add new appset metrics (#18961)

* add new appset metrics

* Rename 18960.added to 18961.added

* don't test in e2e

argocd/changelog.d/18961.added

@@ -0,0 +1 @@
+Add new Application Set metrics

argocd/datadog_checks/argocd/metrics.py

@@ -67,6 +67,10 @@
     'controller_runtime_reconcile_errors': 'reconcile.errors',
     'controller_runtime_reconcile_time_seconds': 'reconcile.time_seconds',
     'controller_runtime_reconcile': 'runtime.reconcile',
+    'argocd_appset_info': 'appset.info',
+    'argocd_appset_reconcile': 'appset.reconcile',
+    'argocd_appset_owned_applications': 'appset.owned.applications',
+    'argocd_appset_labels': 'appset.labels',
 }
 
 API_SERVER = {

argocd/metadata.csv

@@ -103,10 +103,16 @@ argocd.app_controller.workqueue.queue.duration.seconds.count,count,,,,The total
 argocd.app_controller.workqueue.queue.duration.seconds.sum,count,,,,The sum the of events counted in the workqueue duration histogram,0,argocd,app_controller workqueue queue duration seconds sum,
 argocd.app_controller.workqueue.retries.count,count,,,,The total number of retries handled by workqueue,0,argocd,app_controller workqueue retries,
 argocd.app_controller.workqueue.unfinished_work.seconds,gauge,,second,,The number of seconds of work that has been done that is in progress and hasn't been observed by `work_duration`. Large values indicate stuck threads. One can deduce the number of stuck threads by observing the rate at which this increases,0,argocd,app_controller workqueue unfinished_work seconds,
-argocd.app_controller.workqueue.work.duration.seconds.bucket,count,,second,,The histogram bucket for time in seconds it takes for processing of an item in the workqueue ,0,argocd,app_controller workqueue work duration seconds bucket,
-argocd.app_controller.workqueue.work.duration.seconds.count,count,,,,The total number of events in the workqueue item processing duration histogram ,0,argocd,app_controller workqueue work duration seconds count,
-argocd.app_controller.workqueue.work.duration.seconds.sum,count,,,,The sum of events in the workqueue item processing duration histogram ,0,argocd,app_controller workqueue work duration seconds sum,
+argocd.app_controller.workqueue.work.duration.seconds.bucket,count,,second,,The histogram bucket for time in seconds it takes for processing of an item in the workqueue,0,argocd,app_controller workqueue work duration seconds bucket,
+argocd.app_controller.workqueue.work.duration.seconds.count,count,,,,The total number of events in the workqueue item processing duration histogram,0,argocd,app_controller workqueue work duration seconds count,
+argocd.app_controller.workqueue.work.duration.seconds.sum,count,,,,The sum of events in the workqueue item processing duration histogram,0,argocd,app_controller workqueue work duration seconds sum,
 argocd.appset_controller.active.workers,gauge,,,,Number of currently used workers per controller,0,argocd,appset_controller runtime active workers count,
+argocd.appset_controller.appset.info,gauge,,,,Information about Application Sets. It contains labels for the name and namespace of an application set as well as Resource_update_status that reflects the ResourcesUpToDate property,0,argocd,appset_controller appset info,
+argocd.appset_controller.appset.labels,gauge,,,,Applicationset labels translated to Prometheus labels. Disabled by default,0,argocd,appset_controller appset info,
+argocd.appset_controller.appset.owned.applications,gauge,,,,Number of applications owned by the applicationset. It contains labels for the name and namespace of an applicationset.,0,argocd,appset_controller appset info,
+argocd.appset_controller.appset.reconcile.bucket,count,,,,Application reconciliation performance observation counts by histogram buckets. It contains labels for the name and namespace of an applicationset,0,argocd,appset_controller appset info,
+argocd.appset_controller.appset.reconcile.count,count,,,,Application reconciliation performance observation counts total. It contains labels for the name and namespace of an applicationset,0,argocd,appset_controller appset info,
+argocd.appset_controller.appset.reconcile.sum,count,,,,Application reconciliation performance in seconds total. It contains labels for the name and namespace of an applicationset,0,argocd,appset_controller appset info,
 argocd.appset_controller.go.gc.duration.seconds.count,count,,second,,The summary count of garbage collection cycles in the ApplicationSet controller,0,argocd,appset_controller go gc duration seconds count,
 argocd.appset_controller.go.gc.duration.seconds.quantile,gauge,,second,,A summary of the pause duration of garbage collection cycles in the ApplicationSet controller,0,argocd,appset_controller go gc duration seconds,
 argocd.appset_controller.go.gc.duration.seconds.sum,count,,second,,The sum of the pause duration of garbage collection cycles in the ApplicationSet controller,0,argocd,appset_controller go gc duration seconds sum,
@@ -228,4 +234,4 @@ argocd.repo_server.redis.request.count,count,,request,,The number of kubernetes
 argocd.repo_server.redis.request.duration.seconds.bucket,count,,second,,The Redis requests duration histogram buckets,0,argocd,repo_server redis request duration seconds bucket,
 argocd.repo_server.redis.request.duration.seconds.count,count,,second,,The count aggregation of the Redis requests duration histogram,0,argocd,repo_server redis request duration seconds count,
 argocd.repo_server.redis.request.duration.seconds.sum,count,,second,,The sum aggregation of the Redis requests duration histogram,0,argocd,repo_server redis request duration seconds sum,
-argocd.repo_server.repo.pending.request.total,gauge,,request,, The number of pending requests requiring repository lock,0,argocd,repo_server repo pending request,
+argocd.repo_server.repo.pending.request.total,gauge,,request,,The number of pending requests requiring repository lock,0,argocd,repo_server repo pending request,

argocd/tests/common.py

@@ -113,12 +113,18 @@
 appset_controller_gauges = [
     'active.workers',
     'max.concurrent.reconciles',
+    'appset.info',
+    'appset.owned.applications',
+    'appset.labels',
 ]
 
 appset_controller_histograms = [
     'reconcile.time_seconds.bucket',
     'reconcile.time_seconds.count',
     'reconcile.time_seconds.sum',
+    'appset.reconcile.bucket',
+    'appset.reconcile.count',
+    'appset.reconcile.sum',
 ]
 
 api_server_counters = [
@@ -176,6 +182,12 @@
     'argocd.app_controller.app.reconcile.count',
     'argocd.app_controller.app.reconcile.sum',
     'argocd.app_controller.kubectl.exec.pending',
+    'argocd.appset_controller.appset.reconcile.bucket',
+    'argocd.appset_controller.appset.reconcile.count',
+    'argocd.appset_controller.appset.reconcile.sum',
+    'argocd.appset_controller.appset.info',
+    'argocd.appset_controller.appset.owned.applications',
+    'argocd.appset_controller.appset.labels',
     'argocd.appset_controller.reconcile.time_seconds.bucket',
     'argocd.appset_controller.reconcile.time_seconds.count',
     'argocd.appset_controller.reconcile.time_seconds.sum',

argocd/tests/fixtures/appset_controller_metrics.txt

@@ -309,4 +309,19 @@ process_virtual_memory_max_bytes 1.8446744073709552e+19
 # HELP rest_client_requests_total Number of HTTP requests, partitioned by status code, method, and host.
 # TYPE rest_client_requests_total counter
 rest_client_requests_total{code="200",host="172.20.0.1:443",method="GET"} 3770
-rest_client_requests_total{code="404",host="172.20.0.1:443",method="GET"} 1
+rest_client_requests_total{code="404",host="172.20.0.1:443",method="GET"} 1
+# HELP argocd_appset_labels Manually created
+# TYPE argocd_appset_labels gauge
+argocd_appset_labels{controller="applicationset"} 0
+# HELP argocd_appset_info Manually created
+# TYPE argocd_appset_info gauge
+argocd_appset_info{controller="applicationset"} 1
+# HELP argocd_appset_owned_applications Manually created
+# TYPE argocd_appset_owned_applications gauge
+argocd_appset_owned_applications{controller="applicationset"} 1
+# HELP argocd_appset_reconcile manually created to test parsing
+# TYPE argocd_appset_reconcile histogram
+argocd_appset_reconcile_bucket{controller="applicationset",le="0.005"} 155
+argocd_appset_reconcile_bucket{controller="applicationset",le="+Inf"} 1347
+argocd_appset_reconcile_sum{controller="applicationset"} 507.75374146199937
+argocd_appset_reconcile_count{controller="applicationset"} 1347