Merge branch 'master' into ana/add-alert-for-gcpce-cpu

.github/workflows/lint-mixins.yml

@@ -0,0 +1,82 @@
+---
+name: Mixin
+
+permissions:
+  contents: read
+
+on:
+  # To conserve resources we only run tests against main in PRs
+  pull_request:
+    branches:
+      - master
+
+jobs:
+  check-for-changed-mixins:
+    name: Check for changes
+    runs-on: ubuntu-latest
+    outputs:
+      changed-mixins: ${{ steps.changed-mixins.outputs.all_changed_files }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: 1.18
+
+      - name: Install CI dependencies
+        run: make install-ci-deps
+
+      - name: Get changed mixins
+        id: changed-mixins
+        uses: tj-actions/changed-files@v44
+        with:
+          dir_names: true
+          dir_names_exclude_current_dir: true
+          dir_names_max_depth: 1
+          files: | 
+            **-mixin/
+            **-observ-lib/
+          matrix: true
+
+      - name: List all changed mixins
+        run: echo '${{ steps.changed-mixins.outputs.all_changed_files }}'
+
+  lint-mixin:
+    name: Run Mixtool
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      contents: write
+      pull-requests: write
+      repository-projects: write
+    timeout-minutes: 15
+    needs: [check-for-changed-mixins]
+    strategy:
+      matrix:
+        mixin: ${{ fromJSON(needs.check-for-changed-mixins.outputs.changed-mixins) }}
+      fail-fast: false
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: 1.18
+
+      - name: Install CI dependencies
+        run: make install-ci-deps
+
+      - name: Install Mixin dependencies
+        working-directory: ./${{ matrix.mixin }}
+        run: jb install
+
+      - name: Lint Mixin
+        working-directory: ./${{ matrix.mixin }}
+        run: mixtool lint mixin.libsonnet

cilium-enterprise-mixin/alerts/ciliumAlerts.libsonnet

@@ -272,6 +272,76 @@
           },
         ],
       },
+      {
+        name: 'Cilium Clustermesh',
+        rules: [
+          {
+            alert: 'CiliumAgentRemoteClusterNotReady',
+            expr: 'count(cilium_clustermesh_remote_cluster_readiness_status < 1) by (%s) > 0' % std.join(', ', (['source_cluster', 'target_cluster'] + $._config.alertAggregationLabels)),
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: "Agent can't mesh with remote cluster.",
+              description: "Agent can't mesh with {{$labels.target_cluster}}",
+            },
+            'for': '5m',
+          },
+          {
+            alert: 'CiliumAgentRemoteClusterFailing',
+            expr: 'sum(rate(cilium_clustermesh_remote_cluster_failures[5m])) by (%s) > 0' % std.join(', ', (['source_cluster', 'target_cluster'] + $._config.alertAggregationLabels)),
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: 'Agent fails to mesh with remote cluster.',
+              description: 'Agent fails to mesh with {{$labels.target_cluster}}',
+            },
+            'for': '5m',
+          },
+        ],
+      },
+      {
+        name: 'Cilium Kvstoremesh',
+        rules: [
+          {
+            alert: 'CiliumKvstoremeshRemoteClusterNotReady',
+            expr: 'count(cilium_kvstoremesh_remote_cluster_readiness_status < 1) by (%s) > 0' % std.join(', ', (['source_cluster', 'target_cluster'] + $._config.alertAggregationLabels)),
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: "Kvstoremesh can't mesh with remote cluster.",
+              description: "Kvstoremesh can't mesh with {{$labels.target_cluster}}",
+            },
+            'for': '5m',
+          },
+          {
+            alert: 'CiliumKvstoremeshRemoteClusterFailing',
+            expr: 'sum(rate(cilium_kvstoremesh_remote_cluster_failures[5m])) by (%s) > 0' % std.join(', ', (['source_cluster', 'target_cluster'] + $._config.alertAggregationLabels)),
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: 'Kvstoremesh fails to mesh with remote cluster.',
+              description: 'Kvstoremesh fails to mesh with {{$labels.target_cluster}}',
+            },
+            'for': '5m',
+          },
+          {
+            alert: 'CiliumKvstoremeshErrors',
+            expr: 'sum(rate(cilium_kvstoremesh_kvstore_sync_errors_total[5m])) by (%s) > 0' % std.join(', ', (['source_cluster'] + $._config.alertAggregationLabels)),
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: 'Kvstoremesh fails to mesh with remote cluster.',
+              description: 'Kvstoremesh fails to mesh with {{$labels.target_cluster}}',
+            },
+            'for': '5m',
+          },
+        ],
+      },
     ],
   },
 }

cilium-enterprise-mixin/jsonnetfile.json

@@ -0,0 +1,6 @@
+{
+  "version": 1,
+  "dependencies": [],
+  "legacyImports": false
+}
+

common-lib/common/panels/cpu/stat/count.libsonnet

@@ -16,6 +16,7 @@ base {
 
   stylize(allLayers=true):
     (if allLayers then super.stylize() else {})
-    + generic.info.stylize(allLayers=false),
+    + generic.info.stylize(allLayers=false)
+    + g.panel.stat.standardOptions.withUnit('none'),
 
 }

common-lib/common/panels/disk/table/usage.libsonnet

@@ -245,7 +245,13 @@ base {
       fieldOverride.byName.new('Available')
       + fieldOverride.byName.withProperty('custom.width', '80'),
       fieldOverride.byName.new('Used, %')
-      + fieldOverride.byName.withProperty('custom.displayMode', 'basic')
+      + fieldOverride.byName.withProperty(
+        'custom.cellOptions', {
+          type: 'gauge',
+          mode: 'basic',
+          valueDisplayMode: 'text',
+        }
+      )
       + fieldOverride.byName.withPropertiesFromOptions(
         table.standardOptions.withMax(1)
         + table.standardOptions.withMin(0)

common-lib/common/variables/variables.libsonnet

@@ -59,14 +59,21 @@ local utils = import '../utils.libsonnet';
          [root.datasources.prometheus]
          + variablesFromLabels(groupLabels, instanceLabels, filteringSelector, multiInstance=false),
        queriesSelectorAdvancedSyntax:
-         '%s' % [
-           utils.labelsToPromQLSelectorAdvanced(groupLabels + instanceLabels),
-         ],
+         std.join(
+           ',',
+           std.filter(function(x) std.length(x) > 0, [
+             filteringSelector,
+             utils.labelsToPromQLSelectorAdvanced(groupLabels + instanceLabels),
+           ])
+         ),
        queriesSelector:
-         '%s,%s' % [
-           filteringSelector,
-           utils.labelsToPromQLSelector(groupLabels + instanceLabels),
-         ],
+         std.join(
+           ',',
+           std.filter(function(x) std.length(x) > 0, [
+             filteringSelector,
+             utils.labelsToPromQLSelector(groupLabels + instanceLabels),
+           ])
+         ),
 
      }
      + if enableLokiLogs then self.withLokiLogs() else {},

logs-lib/jsonnetfile.json

@@ -5,7 +5,7 @@
       "source": {
         "git": {
           "remote": "https://github.com/grafana/grafonnet.git",
-          "subdir": "gen/grafonnet-v10.0.0"
+          "subdir": "gen/grafonnet-v11.0.0"
         }
       },
       "version": "main"

logs-lib/logs/dashboards.libsonnet

@@ -13,18 +13,20 @@ function(
       + g.dashboard.withUid(g.util.string.slugify(title))
       + g.dashboard.withVariables(variables.toArray)
       + g.dashboard.withPanels(
-        (
-          if showLogsVolume then
-            [panels.logsVolume
-             + g.panel.timeSeries.gridPos.withH(6)
-             + g.panel.timeSeries.gridPos.withW(24)]
-          else []
+        g.util.grid.wrapPanels(
+          (
+            if showLogsVolume then
+              [panels.logsVolume
+               + g.panel.timeSeries.gridPos.withH(6)
+               + g.panel.timeSeries.gridPos.withW(24)]
+            else []
+          )
+          +
+          [
+            panels.logs
+            + g.panel.logs.gridPos.withH(18)
+            + g.panel.logs.gridPos.withW(24),
+          ]
         )
-        +
-        [
-          panels.logs
-          + g.panel.logs.gridPos.withH(18)
-          + g.panel.logs.gridPos.withW(24),
-        ]
       ),
   }

logs-lib/logs/g.libsonnet

@@ -1 +1 @@
-import 'github.com/grafana/grafonnet/gen/grafonnet-v10.0.0/main.libsonnet'
+import 'github.com/grafana/grafonnet/gen/grafonnet-v11.0.0/main.libsonnet'

nginx-mixin/.lint

@@ -5,3 +5,9 @@ exclusions:
     reason: "Units are undefined where panel description is clear, and the entity being graphed is not available in default set of available units."
   template-datasource-rule:
     reason: "mixtool upgrade made this rule stricter. TODO: Fix errors and remove the warning exclusion"
+  template-job-rule:
+    reason: "NGINX Overview dashboard does not use a job label"
+  target-job-rule:
+    reason: "NGINX Overview dashboard does not use a job label"
+  target-rate-interval-rule:
+    reason: "using $__rate_interval breaks the dashboard hence using [5m] instead"

nginx-mixin/README.md

@@ -1,18 +1,16 @@
 # Nginx Mixin
 
-This mixin is a thin veneer over the dashboard designed and published by [Ward Bekker](https://grafana.com/orgs/wardbekker1) in the [Grafana dashboards library](https://grafana.com/grafana/dashboards/12559).
+This mixin is a thin veneer over the dashboard designed and published by [Ward Bekker](https://grafana.com/orgs/wardbekker1) in the [Grafana dashboards library](https://grafana.com/grafana/dashboards/12559) and the metrics dashboard is collected from the [official NGINX exporter repository](https://github.com/nginxinc/nginx-prometheus-exporter/blob/main/grafana/dashboard.png).
 
 Specifically this mixin adds a configurable `cluster` variable to the dashboard in order to support it's use in one or many kubernetes clusters.
 
 The mixin uses revision 14 of the dashboard currently. Change `DASHBOARD_REV` in the Makefile to fetch a different revision of the dashboard.
 
-The Nginx mixin contains the following dashboard:
+The Nginx mixin contains the following dashboards:
 
-- Nginx...
+- **Nginx Overview**: This dashboard provides a comprehensive view of various NGINX metrics, allowing you to monitor performance and health across multiple dimensions.
 
-# Nginx overview
-
-...
+- **Nginx Logs**: This dashboard showcases panels powered by Logs, providing insights into log data to help diagnose issues and track the operational status of your NGINX deployments.
 
 ## Install tools
 

nginx-mixin/dashboards/nginx-overview.json → nginx-mixin/dashboards/nginx-logs.json

@@ -2190,8 +2190,8 @@
     ]
   },
   "timezone": "",
-  "title": "Nginx access logs",
+  "title": "NGINX Logs",
   "uid": "T512JVH7z",
   "version": 4,
   "weekStart": ""
-}
+}