Update metrics to be counters where appropriate

Signed-off-by: Mike Eves <[email protected]>
prometheus-community · Apr 7, 2022 · 2720965 · 2720965
1 parent 6cb3e19
commit 2720965
Show file tree

Hide file tree

Showing 2 changed files with 36 additions and 36 deletions.
diff --git a/README.md b/README.md
@@ -224,20 +224,20 @@ Further Information
 | elasticsearch_clusterinfo_up                                          | gauge     | 1           | Up metric for the cluster info collector
 | elasticsearch_clusterinfo_version_info                                | gauge     | 6           | Constant metric with ES version information as labels
 | elasticsearch_slm_stats_up                                            | gauge     | 0           | Up metric for SLM collector
-| elasticsearch_slm_stats_total_scrapes                                 | gauge     | 0           | Number of scrapes for SLM collector
-| elasticsearch_slm_stats_json_parse_failures                           | gauge     | 0           | JSON parse failures for SLM collector
-| elasticsearch_slm_stats_retention_runs                                | gauge     | 0           | Total retention runs
-| elasticsearch_slm_stats_retention_failed                              | gauge     | 0           | Total failed retention runs
-| elasticsearch_slm_stats_retention_timed_out                           | gauge     | 0           | Total retention run timeouts
-| elasticsearch_slm_stats_retention_retention_deletion_time_millis      | gauge     | 0           | Retention run deletion time
-| elasticsearch_slm_stats_total_snapshots_taken                         | gauge     | 0           | Total snapshots taken
-| elasticsearch_slm_stats_total_snapshots_failed                        | gauge     | 0           | Total snapshots failed
-| elasticsearch_slm_stats_total_snapshots_deleted                       | gauge     | 0           | Total snapshots deleted
-| elasticsearch_slm_stats_total_snapshots_failed                        | gauge     | 0           | Total snapshots failed
-| elasticsearch_slm_stats_snapshots_taken                               | gauge     | 1           | Snapshots taken by policy
-| elasticsearch_slm_stats_snapshots_failed                              | gauge     | 1           | Snapshots failed by policy
-| elasticsearch_slm_stats_snapshots_deleted                             | gauge     | 1           | Snapshots deleted by policy
-| elasticsearch_slm_stats_snapshot_deletion_failures                    | gauge     | 1           | Snapshot deletion failures by policy
+| elasticsearch_slm_stats_total_scrapes                                 | counter   | 0           | Number of scrapes for SLM collector
+| elasticsearch_slm_stats_json_parse_failures                           | counter   | 0           | JSON parse failures for SLM collector
+| elasticsearch_slm_stats_retention_runs_total                          | counter   | 0           | Total retention runs
+| elasticsearch_slm_stats_retention_failed_total                        | counter   | 0           | Total failed retention runs
+| elasticsearch_slm_stats_retention_timed_out_total                     | counter   | 0           | Total retention run timeouts
+| elasticsearch_slm_stats_retention_deletion_time_seconds               | gauge     | 0           | Retention run deletion time
+| elasticsearch_slm_stats_total_snapshots_taken_total                   | counter   | 0           | Total snapshots taken
+| elasticsearch_slm_stats_total_snapshots_failed_total                  | counter   | 0           | Total snapshots failed
+| elasticsearch_slm_stats_total_snapshots_deleted_total                 | counter   | 0           | Total snapshots deleted
+| elasticsearch_slm_stats_total_snapshots_failed_total                  | counter   | 0           | Total snapshots failed
+| elasticsearch_slm_stats_snapshots_taken_total                         | counter   | 1           | Snapshots taken by policy
+| elasticsearch_slm_stats_snapshots_failed_total                        | counter   | 1           | Snapshots failed by policy
+| elasticsearch_slm_stats_snapshots_deleted_total                       | counter   | 1           | Snapshots deleted by policy
+| elasticsearch_slm_stats_snapshot_deletion_failures_total              | counter   | 1           | Snapshot deletion failures by policy
 | elasticsearch_slm_stats_operation_mode                                | gauge     | 1           | SLM operation mode (Running, stopping, stopped)
 
 

diff --git a/collector/slm.go b/collector/slm.go
@@ -90,9 +90,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 		}),
 		slmMetrics: []*slmMetric{
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "retention_runs"),
+					prometheus.BuildFQName(namespace, "slm_stats", "retention_runs_total"),
 					"Total retention runs",
 					nil, nil,
 				),
@@ -101,9 +101,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				},
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "retention_failed"),
+					prometheus.BuildFQName(namespace, "slm_stats", "retention_failed_total"),
 					"Total failed retention runs",
 					nil, nil,
 				),
@@ -112,9 +112,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				},
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "retention_timed_out"),
+					prometheus.BuildFQName(namespace, "slm_stats", "retention_timed_out_total"),
 					"Total timed out retention runs",
 					nil, nil,
 				),
@@ -134,9 +134,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				},
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshots_taken"),
+					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshots_taken_total"),
 					"Total snapshots taken",
 					nil, nil,
 				),
@@ -145,9 +145,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				},
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshots_failed"),
+					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshots_failed_total"),
 					"Total snapshots failed",
 					nil, nil,
 				),
@@ -156,9 +156,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				},
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshots_deleted"),
+					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshots_deleted_total"),
 					"Total snapshots deleted",
 					nil, nil,
 				),
@@ -167,9 +167,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				},
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshot_deletion_failures"),
+					prometheus.BuildFQName(namespace, "slm_stats", "total_snapshot_deletion_failures_total"),
 					"Total snapshot deletion failures",
 					nil, nil,
 				),
@@ -180,9 +180,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 		},
 		policyMetrics: []*policyMetric{
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "snapshots_taken"),
+					prometheus.BuildFQName(namespace, "slm_stats", "snapshots_taken_total"),
 					"Total snapshots taken",
 					defaultPolicyLabels, nil,
 				),
@@ -192,9 +192,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				Labels: defaultPolicyLabelValues,
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "snapshots_failed"),
+					prometheus.BuildFQName(namespace, "slm_stats", "snapshots_failed_total"),
 					"Total snapshots failed",
 					defaultPolicyLabels, nil,
 				),
@@ -204,9 +204,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				Labels: defaultPolicyLabelValues,
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "snapshots_deleted"),
+					prometheus.BuildFQName(namespace, "slm_stats", "snapshots_deleted_total"),
 					"Total snapshots deleted",
 					defaultPolicyLabels, nil,
 				),
@@ -216,9 +216,9 @@ func NewSLM(logger log.Logger, client *http.Client, url *url.URL) *SLM {
 				Labels: defaultPolicyLabelValues,
 			},
 			{
-				Type: prometheus.GaugeValue,
+				Type: prometheus.CounterValue,
 				Desc: prometheus.NewDesc(
-					prometheus.BuildFQName(namespace, "slm_stats", "snapshot_deletion_failures"),
+					prometheus.BuildFQName(namespace, "slm_stats", "snapshot_deletion_failures_total"),
 					"Total snapshot deletion failures",
 					defaultPolicyLabels, nil,
 				),