(container_memory_rss{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", @@ -844,8 +827,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" }, { "expr": "sum(container_memory_cache{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", @@ -853,8 +835,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "G", - "step": 10 + "refId": "G" }, { "expr": "sum(container_memory_swap{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", @@ -862,8 +843,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "H", - "step": 10 + "refId": "H" } ], "thresholds": [ ], @@ -954,8 +934,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1033,8 +1012,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1124,8 +1102,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1203,8 +1180,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1294,8 +1270,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1373,8 +1348,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1465,16 +1439,14 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "Reads", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Writes", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1552,16 +1524,14 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "Reads", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Writes", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1652,8 +1622,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{container}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1731,8 +1700,7 @@ "format": "time_series", "intervalFactor": 2, "legendFormat": "{{container}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1832,7 +1800,7 @@ "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -1840,14 +1808,14 @@ "pattern": "Value #A", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "IOPS(Writes)", "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -1855,14 +1823,14 @@ "pattern": "Value #B", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "IOPS(Reads + Writes)", "colorMode": null, "colors": [ ], "dateFormat": "YYYY-MM-DD HH:mm:ss", - "decimals": -1, + "decimals": 3, "link": false, "linkTargetBlank": false, "linkTooltip": "Drill down", @@ -1870,7 +1838,7 @@ "pattern": "Value #C", "thresholds": [ ], "type": "number", - "unit": "short" + "unit": "iops" }, { "alias": "Throughput(Read)", @@ -1951,8 +1919,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { "expr": "sum by(container) (rate(container_fs_writes_total{job=\"kubelet\",device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", @@ -1960,8 +1927,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { "expr": "sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", @@ -1969,8 +1935,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", @@ -1978,8 +1943,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { "expr": "sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", @@ -1987,8 +1951,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", device=~\"(/dev.+)|mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", @@ -1996,8 +1959,7 @@ "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -2050,7 +2012,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ diff --git a/charts/kubernetes-mixin/dashboards/k8s-resources-workload.json b/charts/kubernetes-mixin/dashboards/k8s-resources-workload.json index 13b2c49d..9512d166 100644 --- a/charts/kubernetes-mixin/dashboards/k8s-resources-workload.json +++ b/charts/kubernetes-mixin/dashboards/k8s-resources-workload.json @@ -48,12 +48,11 @@ "steppedLine": false, "targets": [ { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -248,49 +247,44 @@ ], "targets": [ { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { - "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { - "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" } ], "thresholds": [ ], @@ -377,12 +371,11 @@ "steppedLine": false, "targets": [ { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -577,49 +570,44 @@ ], "targets": [ { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { - "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { - "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { - "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" } ], "thresholds": [ ], @@ -830,58 +818,52 @@ ], "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { - "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { - "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { - "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -968,12 +950,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1047,12 +1028,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1138,12 +1118,11 @@ "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1217,12 +1196,11 @@ "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1308,12 +1286,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1387,12 +1364,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1478,12 +1454,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1557,12 +1532,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{pod}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1614,7 +1588,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ @@ -1686,7 +1660,7 @@ }, "datasource": "$datasource", "hide": 0, - "includeAll": false, + "includeAll": true, "label": null, "multi": false, "name": "type", @@ -1694,7 +1668,7 @@ "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)", "refresh": 2, "regex": "", - "sort": 1, + "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", @@ -1714,7 +1688,7 @@ "multi": false, "name": "workload", "options": [ ], - "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}, workload)", + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}, workload)", "refresh": 2, "regex": "", "sort": 1, diff --git a/charts/kubernetes-mixin/dashboards/k8s-resources-workloads-namespace.json b/charts/kubernetes-mixin/dashboards/k8s-resources-workloads-namespace.json index b0ad8637..d3be1bad 100644 --- a/charts/kubernetes-mixin/dashboards/k8s-resources-workloads-namespace.json +++ b/charts/kubernetes-mixin/dashboards/k8s-resources-workloads-namespace.json @@ -71,28 +71,25 @@ "steppedLine": false, "targets": [ { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}} - {{workload_type}}", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - requests", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - limits", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -317,58 +314,52 @@ ], "targets": [ { - "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { - "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { - "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { - "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -478,28 +469,25 @@ "steppedLine": false, "targets": [ { - "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}} - {{workload_type}}", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - requests", - "legendLink": null, - "step": 10 + "legendLink": null }, { "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "quota - limits", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -724,58 +712,52 @@ ], "targets": [ { - "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { - "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { - "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { - "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { - "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { - "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -1001,58 +983,52 @@ ], "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "A", - "step": 10 + "refId": "A" }, { - "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "B", - "step": 10 + "refId": "B" }, { - "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "C", - "step": 10 + "refId": "C" }, { - "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "D", - "step": 10 + "refId": "D" }, { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "E", - "step": 10 + "refId": "E" }, { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, "legendFormat": "", - "refId": "F", - "step": 10 + "refId": "F" } ], "thresholds": [ ], @@ -1139,12 +1115,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1218,12 +1193,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1309,12 +1283,11 @@ "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1388,12 +1361,11 @@ "steppedLine": false, "targets": [ { - "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1479,12 +1451,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1558,12 +1529,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1649,12 +1619,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1728,12 +1697,11 @@ "steppedLine": false, "targets": [ { - "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{workload}}", - "legendLink": null, - "step": 10 + "legendLink": null } ], "thresholds": [ ], @@ -1785,7 +1753,7 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ @@ -1855,13 +1823,13 @@ "auto_count": 30, "auto_min": "10s", "current": { - "text": "deployment", - "value": "deployment" + "text": "", + "value": "" }, "datasource": "$datasource", "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)", "hide": 0, - "includeAll": false, + "includeAll": true, "label": null, "multi": false, "name": "type", diff --git a/charts/kubernetes-mixin/dashboards/kubelet.json b/charts/kubernetes-mixin/dashboards/kubelet.json index b25a7e91..653b908f 100644 --- a/charts/kubernetes-mixin/dashboards/kubelet.json +++ b/charts/kubernetes-mixin/dashboards/kubelet.json @@ -1884,12 +1884,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/namespace-by-pod.json b/charts/kubernetes-mixin/dashboards/namespace-by-pod.json index 3820986f..b0e7f1e2 100644 --- a/charts/kubernetes-mixin/dashboards/namespace-by-pod.json +++ b/charts/kubernetes-mixin/dashboards/namespace-by-pod.json @@ -1128,12 +1128,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/namespace-by-workload.json b/charts/kubernetes-mixin/dashboards/namespace-by-workload.json index 3cba8de1..2ea4b0f7 100644 --- a/charts/kubernetes-mixin/dashboards/namespace-by-workload.json +++ b/charts/kubernetes-mixin/dashboards/namespace-by-workload.json @@ -89,7 +89,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ workload }}", @@ -184,7 +184,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ workload }}", @@ -441,7 +441,7 @@ ], "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -450,7 +450,7 @@ "step": 10 }, { - "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -459,7 +459,7 @@ "step": 10 }, { - "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -468,7 +468,7 @@ "step": 10 }, { - "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -477,7 +477,7 @@ "step": 10 }, { - "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -486,7 +486,7 @@ "step": 10 }, { - "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -495,7 +495,7 @@ "step": 10 }, { - "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -504,7 +504,7 @@ "step": 10 }, { - "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "table", "instant": true, "intervalFactor": 2, @@ -578,7 +578,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ workload }}", @@ -673,7 +673,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ workload }}", @@ -794,7 +794,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{workload}}", @@ -885,7 +885,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{workload}}", @@ -987,7 +987,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{workload}}", @@ -1078,7 +1078,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{workload}}", @@ -1189,7 +1189,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{workload}}", @@ -1280,7 +1280,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{workload}}", @@ -1340,12 +1340,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, @@ -1412,13 +1413,13 @@ "auto_count": 30, "auto_min": "10s", "current": { - "text": "deployment", - "value": "deployment" + "text": "", + "value": "" }, "datasource": "$datasource", "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)", "hide": 0, - "includeAll": false, + "includeAll": true, "label": null, "multi": false, "name": "type", diff --git a/charts/kubernetes-mixin/dashboards/persistentvolumesusage.json b/charts/kubernetes-mixin/dashboards/persistentvolumesusage.json index f37eaa04..4d91ae35 100644 --- a/charts/kubernetes-mixin/dashboards/persistentvolumesusage.json +++ b/charts/kubernetes-mixin/dashboards/persistentvolumesusage.json @@ -389,12 +389,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/pod-total.json b/charts/kubernetes-mixin/dashboards/pod-total.json index 64750057..e7a37225 100644 --- a/charts/kubernetes-mixin/dashboards/pod-total.json +++ b/charts/kubernetes-mixin/dashboards/pod-total.json @@ -894,12 +894,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/proxy.json b/charts/kubernetes-mixin/dashboards/proxy.json index 3340435a..f625b4cf 100644 --- a/charts/kubernetes-mixin/dashboards/proxy.json +++ b/charts/kubernetes-mixin/dashboards/proxy.json @@ -1007,12 +1007,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/scheduler.json b/charts/kubernetes-mixin/dashboards/scheduler.json index 64c40081..265571e2 100644 --- a/charts/kubernetes-mixin/dashboards/scheduler.json +++ b/charts/kubernetes-mixin/dashboards/scheduler.json @@ -872,12 +872,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, diff --git a/charts/kubernetes-mixin/dashboards/workload-total.json b/charts/kubernetes-mixin/dashboards/workload-total.json index 5e75d762..4e180a3a 100644 --- a/charts/kubernetes-mixin/dashboards/workload-total.json +++ b/charts/kubernetes-mixin/dashboards/workload-total.json @@ -89,7 +89,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -184,7 +184,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -290,7 +290,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -385,7 +385,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{ pod }}", @@ -506,7 +506,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{pod}}", @@ -597,7 +597,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{pod}}", @@ -699,7 +699,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{pod}}", @@ -790,7 +790,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{pod}}", @@ -901,7 +901,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{pod}}", @@ -992,7 +992,7 @@ "steppedLine": false, "targets": [ { - "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{pod}}", @@ -1052,12 +1052,13 @@ "style": "dark", "tags": [ "kubernetes-mixin", - "monitoring-mixins-v1.3.0" + "monitoring-mixins-v1.6.0" ], "templating": { "list": [ { "current": { + "selected": true, "text": "default", "value": "default" }, @@ -1152,13 +1153,13 @@ "auto_count": 30, "auto_min": "10s", "current": { - "text": "deployment", - "value": "deployment" + "text": "", + "value": "" }, "datasource": "$datasource", "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", "hide": 0, - "includeAll": false, + "includeAll": true, "label": null, "multi": false, "name": "type", diff --git a/charts/kubernetes-mixin/templates/alerts.yaml b/charts/kubernetes-mixin/templates/alerts.yaml index f16b8027..7a0d19ba 100644 --- a/charts/kubernetes-mixin/templates/alerts.yaml +++ b/charts/kubernetes-mixin/templates/alerts.yaml @@ -71,11 +71,22 @@ spec: for: 15m labels: severity: warning + - alert: KubeDeploymentRolloutStuck + annotations: + description: Rollout of deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} is not progressing for longer than 15 minutes. + runbook_url: https://github.com/nlamirault/monitoring-mixins/tree/master/runbooks/kubernetes-mixin-runbook.md#alert-name-kubedeploymentrolloutstuck + summary: Deployment rollout is not progressing. + expr: | + kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics"} + != 0 + for: 15m + labels: + severity: warning - alert: KubeStatefulSetReplicasMismatch annotations: description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} has not matched the expected number of replicas for longer than 15 minutes. runbook_url: https://github.com/nlamirault/monitoring-mixins/tree/master/runbooks/kubernetes-mixin-runbook.md#alert-name-kubestatefulsetreplicasmismatch - summary: Deployment has not matched the expected number of replicas. + summary: StatefulSet has not matched the expected number of replicas. expr: | ( kube_statefulset_status_replicas_ready{job="kube-state-metrics"} @@ -343,9 +354,9 @@ spec: runbook_url: https://github.com/nlamirault/monitoring-mixins/tree/master/runbooks/kubernetes-mixin-runbook.md#alert-name-cputhrottlinghigh summary: Processes experience elevated CPU throttling. expr: | - sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace) + sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace) / - sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace) + sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) > ( 25 / 100 ) for: 15m labels: @@ -557,7 +568,7 @@ spec: runbook_url: https://github.com/nlamirault/monitoring-mixins/tree/master/runbooks/kubernetes-mixin-runbook.md#alert-name-kubeaggregatedapierrors summary: Kubernetes aggregated API has reported errors. expr: | - sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total[10m])) > 4 + sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="kube-apiserver"}[10m])) > 4 labels: severity: warning - alert: KubeAggregatedAPIDown @@ -566,7 +577,7 @@ spec: runbook_url: https://github.com/nlamirault/monitoring-mixins/tree/master/runbooks/kubernetes-mixin-runbook.md#alert-name-kubeaggregatedapidown summary: Kubernetes aggregated API is down. expr: | - (1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85 + (1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="kube-apiserver"}[10m]))) * 100 < 85 for: 5m labels: severity: warning diff --git a/charts/kubernetes-mixin/templates/rules.yaml b/charts/kubernetes-mixin/templates/rules.yaml index 6e20c431..36c9ac4c 100644 --- a/charts/kubernetes-mixin/templates/rules.yaml +++ b/charts/kubernetes-mixin/templates/rules.yaml @@ -19,18 +19,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1d])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1d])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1d])) ) ) + @@ -46,18 +46,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1h])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1h])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1h])) ) ) + @@ -73,18 +73,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[2h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[2h])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[2h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[2h])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[2h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[2h])) ) ) + @@ -100,18 +100,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[30m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[30m])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[30m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[30m])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[30m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[30m])) ) ) + @@ -127,18 +127,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[3d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[3d])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[3d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[3d])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[3d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[3d])) ) ) + @@ -154,18 +154,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[5m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[5m])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[5m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[5m])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[5m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[5m])) ) ) + @@ -181,18 +181,18 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h])) - ( ( - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[6h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[6h])) or vector(0) ) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[6h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[6h])) + - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[6h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[6h])) ) ) + @@ -208,9 +208,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1d])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d])) @@ -224,9 +224,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1h])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) @@ -240,9 +240,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[2h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[2h])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h])) @@ -256,9 +256,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[30m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[30m])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m])) @@ -272,9 +272,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[3d])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[3d])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d])) @@ -288,9 +288,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[5m])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[5m])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m])) @@ -304,9 +304,9 @@ spec: ( ( # too slow - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h])) - - sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[6h])) + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[6h])) ) + sum by (cluster) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h])) @@ -319,17 +319,17 @@ spec: - name: kube-apiserver-histogram.rules rules: - expr: | - histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 labels: quantile: "0.99" verb: read - record: cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile + record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile - expr: | - histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 labels: quantile: "0.99" verb: write - record: cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile + record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile - interval: 3m name: kube-apiserver-availability.rules rules: @@ -347,39 +347,39 @@ spec: verb: write record: code:apiserver_request_total:increase30d - expr: | - sum by (cluster, verb, scope) (increase(apiserver_request_slo_duration_seconds_count[1h])) - record: cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase1h + sum by (cluster, verb, scope) (increase(apiserver_request_sli_duration_seconds_count{job="kube-apiserver"}[1h])) + record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h - expr: | - sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase1h[30d]) * 24 * 30) - record: cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d + sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d - expr: | - sum by (cluster, verb, scope, le) (increase(apiserver_request_slo_duration_seconds_bucket[1h])) - record: cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase1h + sum by (cluster, verb, scope, le) (increase(apiserver_request_sli_duration_seconds_bucket[1h])) + record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h - expr: | - sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase1h[30d]) * 24 * 30) - record: cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d + sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d - expr: | 1 - ( ( # write too slow - sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) - - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) ) + ( # read too slow - sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"}) - ( ( - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) or vector(0) ) + - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) ) ) + # errors @@ -392,19 +392,19 @@ spec: record: apiserver_request:availability30d - expr: | 1 - ( - sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"}) - ( # too slow ( - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) or vector(0) ) + - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) ) + # errors @@ -419,9 +419,9 @@ spec: 1 - ( ( # too slow - sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) - - sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) ) + # errors @@ -454,7 +454,7 @@ spec: - expr: | sum by (cluster, code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) record: code_verb:apiserver_request_total:increase1h - - name: k8s.rules + - name: k8s.rules.container_cpu_usage_seconds_total rules: - expr: | sum by (cluster, namespace, pod, container) ( @@ -463,30 +463,40 @@ spec: 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) ) record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate + - name: k8s.rules.container_memory_working_set_bytes + rules: - expr: | container_memory_working_set_bytes{job="kubelet", image!=""} * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) ) record: node_namespace_pod_container:container_memory_working_set_bytes + - name: k8s.rules.container_memory_rss + rules: - expr: | container_memory_rss{job="kubelet", image!=""} * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) ) record: node_namespace_pod_container:container_memory_rss + - name: k8s.rules.container_memory_cache + rules: - expr: | container_memory_cache{job="kubelet", image!=""} * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) ) record: node_namespace_pod_container:container_memory_cache + - name: k8s.rules.container_memory_swap + rules: - expr: | container_memory_swap{job="kubelet", image!=""} * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) ) record: node_namespace_pod_container:container_memory_swap + - name: k8s.rules.container_resource + rules: - expr: | kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( @@ -555,6 +565,8 @@ spec: ) ) record: namespace_cpu:kube_pod_container_resource_limits:sum + - name: k8s.rules.pod_owner + rules: - expr: | max by (cluster, namespace, workload, pod) ( label_replace(