Dist metrics

CHANGELOG.md

@@ -0,0 +1,47 @@
+
+<!-- 0.1.4 START -->
+# 0.1.4 (04/07/2023)
+
+- **[ENHANCEMENT]**: Add set of dashboards for monitoring deep [#22](https://github.com/intergral/deep/pull/22) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Handle error during query, when loading bad blocks [#26](https://github.com/intergral/deep/pull/26) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Ensure minio is started in distributed docker example [#24](https://github.com/intergral/deep/pull/24) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Handle nil when querier tracepoints, when we have no tracepoints [#23](https://github.com/intergral/deep/pull/23) [@Umaaz](https://github.com/Umaaz)
+- **[CHANGE]**: Update metrics from ingester [#25](https://github.com/intergral/deep/pull/25) [@Umaaz](https://github.com/Umaaz)
+- **[CHANGE]**: Update tenants dashboards [#27](https://github.com/intergral/deep/pull/27) [@Umaaz](https://github.com/Umaaz)
+- **[CHANGE]**: Remove references to tempo/traces [#13](https://github.com/intergral/deep/pull/13) [@Umaaz](https://github.com/Umaaz)
+- **[CHANGE]**: Disabled usage reports [#28](https://github.com/intergral/deep/pull/28) [@Umaaz](https://github.com/Umaaz)
+<!-- 0.1.4 END -->
+
+<!-- 0.1.3 START -->
+# 0.1.3 (03/07/2023)
+
+- **[ENHANCEMENT]**: Change distributor to support multi entry points [#20](https://github.com/intergral/deep/pull/20) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Handle possible error during tracepoint requests [#21](https://github.com/intergral/deep/pull/21) [@Umaaz](https://github.com/Umaaz)
+<!-- 0.1.3 END -->
+
+<!-- 0.1.2 START -->
+# 0.1.2 (21/06/2023)
+
+- **[ENHANCEMENT]**: Add perma links to docs [#9](https://github.com/intergral/deep/pull/9) [@Umaaz](https://github.com/Umaaz)
+- **[ENHANCEMENT]**: Add examples for using kubernetes deployment files [#11](https://github.com/intergral/deep/pull/11) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Add exception to middleware auth [#10](https://github.com/intergral/deep/pull/10) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Fix tracepoint worker not working in single binary mode [#16](https://github.com/intergral/deep/pull/16) [@Umaaz](https://github.com/Umaaz)
+- **[BUGFIX]**: Fix possible nil reference in store [#16](https://github.com/intergral/deep/pull/16) [@Umaaz](https://github.com/Umaaz)
+- **[CHANGE]**: Make tracepoint storage use existing services [#14](https://github.com/intergral/deep/pull/14) [@Umaaz](https://github.com/Umaaz)
+- **[CHANGE]**: **BREAKING** Remove unnecessary config embedding [#15](https://github.com/intergral/deep/pull/15) [@Umaaz](https://github.com/Umaaz)
+<!-- 0.1.2 END -->
+
+<!-- 0.1.1 START -->
+# 0.1.1 (16/06/2023)
+
+- **[FEATURE]**: change the queue/worker system to support tracepoints allowing for distributed mode deployments [#8](https://github.com/intergral/deep/pull/8) [@Umaaz](https://github.com/Umaaz)
+<!-- 0.1.1 END -->
+
+<!-- Template START
+# 0.1.1 (16/06/2023)
+
+- **[FEATURE]**: description [#PRid](https://github.com/intergral/deep/pull/) [@user](https://github.com/)
+- **[ENHANCEMENT]**: description [#PRid](https://github.com/intergral/deep/pull/) [@user](https://github.com/)
+- **[BUGFIX]**: description [#PRid](https://github.com/intergral/deep/pull/) [@user](https://github.com/)
+- **[CHANGE]**: description [#PRid](https://github.com/intergral/deep/pull/8) [@user](https://github.com/)
+Template END -->

modules/distributor/distributor.go

@@ -73,54 +73,64 @@ const (
 var (
 	metricDiscardedSnapshots = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
+		Subsystem: "distributor",
 		Name:      "discarded_snapshots_total",
 		Help:      "The total number of samples that were discarded.",
 	}, []string{discardReasonLabel, "tenant"})
 	metricSnapshotBytesIngested = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_snapshot_bytes_received_total",
+		Subsystem: "distributor",
+		Name:      "snapshot_bytes_received_total",
 		Help:      "The total number of snapshot proto bytes received per tenant",
 	}, []string{"tenant"})
 	metricPollBytesIngested = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_poll_bytes_received_total",
+		Subsystem: "distributor",
+		Name:      "poll_bytes_received_total",
 		Help:      "The total number of poll proto bytes received per tenant",
 	}, []string{"tenant"})
 	metricPollBytesResponded = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_poll_bytes_sent_total",
+		Subsystem: "distributor",
+		Name:      "poll_bytes_sent_total",
 		Help:      "The total number of poll proto bytes sent in response per tenant",
 	}, []string{"tenant"})
 
 	metricIngesterAppends = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_ingester_appends_total",
+		Subsystem: "distributor",
+		Name:      "ingester_appends_total",
 		Help:      "The total number of batch appends sent to ingesters.",
 	}, []string{"ingester"})
 	metricIngesterAppendFailures = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_ingester_append_failures_total",
+		Subsystem: "distributor",
+		Name:      "ingester_append_failures_total",
 		Help:      "The total number of failed batch appends sent to ingesters.",
 	}, []string{"ingester"})
 
 	metricGeneratorPushes = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_metrics_generator_pushes_total",
+		Subsystem: "distributor",
+		Name:      "metrics_generator_pushes_total",
 		Help:      "The total number of span pushes sent to metrics-generators.",
 	}, []string{"metrics_generator"})
 	metricGeneratorPushesFailures = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_metrics_generator_pushes_failures_total",
+		Subsystem: "distributor",
+		Name:      "metrics_generator_pushes_failures_total",
 		Help:      "The total number of failed span pushes sent to metrics-generators.",
 	}, []string{"metrics_generator"})
 	metricIngesterClients = promauto.NewGauge(prometheus.GaugeOpts{
 		Namespace: "deep",
-		Name:      "distributor_ingester_clients",
+		Subsystem: "distributor",
+		Name:      "ingester_clients",
 		Help:      "The current number of ingester clients.",
 	})
 	metricGeneratorClients = promauto.NewGauge(prometheus.GaugeOpts{
 		Namespace: "deep",
-		Name:      "distributor_metrics_generator_clients",
+		Subsystem: "distributor",
+		Name:      "metrics_generator_clients",
 		Help:      "The current number of metrics-generator clients.",
 	})
 )

modules/distributor/forwarder.go

@@ -42,12 +42,14 @@ const (
 var (
 	metricForwarderPushes = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_forwarder_pushes_total",
+		Subsystem: "distributor",
+		Name:      "forwarder_pushes_total",
 		Help:      "Total number of successful requests queued up for a tenant to the generatorForwarder. This metric is now deprecated in favor of deep_distributor_queue_pushes_total.",
 	}, []string{"tenant"})
 	metricForwarderPushesFailures = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_forwarder_pushes_failures_total",
+		Subsystem: "distributor",
+		Name:      "forwarder_pushes_failures_total",
 		Help:      "Total number of failed pushes to the queue for a tenant to the generatorForwarder. This metric is now deprecated in favor of deep_distributor_queue_pushes_failures_total.",
 	}, []string{"tenant"})
 )

modules/distributor/snapshotreceiver/reciever.go

@@ -45,36 +45,42 @@ const (
 var (
 	metricPollDuration = promauto.NewHistogram(prometheus.HistogramOpts{
 		Namespace: "deep",
-		Name:      "distributor_poll_duration_seconds",
+		Subsystem: "distributor",
+		Name:      "poll_duration_seconds",
 		Help:      "Records the amount of time to poll a config from tracepoint.",
 		Buckets:   prometheus.DefBuckets,
 	})
 	metricPushDuration = promauto.NewHistogram(prometheus.HistogramOpts{
 		Namespace: "deep",
-		Name:      "distributor_push_duration_seconds",
+		Subsystem: "distributor",
+		Name:      "push_duration_seconds",
 		Help:      "Records the amount of time to push a batch to the ingester.",
 		Buckets:   prometheus.DefBuckets,
 	})
 
 	metricDistributorAccepted = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_snapshots_requests",
+		Subsystem: "distributor",
+		Name:      "snapshots_requests",
 		Help:      "Number of snapshots successfully pushed into the pipeline.",
 	}, []string{"tenant", "receiver"})
 	metricPollAccepted = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_poll_requests",
+		Subsystem: "distributor",
+		Name:      "poll_requests",
 		Help:      "Number of completed poll requests.",
 	}, []string{"tenant", "receiver"})
 
 	metricDistributorRefused = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_failed_snapshots_requests",
+		Subsystem: "distributor",
+		Name:      "failed_snapshots_requests",
 		Help:      "Number of snapshots that could not be pushed into the pipeline.",
 	}, []string{"tenant", "receiver"})
 	metricPollRefused = promauto.NewCounterVec(prometheus.CounterOpts{
 		Namespace: "deep",
-		Name:      "distributor_failed_poll_requests",
+		Subsystem: "distributor",
+		Name:      "failed_poll_requests",
 		Help:      "Number of failed poll requests.",
 	}, []string{"tenant", "receiver"})
 )