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

contrib/kube-prometheus: Generate

Browse Source
This commit is contained in:
Max Leonard Inden
2018-11-13 16:21:02 +01:00
parent 1b8684083c
commit cea2da78e4
5 changed files with 44 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -255,7 +255,7 @@ These are the available fields with their respective default values:
namespace: "default", namespace: "default",
versions+:: { versions+:: {
alertmanager: "v0.15.2", alertmanager: "v0.15.3",
nodeExporter: "v0.16.0", nodeExporter: "v0.16.0",
kubeStateMetrics: "v1.3.1", kubeStateMetrics: "v1.3.1",
kubeRbacProxy: "v0.3.1", kubeRbacProxy: "v0.3.1",
@@ -377,9 +377,9 @@ $ jsonnet -J vendor -S --tla-str repository=internal-registry.com/organization s
docker pull quay.io/coreos/addon-resizer:1.0 docker pull quay.io/coreos/addon-resizer:1.0
docker tag quay.io/coreos/addon-resizer:1.0 internal-registry.com/organization/addon-resizer:1.0 docker tag quay.io/coreos/addon-resizer:1.0 internal-registry.com/organization/addon-resizer:1.0
docker push internal-registry.com/organization/addon-resizer:1.0 docker push internal-registry.com/organization/addon-resizer:1.0
docker pull quay.io/prometheus/alertmanager:v0.15.2 docker pull quay.io/prometheus/alertmanager:v0.15.3
docker tag quay.io/prometheus/alertmanager:v0.15.2 internal-registry.com/organization/alertmanager:v0.15.2 docker tag quay.io/prometheus/alertmanager:v0.15.3 internal-registry.com/organization/alertmanager:v0.15.3
docker push internal-registry.com/organization/alertmanager:v0.15.2 docker push internal-registry.com/organization/alertmanager:v0.15.3
... ...
``` ```

10
jsonnetfile.lock.json
View File

@@ -8,7 +8,7 @@
"subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus" "subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus"
} }
}, },
"version": "5185231304f688cf127bf235a4dfdf9f4f9e7821" "version": "c9350aab06b47bcf8410b597ba50b4addf21ee3d"
}, },
{ {
"name": "ksonnet", "name": "ksonnet",
@@ -28,7 +28,7 @@
"subdir": "" "subdir": ""
} }
}, },
"version": "1595151b85934d55ea6969a781039d66f82b22d5" "version": "f7ca48cca5d9cadc9a2203b8c0b3bb3eb85f3294"
}, },
{ {
"name": "grafonnet", "name": "grafonnet",
@@ -38,7 +38,7 @@
"subdir": "grafonnet" "subdir": "grafonnet"
} }
}, },
"version": "1ed195577cd8a406d4811dd6818e939169b686a7" "version": "d407225c5a2e087eb68843528aab2be0507c73b8"
}, },
{ {
"name": "grafana-builder", "name": "grafana-builder",
@@ -48,7 +48,7 @@
"subdir": "grafana-builder" "subdir": "grafana-builder"
} }
}, },
"version": "04e51ce1caeaa4c9aed4c446c9922388a13f6cb1" "version": "90fbdbf08cf0d4bdc78ab52151041da36a7b0abc"
}, },
{ {
"name": "grafana", "name": "grafana",
@@ -78,7 +78,7 @@
"subdir": "Documentation/etcd-mixin" "subdir": "Documentation/etcd-mixin"
} }
}, },
"version": "83304cfc808cf6303d48c45a696f169fae422e68" "version": "ee9dcbca0d89dc563c9e6bc725fab0c6f21d689b"
} }
] ]
} }

2
manifests/alertmanager-alertmanager.yaml
View File

@@ -11,4 +11,4 @@ spec:
beta.kubernetes.io/os: linux beta.kubernetes.io/os: linux
replicas: 3 replicas: 3
serviceAccountName: alertmanager-main serviceAccountName: alertmanager-main
version: v0.15.2 version: v0.15.3

27
manifests/grafana-dashboardDefinitions.yaml
View File

@@ -5279,7 +5279,8 @@ items:
"expr": "avg(sum by (cpu) (irate(node_cpu_seconds_total{job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[2m]))) * 100\n", "expr": "avg(sum by (cpu) (irate(node_cpu_seconds_total{job=\"node-exporter\", mode!=\"idle\", instance=\"$instance\"}[2m]))) * 100\n",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "80, 90", "thresholds": "80, 90",
@@ -5484,7 +5485,8 @@ items:
"expr": "max(\n (\n (\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n )\n / node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n ) * 100)\n", "expr": "max(\n (\n (\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n - node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n )\n / node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n ) * 100)\n",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "80, 90", "thresholds": "80, 90",
@@ -6580,7 +6582,8 @@ items:
"expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}[3m]))", "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}[3m]))",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",
@@ -6659,7 +6662,8 @@ items:
"expr": "sum(container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}) / 1024^3", "expr": "sum(container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}) / 1024^3",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",
@@ -6738,7 +6742,8 @@ items:
"expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=\u007e\"$statefulset.*\"}[3m]))", "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{namespace=\"$namespace\",pod_name=\u007e\"$statefulset.*\"}[3m]))",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",
@@ -6832,7 +6837,8 @@ items:
"expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",
@@ -6912,7 +6918,8 @@ items:
"expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",
@@ -6992,7 +6999,8 @@ items:
"expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)", "expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",
@@ -7072,7 +7080,8 @@ items:
"expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", namespace=\"$namespace\"}) without (instance, pod)", "expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", namespace=\"$namespace\"}) without (instance, pod)",
"format": "time_series", "format": "time_series",
"intervalFactor": 2, "intervalFactor": 2,
"legendFormat": "" "legendFormat": "",
"refId": "A"
} }
], ],
"thresholds": "", "thresholds": "",

22
manifests/prometheus-rules.yaml
View File

@@ -223,22 +223,22 @@ spec:
) )
record: node:node_disk_utilisation:avg_irate record: node:node_disk_utilisation:avg_irate
- expr: | - expr: |
avg(irate(node_disk_io_time_weighted_seconds_total_seconds_total{job="node-exporter",device=~"(sd|xvd|nvme).+"}[1m]) / 1e3) avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"(sd|xvd|nvme).+"}[1m]) / 1e3)
record: :node_disk_saturation:avg_irate record: :node_disk_saturation:avg_irate
- expr: | - expr: |
avg by (node) ( avg by (node) (
irate(node_disk_io_time_weighted_seconds_total_seconds_total{job="node-exporter",device=~"(sd|xvd|nvme).+"}[1m]) / 1e3 irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"(sd|xvd|nvme).+"}[1m]) / 1e3
* on (namespace, pod) group_left(node) * on (namespace, pod) group_left(node)
node_namespace_pod:kube_pod_info: node_namespace_pod:kube_pod_info:
) )
record: node:node_disk_saturation:avg_irate record: node:node_disk_saturation:avg_irate
- expr: | - expr: |
max by (namespace, pod, device) ((node_filesystem_size{fstype=~"ext[234]|btrfs|xfs|zfs"} max by (namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
- node_filesystem_avail{fstype=~"ext[234]|btrfs|xfs|zfs"}) - node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
/ node_filesystem_size{fstype=~"ext[234]|btrfs|xfs|zfs"}) / node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_usage:' record: 'node:node_filesystem_usage:'
- expr: | - expr: |
max by (namespace, pod, device) (node_filesystem_avail{fstype=~"ext[234]|btrfs|xfs|zfs"} / node_filesystem_size{fstype=~"ext[234]|btrfs|xfs|zfs"}) max by (namespace, pod, device) (node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"} / node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
record: 'node:node_filesystem_avail:' record: 'node:node_filesystem_avail:'
- expr: | - expr: |
sum(irate(node_network_receive_bytes_total{job="node-exporter",device="eth0"}[1m])) + sum(irate(node_network_receive_bytes_total{job="node-exporter",device="eth0"}[1m])) +
@@ -829,6 +829,16 @@ spec:
for: 5m for: 5m
labels: labels:
severity: critical severity: critical
- alert: KubePersistentVolumeErrors
annotations:
message: The persistent volume {{ $labels.persistentvolume }} has status {{
$labels.phase }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors
expr: |
kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
for: 5m
labels:
severity: critical
- name: kubernetes-system - name: kubernetes-system
rules: rules:
- alert: KubeNodeNotReady - alert: KubeNodeNotReady