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

2
manifests/alertmanager-alertmanager.yaml
View File

@@ -11,4 +11,4 @@ spec:
beta.kubernetes.io/os: linux
replicas: 3
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=\"$instance\"}[2m]))) * 100\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "80, 90",
@@ -5484,7 +5485,8 @@ items:
"expr": "max(\n (\n (\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$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",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"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]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
@@ -6659,7 +6662,8 @@ items:
"expr": "sum(container_memory_usage_bytes{job=\"kubelet\", namespace=\"$namespace\", pod_name=\u007e\"$statefulset.*\"}) / 1024^3",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"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]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
@@ -6832,7 +6837,8 @@ items:
"expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
@@ -6912,7 +6918,8 @@ items:
"expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
@@ -6992,7 +6999,8 @@ items:
"expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
@@ -7072,7 +7080,8 @@ items:
"expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", namespace=\"$namespace\"}) without (instance, pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": ""
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",

22
manifests/prometheus-rules.yaml
View File

@@ -223,22 +223,22 @@ spec:
)
record: node:node_disk_utilisation:avg_irate
- 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
- expr: |
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)
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"})
max by (namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
- node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
/ node_filesystem_size_bytes{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"})
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:'
- expr: |
sum(irate(node_network_receive_bytes_total{job="node-exporter",device="eth0"}[1m])) +
@@ -829,6 +829,16 @@ spec:
for: 5m
labels:
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
rules:
- alert: KubeNodeNotReady