Fix static mode operational dash for agent-logs namespace (#4300)

grafana · Aug 14, 2023 · bad8c78 · bad8c78
1 parent 6b1a9c9
commit bad8c78
Show file tree

Hide file tree

Showing 3 changed files with 41 additions and 34 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -61,6 +61,8 @@ Main (unreleased)
 
 - The Grafana Agent mixin now includes a dashboard for the logs pipeline. (@thampiotr)
 
+- The Agent Operational dashboard of Grafana Agent mixin now has more descriptive panel titles, Y-axis units
+
 ### Bugfixes
 
 - Add signing region to remote.s3 component for use with custom endpoints so that Authorization Headers work correctly when
@@ -79,6 +81,8 @@ Main (unreleased)
 - Fix issue where flow mode exports labeled as "string or secret" could not be
   used in a binary operation. (@rfratto)
 
+- Fix Grafana Agent mixin's "Agent Operational" dashboard expecting pods to always have `grafana-agent-.*` prefix. (@thampiotr)
+
 v0.34.3 (2023-06-27)
 --------------------
 

diff --git a/example/docker-compose/grafana/dashboards/agent-operational.json b/example/docker-compose/grafana/dashboards/agent-operational.json
@@ -56,7 +56,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "GCs",
+               "title": "GCs [count/s]",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -132,7 +132,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Go Heap",
+               "title": "Go Heap In Use",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -284,7 +284,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "CPU",
+               "title": "CPU Usage [time/s]",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -360,7 +360,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "WSS",
+               "title": "Working Set Size",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -376,7 +376,7 @@
                },
                "yaxes": [
                   {
-                     "format": "short",
+                     "format": "decbytes",
                      "label": null,
                      "logBase": 1,
                      "max": null,
@@ -436,7 +436,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Bad Words",
+               "title": "Promtail Bad Words",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -524,7 +524,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "RX by Pod",
+               "title": "Received Bytes [B/s]",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -540,7 +540,7 @@
                },
                "yaxes": [
                   {
-                     "format": "short",
+                     "format": "Bps",
                      "label": null,
                      "logBase": 1,
                      "max": null,
@@ -600,7 +600,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "TX by Pod",
+               "title": "Transmitted Bytes [B/s]",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -616,7 +616,7 @@
                },
                "yaxes": [
                   {
-                     "format": "short",
+                     "format": "Bps",
                      "label": null,
                      "logBase": 1,
                      "max": null,
@@ -688,7 +688,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Bytes/Series/Pod",
+               "title": "Heap Used per Series per Pod",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -764,7 +764,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Bytes/Series",
+               "title": "Avg Heap Used per Series",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -840,7 +840,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Series/Pod",
+               "title": "Series Count per Pod",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -916,7 +916,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Series/Config",
+               "title": "Series per Config",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -992,7 +992,7 @@
                "thresholds": [ ],
                "timeFrom": null,
                "timeShift": null,
-               "title": "Series",
+               "title": "Total Series",
                "tooltip": {
                   "shared": true,
                   "sort": 2,
@@ -1093,7 +1093,7 @@
             "multi": true,
             "name": "namespace",
             "options": [ ],
-            "query": "label_values(agent_build_info, namespace)",
+            "query": "label_values(agent_build_info{cluster=~\"$cluster\"}, namespace)",
             "refresh": 1,
             "regex": "",
             "sort": 2,
@@ -1117,7 +1117,7 @@
             "multi": true,
             "name": "container",
             "options": [ ],
-            "query": "label_values(agent_build_info, container)",
+            "query": "label_values(agent_build_info{cluster=~\"$cluster\", namespace=\"$namespace\"}, container)",
             "refresh": 1,
             "regex": "",
             "sort": 2,
@@ -1128,7 +1128,7 @@
             "useTags": false
          },
          {
-            "allValue": "grafana-agent-.*",
+            "allValue": ".+",
             "current": {
                "selected": true,
                "text": "All",
@@ -1141,7 +1141,7 @@
             "multi": true,
             "name": "pod",
             "options": [ ],
-            "query": "label_values(agent_build_info{container=~\"$container\", namespace=\"$namespace\"}, pod)",
+            "query": "label_values(agent_build_info{cluster=~\"$cluster\", namespace=\"$namespace\", container=\"$container\"}, pod)",
             "refresh": 1,
             "regex": "",
             "sort": 2,

diff --git a/production/grafana-agent-mixin/debugging.libsonnet b/production/grafana-agent-mixin/debugging.libsonnet
@@ -6,20 +6,20 @@ local g = import 'grafana-builder/grafana.libsonnet';
     'agent-operational.json':
       utils.injectUtils(g.dashboard('Agent Operational'))
       .addMultiTemplate('cluster', 'agent_build_info', 'cluster')
-      .addMultiTemplate('namespace', 'agent_build_info', 'namespace')
-      .addMultiTemplate('container', 'agent_build_info', 'container')
-      .addMultiTemplateWithAll('pod', 'agent_build_info{container=~"$container", namespace="$namespace"}', 'pod', all='grafana-agent-.*')
+      .addMultiTemplate('namespace', 'agent_build_info{cluster=~"$cluster"}', 'namespace')
+      .addMultiTemplate('container', 'agent_build_info{cluster=~"$cluster", namespace="$namespace"}', 'container')
+      .addMultiTemplate('pod', 'agent_build_info{cluster=~"$cluster", namespace="$namespace", container="$container"}', 'pod')
       .addRow(
         g.row('General')
         .addPanel(
-          g.panel('GCs') +
+          g.panel('GCs [count/s]') +
           g.queryPanel(
             'rate(go_gc_duration_seconds_count{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"}[5m])',
             '{{pod}}',
           )
         )
         .addPanel(
-          g.panel('Go Heap') +
+          g.panel('Go Heap In Use') +
           { yaxes: g.yaxes('decbytes') } +
           g.queryPanel(
             'go_memstats_heap_inuse_bytes{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"}',
@@ -34,21 +34,22 @@ local g = import 'grafana-builder/grafana.libsonnet';
           )
         )
         .addPanel(
-          g.panel('CPU') +
+          g.panel('CPU Usage [time/s]') +
           g.queryPanel(
             'rate(container_cpu_usage_seconds_total{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"}[5m])',
             '{{pod}}',
           )
         )
         .addPanel(
-          g.panel('WSS') +
+          g.panel('Working Set Size') +
+          { yaxes: g.yaxes('decbytes') } +
           g.queryPanel(
             'container_memory_working_set_bytes{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"}',
             '{{pod}}',
           )
         )
         .addPanel(
-          g.panel('Bad Words') +
+          g.panel('Promtail Bad Words') +
           g.queryPanel(
             'rate(promtail_custom_bad_words_total{cluster=~"$cluster", exported_namespace=~"$namespace", exported_job=~"$job"}[5m])',
             '{{job}}',
@@ -58,14 +59,16 @@ local g = import 'grafana-builder/grafana.libsonnet';
       .addRow(
         g.row('Network')
         .addPanel(
-          g.panel('RX by Pod') +
+          g.panel('Received Bytes [B/s]') +
+          { yaxes: g.yaxes('Bps') } +
           g.queryPanel(
             'sum by (pod) (rate(container_network_receive_bytes_total{cluster=~"$cluster", namespace=~"$namespace", pod=~"$pod"}[5m]))',
             '{{pod}}',
           )
         )
         .addPanel(
-          g.panel('TX by Pod') +
+          g.panel('Transmitted Bytes [B/s]') +
+          { yaxes: g.yaxes('Bps') } +
           g.queryPanel(
             'sum by (pod) (rate(container_network_transmit_bytes_total{cluster=~"$cluster", namespace=~"$namespace", pod=~"$pod"}[5m]))',
             '{{pod}}',
@@ -75,7 +78,7 @@ local g = import 'grafana-builder/grafana.libsonnet';
       .addRow(
         g.row('Prometheus Read')
         .addPanel(
-          g.panel('Bytes/Series/Pod') +
+          g.panel('Heap Used per Series per Pod') +
           { yaxes: g.yaxes('decbytes') } +
           g.queryPanel(
             |||
@@ -87,7 +90,7 @@ local g = import 'grafana-builder/grafana.libsonnet';
           )
         )
         .addPanel(
-          g.panel('Bytes/Series') +
+          g.panel('Avg Heap Used per Series') +
           { yaxes: g.yaxes('decbytes') } +
           g.queryPanel(
             |||
@@ -99,21 +102,21 @@ local g = import 'grafana-builder/grafana.libsonnet';
           )
         )
         .addPanel(
-          g.panel('Series/Pod') +
+          g.panel('Series Count per Pod') +
           g.queryPanel(
             'sum by (pod) (agent_wal_storage_active_series{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"})',
             '{{pod}}',
           )
         )
         .addPanel(
-          g.panel('Series/Config') +
+          g.panel('Series per Config') +
           g.queryPanel(
             'sum by (instance_group_name) (agent_wal_storage_active_series{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"})',
             '{{instance_group_name}}',
           )
         )
         .addPanel(
-          g.panel('Series') +
+          g.panel('Total Series') +
           g.queryPanel(
             'sum by (container) (agent_wal_storage_active_series{cluster=~"$cluster", namespace=~"$namespace", container=~"$container", pod=~"$pod"})',
             '{{container}}',