自定义监控大盘

在 KubeVela 中，借助 Kubernetes 原生的 Aggregated API Layer，KubeVela 用户可以比较轻易地在集群中操作修改 Grafana 上的监控大盘。

除了 开箱即用 章节中 grafana 插件预置的监控大盘外，KubeVela 用户同样也可以在系统中部署自定义大盘。

自定义监控大盘 - 图1提示

如果你还不了解如何在 Grafana 上创建大盘并将它们以 JSON 格式导出，你可以阅读下列 Grafana 官方文档来学习。

  1. 创建你的第一个监控大盘
  2. 导出一个监控大盘

一种部署监控大盘的方式是在 KubeVela 应用中使用相应的组件类型。

  1. apiVersion: core.oam.dev/v1beta1
  2. kind: Application
  3. metadata:
  4.   name: my-dashboard
  5. spec:
  6.   components:
  7.     - name: my-dashboard
  8.       type: grafana-dashboard
  9.       properties:
  10.         uid: my-example-dashboard
  11.         data: |
  12.           {
  13.             "panels": [{
  14.                 "gridPos": {
  15.                     "h": 9,
  16.                     "w": 12
  17.                 },
  18.                 "targets": [{
  19.                     "datasource": {
  20.                         "type": "prometheus",
  21.                         "uid": "prometheus-vela"
  22.                     },
  23.                     "expr": "max(up) by (cluster)"
  24.                 }],
  25.                 "title": "Clusters",
  26.                 "type": "timeseries"
  27.             }],
  28.             "title": "My Dashboard"
  29.           }

除了组件外，用户也可以将监控大盘放在运维特征中进行部署。

  1. apiVersion: core.oam.dev/v1beta1
  2. kind: Application
  3. metadata:
  4.   name: my-app
  5. spec:
  6.   components:
  7.     - name: my-app
  8.       type: webservice
  9.       properties:
  10.         image: somefive/prometheus-client-example:new
  11.       traits:
  12.         - type: prometheus-scrape
  13.         - type: grafana-dashboard
  14.           properties:
  15.             data: |
  16.                 {"__inputs":[{"name":"DS_PROMETHEUS","label":"prometheus-vela","description":"","type":"datasource","pluginId":"prometheus","pluginName":"Prometheus"}],"__elements":[],"__requires":[{"type":"grafana","id":"grafana","name":"Grafana","version":"8.5.3"},{"type":"panel","id":"graph","name":"Graph (old)","version":""},{"type":"datasource","id":"prometheus","name":"Prometheus","version":"1.0.0"}],"annotations":{"list":[{"builtIn":1,"datasource":{"type":"grafana","uid":"-- Grafana --"},"enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","target":{"limit":100,"matchAny":false,"tags":[],"type":"dashboard"},"type":"dashboard"}]},"description":"Auto-generated Dashboard","editable":true,"fiscalYearStartMonth":0,"graphTooltip":0,"id":null,"iteration":1667283876999,"links":[],"liveNow":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Build information about the main Go module.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":0,"y":0},"hiddenSeries":false,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_build_info)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_build_info","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"A summary of the pause duration of garbage collection cycles.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":6,"y":0},"hiddenSeries":false,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(go_gc_duration_seconds_sum[$rate_interval])) / sum(rate(go_gc_duration_seconds_count[$rate_interval]))","legendFormat":"avg","refId":"A"},{"expr":"histogram_quantile(0.75, sum(rate(go_gc_duration_seconds_bucket[$rate_interval])) by (le))","legendFormat":"p75","refId":"B"},{"expr":"histogram_quantile(0.99, sum(rate(go_gc_duration_seconds_bucket[$rate_interval])) by (le))","legendFormat":"p99","refId":"C"}],"thresholds":[],"timeRegions":[],"title":"go_gc_duration_seconds","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of goroutines that currently exist.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":12,"y":0},"hiddenSeries":false,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_goroutines)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_goroutines","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Information about the Go environment.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":18,"y":0},"hiddenSeries":false,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_info)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_info","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes allocated and still in use.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":0,"y":8},"hiddenSeries":false,"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_memstats_alloc_bytes)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_alloc_bytes","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Total number of bytes allocated, even if freed.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":6,"y":8},"hiddenSeries":false,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(go_memstats_alloc_bytes_total[$rate_interval]))","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_alloc_bytes_total","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes used by the profiling bucket hash table.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":12,"y":8},"hiddenSeries":false,"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_memstats_buck_hash_sys_bytes)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_buck_hash_sys_bytes","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Total number of frees.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":18,"y":8},"hiddenSeries":false,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(go_memstats_frees_total[$rate_interval]))","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_frees_total","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes used for garbage collection system metadata.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":0,"y":16},"hiddenSeries":false,"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_memstats_gc_sys_bytes)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_gc_sys_bytes","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of heap bytes allocated and still in use.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":6,"y":16},"hiddenSeries":false,"id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_memstats_heap_alloc_bytes)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_heap_alloc_bytes","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of heap bytes waiting to be used.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":12,"y":16},"hiddenSeries":false,"id":11,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_memstats_heap_idle_bytes)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_heap_idle_bytes","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of heap bytes that are in use.","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":6,"x":18,"y":16},"hiddenSeries":false,"id":12,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.5.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_memstats_heap_inuse_bytes)","refId":"A"}],"thresholds":[],"timeRegions":[],"title":"go_memstats_heap_inuse_bytes","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"mode":"time","show":true,"values":[]},"yaxes":[{"format":"short","logBase":1,"show":true},{"format":"short","logBase":1,"show":true}],"yaxis":{"align":false}},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of allocated objects.","gridPos":{"h":8,"w":6,"x":0,"y":24},"id":13,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_heap_objects)","refId":"A"}],"title":"go_memstats_heap_objects","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of heap bytes released to OS.","gridPos":{"h":8,"w":6,"x":6,"y":24},"id":14,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_heap_released_bytes)","refId":"A"}],"title":"go_memstats_heap_released_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of heap bytes obtained from system.","gridPos":{"h":8,"w":6,"x":12,"y":24},"id":15,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_heap_sys_bytes)","refId":"A"}],"title":"go_memstats_heap_sys_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of seconds since 1970 of last garbage collection.","gridPos":{"h":8,"w":6,"x":18,"y":24},"id":16,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_last_gc_time_seconds)","refId":"A"}],"title":"go_memstats_last_gc_time_seconds","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Total number of pointer lookups.","gridPos":{"h":8,"w":6,"x":0,"y":32},"id":17,"legend":{"show":false},"targets":[{"expr":"sum(rate(go_memstats_lookups_total[$rate_interval]))","refId":"A"}],"title":"go_memstats_lookups_total","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Total number of mallocs.","gridPos":{"h":8,"w":6,"x":6,"y":32},"id":18,"legend":{"show":false},"targets":[{"expr":"sum(rate(go_memstats_mallocs_total[$rate_interval]))","refId":"A"}],"title":"go_memstats_mallocs_total","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes in use by mcache structures.","gridPos":{"h":8,"w":6,"x":12,"y":32},"id":19,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_mcache_inuse_bytes)","refId":"A"}],"title":"go_memstats_mcache_inuse_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes used for mcache structures obtained from system.","gridPos":{"h":8,"w":6,"x":18,"y":32},"id":20,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_mcache_sys_bytes)","refId":"A"}],"title":"go_memstats_mcache_sys_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes in use by mspan structures.","gridPos":{"h":8,"w":6,"x":0,"y":40},"id":21,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_mspan_inuse_bytes)","refId":"A"}],"title":"go_memstats_mspan_inuse_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes used for mspan structures obtained from system.","gridPos":{"h":8,"w":6,"x":6,"y":40},"id":22,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_mspan_sys_bytes)","refId":"A"}],"title":"go_memstats_mspan_sys_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of heap bytes when next garbage collection will take place.","gridPos":{"h":8,"w":6,"x":12,"y":40},"id":23,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_next_gc_bytes)","refId":"A"}],"title":"go_memstats_next_gc_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes used for other system allocations.","gridPos":{"h":8,"w":6,"x":18,"y":40},"id":24,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_other_sys_bytes)","refId":"A"}],"title":"go_memstats_other_sys_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes in use by the stack allocator.","gridPos":{"h":8,"w":6,"x":0,"y":48},"id":25,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_stack_inuse_bytes)","refId":"A"}],"title":"go_memstats_stack_inuse_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes obtained from system for stack allocator.","gridPos":{"h":8,"w":6,"x":6,"y":48},"id":26,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_stack_sys_bytes)","refId":"A"}],"title":"go_memstats_stack_sys_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of bytes obtained from system.","gridPos":{"h":8,"w":6,"x":12,"y":48},"id":27,"legend":{"show":false},"targets":[{"expr":"sum(go_memstats_sys_bytes)","refId":"A"}],"title":"go_memstats_sys_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of OS threads created.","gridPos":{"h":8,"w":6,"x":18,"y":48},"id":28,"legend":{"show":false},"targets":[{"expr":"sum(go_threads)","refId":"A"}],"title":"go_threads","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Total user and system CPU time spent in seconds.","gridPos":{"h":8,"w":6,"x":0,"y":56},"id":29,"legend":{"show":false},"targets":[{"expr":"sum(rate(process_cpu_seconds_total[$rate_interval]))","refId":"A"}],"title":"process_cpu_seconds_total","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Maximum number of open file descriptors.","gridPos":{"h":8,"w":6,"x":6,"y":56},"id":30,"legend":{"show":false},"targets":[{"expr":"sum(process_max_fds)","refId":"A"}],"title":"process_max_fds","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Number of open file descriptors.","gridPos":{"h":8,"w":6,"x":12,"y":56},"id":31,"legend":{"show":false},"targets":[{"expr":"sum(process_open_fds)","refId":"A"}],"title":"process_open_fds","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Resident memory size in bytes.","gridPos":{"h":8,"w":6,"x":18,"y":56},"id":32,"legend":{"show":false},"targets":[{"expr":"sum(process_resident_memory_bytes)","refId":"A"}],"title":"process_resident_memory_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Start time of the process since unix epoch in seconds.","gridPos":{"h":8,"w":6,"x":0,"y":64},"id":33,"legend":{"show":false},"targets":[{"expr":"sum(process_start_time_seconds)","refId":"A"}],"title":"process_start_time_seconds","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Virtual memory size in bytes.","gridPos":{"h":8,"w":6,"x":6,"y":64},"id":34,"legend":{"show":false},"targets":[{"expr":"sum(process_virtual_memory_bytes)","refId":"A"}],"title":"process_virtual_memory_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"Maximum amount of virtual memory available in bytes.","gridPos":{"h":8,"w":6,"x":12,"y":64},"id":35,"legend":{"show":false},"targets":[{"expr":"sum(process_virtual_memory_max_bytes)","refId":"A"}],"title":"process_virtual_memory_max_bytes","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"RPC latency distributions.","gridPos":{"h":8,"w":6,"x":18,"y":64},"id":36,"targets":[{"expr":"sum(rate(rpc_durations_histogram_seconds_sum[$rate_interval])) / sum(rate(rpc_durations_histogram_seconds_count[$rate_interval]))","legendFormat":"avg","refId":"A"},{"expr":"histogram_quantile(0.75, sum(rate(rpc_durations_histogram_seconds_bucket[$rate_interval])) by (le))","legendFormat":"p75","refId":"B"},{"expr":"histogram_quantile(0.99, sum(rate(rpc_durations_histogram_seconds_bucket[$rate_interval])) by (le))","legendFormat":"p99","refId":"C"}],"title":"rpc_durations_histogram_seconds","type":"graph"},{"datasource":{"type":"prometheus","uid":"${DS_PROMETHEUS}"},"description":"RPC latency distributions.","gridPos":{"h":8,"w":6,"x":0,"y":72},"id":37,"targets":[{"expr":"sum(rate(rpc_durations_seconds_sum[$rate_interval])) / sum(rate(rpc_durations_seconds_count[$rate_interval]))","legendFormat":"avg","refId":"A"},{"expr":"histogram_quantile(0.75, sum(rate(rpc_durations_seconds_bucket[$rate_interval])) by (le))","legendFormat":"p75","refId":"B"},{"expr":"histogram_quantile(0.99, sum(rate(rpc_durations_seconds_bucket[$rate_interval])) by (le))","legendFormat":"p99","refId":"C"}],"title":"rpc_durations_seconds","type":"graph"}],"refresh":"30s","schemaVersion":36,"style":"dark","tags":[],"templating":{"list":[{"allFormat":"glob","current":{"selected":false,"text":"prometheus-vela","value":"prometheus-vela"},"hide":2,"includeAll":false,"label":"Data Source","multi":false,"name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allFormat":"glob","auto":false,"auto_count":30,"auto_min":"10s","current":{"selected":false,"text":"3m","value":"3m"},"hide":2,"label":"Rate","name":"rate_interval","options":[{"selected":true,"text":"3m","value":"3m"},{"selected":false,"text":"5m","value":"5m"},{"selected":false,"text":"10m","value":"10m"},{"selected":false,"text":"30m","value":"30m"}],"query":"3m,5m,10m,30m","refresh":2,"skipUrlSync":false,"type":"interval"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{},"timezone":"","title":"my-app","uid":"my-app-default","version":4,"weekStart":""}

有时，你可能已经把编写好的 Grafana 监控大盘存储在了 OSS 或者其他 HTTP 服务器上。在 KubeVela 的应用中，你同样也可以使用 import-grafana-dashboard 工作流步骤来将大盘导入。

  1. apiVersion: core.oam.dev/v1beta1
  2. kind: Application
  3. metadata:
  4.   name: my-dashboard
  5. spec:
  6.   components: []
  7.   workflow:
  8.     steps:
  9.       - type: import-grafana-dashboard
  10.         name: import-grafana-dashboard
  11.         properties: 
  12.           uid: my-dashboard
  13.           title: My Dashboard
  14.           url: https://kubevelacharts.oss-accelerate.aliyuncs.com/dashboards/up-cluster-dashboard.json

在 import-grafana-dashboard 步骤中, 应用首先将会从 URL 上下载监控大盘的数据，然后将它创建到 Grafana 上。

自定义监控大盘 - 图2危险

下面的章节将会要求您具有一定的 CUE 语言开发经验，尤其是 KubeVela 的工作流自定义步骤的开发经验。此外，Grafana 监控大盘基础数据结构的相关知识也是必要的。如果缺少这些知识，下面的内容将会比较难理解。

下文是一个在 KubeVela 中实践 Dashboard as Code 的样例。当你在实际环境中使用它时，根据场景可能存在额外的问题需要注意，比如部分指标的延迟出现。目前该技术尚未使用在生产环境中，它是否能够在不同的环境中顺利运行也尚未验证。欢迎将你的想法和用例提交在 GitHub 上进行讨论。

Details

你可以使用 CUE 来定制监控大盘的生成过程。它允许你根据其他动作行为的结果来动态创建监控大盘的表盘内容。例如，你可以用如下的代码创建一个 create-dashboard 工作流步骤定义，它会自动从应用提供的服务端口中找到相应的指标内容并为不同类型的指标生成相应的折线图。

  1. import (
  2.     "vela/op"
  3.     "vela/ql"
  4.     "strconv"
  5.     "math"
  6.     "regexp"
  7. )
  9. "create-dashboard": {
  10.     type: "workflow-step"
  11.     annotations: {}
  12.     labels: {}
  13.     description: "Create dashboard for application."
  14. }
  15. template: {
  16.     resources: ql.#CollectServiceEndpoints & {
  17.         app: {
  18.             name:      context.name
  19.             namespace: context.namespace
  20.             filter: {}
  21.         }
  22.     } @step(1)
  24.     status: {
  25.         endpoints: *[] | [...{...}]
  26.         if resources.err == _|_ && resources.list != _|_ {
  27.             endpoints: [ for ep in resources.list if ep.endpoint.port == parameter.port {
  28.                 name: "\(ep.ref.name):\(ep.ref.namespace):\(ep.cluster)"
  29.                 portStr: strconv.FormatInt(ep.endpoint.port, 10)
  30.                 if ep.cluster == "local" && ep.ref.kind == "Service" {
  31.                     url: "http://\(ep.ref.name).\(ep.ref.namespace):\(portStr)"
  32.                 }
  33.                 if ep.cluster != "local" || ep.ref.kind != "Service" {
  34.                     url: "http://\(ep.endpoint.host):\(portStr)"
  35.                 }
  36.             }]
  37.         }
  38.     } @step(2)
  40.     getMetrics: op.#Steps & {
  41.         for ep in status.endpoints {
  42.             "\(ep.name)": op.#HTTPGet & {
  43.                 url: ep.url + "/metrics"
  44.             }
  45.         }
  46.     } @step(3)
  48.     checkErrors: op.#Steps & {
  49.         for ep in status.endpoints if getMetrics["\(ep.name)"] != _|_ {
  50.             if getMetrics["\(ep.name)"].response.statusCode != 200 {
  51.                 "\(ep.name)": op.#Steps & {
  52.                     src: getMetrics["\(ep.name)"]
  53.                     err: op.#Fail & {
  54.                         message: "failed to get metrics for \(ep.name) from \(ep.url), code \(src.response.statusCode)"
  55.                     }
  56.                 }
  57.             }
  58.         }
  59.     } @step(4)
  61.     createDashboards: op.#Steps & {
  62.         for ep in status.endpoints if getMetrics["\(ep.name)"] != _|_ {
  63.             if getMetrics["\(ep.name)"].response.body != "" {
  64.                 "\(ep.name)": dashboard & {
  65.                     title: context.name
  66.                     uid: "\(context.name)-\(context.namespace)"
  67.                     description: "Auto-generated Dashboard"
  68.                     metrics: *[] | [...{...}]
  69.                     metrics: regexp.FindAllNamedSubmatch(#"""
  70.                         # HELP \w+ (?P<desc>[^\n]+)\n# TYPE (?P<name>\w+) (?P<type>\w+)
  71.                         """#, getMetrics["\(ep.name)"].response.body, -1)
  72.                 }
  73.             }
  74.         }
  75.     } @step(5)
  77.     applyDashboards: op.#Steps & {
  78.         for ep in status.endpoints if createDashboards["\(ep.name)"] != _|_ {
  79.             "\(ep.name)": op.#Apply & {
  80.                 db: {for k, v in createDashboards["\(ep.name)"] if k != "metrics" {
  81.                     "\(k)": v
  82.                 }}
  83.                 value: {
  84.                     apiVersion: "o11y.prism.oam.dev/v1alpha1"
  85.                     kind:       "GrafanaDashboard"
  86.                     metadata: name: "\(db.uid)@\(parameter.grafana)"
  87.                     spec: db
  88.                 }
  89.             }
  90.         }
  91.     } @step(6)
  93.     dashboard: {
  94.         title: *"Example Dashboard" | string
  95.         uid: *"" | string
  96.         description: *"" | string
  97.         metrics: [...{...}]
  98.         time: {
  99.             from: *"now-1h" | string
  100.             to: *"now" | string
  101.         }
  102.         refresh: *"30s" | string
  103.         templating: list: [{
  104.             type: "datasource"
  105.             name: "datasource"
  106.             label: "Data Source"
  107.             query: "prometheus"
  108.             hide: 2
  109.         }, {
  110.             type: "interval"
  111.             name: "rate_interval"
  112.             label: "Rate"
  113.             query: "3m,5m,10m,30m"
  114.             hide: 2
  115.         }]
  117.         panels: [for i, m in metrics {
  118.             title: m.name
  119.             type: "graph"
  120.             datasource: {
  121.                 uid: "${datasource}"
  122.                 type: "prometheus"
  123.             }
  124.             gridPos: {
  125.                 w: 6
  126.                 h: 8
  127.                 x: math.Floor((i - y * 4) * 6)
  128.                 y: math.Floor(i / 4)
  129.             }
  130.             description: m.desc
  131.             if m.type == "gauge" {
  132.                 targets: [{
  133.                     expr: "sum(\(m.name))"
  134.                 }]
  135.                 legend: show: false
  136.             }
  137.             if m.type == "counter" {
  138.                 targets: [{
  139.                     expr: "sum(rate(\(m.name)[$rate_interval]))"
  140.                 }]
  141.                 legend: show: false
  142.             }
  143.             if m.type == "histogram" || m.type == "summary" {
  144.                 targets: [{
  145.                     expr: "sum(rate(\(m.name)_sum[$rate_interval])) / sum(rate(\(m.name)_count[$rate_interval]))"
  146.                     legendFormat: "avg"
  147.                 }, {
  148.                     expr: "histogram_quantile(0.75, sum(rate(\(m.name)_bucket[$rate_interval])) by (le))"
  149.                     legendFormat: "p75"
  150.                 }, {
  151.                     expr: "histogram_quantile(0.99, sum(rate(\(m.name)_bucket[$rate_interval])) by (le))"
  152.                     legendFormat: "p99"
  153.                 }]
  154.             }
  155.         }]
  156.     }
  158.     parameter: {
  159.         port: *8080 | int
  160.         grafana: *"default" | string
  161.     }
  162. }

然后你可以按照如下方式创建一个应用。

  1. apiVersion: core.oam.dev/v1beta1
  2. kind: Application
  3. metadata:
  4.   name: my-app
  5. spec:
  6.   # the core workload
  7.   components:
  8.     - name: my-app
  9.       type: webservice
  10.       properties:
  11.         image: somefive/prometheus-client-example:new
  12.       traits:
  13.         - type: prometheus-scrape
  14.   # deploy and create dashboard automatically
  15.   workflow:
  16.     steps:
  17.       - type: deploy
  18.         name: deploy
  19.         properties:
  20.           policies: []
  21.       - type: create-dashboard
  22.         name: create-dashboard

该应用会首先部署 webservice 组件，然后自动采集它的指标并为其生成监控大盘。

Last updated on 2023年8月4日 by Daniel Higuero