213 lines
10 KiB
YAML
213 lines
10 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-provider
|
|
namespace: monitoring
|
|
data:
|
|
dashboards.yaml: |
|
|
apiVersion: 1
|
|
providers:
|
|
- name: default
|
|
orgId: 1
|
|
folder: ""
|
|
type: file
|
|
disableDeletion: false
|
|
updateIntervalSeconds: 30
|
|
options:
|
|
path: /var/lib/grafana/dashboards
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboards
|
|
namespace: monitoring
|
|
data:
|
|
k3s-cluster.json: |
|
|
{
|
|
"title": "planck k3s cluster",
|
|
"uid": "planckk3s",
|
|
"timezone": "browser",
|
|
"refresh": "15s",
|
|
"time": { "from": "now-3h", "to": "now" },
|
|
"panels": [
|
|
{
|
|
"id": 1, "type": "timeseries", "title": "Pods running by node",
|
|
"gridPos": {"x": 0, "y": 0, "w": 12, "h": 9},
|
|
"targets": [{"expr": "count by (node) (kube_pod_status_phase{phase=\"Running\"} == 1)", "legendFormat": "{{node}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 2, "type": "timeseries", "title": "Deployment replicas: ready vs desired",
|
|
"gridPos": {"x": 12, "y": 0, "w": 12, "h": 9},
|
|
"targets": [
|
|
{"expr": "sum by (deployment, namespace) (kube_deployment_status_replicas_ready)", "legendFormat": "ready {{namespace}}/{{deployment}}"},
|
|
{"expr": "sum by (deployment, namespace) (kube_deployment_spec_replicas)", "legendFormat": "want {{namespace}}/{{deployment}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 3, "type": "timeseries", "title": "Top pods by CPU (cores)",
|
|
"gridPos": {"x": 0, "y": 9, "w": 12, "h": 9},
|
|
"targets": [{"expr": "topk(12, sum by (pod, namespace) (rate(container_cpu_usage_seconds_total{container!=\"\", container!=\"POD\"}[2m])))", "legendFormat": "{{namespace}}/{{pod}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "none"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 4, "type": "timeseries", "title": "Top pods by memory (working set)",
|
|
"gridPos": {"x": 12, "y": 9, "w": 12, "h": 9},
|
|
"targets": [{"expr": "topk(12, sum by (pod, namespace) (container_memory_working_set_bytes{container!=\"\", container!=\"POD\"}))", "legendFormat": "{{namespace}}/{{pod}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "bytes"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 5, "type": "timeseries", "title": "Container restarts (cumulative)",
|
|
"gridPos": {"x": 0, "y": 18, "w": 12, "h": 9},
|
|
"targets": [{"expr": "sum by (pod, namespace) (kube_pod_container_status_restarts_total)", "legendFormat": "{{namespace}}/{{pod}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 6, "type": "timeseries", "title": "CPU: requested vs allocatable (per node, top 10 nodes)",
|
|
"gridPos": {"x": 12, "y": 18, "w": 12, "h": 9},
|
|
"targets": [
|
|
{"expr": "topk(10, sum by (node) (kube_pod_container_resource_requests{resource=\"cpu\", unit=\"core\"}))", "legendFormat": "requested {{node}}"},
|
|
{"expr": "kube_node_status_allocatable{resource=\"cpu\", unit=\"core\"}", "legendFormat": "allocatable {{node}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "none"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 7, "type": "timeseries", "title": "Nodes Ready",
|
|
"gridPos": {"x": 0, "y": 27, "w": 12, "h": 7},
|
|
"targets": [{"expr": "count(kube_node_status_condition{condition=\"Ready\", status=\"true\"} == 1)", "legendFormat": "nodes ready"}],
|
|
"fieldConfig": {"defaults": {"unit": "short", "min": 0, "max": 20}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 8, "type": "timeseries", "title": "Pods not Running (pending/failed/succeeded)",
|
|
"gridPos": {"x": 12, "y": 27, "w": 12, "h": 7},
|
|
"targets": [{"expr": "count by (phase) (kube_pod_status_phase == 1) unless on(pod, namespace, phase) label_replace(kube_pod_status_phase{phase=\"Running\"}, \"phase\", \"running\", \"\", \"\") * 0", "legendFormat": "{{phase}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"version": 1
|
|
}
|
|
node-health.json: |
|
|
{
|
|
"title": "planck node health",
|
|
"uid": "plancknodes",
|
|
"timezone": "browser",
|
|
"refresh": "10s",
|
|
"time": { "from": "now-1h", "to": "now" },
|
|
"panels": [
|
|
{
|
|
"id": 1, "type": "timeseries", "title": "CPU temperature (all nodes)",
|
|
"gridPos": {"x": 0, "y": 0, "w": 12, "h": 8},
|
|
"targets": [{"expr": "node_thermal_zone_temp", "legendFormat": "{{instance}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "celsius"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 2, "type": "timeseries", "title": "CPU usage % (all nodes)",
|
|
"gridPos": {"x": 12, "y": 0, "w": 12, "h": 8},
|
|
"targets": [{"expr": "100 * (1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[2m])))", "legendFormat": "{{instance}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "percent", "min": 0, "max": 100}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 3, "type": "timeseries", "title": "Memory used % (all nodes)",
|
|
"gridPos": {"x": 0, "y": 8, "w": 12, "h": 8},
|
|
"targets": [{"expr": "100 * (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)", "legendFormat": "{{instance}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "percent", "min": 0, "max": 100}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 4, "type": "timeseries", "title": "Disk used % (root, all nodes)",
|
|
"gridPos": {"x": 12, "y": 8, "w": 12, "h": 8},
|
|
"targets": [{"expr": "100 * (1 - node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"})", "legendFormat": "{{instance}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "percent", "min": 0, "max": 100}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 5, "type": "timeseries", "title": "Network eth0: RX / TX",
|
|
"gridPos": {"x": 0, "y": 16, "w": 12, "h": 8},
|
|
"targets": [
|
|
{"expr": "sum by (instance) (rate(node_network_receive_bytes_total{device=\"eth0\"}[1m]))", "legendFormat": "rx {{instance}}"},
|
|
{"expr": "sum by (instance) (rate(node_network_transmit_bytes_total{device=\"eth0\"}[1m]))", "legendFormat": "tx {{instance}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "Bps"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 6, "type": "timeseries", "title": "SSD I/O: read / write",
|
|
"gridPos": {"x": 12, "y": 16, "w": 12, "h": 8},
|
|
"targets": [
|
|
{"expr": "sum by (instance) (rate(node_disk_read_bytes_total{device=~\"sda.*\"}[1m]))", "legendFormat": "read {{instance}}"},
|
|
{"expr": "sum by (instance) (rate(node_disk_written_bytes_total{device=~\"sda.*\"}[1m]))", "legendFormat": "write {{instance}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "Bps"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 7, "type": "timeseries", "title": "Load (1 min, all nodes)",
|
|
"gridPos": {"x": 0, "y": 24, "w": 24, "h": 7},
|
|
"targets": [{"expr": "node_load1", "legendFormat": "{{instance}}"}],
|
|
"fieldConfig": {"defaults": {"unit": "short"}, "overrides": []}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"version": 1
|
|
}
|
|
k6-step-load.json: |
|
|
{
|
|
"title": "k6 Step Load",
|
|
"uid": "k6step",
|
|
"timezone": "browser",
|
|
"refresh": "5s",
|
|
"time": { "from": "now-30m", "to": "now" },
|
|
"panels": [
|
|
{
|
|
"id": 1, "type": "timeseries", "title": "Request rate (the staircase)",
|
|
"gridPos": {"x": 0, "y": 0, "w": 24, "h": 8},
|
|
"targets": [
|
|
{"expr": "sum(rate(k6_http_reqs_total[30s]))", "legendFormat": "total rps"},
|
|
{"expr": "sum by (name) (rate(k6_http_reqs_total[30s]))", "legendFormat": "{{name}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "reqps"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 2, "type": "timeseries", "title": "Latency avg / p50 / p95 / p99",
|
|
"gridPos": {"x": 0, "y": 8, "w": 12, "h": 8},
|
|
"targets": [
|
|
{"expr": "k6_http_req_duration_avg", "legendFormat": "avg"},
|
|
{"expr": "k6_http_req_duration_p50", "legendFormat": "p50"},
|
|
{"expr": "k6_http_req_duration_p95", "legendFormat": "p95"},
|
|
{"expr": "k6_http_req_duration_p99", "legendFormat": "p99"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "s"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 3, "type": "timeseries", "title": "p95 latency per step",
|
|
"gridPos": {"x": 12, "y": 8, "w": 12, "h": 8},
|
|
"targets": [
|
|
{"expr": "k6_http_req_duration_p95", "legendFormat": "{{step}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "s"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 4, "type": "timeseries", "title": "p95 latency per endpoint",
|
|
"gridPos": {"x": 0, "y": 16, "w": 12, "h": 8},
|
|
"targets": [
|
|
{"expr": "k6_http_req_duration_p95", "legendFormat": "{{name}}"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "s"}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 5, "type": "timeseries", "title": "Error rate",
|
|
"gridPos": {"x": 12, "y": 16, "w": 12, "h": 8},
|
|
"targets": [
|
|
{"expr": "sum(rate(k6_http_req_failed_total[30s])) / sum(rate(k6_http_reqs_total[30s]))", "legendFormat": "error fraction"}
|
|
],
|
|
"fieldConfig": {"defaults": {"unit": "percentunit", "min": 0, "max": 1}, "overrides": []}
|
|
},
|
|
{
|
|
"id": 6, "type": "timeseries", "title": "Active VUs",
|
|
"gridPos": {"x": 0, "y": 24, "w": 24, "h": 6},
|
|
"targets": [{"expr": "k6_vus", "legendFormat": "vus"}],
|
|
"fieldConfig": {"defaults": {"unit": "short"}, "overrides": []}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"version": 1
|
|
}
|