From f771ec76a036f487a64609b65077ba05c2fab307 Mon Sep 17 00:00:00 2001 From: Ryan Yin Date: Thu, 11 Sep 2025 13:48:01 +0800 Subject: [PATCH 1/4] fix: idols-aquamarine - alert --- flake.lock | 6 +- hosts/idols-aquamarine/caddy.nix | 5 + hosts/idols-aquamarine/monitoring/alert.nix | 125 ++++++++++++++++++ .../monitoring/alert_rules/istio-exporter.yml | 2 +- .../monitoring/alertmanager.nix | 48 ------- hosts/idols-aquamarine/monitoring/default.nix | 2 +- .../monitoring/victoriametrics.nix | 21 --- 7 files changed, 135 insertions(+), 74 deletions(-) create mode 100644 hosts/idols-aquamarine/monitoring/alert.nix delete mode 100644 hosts/idols-aquamarine/monitoring/alertmanager.nix diff --git a/flake.lock b/flake.lock index 88422e5c..2644a3f9 100644 --- a/flake.lock +++ b/flake.lock @@ -526,10 +526,10 @@ "mysecrets": { "flake": false, "locked": { - "lastModified": 1752678564, - "narHash": "sha256-x2sbH7Umncbyc9oca5mqX8kMChHVUTytKk+QXEcB4i4=", + "lastModified": 1757651423, + "narHash": "sha256-w2hBme0vg3uDoEjP+0WuBT9hAhf1xJa4Np+GS2zQKXU=", "ref": "refs/heads/main", - "rev": "a231913597362c15c71fd9212cef5092ae85a64c", + "rev": "44b2943b7ebed5717bb9855c1b7a95c8a89fb7f7", "shallow": true, "type": "git", "url": "ssh://git@github.com/ryan4yin/nix-secrets.git" diff --git a/hosts/idols-aquamarine/caddy.nix b/hosts/idols-aquamarine/caddy.nix index 36766bd0..88932720 100644 --- a/hosts/idols-aquamarine/caddy.nix +++ b/hosts/idols-aquamarine/caddy.nix @@ -88,6 +88,11 @@ in encode zstd gzip reverse_proxy http://localhost:9093 ''; + virtualHosts."vmalert.writefor.fun".extraConfig = '' + ${hostCommonConfig} + encode zstd gzip + reverse_proxy http://localhost:8880 + ''; virtualHosts."minio.writefor.fun".extraConfig = '' ${hostCommonConfig} encode zstd gzip diff --git a/hosts/idols-aquamarine/monitoring/alert.nix b/hosts/idols-aquamarine/monitoring/alert.nix new file mode 100644 index 00000000..6da20c07 --- /dev/null +++ b/hosts/idols-aquamarine/monitoring/alert.nix @@ -0,0 +1,125 @@ +{ config, lib, ... }: +{ + services.vmalert = { + enable = true; + settings = { + "httpListenAddr" = "127.0.0.1:8880"; + + "datasource.url" = "http://localhost:9090"; + "notifier.url" = [ "http://localhost:9093" ]; # alertmanager's api + + # Whether to disable long-lived connections to the datasource. + "datasource.disableKeepAlive" = true; + # Whether to avoid stripping sensitive information such as auth headers or passwords + # from URLs in log messages or UI and exported metrics. + "datasource.showURL" = false; + # Path to the files with alerting and/or recording rules. + rule = [ + "${./alert_rules}/*.yml" + ]; + }; + }; + + services.prometheus.alertmanager = { + enable = true; + listenAddress = "127.0.0.1"; + port = 9093; + webExternalUrl = "http://alertmanager.writefor.fun"; + logLevel = "info"; + environmentFile = config.age.secrets."alertmanager.env".path; + configuration = { + global = { + # The smarthost and SMTP sender used for mail notifications. + smtp_smarthost = "smtp.qq.com:465"; + smtp_from = "$SMTP_SENDER_EMAIL"; + smtp_auth_username = "$SMTP_AUTH_USERNAME"; + smtp_auth_password = "$SMTP_AUTH_PASSWORD"; + # smtp.qq.com:465 support SSL only, so we need to disable TLS here. + # https://service.mail.qq.com/detail/0/310 + smtp_require_tls = false; + }; + route = { + receiver = "telegram"; + routes = [ + { + receiver = "telegram"; + # group alerts by labels + group_by = [ + "host" + "namespace" + "pod" + "job" + ]; + group_wait = "5m"; + group_interval = "5m"; + repeat_interval = "4h"; + } + # { + # # Route critical alerts to email (most severe alerts) + # match = { + # severity = "critical"; + # }; + # receiver = "email"; + # group_by = [ + # "host" + # "namespace" + # "pod" + # "job" + # ]; + # group_wait = "1m"; + # group_interval = "5m"; + # repeat_interval = "2h"; + # } + ]; + }; + receivers = [ + # { + # name = "email"; + # email_configs = [ + # { + # to = "ryan4yin@linux.com"; + # # Whether to notify about resolved alerts. + # send_resolved = true; + # } + # ]; + # } + { + name = "telegram"; + telegram_configs = [ + { + bot_token = "$TELEGRAM_BOT_TOKEN"; + chat_id = 586169186; # My Telegram ID + # Whether to notify about resolved alerts. + send_resolved = true; + # Disable notifications for resolved alerts + disable_notifications = false; + # Parse mode for the message + parse_mode = "Markdown"; + # Message template + message = '' + *Alert:* {{ .GroupLabels.alertname }} + *Status:* {{ .Status }} + *Severity:* {{ .CommonLabels.severity }} + {{ if .GroupLabels.namespace }}*Namespace:* {{ .GroupLabels.namespace }}{{ end }} + {{ if .GroupLabels.pod }}*Pod:* {{ .GroupLabels.pod }}{{ end }} + {{ if .GroupLabels.job }}*Job:* {{ .GroupLabels.job }}{{ end }} + {{ if .GroupLabels.host }}*Host:* {{ .GroupLabels.host }}{{ end }} + + {{ range .Alerts }} + *Alert:* {{ .Annotations.summary }} + *Description:* {{ .Annotations.description }} + {{ if .Labels.instance }}*Instance:* {{ .Labels.instance }}{{ end }} + {{ if .Labels.container }}*Container:* {{ .Labels.container }}{{ end }} + *Started:* {{ .StartsAt.Format "2006-01-02 15:04:05" }} + {{ if .EndsAt }} + *Ended:* {{ .EndsAt.Format "2006-01-02 15:04:05" }} + {{ end }} + {{ end }} + ''; + } + ]; + } + ]; + }; + }; +} diff --git a/hosts/idols-aquamarine/monitoring/alert_rules/istio-exporter.yml b/hosts/idols-aquamarine/monitoring/alert_rules/istio-exporter.yml index 8a2ff838..ec2676a3 100644 --- a/hosts/idols-aquamarine/monitoring/alert_rules/istio-exporter.yml +++ b/hosts/idols-aquamarine/monitoring/alert_rules/istio-exporter.yml @@ -69,7 +69,7 @@ groups: annotations: summary: Istio high 4xx error rate (instance {{ $labels.instance }}) description: - "High percentage of HTTP 5xx responses in Istio (> 5%).\n VALUE = {{ $value + "High percentage of HTTP 4xx responses in Istio (> 5%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: IstioHigh5xxErrorRate diff --git a/hosts/idols-aquamarine/monitoring/alertmanager.nix b/hosts/idols-aquamarine/monitoring/alertmanager.nix deleted file mode 100644 index 3269d75d..00000000 --- a/hosts/idols-aquamarine/monitoring/alertmanager.nix +++ /dev/null @@ -1,48 +0,0 @@ -{ config, ... }: -{ - services.prometheus.alertmanager = { - enable = true; - listenAddress = "127.0.0.1"; - port = 9093; - webExternalUrl = "http://alertmanager.writefor.fun"; - logLevel = "info"; - - environmentFile = config.age.secrets."alertmanager.env".path; - configuration = { - global = { - # The smarthost and SMTP sender used for mail notifications. - smtp_smarthost = "smtp.qq.com:465"; - smtp_from = "$SMTP_SENDER_EMAIL"; - smtp_auth_username = "$SMTP_AUTH_USERNAME"; - smtp_auth_password = "$SMTP_AUTH_PASSWORD"; - # smtp.qq.com:465 support SSL only, so we need to disable TLS here. - # https://service.mail.qq.com/detail/0/310 - smtp_require_tls = false; - }; - route = { - receiver = "default"; - routes = [ - { - group_by = [ "host" ]; - group_wait = "5m"; - group_interval = "5m"; - repeat_interval = "4h"; - receiver = "default"; - } - ]; - }; - receivers = [ - { - name = "default"; - email_configs = [ - { - to = "ryan4yin@linux.com"; - # Whether to notify about resolved alerts. - send_resolved = true; - } - ]; - } - ]; - }; - }; -} diff --git a/hosts/idols-aquamarine/monitoring/default.nix b/hosts/idols-aquamarine/monitoring/default.nix index 4eec1724..4bac8bae 100644 --- a/hosts/idols-aquamarine/monitoring/default.nix +++ b/hosts/idols-aquamarine/monitoring/default.nix @@ -2,6 +2,6 @@ { imports = [ ./victoriametrics.nix - ./alertmanager.nix + ./alert.nix ]; } diff --git a/hosts/idols-aquamarine/monitoring/victoriametrics.nix b/hosts/idols-aquamarine/monitoring/victoriametrics.nix index 5a375c12..10a55b1a 100644 --- a/hosts/idols-aquamarine/monitoring/victoriametrics.nix +++ b/hosts/idols-aquamarine/monitoring/victoriametrics.nix @@ -116,25 +116,4 @@ ) [ ] myvars.networking.hostsAddr); }; }; - - services.vmalert = { - enable = true; - settings = { - "datasource.url" = "http://localhost:9090"; - "notifier.url" = [ "http://localhost:9093" ]; # alertmanager's api - - # Whether to disable long-lived connections to the datasource. - "datasource.disableKeepAlive" = true; - # Whether to avoid stripping sensitive information such as auth headers or passwords - # from URLs in log messages or UI and exported metrics. - "datasource.showURL" = false; - rule = [ - ./alert_rules/node-exporter.yml - ./alert_rules/kubestate-exporter.yml - ./alert_rules/etcd_embedded-exporter.yml - ./alert_rules/istio_embedded-exporter.yml - ./alert_rules/coredns_embedded-exporter.yml - ]; - }; - }; } From e5b9a4917e0ae8a98366e36758e6727093571ee1 Mon Sep 17 00:00:00 2001 From: Ryan Yin Date: Fri, 12 Sep 2025 19:15:23 +0800 Subject: [PATCH 2/4] feat: add dashboards for victoriametrics --- .../grafana/dashboards/README.md | 4 + .../victoria-metrics-single.json | 6549 +++++++++++++++++ hosts/idols-aquamarine/monitoring/alert.nix | 17 +- 3 files changed, 6566 insertions(+), 4 deletions(-) create mode 100644 hosts/idols-aquamarine/grafana/dashboards/victoriametrics/victoria-metrics-single.json diff --git a/hosts/idols-aquamarine/grafana/dashboards/README.md b/hosts/idols-aquamarine/grafana/dashboards/README.md index 19b9b18f..0c2458e1 100644 --- a/hosts/idols-aquamarine/grafana/dashboards/README.md +++ b/hosts/idols-aquamarine/grafana/dashboards/README.md @@ -32,3 +32,7 @@ mixin provides a comprehensive package for monitoring Loki in production. - Instance: https://github.com/cloudnative-pg/grafana-dashboards/blob/main/charts/cluster/grafana-dashboard.json - Pooler(PGBouncer): https://github.com/cloudnative-pg/grafana-dashboards/issues/7 + +## VictoriaMetrics + +- https://grafana.com/orgs/victoriametrics/dashboards diff --git a/hosts/idols-aquamarine/grafana/dashboards/victoriametrics/victoria-metrics-single.json b/hosts/idols-aquamarine/grafana/dashboards/victoriametrics/victoria-metrics-single.json new file mode 100644 index 00000000..4c0d21cb --- /dev/null +++ b/hosts/idols-aquamarine/grafana/dashboards/victoriametrics/victoria-metrics-single.json @@ -0,0 +1,6549 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": { + "type": "datasource", + "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" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "enable": false, + "expr": "sum(ALERTS{job=~\"$job\", instance=~\"$instance\", alertgroup=\"vmsingle\",alertstate=\"firing\",show_at=\"dashboard\"}) by(alertname)", + "hide": false, + "iconColor": "red", + "name": "alerts", + "titleFormat": "{{alertname}}" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "enable": true, + "expr": "sum(vm_app_version{job=~\"$job\", instance=~\"$instance\"}) by(version) unless (sum(vm_app_version{job=~\"$job\", instance=~\"$instance\"} offset $__interval) by(version))", + "hide": true, + "iconColor": "dark-blue", + "name": "version", + "textFormat": "{{version}}", + "titleFormat": "Version change" + } + ] + }, + "description": "Overview for single-node VictoriaMetrics v1.117.0 or higher", + "editable": true, + "fiscalYearStartMonth": 0, + "graphTooltip": 1, + "id": 1, + "links": [ + { + "icon": "doc", + "tags": [], + "targetBlank": true, + "title": "Single server Wiki", + "type": "link", + "url": "https://docs.victoriametrics.com/" + }, + { + "icon": "external link", + "tags": [], + "targetBlank": true, + "title": "Found a bug?", + "type": "link", + "url": "https://github.com/VictoriaMetrics/VictoriaMetrics/issues" + }, + { + "icon": "external link", + "tags": [], + "targetBlank": true, + "title": "New releases", + "tooltip": "", + "type": "link", + "url": "https://github.com/VictoriaMetrics/VictoriaMetrics/releases" + } + ], + "panels": [ + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 6, + "panels": [], + "title": "Stats", + "type": "row" + }, + { + "description": "", + "fieldConfig": { + "defaults": {}, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 4, + "x": 0, + "y": 1 + }, + "id": 85, + "options": { + "code": { + "language": "plaintext", + "showLineNumbers": false, + "showMiniMap": false + }, + "content": "
$version
", + "mode": "markdown" + }, + "pluginVersion": "11.5.0", + "title": "Version", + "type": "text" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many datapoints are in storage", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 4, + "y": 1 + }, + "id": 26, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!~\"indexdb.*\"})", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Total datapoints", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the datapoints ingestion rate.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 9, + "y": 1 + }, + "id": 107, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Ingestion rate", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the rate of HTTP read requests.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 14, + "y": 1 + }, + "id": 108, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(rate(vm_http_requests_total{job=~\"$job\", instance=~\"$instance\", path!~\".*(/write|/metrics)\"}[$__rate_interval]))", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Read requests", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Total number of available CPUs for VM process", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 19, + "y": 1 + }, + "id": 77, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "exemplar": false, + "expr": "sum(vm_available_cpu_cores{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Available CPU", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "green", + "value": 1800 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 4, + "x": 0, + "y": 3 + }, + "id": 87, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "min(vm_app_uptime_seconds{job=~\"$job\", instance=~\"$instance\"})", + "instant": true, + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "title": "Uptime", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of [active time series](https://docs.victoriametrics.com/victoriametrics/faq/#what-is-an-active-time-series) with new data points inserted during the last hour. High value may result in ingestion slowdown.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 4, + "y": 3 + }, + "id": 38, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(vm_cache_entries{job=~\"$job\", instance=~\"$instance\", type=\"storage/hour_metric_ids\"})", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Active series", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Total amount of used disk space", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 9, + "y": 3 + }, + "id": 81, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Disk space usage", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Average disk usage per datapoint.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 14, + "y": 3 + }, + "id": 82, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "max(sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\"}) / sum(vm_rows{job=~\"$job\", instance=~\"$instance\"}))", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Bytes per point", + "type": "stat" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Total size of available memory for VM process", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 2, + "w": 5, + "x": 19, + "y": 3 + }, + "id": 78, + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "text": {}, + "textMode": "auto", + "wideLayout": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "uid": "$ds" + }, + "exemplar": false, + "expr": "sum(vm_available_memory_bytes{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "instant": true, + "interval": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Available memory", + "type": "stat" + }, + { + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 5 + }, + "id": 24, + "panels": [], + "title": "Overview", + "type": "row" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many datapoints are inserted into storage per second", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 6 + }, + "id": 106, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (type, instance) > 0", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints ingestion rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 6 + }, + "id": 12, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_http_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (path, instance) > 0", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{path}}", + "range": true, + "refId": "A" + } + ], + "title": "Requests rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of [active time series](https://docs.victoriametrics.com/victoriametrics/faq/#what-is-an-active-time-series) with new data points inserted during the last hour. High value may result in ingestion slowdown. \n\nSee following link for details:", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 14 + }, + "id": 51, + "links": [ + { + "targetBlank": true, + "title": "troubleshooting", + "url": "https://docs.victoriametrics.com/victoriametrics/troubleshooting/" + } + ], + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "vm_cache_entries{job=~\"$job\", instance=~\"$instance\", type=\"storage/hour_metric_ids\"}", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Active time series", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "The less time it takes is better.\n* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 14 + }, + "id": 22, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max(vm_request_duration_seconds{job=~\"$job\", instance=~\"$instance\", quantile=\"0.99\"}) by (instance, path) > 0", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{path}}", + "range": true, + "refId": "A" + } + ], + "title": "Query duration 0.99 quantile", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "* `*` - unsupported query path\n* `/write` - insert into VM\n* `/metrics` - query VM system metrics\n* `/query` - query instant values\n* `/query_range` - query over a range of time\n* `/series` - match a certain label set\n* `/label/{}/values` - query a list of label values (variables mostly)", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 35, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(rate(vm_http_request_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, path) > 0", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{path}}", + "range": true, + "refId": "A" + } + ], + "title": "Requests error rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the rate of logging the messages by their level. Unexpected spike in rate is a good reason to check logs.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 100, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 22 + }, + "id": 110, + "options": { + "legend": { + "calcs": ["lastNotNull", "mean", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_log_messages_total{job=~\"$job\", instance=~\"$instance\", level!=\"info\"}[$__rate_interval])) by (instance, level, location) > 0", + "interval": "5m", + "legendFormat": "{{instance}} - {{level}}: {{location}}", + "range": true, + "refId": "A" + } + ], + "title": "Logging rate", + "type": "timeseries" + }, + { + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 46, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How much resident memory (RAM) the process is actually using, compared to its allowed container or system limit.\n\n- Good: Below 70% most of the time, maybe spiking a bit under load.\n- Bad: Above 90% for more than 5 minutes = risk of out-of-memory (OOM) kill.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 95 + }, + "id": 112, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "max(\n max_over_time(process_resident_memory_bytes{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job\", instance=~\"$instance\"}\n) by(instance)", + "interval": "", + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "RSS memory % usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 95 + }, + "id": 114, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "max(\n rate(process_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n process_cpu_cores_available{job=~\"$job\", instance=~\"$instance\"}\n) by(instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "CPU % usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Share for memory allocated by the process itself. When memory usage reaches 100% it will be likely OOM-killed.\nSafe memory usage % considered to be below 80%", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 103 + }, + "id": 123, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "max(\n max_over_time(process_resident_memory_anon_bytes{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n vm_available_memory_bytes{job=~\"$job\", instance=~\"$instance\"}\n) by(instance)", + "interval": "", + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "RSS anonymous memory % usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "CPU cores used by instance", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Limit" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#F2495C", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 103 + }, + "id": 57, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "rate(process_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "min(process_cpu_cores_available{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "Limit", + "range": true, + "refId": "B" + } + ], + "title": "CPU", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 111 + }, + "id": 44, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(go_memstats_sys_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance) + sum(vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - requested from system", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(go_memstats_heap_inuse_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance) + sum(vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - heap inuse", + "range": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(go_memstats_stack_inuse_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - stack inuse", + "range": true, + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(process_resident_memory_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - resident", + "range": true, + "refId": "D" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(process_resident_memory_anon_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - resident anonymous", + "range": true, + "refId": "E" + } + ], + "title": "Memory usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "CPU pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html). Helps troubleshoot high CPU usage or throttling.\nLower is better.\n\n- waiting: The percentage of time at least one task in the process was ready to run (runnable) but couldn't get scheduled on the CPU.\n- stalled: The percentage of time all tasks in the process (except idle ones) were unable to get CPU time — a full CPU stall.\n\nIf there's a CPU burst, it's normal to see waiting or stalled > 1%. It only becomes a concern if it consistently climbs above 5–10% and aligns with latency spikes or GC slowdowns.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 111 + }, + "id": 134, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_pressure_cpu_waiting_seconds_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}} - waiting", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_pressure_cpu_stalled_seconds_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}} - stalled", + "range": true, + "refId": "B" + } + ], + "title": "CPU pressure", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows memory pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\nLower is better.\n\n- waiting: Time fraction where at least one thread was blocked on memory.\n- stalled: Time fraction where every thread was blocked on memory (severe pressure).\n\nIf queries slow down and both series spike, the host is likely limited by RAM or I/O throughput.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 119 + }, + "id": 135, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_pressure_memory_waiting_seconds_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}} - waiting", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_pressure_memory_stalled_seconds_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}} - stalled", + "range": true, + "refId": "B" + } + ], + "title": "Memory pressure", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of bytes read/write from the storage layer.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/.*read/" + }, + "properties": [ + { + "id": "custom.transform", + "value": "negative-Y" + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 119 + }, + "id": 76, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_io_storage_read_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - read", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_io_storage_written_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - write", + "range": true, + "refId": "B" + } + ], + "title": "Disk writes/reads", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 127 + }, + "id": 47, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(go_goroutines{job=~\"$job\", instance=~\"$instance\"}) by(instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Goroutines", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of read/write syscalls such as read, pread, write, pwrite.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/.*read.*/" + }, + "properties": [ + { + "id": "custom.transform", + "value": "negative-Y" + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 127 + }, + "id": 124, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_io_read_syscalls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - read calls", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_io_write_syscalls_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - write calls", + "range": true, + "refId": "B" + } + ], + "title": "Disk write/read calls", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 135 + }, + "id": 48, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(process_num_threads{job=~\"$job\", instance=~\"$instance\"}) by(instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Threads", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows IO pressure based on [Pressure Stall Information](https://docs.kernel.org/accounting/psi.html).\n\nThe lower the better.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 135 + }, + "id": 136, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_pressure_io_waiting_seconds_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}} - waiting", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(process_pressure_io_stalled_seconds_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}} - stalled", + "range": true, + "refId": "B" + } + ], + "title": "IO pressure", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 143 + }, + "id": 49, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_tcplistener_accepts_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "TCP connections rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 143 + }, + "id": 37, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_tcplistener_conns{job=~\"$job\", instance=~\"$instance\"}) by(instance)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "TCP connections", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the percentage of open file descriptors compared to the limit set in the OS.\nReaching the limit of open files can cause various issues and must be prevented.\n\nSee how to change limits here https://medium.com/@muhammadtriwibowo/set-permanently-ulimit-n-open-files-in-ubuntu-4d61064429a", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "max" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#C4162A", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 151 + }, + "id": 75, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max_over_time(process_open_fds{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n/\nprocess_max_fds{job=~\"$job\", instance=~\"$instance\"}", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Open FDs", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the percent of CPU spent on garbage collection.\n\nIf % is high, then CPU usage can be decreased by changing GOGC to higher values. Increasing GOGC value will increase memory usage, and decrease CPU usage.\n\nTry searching for keyword `GOGC` at https://docs.victoriametrics.com/victoriametrics/troubleshooting/ ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 151 + }, + "id": 125, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max(\n rate(go_gc_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) \n / rate(process_cpu_seconds_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n ) by(instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "CPU spent on GC", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows network usage by VM:\n* Writes show traffic sent to clients\n* Reads show traffic received from clients", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "decbits" + }, + "overrides": [ + { + "matcher": { + "id": "byRegexp", + "options": "/read.*/" + }, + "properties": [ + { + "id": "custom.transform", + "value": "negative-Y" + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 159 + }, + "id": 127, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_tcplistener_read_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(name) * 8 > 0", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "read via {{name}}", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_tcplistener_written_bytes_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(name) * 8 > 0", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "write via {{name}}", + "range": true, + "refId": "B" + } + ], + "title": "Network usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the rate of allocations in memory. Sudden increase in allocations would mean increased pressure on Go Garbage Collector and can saturate CPU resources of the application.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 159 + }, + "id": 133, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(go_memstats_alloc_bytes_total{job=~\"$job\"}[$__rate_interval])) by (job, instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Memory allocations rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the time goroutines have spent in runnable state before actually running. The lower is better.\n\nHigh values or values exceeding the threshold is usually a sign of insufficient CPU resources or CPU throttling. \n\nVerify that service has enough CPU resources. Otherwise, the service could work unreliably with delays in processing.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 0.1 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 167 + }, + "id": 128, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "histogram_quantile(0.99, sum(rate(go_sched_latencies_seconds_bucket{job=~\"$job\"}[$__rate_interval])) by (job, instance, le))", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Go scheduling latency", + "type": "timeseries" + } + ], + "title": "Resource usage", + "type": "row" + }, + { + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 71, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the rate and total number of new series created over last 24h.\n\nHigh [churn rate](https://docs.victoriametrics.com/victoriametrics/faq/#what-is-high-churn-rate) tightly connected with database performance and may result in unexpected OOM's or slow queries. It is recommended to always keep an eye on this metric to avoid unexpected [cardinality](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#cardinality) \"explosions\".\n\nThe higher churn rate is, the more resources required to handle it. Consider to keep the churn rate as low as possible.\n\nGood references to read:\n* https://www.robustperception.io/cardinality-is-key\n* https://www.robustperception.io/using-tsdb-analyze-to-investigate-churn-and-cardinality", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 593 + }, + "id": 66, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "interval": "", + "legendFormat": "{{instance}} - churn rate", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(increase(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[24h])) by (instance)", + "interval": "", + "legendFormat": "{{instance}} - new series over 24h", + "range": true, + "refId": "B" + } + ], + "title": "Churn rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "The percentage of [slow inserts](https://docs.victoriametrics.com/victoriametrics/faq/#what-is-a-slow-insert) compared to the total ingestion rate. \n\nThe lower the better. \n\nIn short, slow insert is a cache miss. There are following reasons for slow inserts to go up: \n* Ingestion of completely new, not seen before time series;\n* Not enough memory to maintain big enough caches for the current workload.\n\nIf percentage remains high (>10%) during extended periods of time, then it is likely more RAM is needed for optimal handling of the current number of [active time series](https://docs.victoriametrics.com/victoriametrics/faq/#what-is-an-active-time-series). \n\nSee [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3976#issuecomment-1476883183) for details.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line+area" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "transparent" + }, + { + "color": "red", + "value": 0.1 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 593 + }, + "id": 68, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max(\n rate(vm_slow_row_inserts_total{job=~\"$job\"}[$__rate_interval]) \n / rate(vm_rows_added_to_storage_total{job=~\"$job\"}[$__rate_interval])\n) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Slow inserts %", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Merge assist happens when storage can't keep up with merging parts. This is usually a sign of overload for storage.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "bars", + "fillOpacity": 100, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 601 + }, + "id": 116, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(increase(vm_assisted_merges_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance, type) > 0", + "format": "time_series", + "interval": "5m", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Assisted merges", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Slow queries rate according to `search.logSlowQueryDuration` flag, which is `5s` by default.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 601 + }, + "id": 60, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_slow_queries_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Slow queries rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the percentage of used cache size from the allowed size by type. \nValues close to 100% show the maximum potential utilization.\nValues close to 0% show that cache is underutilized.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 609 + }, + "id": 90, + "options": { + "legend": { + "calcs": ["lastNotNull", "mean", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "vm_cache_size_bytes{job=~\"$job\", instance=~\"$instance\"} / vm_cache_size_max_bytes{job=~\"$job\", instance=~\"$instance\"}", + "interval": "", + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Cache usage % by type", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows cache miss ratio. Lower is better.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percentunit" + }, + "overrides": [] + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 609 + }, + "id": 118, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "(\n rate(vm_cache_misses_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n /\n rate(vm_cache_requests_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])\n) > 0", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Cache miss ratio", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many samples were ignored or dropped on insertion due to various reasons:\n* timestamp out of retention period or timestamp in future;\n* invalid metric name;\n* exceeding limit for labels length or number;\n* dropped by [relabeling configuration](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#relabeling).", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 618 + }, + "id": 131, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": true, + "expr": "sum(increase(vm_rows_ignored_total{job=~\"$job\", instance=~\"$instance\"}[1h])) by (instance, reason)", + "hide": false, + "interval": "", + "legendFormat": "{{instance}} - {{reason}}", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(increase(vm_relabel_metrics_dropped_total{job=~\"$job\", instance=~\"$instance\"}[1h])) by(instance)", + "hide": false, + "instant": false, + "legendFormat": "{{instance}} - relabeling", + "range": true, + "refId": "B" + } + ], + "title": "Samples dropped for last 1h", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows rate of deduplicated samples during [deduplication](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) or [downsampling](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#downsampling), according to the configured `-dedup.minScrapeInterval` or `-downsampling.period`.\n\nShould be empty if `-dedup.minScrapeInterval` and `-downsampling.period` isn't set.\n\nDeduplication happens in two places:\n* `type=\"merge\"` - during [background merges](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#storage). Deduplication during merges is permanent.\n* `type=\"select\"` - during [read queries](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#query-data). Deduplication happens in-flight and has no permanent effect.\n\nThe more samples need to be deduplicated, the higher will be resource usage.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 618 + }, + "id": 132, + "links": [ + { + "targetBlank": true, + "title": "Readonly mode", + "url": "https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#readonly-mode" + } + ], + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": true, + "expr": "sum(rate(vm_deduplicated_samples_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance, type) > 0", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "__auto", + "range": true, + "refId": "A" + } + ], + "title": "Deduplication rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Flags explicitly set to non-default values", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "inspect": false + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Time" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Value" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "job" + }, + "properties": [ + { + "id": "custom.hidden", + "value": true + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 626 + }, + "id": 126, + "options": { + "cellHeight": "sm", + "footer": { + "countRows": false, + "fields": "", + "reducer": ["sum"], + "show": false + }, + "showHeader": true + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(flag{is_set=\"true\", job=~\"$job\", instance=~\"$instance\"}) by(job, instance, name, value)", + "format": "table", + "instant": true, + "legendFormat": "__auto", + "range": false, + "refId": "A" + } + ], + "title": "Non-default flags", + "type": "table" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the number of restarts per job. The chart can be useful to identify periodic process restarts and correlate them with potential issues or anomalies. Normally, processes shouldn't restart unless restart was inited by user. The reason of restarts should be figured out by checking the logs of each specific service. ", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "stepAfter", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 626 + }, + "id": 129, + "options": { + "legend": { + "calcs": ["lastNotNull"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(changes(vm_app_start_timestamp{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]) > 0) by(job)", + "format": "time_series", + "instant": false, + "legendFormat": "{{job}}", + "refId": "A" + } + ], + "title": "Restarts ($job)", + "type": "timeseries" + } + ], + "title": "Troubleshooting", + "type": "row" + }, + { + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 32 + }, + "id": 14, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows the approx time needed to reach 100% of disk capacity based on the following params:\n* free disk space (after -storage.minFreeDiskSpaceBytes);\n* row ingestion rate;\n* compression.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 163 + }, + "id": 73, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "min"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "(vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"}-vm_free_disk_space_limit_bytes{job=~\"$job\", instance=~\"$instance\"}) \n/ \nignoring(path) (\n (rate(vm_rows_added_to_storage_total{job=~\"$job\", instance=~\"$instance\"}[1d]) - \n sum(rate(vm_deduplicated_samples_total{job=~\"$job\", instance=~\"$instance\"}[1d])) without (type)) * \n (\n sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!~\"indexdb.*\"}) without(type) /\n sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!~\"indexdb.*\"}) without(type)\n )\n +\n rate(vm_new_timeseries_created_total{job=~\"$job\", instance=~\"$instance\"}[1d]) * \n (\n sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type=\"indexdb/file\"}) /\n sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type=\"indexdb/file\"})\n )\n) > 0", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Storage full ETA", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many datapoints are inserted into storage per second", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 185 + }, + "id": 10, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_rows_inserted_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, type) > 0", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints ingestion rate", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "How many data points are in RAM queue waiting to be written into storage. The number of pending data points should be in the range from 0 to `5*`, since VictoriaMetrics pushes pending data to persistent storage every 5 seconds. The index datapoints value in general is much lower", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "pending index entries" + }, + "properties": [ + { + "id": "unit", + "value": "none" + }, + { + "id": "decimals", + "value": 3 + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 185 + }, + "id": 34, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "vm_pending_rows{job=~\"$job\", instance=~\"$instance\", type=\"storage\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - pending datapoints", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "vm_pending_rows{job=~\"$job\", instance=~\"$instance\", type=\"indexdb\"}", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - pending index entries", + "range": true, + "refId": "B" + } + ], + "title": "Pending datapoints", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows amount of on-disk space occupied by data points and the remaining disk space at `-storageDataPath`. Calculation accounts for -storage.minFreeDiskSpaceBytes", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 193 + }, + "id": 53, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type!~\"indexdb.*\"}) by (instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - Used (datapoints)", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "expr": "vm_free_disk_space_bytes{job=~\"$job\", instance=~\"$instance\"} - vm_free_disk_space_limit_bytes{job=~\"$job\", instance=~\"$instance\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - Free", + "range": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\", type=~\"indexdb.*\"}) by (instance)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - Used (index)", + "range": true, + "refId": "C" + } + ], + "title": "Disk space usage - datapoints", + "type": "timeseries" + }, + { + "datasource": { + "uid": "$ds" + }, + "description": "The max number of data parts of LSM tree across all storage nodes in the last [partition](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#storage).\nIncrease in number of parts (the hard limit is 512) is an evidence of slow merge performance - check the resource utilization.\n* `indexdb` - inverted index\n* `storage/small` - recently added parts of data ingested into storage (hot data)\n* `storage/big` - small parts gradually merged into bigger parts (cold data)", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 193 + }, + "id": 36, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_parts{job=~\"$job\", instance=~\"$instance\", type=~\"indexdb.*\"}) by (instance, type)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max(vm_last_partition_parts{job=~\"$job\", instance=~\"$instance\"}) by(instance, type)", + "format": "time_series", + "hide": false, + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "B" + } + ], + "title": "LSM parts max by type", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many datapoints are in the storage and what is average disk usage per datapoint.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "bytes-per-datapoint" + }, + "properties": [ + { + "id": "unit", + "value": "bytes" + }, + { + "id": "decimals", + "value": 2 + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 201 + }, + "id": 30, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!~\"indexdb.*\"}) by (instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - total datapoints", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_data_size_bytes{job=~\"$job\", instance=~\"$instance\"}) by (instance)\n/ sum(vm_rows{job=~\"$job\", instance=~\"$instance\", type!~\"indexdb.*\"}) by (instance)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - bytes-per-datapoint", + "range": true, + "refId": "B" + } + ], + "title": "Datapoints", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "The number of on-going merges in storage nodes. It is expected to have high numbers for `storage/small` metric.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 201 + }, + "id": 62, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_active_merges{job=~\"$job\", instance=~\"$instance\"}) by(instance, type)", + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Active merges", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many rows were ignored on insertion due to corrupted or out of retention timestamps and how many series were ignored on insertion or during scrape due to too long label names, values and excessive labels count.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 209 + }, + "id": 58, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": false, + "expr": "sum(increase(vm_rows_ignored_total{job=~\"$job\", instance=~\"$instance\"}[1h])) by (instance, reason)", + "format": "time_series", + "hide": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - {{reason}}", + "range": true, + "refId": "A" + } + ], + "title": "Rows ignored for last 1h", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "The number of rows merged per second by storage nodes.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 209 + }, + "id": 64, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(rate(vm_rows_merged_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by(instance, type)", + "legendFormat": "{{instance}} - {{type}}", + "range": true, + "refId": "A" + } + ], + "title": "Merge speed", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows how many ongoing insertions (not API /write calls) on disk are taking place, where:\n* `max` - equal to number of CPUs;\n* `current` - current number of goroutines busy with inserting rows into underlying storage.\n\nEvery successful API /write call results into flush on disk. However, these two actions are separated and controlled via different concurrency limiters. The `max` on this panel can't be changed and always equal to number of CPUs. \n\nWhen `current` hits `max` constantly, it means storage is overloaded and requires more CPU.\n\n", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "max" + }, + "properties": [ + { + "id": "color", + "value": { + "fixedColor": "#C4162A", + "mode": "fixed" + } + } + ] + } + ] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 217 + }, + "id": 59, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "max_over_time(vm_concurrent_insert_capacity{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}} - max", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "sum(vm_concurrent_insert_current{job=~\"$job\", instance=~\"$instance\"}) by (instance)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}} - current", + "range": true, + "refId": "B" + } + ], + "title": "Concurrent flushes on disk", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per queried series.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 217 + }, + "id": 103, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "histogram_quantile(0.99, sum(rate(vm_rows_read_per_series_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints read per series", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of series read per query.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 225 + }, + "id": 99, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "histogram_quantile(0.99, sum(rate(vm_series_read_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Series read per query", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) scanner per query.\n\nThis number can exceed number of RowsReadPerQuery if `step` query arg passed to [/api/v1/query_range](https://prometheus.io/docs/prometheus/latest/querying/api/#range-queries) is smaller than the lookbehind window set in square brackets of [rollup function](https://docs.victoriametrics.com/victoriametrics/metricsql/#rollup-functions). For example, if `increase(some_metric[1h])` is executed with the `step=5m`, then the same [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) on a hour time range are scanned `1h/5m=12` times. See [this article](https://valyala.medium.com/how-to-optimize-promql-and-metricsql-queries-85a1b75bf986) for details.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 225 + }, + "id": 105, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "histogram_quantile(0.99, sum(rate(vm_rows_scanned_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints scanned per query", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "99th percentile of number of [data samples](https://docs.victoriametrics.com/victoriametrics/keyconcepts/#raw-samples) read per query.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 2, + "links": [], + "mappings": [], + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 233 + }, + "id": 122, + "options": { + "legend": { + "calcs": ["mean", "lastNotNull", "max"], + "displayMode": "table", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "expr": "histogram_quantile(0.99, sum(rate(vm_rows_read_per_query_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])) by (instance, vmrange))", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Datapoints read per query", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "description": "Shows number of existing [snapshots](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#how-to-work-with-snapshots).\n\nRecently made snapshots do not occupy disk space. But with time, as snapshots become older, they start to occupy more and more disk space.\n\nIt is recommended deleting old snapshots when they are no longer needed to free up disk space.", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 233 + }, + "id": 130, + "options": { + "legend": { + "calcs": [], + "displayMode": "list", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "multi", + "sort": "desc" + } + }, + "pluginVersion": "11.5.0", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "editorMode": "code", + "exemplar": true, + "expr": "vm_snapshots{job=~\"$job\", instance=~\"$instance\"}", + "interval": "", + "legendFormat": "{{instance}}", + "range": true, + "refId": "A" + } + ], + "title": "Number of snapshots", + "type": "timeseries" + } + ], + "title": "Storage", + "type": "row" + } + ], + "preload": false, + "refresh": "", + "schemaVersion": 40, + "tags": ["victoriametrics"], + "templating": { + "list": [ + { + "current": { + "text": "VictoriaMetrics", + "value": "P4169E866C3094E38" + }, + "includeAll": false, + "name": "ds", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "definition": "label_values(vm_app_version{version=~\"victoria-metrics-.*\"}, job)", + "includeAll": false, + "name": "job", + "options": [], + "query": { + "query": "label_values(vm_app_version{version=~\"victoria-metrics-.*\"}, job)", + "refId": "VictoriaMetrics-job-Variable-Query" + }, + "refresh": 1, + "regex": "", + "type": "query" + }, + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "definition": "label_values(vm_app_version{job=~\"$job\", instance=~\"$instance\"}, version)", + "hide": 2, + "includeAll": false, + "name": "version", + "options": [], + "query": { + "query": "label_values(vm_app_version{job=~\"$job\", instance=~\"$instance\"}, version)", + "refId": "VictoriaMetrics-version-Variable-Query" + }, + "refresh": 1, + "regex": "/.*-(?:tags|heads)-(.*)-(?:0|dirty)-.*/", + "sort": 2, + "type": "query" + }, + { + "allValue": ".*", + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "definition": "label_values(vm_app_version{job=~\"$job\"}, instance)", + "includeAll": true, + "multi": true, + "name": "instance", + "options": [], + "query": { + "query": "label_values(vm_app_version{job=~\"$job\"}, instance)", + "refId": "VictoriaMetrics-instance-Variable-Query" + }, + "refresh": 1, + "regex": "", + "type": "query" + }, + { + "baseFilters": [], + "datasource": { + "type": "prometheus", + "uid": "$ds" + }, + "filters": [], + "name": "adhoc", + "type": "adhoc" + } + ] + }, + "time": { + "from": "now-3h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": ["10s", "30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d"] + }, + "timezone": "", + "title": "VictoriaMetrics - single-node", + "uid": "wNf0q_kZk", + "version": 1, + "weekStart": "", + "gnetId": 10229 +} diff --git a/hosts/idols-aquamarine/monitoring/alert.nix b/hosts/idols-aquamarine/monitoring/alert.nix index 6da20c07..e5ac9f23 100644 --- a/hosts/idols-aquamarine/monitoring/alert.nix +++ b/hosts/idols-aquamarine/monitoring/alert.nix @@ -45,19 +45,28 @@ receiver = "telegram"; # group alerts by labels group_by = [ - "host" - "namespace" - "pod" "job" + # --- Alert labels --- + "alertname" + "alertgroup" + # --- kubernetes labels --- + "namespace" + "service" + # --- custom labels --- + "cluster" + "env" + "type" + "host" ]; group_wait = "5m"; group_interval = "5m"; repeat_interval = "4h"; } # { - # # Route critical alerts to email (most severe alerts) + # # Route only prod env's critical alerts to email (most severe alerts) # match = { # severity = "critical"; + # env = "prd"; # }; # receiver = "email"; # group_by = [ From c8182216aefa4b770ae437a84267a1db8f59fc42 Mon Sep 17 00:00:00 2001 From: Ryan Yin Date: Sun, 14 Sep 2025 10:13:13 +0800 Subject: [PATCH 3/4] fix: node_exporter - exclude docker/podman/kubelet mounts and /home/ryan bindmounts --- modules/nixos/base/monitoring.nix | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/modules/nixos/base/monitoring.nix b/modules/nixos/base/monitoring.nix index ee791ced..0d9aee69 100644 --- a/modules/nixos/base/monitoring.nix +++ b/modules/nixos/base/monitoring.nix @@ -14,5 +14,18 @@ # use either enabledCollectors or disabledCollectors # disabledCollectors = []; + + extraFlags = [ + # Exclude pseudo/ephemeral FS: + # - /proc, /sys: kernel pseudo-FS, always size 0 + # - /dev: tmpfs/devices, not meaningful for disk usage + # Exclude container/runtime mounts: + # - /var/lib/docker/, /var/lib/containers/ and /var/lib/kubelet/ → too much overlay/tmpfs mounts, + # often EACCES (strict perms, namespaces) → false alerts + # Exclude user bind mounts: + # - /home/ryan/.+ → bind-mounted from /persistent (NixOS tmpfs-root setup), + # monitoring /persistent is sufficient + "--collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/containers/.+|var/lib/kubelet/.+|home/ryan/.+)($|/)" + ]; }; } From 7a82b8085a08f725b0c1dabd32dbd64aeb8eb8cb Mon Sep 17 00:00:00 2001 From: Ryan Yin Date: Sun, 14 Sep 2025 10:40:12 +0800 Subject: [PATCH 4/4] fix: alert - add coredns, comment out some useless alert rules --- .gitignore | 1 + .../alert_rules/coredns-exporter.yml | 13 ++++++ .../monitoring/alert_rules/node-exporter.yml | 24 +++++------ .../alert_rules/postgres-exporter.yml | 42 +++++++++---------- 4 files changed, 47 insertions(+), 33 deletions(-) create mode 100644 hosts/idols-aquamarine/monitoring/alert_rules/coredns-exporter.yml diff --git a/.gitignore b/.gitignore index 5e9d423d..dc6ba733 100644 --- a/.gitignore +++ b/.gitignore @@ -8,3 +8,4 @@ logs/ core* !core/ !core.nix +!coredns* diff --git a/hosts/idols-aquamarine/monitoring/alert_rules/coredns-exporter.yml b/hosts/idols-aquamarine/monitoring/alert_rules/coredns-exporter.yml new file mode 100644 index 00000000..0ca8b86d --- /dev/null +++ b/hosts/idols-aquamarine/monitoring/alert_rules/coredns-exporter.yml @@ -0,0 +1,13 @@ +groups: + - name: CoreDNS Exporter + + rules: + - alert: CorednsPanicCount + expr: "increase(coredns_panics_total[1m]) > 0" + for: 0m + labels: + severity: critical + annotations: + summary: CoreDNS Panic Count (instance {{ $labels.instance }}) + description: + "Number of CoreDNS panics encountered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" diff --git a/hosts/idols-aquamarine/monitoring/alert_rules/node-exporter.yml b/hosts/idols-aquamarine/monitoring/alert_rules/node-exporter.yml index 8ea26f8c..b28f4f4b 100644 --- a/hosts/idols-aquamarine/monitoring/alert_rules/node-exporter.yml +++ b/hosts/idols-aquamarine/monitoring/alert_rules/node-exporter.yml @@ -203,18 +203,18 @@ groups: summary: Host high CPU load (instance {{ $labels.instance }}) description: "CPU load is > 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: HostCpuIsUnderutilized - expr: - '(100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) - group_left (nodename) node_uname_info{nodename=~".+"}' - for: 1w - labels: - severity: info - annotations: - summary: Host CPU is underutilized (instance {{ $labels.instance }}) - description: - "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ - $value }}\n LABELS = {{ $labels }}" + # - alert: HostCpuIsUnderutilized + # expr: + # '(100 - (rate(node_cpu_seconds_total{mode="idle"}[30m]) * 100) < 20) * on(instance) + # group_left (nodename) node_uname_info{nodename=~".+"}' + # for: 1w + # labels: + # severity: info + # annotations: + # summary: Host CPU is underutilized (instance {{ $labels.instance }}) + # description: + # "CPU load is < 20% for 1 week. Consider reducing the number of CPUs.\n VALUE = {{ + # $value }}\n LABELS = {{ $labels }}" - alert: HostCpuStealNoisyNeighbor expr: diff --git a/hosts/idols-aquamarine/monitoring/alert_rules/postgres-exporter.yml b/hosts/idols-aquamarine/monitoring/alert_rules/postgres-exporter.yml index 75d86a6b..9ea6ef5a 100644 --- a/hosts/idols-aquamarine/monitoring/alert_rules/postgres-exporter.yml +++ b/hosts/idols-aquamarine/monitoring/alert_rules/postgres-exporter.yml @@ -73,16 +73,16 @@ groups: "PostgreSQL instance has too many connections (> 80%).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: PostgresqlNotEnoughConnections - expr: 'sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5' - for: 2m - labels: - severity: critical - annotations: - summary: Postgresql not enough connections (instance {{ $labels.instance }}) - description: - "PostgreSQL instance should have more connections (> 5)\n VALUE = {{ $value - }}\n LABELS = {{ $labels }}" + # - alert: PostgresqlNotEnoughConnections + # expr: 'sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5' + # for: 2m + # labels: + # severity: critical + # annotations: + # summary: Postgresql not enough connections (instance {{ $labels.instance }}) + # description: + # "PostgreSQL instance should have more connections (> 5)\n VALUE = {{ $value + # }}\n LABELS = {{ $labels }}" - alert: PostgresqlDeadLocks expr: 'increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5' @@ -109,17 +109,17 @@ groups: "Ratio of transactions being aborted compared to committed is > 2 %\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: PostgresqlCommitRateLow - expr: - 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[5m]) < 5' - for: 2m - labels: - severity: critical - annotations: - summary: Postgresql commit rate low (instance {{ $labels.instance }}) - description: - "Postgresql seems to be processing very few transactions\n VALUE = {{ $value - }}\n LABELS = {{ $labels }}" + # - alert: PostgresqlCommitRateLow + # expr: + # 'increase(pg_stat_database_xact_commit{datname!~"template.*|postgres",datid!="0"}[5m]) < 5' + # for: 2m + # labels: + # severity: critical + # annotations: + # summary: Postgresql commit rate low (instance {{ $labels.instance }}) + # description: + # "Postgresql seems to be processing very few transactions\n VALUE = {{ $value + # }}\n LABELS = {{ $labels }}" - alert: PostgresqlLowXidConsumption expr: "rate(pg_txid_current[1m]) < 5"