chore: Modernize ibm-mq-mixin

.gitignore

@@ -2,3 +2,4 @@
 vendor
 jsonnetfile.lock.json
 *.zip
+.worktrees

ibm-mq-mixin/.lint

@@ -20,6 +20,8 @@ exclusions:
       - panel: "Queue operations"
       - panel: "Operations"
       - panel: "Depth"
+  panel-datasource-rule:
+    reason: "Panels using signal-based targets with multiple queries may show '-- Mixed --' datasource, which is expected for panels with multi-datasource support"
   template-datasource-rule:
     reason: "Based on new convention we are using variable names prometheus_datasource and loki_datasource where as linter expects 'datasource'"
   template-instance-rule:

ibm-mq-mixin/alerts.libsonnet

@@ -0,0 +1,79 @@
+{
+  new(this): {
+    groups: [
+      {
+        name: this.config.uid + '-alerts',
+        rules: [
+          {
+            alert: 'IBMMQExpiredMessages',
+            expr: |||
+              sum without (description,hostname,instance,job,platform) (ibmmq_qmgr_expired_message_count) > %(alertsExpiredMessages)s
+            ||| % this.config,
+            'for': '5m',
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: 'There are expired messages, which imply that application resilience is failing.',
+              description:
+                (
+                  'The number of expired messages in the {{$labels.qmgr}} is {{$value}} which is above the threshold of %(alertsExpiredMessages)s.'
+                ) % this.config,
+            },
+          },
+          {
+            alert: 'IBMMQStaleMessages',
+            expr: |||
+              sum without (description,instance,job,platform) (ibmmq_queue_oldest_message_age) >= %(alertsStaleMessagesSeconds)s
+            ||| % this.config,
+            'for': '5m',
+            labels: {
+              severity: 'warning',
+            },
+            annotations: {
+              summary: 'Stale messages have been detected.',
+              description:
+                (
+                  'A stale message with an age of {{$value}} has been sitting in the {{$labels.queue}} which is above the threshold of %(alertsStaleMessagesSeconds)s seconds.'
+                ) % this.config,
+            },
+          },
+          {
+            alert: 'IBMMQLowDiskSpace',
+            expr: |||
+              sum without (description,hostname,instance,job,platform) (ibmmq_qmgr_queue_manager_file_system_free_space_percentage) <= %(alertsLowDiskSpace)s
+            ||| % this.config,
+            'for': '5m',
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: 'There is limited disk available for a queue manager.',
+              description:
+                (
+                  'The amount of disk space available for {{$labels.qmgr}} is at {{$value}}%% which is below the threshold of %(alertsLowDiskSpace)s%%.'
+                ) % this.config,
+            },
+          },
+          {
+            alert: 'IBMMQHighQMgrCpuUsage',
+            expr: |||
+              sum without (description,hostname,instance,job,platform) (ibmmq_qmgr_user_cpu_time_estimate_for_queue_manager_percentage) >= %(alertsHighQueueManagerCpuUsage)s
+            ||| % this.config,
+            'for': '5m',
+            labels: {
+              severity: 'critical',
+            },
+            annotations: {
+              summary: 'There is a high CPU usage estimate for a queue manager.',
+              description:
+                (
+                  'The amount of CPU usage for the queue manager {{$labels.qmgr}} is at {{$value}}%% which is above the threshold of %(alertsHighQueueManagerCpuUsage)s%%.'
+                ) % this.config,
+            },
+          },
+        ],
+      },
+    ],
+  },
+}

ibm-mq-mixin/config.libsonnet

@@ -1,20 +1,46 @@
 {
-  _config+:: {
-    enableMultiCluster: false,
-    ibmmqSelector: if self.enableMultiCluster then 'job=~"$job", cluster=~"$cluster"' else 'job=~"$job"',
-    dashboardTags: ['ibm-mq-mixin'],
-    dashboardPeriod: 'now-1h',
-    dashboardTimezone: 'default',
-    dashboardRefresh: '1m',
-    logExpression: if self.enableMultiCluster then 'job=~"$job", cluster=~"$cluster", qmgr=~"$qmgr"'
-    else 'job=~"$job", qmgr=~"$qmgr"',
+  local this = self,
 
-    //alerts thresholds
-    alertsExpiredMessages: 2,  //count
-    alertsStaleMessagesSeconds: 300,  //seconds
-    alertsLowDiskSpace: 5,  //percentage: 0-100
-    alertsHighQueueManagerCpuUsage: 85,  //percentage: 0-100
+  // Enable multi-cluster support
+  enableMultiCluster: false,
 
-    enableLokiLogs: true,
+  // Basic filtering and labeling
+  filteringSelector: '',
+  groupLabels: if self.enableMultiCluster then ['job', 'cluster'] else ['job'],
+  instanceLabels: ['qmgr'],
+
+  // Dashboard settings
+  dashboardTags: ['ibm-mq-mixin'],
+  dashboardPeriod: 'now-1h',
+  dashboardTimezone: 'default',
+  dashboardRefresh: '1m',
+  dashboardNamePrefix: 'IBM MQ',
+  uid: 'ibm-mq',
+
+  // Log settings
+  enableLokiLogs: true,
+  logLabels: ['job', 'qmgr', 'filename'],
+  extraLogLabels: if self.enableMultiCluster then ['cluster'] else [],
+  logsVolumeGroupBy: 'level',
+  showLogsVolume: true,
+  logExpression: if self.enableMultiCluster then 'job=~"$job", cluster=~"$cluster", qmgr=~"$qmgr"' else 'job=~"$job", qmgr=~"$qmgr"',
+
+  // Alert thresholds
+  alertsExpiredMessages: 2,  // count
+  alertsStaleMessagesSeconds: 300,  // seconds
+  alertsLowDiskSpace: 5,  // %
+  alertsHighQueueManagerCpuUsage: 85,  // %
+
+  // Metrics source
+  metricsSource: 'prometheus',
+
+  // Signal definitions
+  signals: {
+    cluster: (import './signals/cluster.libsonnet')(this),
+    qmgr: (import './signals/qmgr.libsonnet')(this),
+    queue: (import './signals/queue.libsonnet')(this),
+    topic: (import './signals/topic.libsonnet')(this),
+    subscription: (import './signals/subscription.libsonnet')(this),
+    channel: (import './signals/channel.libsonnet')(this),
   },
 }

ibm-mq-mixin/dashboards.libsonnet

@@ -0,0 +1,138 @@
+local g = import './g.libsonnet';
+local commonlib = import 'common-lib/common/main.libsonnet';
+
+{
+  local root = self,
+  new(this): {
+    local prefix = this.config.dashboardNamePrefix,
+    local links = this.grafana.links,
+    local tags = this.config.dashboardTags,
+    local uid = this.config.uid,
+    local vars = this.grafana.variables,
+    local annotations = this.grafana.annotations,
+    local refresh = this.config.dashboardRefresh,
+    local period = this.config.dashboardPeriod,
+    local timezone = this.config.dashboardTimezone,
+    local rows = this.grafana.rows,
+
+    clusterOverview:
+      g.dashboard.new(prefix + ' - cluster overview')
+      + g.dashboard.withPanels(
+        g.util.grid.wrapPanels(
+          [
+            rows.clusterOverviewStats,
+            rows.clusterStatus,
+            rows.clusterChannels,
+          ], panelHeight=1, startY=0
+        )
+      )
+      + root.applyCommon(
+        vars.multiInstance,
+        uid + '-cluster-overview',
+        tags,
+        links,
+        annotations,
+        timezone,
+        refresh,
+        period
+      ),
+
+    queueManagerOverview:
+      g.dashboard.new(prefix + ' - queue manager overview')
+      + g.dashboard.withPanels(
+        g.util.grid.wrapPanels(
+          [
+            rows.queueManagerOverviewStats,
+            rows.queueManagerStatus,
+            rows.queueManagerPerformance,
+            rows.queueManagerLogs,
+          ], panelHeight=1, startY=0
+        )
+      )
+      + root.applyCommon(
+        vars.multiInstance,
+        uid + '-queue-manager-overview',
+        tags,
+        links,
+        annotations,
+        timezone,
+        refresh,
+        period
+      ),
+
+    queueOverview:
+      local queueVar = g.dashboard.variable.query.new('queue')
+                       + g.dashboard.variable.query.withDatasourceFromVariable(vars.datasources.prometheus)
+                       + g.dashboard.variable.query.queryTypes.withLabelValues('queue', 'ibmmq_queue_depth{%(filteringSelector)s,queue!~"SYSTEM.*|AMQ.*"}' % this.config)
+                       + g.dashboard.variable.query.withRegex('')
+                       + g.dashboard.variable.query.selectionOptions.withIncludeAll(true, '.+')
+                       + g.dashboard.variable.query.generalOptions.withLabel('Queue')
+                       + g.dashboard.variable.query.refresh.onTime()
+                       + g.dashboard.variable.query.withSort(type='alphabetical');
+      g.dashboard.new(prefix + ' - queue overview')
+      + g.dashboard.withPanels(
+        g.util.grid.wrapPanels(
+          [
+            rows.queueMetrics,
+          ], panelHeight=1, startY=0
+        )
+      )
+      + root.applyCommon(
+        vars.multiInstance + [queueVar],
+        uid + '-queue-overview',
+        tags,
+        links,
+        annotations,
+        timezone,
+        refresh,
+        period
+      ),
+
+    topicsOverview:
+      local topicVar = g.dashboard.variable.query.new('topic')
+                       + g.dashboard.variable.query.withDatasourceFromVariable(vars.datasources.prometheus)
+                       + g.dashboard.variable.query.queryTypes.withLabelValues('topic', 'ibmmq_topic_subscriber_count{%(filteringSelector)s,topic!~"SYSTEM.*|\\\\$SYS.*|"}' % this.config)
+                       + g.dashboard.variable.query.withRegex('')
+                       + g.dashboard.variable.query.selectionOptions.withIncludeAll(true, '.+')
+                       + g.dashboard.variable.query.generalOptions.withLabel('Topic')
+                       + g.dashboard.variable.query.refresh.onTime()
+                       + g.dashboard.variable.query.withSort(type='alphabetical');
+      local subscriptionVar = g.dashboard.variable.query.new('subscription')
+                              + g.dashboard.variable.query.withDatasourceFromVariable(vars.datasources.prometheus)
+                              + g.dashboard.variable.query.queryTypes.withLabelValues('subscription', 'ibmmq_subscription_messsages_received{%(filteringSelector)s,subscription!~"SYSTEM.*|"}' % this.config)
+                              + g.dashboard.variable.query.withRegex('')
+                              + g.dashboard.variable.query.selectionOptions.withIncludeAll(true, '.+')
+                              + g.dashboard.variable.query.generalOptions.withLabel('Subscription')
+                              + g.dashboard.variable.query.refresh.onTime()
+                              + g.dashboard.variable.query.withSort(type='alphabetical');
+      g.dashboard.new(prefix + ' - topics overview')
+      + g.dashboard.withPanels(
+        g.util.grid.wrapPanels(
+          [
+            rows.topics,
+            rows.subscriptions,
+          ], panelHeight=1, startY=0
+        )
+      )
+      + root.applyCommon(
+        vars.multiInstance + [topicVar, subscriptionVar],
+        uid + '-topics-overview',
+        tags,
+        links,
+        annotations,
+        timezone,
+        refresh,
+        period
+      ),
+  },
+
+  applyCommon(vars, uid, tags, links, annotations, timezone, refresh, period):
+    g.dashboard.withTags(tags)
+    + g.dashboard.withUid(uid)
+    + g.dashboard.withLinks(std.objectValues(links))
+    + g.dashboard.withTimezone(timezone)
+    + g.dashboard.withRefresh(refresh)
+    + g.dashboard.time.withFrom(period)
+    + g.dashboard.withVariables(vars)
+    + g.dashboard.withAnnotations(std.objectValues(annotations)),
+}