starred/nix-config
1
0
Fork 0
mirror of https://github.com/ryan4yin/nix-config.git synced 2026-08-06 19:58:33 +02:00
Code Issues Packages Projects Releases 10 Wiki Activity

feat(grafana): add kubernetes service and storage dashboards

Browse Source
This commit is contained in:
Ryan Yin
2026-07-31 17:34:52 +08:00
parent 071212e40f
commit 41512097e5
4 changed files with 4295 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
hosts/idols-aquamarine/grafana/dashboards/kubernetes/k8s-views-pods.json
+22 -22
View File
@@ -668,7 +668,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}[$__rate_interval])) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"})",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"})",
"instant": true,
"interval": "$resolution",
"legendFormat": "Requests",
@@ -738,7 +738,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}[$__rate_interval])) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"})",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"})",
"instant": true,
"interval": "$resolution",
"legendFormat": "Limits",
@@ -812,7 +812,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"})",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"})",
"instant": true,
"interval": "$resolution",
"legendFormat": "Requests",
@@ -882,7 +882,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"}) ",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"}) ",
"instant": true,
"interval": "$resolution",
"legendFormat": "Limits",
@@ -1057,7 +1057,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"format": "table",
"hide": false,
"instant": true,
@@ -1072,7 +1072,7 @@
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", container!=\"\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}) by (container)",
"format": "table",
"hide": false,
"instant": true,
@@ -1274,7 +1274,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) by (container) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"interval": "$resolution",
"legendFormat": "{{ container }} REQUESTS",
"range": true,
@@ -1286,7 +1286,7 @@
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) by (container) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"hide": false,
"legendFormat": "{{ container }} LIMITS",
"range": true,
@@ -1402,7 +1402,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}) by (container) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}) by (container) / sum(kube_pod_container_resource_requests{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"interval": "",
"legendFormat": "{{ container }} REQUESTS",
"range": true,
@@ -1414,7 +1414,7 @@
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", cluster=\"$cluster\"}) by (container) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}) by (container) / sum(kube_pod_container_resource_limits{namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\", job=~\"$job\", cluster=\"$cluster\"}) by (container)",
"hide": false,
"legendFormat": "{{ container }} LIMITS",
"range": true,
@@ -1533,7 +1533,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"interval": "$resolution",
"legendFormat": "{{ container }}",
"range": true,
@@ -1635,7 +1635,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", image!=\"\", container!=\"\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}) by (container)",
"interval": "",
"legendFormat": "{{ container }}",
"range": true,
@@ -1739,7 +1739,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~\"$namespace\", pod=\"$pod\", image!=\"\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"expr": "sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~\"$namespace\", pod=\"$pod\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"interval": "$resolution",
"legendFormat": "{{ container }}",
"range": true,
@@ -1867,7 +1867,7 @@
},
"editorMode": "code",
"exemplar": true,
"expr": "sum(increase(container_oom_events_total{namespace=\"${namespace}\", pod=\"${pod}\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"expr": "sum(increase(container_oom_events_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"${namespace}\", pod=\"${pod}\", container!=\"\", container!=\"POD\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"interval": "",
"legendFormat": "{{ container }}",
"range": true,
@@ -2104,7 +2104,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "sum(rate(container_network_receive_bytes_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "sum(rate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Received",
"refId": "A"
@@ -2115,7 +2115,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "- sum(rate(container_network_transmit_bytes_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "- sum(rate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Transmitted",
"refId": "B"
@@ -2210,7 +2210,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "sum(rate(container_network_receive_packets_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "sum(rate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Received",
"refId": "A"
@@ -2221,7 +2221,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "- sum(rate(container_network_transmit_packets_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "- sum(rate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Transmitted",
"refId": "B"
@@ -2316,7 +2316,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "sum(rate(container_network_receive_packets_dropped_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "sum(rate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Received",
"refId": "A"
@@ -2327,7 +2327,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "- sum(rate(container_network_transmit_packets_dropped_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "- sum(rate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Transmitted",
"refId": "B"
@@ -2422,7 +2422,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "sum(rate(container_network_receive_errors_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "sum(rate(container_network_receive_errors_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Received",
"refId": "A"
@@ -2433,7 +2433,7 @@
"uid": "${datasource}"
},
"exemplar": true,
"expr": "- sum(rate(container_network_transmit_errors_total{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"expr": "- sum(rate(container_network_transmit_errors_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}[$__rate_interval]))",
"interval": "$resolution",
"legendFormat": "Transmitted",
"refId": "B"
hosts/idols-aquamarine/grafana/dashboards/kubernetes/k8s-views-service.json
+2645
View File
File diff suppressed because it is too large Load Diff
hosts/idols-aquamarine/grafana/dashboards/kubernetes/kubernetes-persistent-volumes.json
+1623
View File
File diff suppressed because it is too large Load Diff
hosts/idols-aquamarine/monitoring/recoding_rules/k8s.yml
+5 -5
View File
@@ -3,31 +3,31 @@ groups:
rules:
- expr: |-
sum by (cluster, namespace, pod, container) (
irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", container!="", container!="POD"}[5m])
) * 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_cpu_usage_seconds_total:sum_irate
- expr: |-
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", container!="", container!="POD"}
* 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
- expr: |-
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", container!="", container!="POD"}
* 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
- expr: |-
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", container!="", container!="POD"}
* 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
- expr: |-
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", container!="", container!="POD"}
* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
)