From af5fb9ee09ecbc33a69b6aae19d85f710d571822 Mon Sep 17 00:00:00 2001
From: Sergiusz Urbaniak <sergiusz.urbaniak@gmail.com>
Date: Thu, 23 Aug 2018 13:38:13 +0200
Subject: [PATCH] kubernetes-prometheus: regenerate
Signed-off-by: Sergiusz Urbaniak <sergiusz.urbaniak@gmail.com>
---
manifests/grafana-dashboardDefinitions.yaml | 32 ++++++++++-----------
manifests/node-exporter-daemonset.yaml | 2 +-
manifests/prometheus-rules.yaml | 21 ++++++++++----
3 files changed, 33 insertions(+), 22 deletions(-)
diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml
index af2b2b0a..db2d0939 100644
--- a/manifests/grafana-dashboardDefinitions.yaml
+++ b/manifests/grafana-dashboardDefinitions.yaml
@@ -1920,7 +1920,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": ":node_cpu_utilisation:avg1m",
+ "expr": "1 - avg(rate(node_cpu{mode=\"idle\"}[1m]))",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -2172,7 +2172,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": ":node_memory_utilisation:",
+ "expr": "1 - sum(:node_memory_MemFreeCachedBuffers:sum) / sum(:node_memory_MemTotal:sum)",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -2256,7 +2256,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(kube_pod_container_resource_requests_memory_bytes) / sum(node_memory_MemTotal)",
+ "expr": "sum(kube_pod_container_resource_requests_memory_bytes) / sum(:node_memory_MemTotal:sum)",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -2340,7 +2340,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(kube_pod_container_resource_limits_memory_bytes) / sum(node_memory_MemTotal)",
+ "expr": "sum(kube_pod_container_resource_limits_memory_bytes) / sum(:node_memory_MemTotal:sum)",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@@ -2435,7 +2435,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_cpu_usage_seconds_total[1m])) by (namespace)",
+ "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@@ -2664,7 +2664,7 @@ items:
],
"targets": [
{
- "expr": "sum(rate(container_cpu_usage_seconds_total[5m])) by (namespace)",
+ "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -2682,7 +2682,7 @@ items:
"step": 10
},
{
- "expr": "sum(rate(container_cpu_usage_seconds_total[5m])) by (namespace) / sum(kube_pod_container_resource_requests_cpu_cores) by (namespace)",
+ "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate) by (namespace) / sum(kube_pod_container_resource_requests_cpu_cores) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -2700,7 +2700,7 @@ items:
"step": 10
},
{
- "expr": "sum(rate(container_cpu_usage_seconds_total[5m])) by (namespace) / sum(kube_pod_container_resource_limits_cpu_cores) by (namespace)",
+ "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate) by (namespace) / sum(kube_pod_container_resource_limits_cpu_cores) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3247,7 +3247,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_cpu_usage_seconds_total{namespace=\"$namespace\"}[1m])) by (pod_name)",
+ "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\"}) by (pod_name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod_name}}",
@@ -3476,7 +3476,7 @@ items:
],
"targets": [
{
- "expr": "sum(label_replace(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\"}[5m]), \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)",
+ "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3494,7 +3494,7 @@ items:
"step": 10
},
{
- "expr": "sum(label_replace(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\"}[5m]), \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{namespace=\"$namespace\"}) by (pod)",
+ "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -3512,7 +3512,7 @@ items:
"step": 10
},
{
- "expr": "sum(label_replace(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\"}[5m]), \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{namespace=\"$namespace\"}) by (pod)",
+ "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\"}, \"pod\", \"$1\", \"pod_name\", \"(.*)\")) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -4086,7 +4086,7 @@ items:
"steppedLine": false,
"targets": [
{
- "expr": "sum(irate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}[1m])) by (container_name)",
+ "expr": "sum(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}) by (container_name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container_name}}",
@@ -4315,7 +4315,7 @@ items:
],
"targets": [
{
- "expr": "sum(label_replace(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}[5m]), \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)",
+ "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod_name=\"$pod\", container_name!=\"POD\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -4333,7 +4333,7 @@ items:
"step": 10
},
{
- "expr": "sum(label_replace(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod_name=\"$pod\"}[5m]), \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_requests_cpu_cores{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+ "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod_name=\"$pod\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_requests_cpu_cores{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@@ -4351,7 +4351,7 @@ items:
"step": 10
},
{
- "expr": "sum(label_replace(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod_name=\"$pod\"}[5m]), \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_limits_cpu_cores{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+ "expr": "sum(label_replace(namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod_name=\"$pod\"}, \"container\", \"$1\", \"container_name\", \"(.*)\")) by (container) / sum(kube_pod_container_resource_limits_cpu_cores{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
diff --git a/manifests/node-exporter-daemonset.yaml b/manifests/node-exporter-daemonset.yaml
index a2669187..b3febf8c 100644
--- a/manifests/node-exporter-daemonset.yaml
+++ b/manifests/node-exporter-daemonset.yaml
@@ -76,5 +76,5 @@ spec:
path: /sys
name: sys
- hostPath:
- path: /root
+ path: /
name: root
diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml
index bf07b9a4..121b974f 100644
--- a/manifests/prometheus-rules.yaml
+++ b/manifests/prometheus-rules.yaml
@@ -13,6 +13,11 @@ spec:
- expr: |
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!=""}[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])
+ )
+ record: namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate
- expr: |
sum(container_memory_usage_bytes{job="kubelet", image!=""}) by (namespace)
record: namespace:container_memory_usage_bytes:sum
@@ -151,6 +156,12 @@ spec:
/
sum(node_memory_MemTotal{job="node-exporter"})
record: ':node_memory_utilisation:'
+ - expr: |
+ sum(node_memory_MemFree{job="node-exporter"} + node_memory_Cached{job="node-exporter"} + node_memory_Buffers{job="node-exporter"})
+ record: :node_memory_MemFreeCachedBuffers:sum
+ - expr: |
+ sum(node_memory_MemTotal{job="node-exporter"})
+ record: :node_memory_MemTotal:sum
- expr: |
sum by (node) (
(node_memory_MemFree{job="node-exporter"} + node_memory_Cached{job="node-exporter"} + node_memory_Buffers{job="node-exporter"})
@@ -796,10 +807,10 @@ spec:
}}' is experiencing {{ printf "%0.0f" $value }}% errors.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors
expr: |
- sum(rate(rest_client_requests_total{code!~"2.."}[5m])) by (instance, job) * 100
+ (sum(rate(rest_client_requests_total{code!~"2..|404"}[5m])) by (instance, job)
/
- sum(rate(rest_client_requests_total[5m])) by (instance, job)
- > 1
+ sum(rate(rest_client_requests_total[5m])) by (instance, job))
+ * 100 > 1
for: 15m
labels:
severity: warning
@@ -829,7 +840,7 @@ spec:
for {{$labels.verb}} {{$labels.resource}}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh
expr: |
- cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"} > 1
+ cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 1
for: 10m
labels:
severity: warning
@@ -839,7 +850,7 @@ spec:
for {{$labels.verb}} {{$labels.resource}}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh
expr: |
- cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"} > 4
+ cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 4
for: 10m
labels:
severity: critical
--
GitLab