easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

kube-prometheus: bump kubernetes-mixins

Browse Source 
This bumps the kubernetes-mixin dependency to add
https://github.com/kubernetes-monitoring/kubernetes-mixin/pull/76.
This commit is contained in:
Sergiusz Urbaniak
2018-09-05 12:00:40 +02:00
parent 35c90355ba
commit b338940208
3 changed files with 33 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
manifests/grafana-dashboardDefinitions.yaml
View File

@@ -1712,7 +1712,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "max ((node_filesystem_size{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\"} - node_filesystem_avail{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\"})\n/ node_filesystem_size{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\"}) by (namespace, pod, device)\n* on (namespace, pod) group_left (node) node_namespace_pod:kube_pod_info:{node=\"$node\"}\n",
"expr": "node:node_filesystem_usage:\n* on (namespace, pod) group_left (node) node_namespace_pod:kube_pod_info:{node=\"$node\"}\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{device}}",
@@ -2800,7 +2800,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_rss) by (namespace)",
"expr": "sum(container_memory_rss{container_name!=\"\"}) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@@ -3029,7 +3029,7 @@ items:
],
"targets": [
{
"expr": "sum(container_memory_rss) by (namespace)",
"expr": "sum(container_memory_rss{container_name!=\"\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3047,7 +3047,7 @@ items:
"step": 10
},
{
"expr": "sum(container_memory_rss) by (namespace) / sum(kube_pod_container_resource_requests_memory_bytes) by (namespace)",
"expr": "sum(container_memory_rss{container_name!=\"\"}) by (namespace) / sum(kube_pod_container_resource_requests_memory_bytes) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3065,7 +3065,7 @@ items:
"step": 10
},
{
"expr": "sum(container_memory_rss) by (namespace) / sum(kube_pod_container_resource_limits_memory_bytes) by (namespace)",
"expr": "sum(container_memory_rss{container_name!=\"\"}) by (namespace) / sum(kube_pod_container_resource_limits_memory_bytes) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3612,7 +3612,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_usage_bytes{namespace=\"$namespace\"}) by (pod_name)",
"expr": "sum(container_memory_usage_bytes{namespace=\"$namespace\", container_name!=\"\"}) by (pod_name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod_name}}",
@@ -3841,7 +3841,7 @@ items:
],
"targets": [
{
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)",
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3859,7 +3859,7 @@ items:
"step": 10
},
{
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3877,7 +3877,7 @@ items:
"step": 10
},
{
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\",container_name!=\"\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -4451,7 +4451,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}) by (container_name)",
"expr": "sum(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", container_name!=\"\"}) by (container_name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container_name}}",
@@ -4680,7 +4680,7 @@ items:
],
"targets": [
{
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)",
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\", container_name!=\"\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -4707,7 +4707,7 @@ items:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\", container_name!=\"\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -4716,7 +4716,7 @@ items:
"step": 10
},
{
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=\"$pod\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(label_replace(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -5669,7 +5669,7 @@ items:
"steppedLine": false,
"targets": [
{
"expr": "max ((node_filesystem_size{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\",instance=\"$instance\"}\n- node_filesystem_avail{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\",instance=\"$instance\"})\n/ node_filesystem_size{fstype=\u007e\"ext[234]|btrfs|xfs|zfs\",instance=\"$instance\"}) by (namespace, pod, device)\n",
"expr": "node:node_filesystem_usage:\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{device}}",

20
manifests/prometheus-rules.yaml
View File

@@ -11,26 +11,26 @@ spec:
- name: k8s.rules
rules:
- expr: |
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!=""}[5m])) by (namespace)
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m])) by (namespace)
record: namespace:container_cpu_usage_seconds_total:sum_rate
- expr: |
sum by (namespace, pod_name, container_name) (
rate(container_cpu_usage_seconds_total{job="kubelet", image!=""}[5m])
rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m])
)
record: namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate
- expr: |
sum(container_memory_usage_bytes{job="kubelet", image!=""}) by (namespace)
sum(container_memory_usage_bytes{job="kubelet", image!="", container_name!=""}) by (namespace)
record: namespace:container_memory_usage_bytes:sum
- expr: |
sum by (namespace, label_name) (
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!=""}[5m])) by (namespace, pod_name)
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container_name!=""}[5m])) by (namespace, pod_name)
* on (namespace, pod_name) group_left(label_name)
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
)
record: namespace_name:container_cpu_usage_seconds_total:sum_rate
- expr: |
sum by (namespace, label_name) (
sum(container_memory_usage_bytes{job="kubelet",image!=""}) by (pod_name, namespace)
sum(container_memory_usage_bytes{job="kubelet",image!="", container_name!=""}) by (pod_name, namespace)
* on (namespace, pod_name) group_left(label_name)
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
)
@@ -232,6 +232,14 @@ spec:
node_namespace_pod:kube_pod_info:
)
record: node:node_disk_saturation:avg_irate
- expr: |
max by (namespace, pod, device) ((node_filesystem_size{fstype=~"ext[234]|btrfs|xfs|zfs"}
- node_filesystem_avail{fstype=~"ext[234]|btrfs|xfs|zfs"})
/ node_filesystem_size{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_usage:'
- expr: |
max by (namespace, pod, device) (node_filesystem_avail{fstype=~"ext[234]|btrfs|xfs|zfs"} / node_filesystem_size{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_avail:'
- expr: |
sum(irate(node_network_receive_bytes{job="node-exporter",device="eth0"}[1m])) +
sum(irate(node_network_transmit_bytes{job="node-exporter",device="eth0"}[1m]))
@@ -569,7 +577,7 @@ spec:
message: '{{ $labels.namespace }}/{{ $labels.pod }} is not ready.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready
expr: |
sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase!~"Running|Succeeded"}) > 0
sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Pending|Unknown"}) > 0
for: 1h
labels:
severity: critical