Merge branch 'master' into system-slice-metrics

Author: bboreham

.github/workflows/build.yml

@@ -19,12 +19,12 @@ jobs:
       cache-hit: ${{ steps.tools-cache.outputs.cache-hit }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
           persist-credentials: false
       - name: Setup Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6
         with:
           go-version: 1.23
       - name: Tools cache
@@ -45,12 +45,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
           persist-credentials: false
       - name: Setup Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6
         with:
           go-version: 1.23
       - name: Restore Tools cache
@@ -69,12 +69,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
           persist-credentials: false
       - name: Setup Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6
         with:
           go-version: 1.23
       - name: Restore Tools cache

.github/workflows/test-mixins.yml

@@ -18,12 +18,12 @@ jobs:
       cache-hit: ${{ steps.tools-cache.outputs.cache-hit }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
           persist-credentials: false
       - name: Setup Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6
         with:
           go-version: 1.23
       - name: Tools cache
@@ -46,13 +46,13 @@ jobs:
       changed-mixins: ${{ steps.changed-mixins.outputs.all_changed_files }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
           persist-credentials: false
       - name: Get changed mixins
         id: changed-mixins
-        uses: step-security/changed-files@3dbe17c78367e7d60f00d78ae6781a35be47b4a1 # v45.0.1
+        uses: step-security/changed-files@95b56dadb92a30ca9036f16423fd3c088a71ee94 # v46.0.5
         with:
           dir_names: true
           dir_names_exclude_current_dir: true
@@ -82,7 +82,7 @@ jobs:
       fail-fast: false
     services:
       grafana:
-        image: grafana/grafana:11.4.0
+        image: grafana/grafana:12.2.1@sha256:35c41e0fd0295f5d0ee5db7e780cf33506abfaf47686196f825364889dee878b
         ports:
           - 3000:3000
         env:
@@ -91,12 +91,12 @@ jobs:
           GF_AUTH_ANONYMOUS_ORG_ROLE: "Admin"
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
         with:
           fetch-depth: 0
           persist-credentials: false
       - name: Setup Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6
         with:
           go-version: 1.23
       - name: Restore Tools cache

Makefile

@@ -87,4 +87,5 @@ update-mixins:
 
 tests:
 	pushd . && cd ./common-lib && make vendor && make tests
+	pushd . && cd ./grafana-builder/test && make tests
 	pushd . && cd ./mixin-utils/test && make tests

README.md

@@ -41,11 +41,6 @@ The monitoring mixins in this repository use two linting tools to ensure quality
 
 Observability library is a flexible format to describe dashboards and alerts in a modular way so libraries can be imported into one another or into monitoring-mixins. Observability libraries can be found in folders with `-observ-lib` suffix. [Common library](https://github.com/grafana/jsonnet-libs/tree/master/common-lib) is also used to apply consistent style options.
 
-See [helloworld-observ-lib](helloworld-observ-lib/) for starter template and format description.
-
-More examples:
- - [windows-observ-lib](windows-observ-lib/)
-
  ### Observability libraries signal extention
 
  [Signal](https://github.com/grafana/jsonnet-libs/tree/master/common-lib/common/signal#signal) is the experimental extension to observability libraries format to declare metrics (signals) and then render them as different grafana panel types (timeseries, stat, table, etc), or alert rules.
@@ -58,6 +53,7 @@ Examples:
  - [process-observ-lib](process-observ-lib/)
  - [golang-observ-lib](golang-observ-lib/)
  - [csp-mixin](csp-mixin/)
+ - [windows-observ-lib](windows-observ-lib/)
 
  ## Prometheus rules testing for monitoring mixins and observability libraries
 

aerospike-mixin/alerts/alerts.libsonnet renamed to aerospike-mixin/alerts.libsonnet

@@ -1,14 +1,14 @@
 {
-  prometheusAlerts+:: {
-    groups+: [
+  new(this): {
+    groups: [
       {
-        name: 'aerospike',
+        name: 'aerospike.rules',
         rules: [
           {
             alert: 'AerospikeNodeHighMemoryUsage',
             expr: |||
               100 - sum without (service) (aerospike_node_stats_system_free_mem_pct) >= %(alertsCriticalNodeHighMemoryUsage)s
-            ||| % $._config,
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'critical',
@@ -19,14 +19,14 @@
                 (
                   '{{ printf "%%.0f" $value }} percent of system memory used on node {{$labels.instance}} on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsCriticalNodeHighMemoryUsage)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeNamespaceHighDiskUsage',
             expr: |||
               100 - sum without (service) (aerospike_namespace_device_free_pct) >= %(alertsCriticalNamespaceHighDiskUsage)s
-            ||| % $._config,
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'critical',
@@ -37,14 +37,14 @@
                 (
                   '{{ printf "%%.0f" $value }} percent of disk space available for namespace {{$labels.ns}} on node {{$labels.instance}}, on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsCriticalNamespaceHighDiskUsage)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeUnavailablePartitions',
             expr: |||
               sum without(service) (aerospike_namespace_unavailable_partitions) > %(alertsCriticalUnavailablePartitions)s
-            ||| % $._config,
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'critical',
@@ -55,14 +55,14 @@
                 (
                   '{{ printf "%%.0f" $value }} unavailable partition(s) in namespace {{$labels.ns}}, on node {{$labels.instance}}, on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsCriticalUnavailablePartitions)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeDeadPartitions',
             expr: |||
               sum without(service) (aerospike_namespace_dead_partitions) > %(alertsCriticalDeadPartitions)s
-            ||| % $._config,
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'critical',
@@ -73,14 +73,14 @@
                 (
                   '{{ printf "%%.0f" $value }} dead partition(s) in namespace {{$labels.ns}}, on node {{$labels.instance}}, on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsCriticalDeadPartitions)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeNamespaceRejectingWrites',
             expr: |||
               sum without(service) (aerospike_namespace_stop_writes + aerospike_namespace_clock_skew_stop_writes) > %(alertsCriticalSystemRejectingWrites)s
-            ||| % $._config,
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'critical',
@@ -90,14 +90,14 @@
               description:
                 (
                   'Namespace {{$labels.ns}} on node {{$labels.instance}} on cluster {{$labels.aerospike_cluster}} is currently rejecting all client-originated writes.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeHighClientReadErrorRate',
             expr: |||
-              sum without(service) (rate(aerospike_namespace_client_read_error[5m])) / (clamp_min(sum without(service) (rate(aerospike_namespace_client_read_error[5m])) + sum without(service) (rate(aerospike_namespace_client_read_success[5m])), 1)) > %(alertsWarningHighClientReadErrorRate)s
-            ||| % $._config,
+              sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_read_error[5m])) / (clamp_min(sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_read_error[5m])) + sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_read_success[5m])), 1)) > %(alertsWarningHighClientReadErrorRate)s
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'warning',
@@ -108,14 +108,14 @@
                 (
                   '{{ printf "%%.0f" $value }} percent of client read transactions are resulting in errors for namespace {{$labels.ns}}, on node {{$labels.instance}}, on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsWarningHighClientReadErrorRate)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeHighClientWriteErrorRate',
             expr: |||
-              sum without(service) (rate(aerospike_namespace_client_write_error[5m])) / (clamp_min(sum without(service) (rate(aerospike_namespace_client_write_error[5m])) + sum without(service) (rate(aerospike_namespace_client_write_success[5m])), 1)) > %(alertsWarningHighClientWriteErrorRate)s
-            ||| % $._config,
+              sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_write_error[5m])) / (clamp_min(sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_write_error[5m])) + sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_write_success[5m])), 1)) > %(alertsWarningHighClientWriteErrorRate)s
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'warning',
@@ -126,14 +126,14 @@
                 (
                   '{{ printf "%%.0f" $value }} percent of client write transactions are resulting in errors for namespace {{$labels.ns}}, on node {{$labels.instance}}, on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsWarningHighClientWriteErrorRate)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
           {
             alert: 'AerospikeHighClientUDFErrorRate',
             expr: |||
-              sum without(service) (rate(aerospike_namespace_client_udf_error[5m])) / (clamp_min(sum without(service) (rate(aerospike_namespace_client_udf_error[5m])) + sum without(service) (rate(aerospike_namespace_client_udf_complete[5m])), 1)) > %(alertsWarningHighClientUDFErrorRate)s
-            ||| % $._config,
+              sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_udf_error[5m])) / (clamp_min(sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_udf_error[5m])) + sum by(instance, aerospike_cluster, ns) (rate(aerospike_namespace_client_udf_complete[5m])), 1)) > %(alertsWarningHighClientUDFErrorRate)s
+            ||| % this.config,
             'for': '5m',
             labels: {
               severity: 'warning',
@@ -144,7 +144,7 @@
                 (
                   '{{ printf "%%.0f" $value }} percent of client UDF transactions are resulting in errors for namespace {{$labels.ns}}, on node {{$labels.instance}}, on cluster {{$labels.aerospike_cluster}}, ' +
                   'which is above the threshold of %(alertsWarningHighClientUDFErrorRate)s.'
-                ) % $._config,
+                ) % this.config,
             },
           },
         ],

aerospike-mixin/config.libsonnet

@@ -1,25 +1,41 @@
 {
-  _config+:: {
-    enableMultiCluster: false,
-    aerospikeSelector: if self.enableMultiCluster then 'job=~"$job", cluster=~"$cluster"' else 'job=~"$job"',
-    multiclusterSelector: 'job=~"$job"',
-    filterSelector: 'job=~"integrations/aerospike"',
+  local this = self,
+  filteringSelector: 'job="integrations/aerospike"',
+  groupLabels: ['job', 'aerospike_cluster', 'cluster'],
+  logLabels: ['job', 'cluster', 'instance'],
+  instanceLabels: ['instance', 'ns'],  // ns == namespace
 
-    dashboardTags: ['aerospike-mixin'],
-    dashboardPeriod: 'now-30m',
-    dashboardTimezone: 'default',
-    dashboardRefresh: '1m',
+  dashboardTags: [self.uid],
+  uid: 'aerospike',
+  dashboardNamePrefix: 'Aerospike',
+  dashboardPeriod: 'now-30m',
+  dashboardTimezone: 'default',
+  dashboardRefresh: '1m',
+  metricsSource: [
+    'prometheusAerospike7',  // For queries that are required for Aerospike 7.0+ with metric changes
+    'prometheus',  // For Aerospike < 7.0
+  ],
 
-    // alerts thresholds
-    alertsCriticalNodeHighMemoryUsage: 80,  // %
-    alertsCriticalNamespaceHighDiskUsage: 80,  // %
-    alertsCriticalUnavailablePartitions: 0,  // count
-    alertsCriticalDeadPartitions: 0,  // count
-    alertsCriticalSystemRejectingWrites: 0,  // count
-    alertsWarningHighClientReadErrorRate: 25,  // %
-    alertsWarningHighClientWriteErrorRate: 25,  // %
-    alertsWarningHighClientUDFErrorRate: 25,  // %
+  // Logging configuration
+  enableLokiLogs: true,
+  extraLogLabels: ['level'],  // Required by logs-lib
+  logsVolumeGroupBy: 'level',
+  showLogsVolume: true,
 
-    enableLokiLogs: true,
+  // Alerts thresholds
+  alertsCriticalNodeHighMemoryUsage: 80,  // %
+  alertsCriticalNamespaceHighDiskUsage: 80,  // %
+  alertsCriticalUnavailablePartitions: 0,  // count
+  alertsCriticalDeadPartitions: 0,  // count
+  alertsCriticalSystemRejectingWrites: 0,  // count
+  alertsWarningHighClientReadErrorRate: 25,  // %
+  alertsWarningHighClientWriteErrorRate: 25,  // %
+  alertsWarningHighClientUDFErrorRate: 25,  // %
+
+  // Signals configuration
+  signals+: {
+    overview: (import './signals/overview.libsonnet')(this),
+    namespace: (import './signals/namespace.libsonnet')(this),
+    instance: (import './signals/instance.libsonnet')(this),
   },
 }