Add metrics for number of series queried

CHANGELOG.md

@@ -9,6 +9,7 @@
 * [FEATURE] StoreGateway: Introduces a new parquet mode. #7046
 * [FEATURE] Distributor: Add a per-tenant flag `-distributor.enable-type-and-unit-labels` that enables adding `__unit__` and `__type__` labels for remote write v2 and OTLP requests. This is a breaking change; the `-distributor.otlp.enable-type-and-unit-labels` flag is now deprecated, operates as a no-op, and has been consolidated into this new flag. #7077
 * [FEATURE] Querier: Add experimental projection pushdown support in Parquet Queryable. #7152
+* [FEATURE] Ingester: Add experimental active series queried metric. #7173
 * [ENHANCEMENT] StoreGateway: Add tracings to parquet mode. #7125
 * [ENHANCEMENT] Alertmanager: Upgrade alertmanger to 0.29.0 and add a new incidentIO integration. #7092
 * [ENHANCEMENT] Querier: Add a `-querier.parquet-queryable-shard-cache-ttl` flag to add TTL to parquet shard cache. #7098

docs/configuration/config-file-reference.md

@@ -3702,6 +3702,30 @@ lifecycler:
 # CLI flag: -ingester.active-series-metrics-idle-timeout
 [active_series_metrics_idle_timeout: <duration> | default = 10m]
 
+# Enable tracking of active queried series using probabilistic data structure
+# and export them as metrics.
+# CLI flag: -ingester.active-queried-series-metrics-enabled
+[active_queried_series_metrics_enabled: <boolean> | default = false]
+
+# How often to update active queried series metrics.
+# CLI flag: -ingester.active-queried-series-metrics-update-period
+[active_queried_series_metrics_update_period: <duration> | default = 1m]
+
+# Duration of each sub-window for active queried series tracking (e.g., 1
+# minute). Used to divide the total tracking period into smaller windows.
+# CLI flag: -ingester.active-queried-series-metrics-window-duration
+[active_queried_series_metrics_window_duration: <duration> | default = 15m]
+
+# Sampling rate for active queried series tracking (1.0 = 100% sampling, 0.1 =
+# 10% sampling). By default, all queries are sampled.
+# CLI flag: -ingester.active-queried-series-metrics-sample-rate
+[active_queried_series_metrics_sample_rate: <float> | default = 1]
+
+# Time windows to expose queried series metric. Each window tracks queried
+# series within that time period.
+# CLI flag: -ingester.active-queried-series-metrics-windows
+[active_queried_series_metrics_windows: <list of duration> | default = 2h0m0s]
+
 # Enable uploading compacted blocks.
 # CLI flag: -ingester.upload-compacted-blocks-enabled
 [upload_compacted_blocks_enabled: <boolean> | default = true]

docs/configuration/v1-guarantees.md

@@ -133,3 +133,9 @@ Currently experimental features are:
 - Distributor/Ingester: Stream push connection
   - Enable stream push connection between distributor and ingester by setting `-distributor.use-stream-push=true` on Distributor.
   - Add `__type__` and `__unit__` labels to OTLP and remote write v2 requests (`-distributor.enable-type-and-unit-labels`)
+- Ingester: Series Queried Metric
+  - Enable on Ingester via `-ingester.active-queried-series-metrics-enabled=true`
+  - Set the time window to expose via metrics using `-ingester.active-queried-series-metrics-windows=2h`. At least 1 time window is required to expose the metric.
+  - `-ingester.active-queried-series-metrics-update-period` metric update interval
+  - `-ingester.active-queried-series-metrics-window-duration` each HyperLogLog time window size
+  - `-ingester.active-queried-series-metrics-sample-rate` query sampling rate

go.mod

@@ -78,6 +78,7 @@ require (
 	github.com/aws/aws-sdk-go-v2 v1.39.2
 	github.com/aws/aws-sdk-go-v2/config v1.31.12
 	github.com/aws/aws-sdk-go-v2/service/dynamodb v1.50.1
+	github.com/axiomhq/hyperloglog v0.2.6
 	github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3
 	github.com/cespare/xxhash/v2 v2.3.0
 	github.com/go-openapi/swag/jsonutils v0.25.1
@@ -202,6 +203,7 @@ require (
 	github.com/jessevdk/go-flags v1.6.1 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
 	github.com/julienschmidt/httprouter v1.3.0 // indirect
+	github.com/kamstrup/intmap v0.5.2 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.10 // indirect
 	github.com/knadh/koanf/maps v0.1.2 // indirect
 	github.com/knadh/koanf/providers/confmap v1.0.0 // indirect

go.sum

@@ -897,6 +897,8 @@ github.com/aws/aws-sdk-go-v2/service/sts v1.38.6 h1:p3jIvqYwUZgu/XYeI48bJxOhvm47
 github.com/aws/aws-sdk-go-v2/service/sts v1.38.6/go.mod h1:WtKK+ppze5yKPkZ0XwqIVWD4beCwv056ZbPQNoeHqM8=
 github.com/aws/smithy-go v1.23.0 h1:8n6I3gXzWJB2DxBDnfxgBaSX6oe0d/t10qGz7OKqMCE=
 github.com/aws/smithy-go v1.23.0/go.mod h1:t1ufH5HMublsJYulve2RKmHDC15xu1f26kHCp/HgceI=
+github.com/axiomhq/hyperloglog v0.2.6 h1:sRhvvF3RIXWQgAXaTphLp4yJiX4S0IN3MWTaAgZoRJw=
+github.com/axiomhq/hyperloglog v0.2.6/go.mod h1:YjX/dQqCR/7QYX0g8mu8UZAjpIenz1FKM71UEsjFoTo=
 github.com/baidubce/bce-sdk-go v0.9.230 h1:HzELBKiD7QAgYqZ1qHZexoI2A3Lo/6zYGQFvcUbS5cA=
 github.com/baidubce/bce-sdk-go v0.9.230/go.mod h1:zbYJMQwE4IZuyrJiFO8tO8NbtYiKTFTbwh4eIsqjVdg=
 github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3 h1:6df1vn4bBlDDo4tARvBm7l6KA9iVMnE3NWizDeWSrps=
@@ -1422,6 +1424,8 @@ github.com/julienschmidt/httprouter v1.3.0 h1:U0609e9tgbseu3rBINet9P48AI/D3oJs4d
 github.com/julienschmidt/httprouter v1.3.0/go.mod h1:JR6WtHb+2LUe8TCKY3cZOxFyyO8IZAc4RVcycCCAKdM=
 github.com/jung-kurt/gofpdf v1.0.0/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
 github.com/jung-kurt/gofpdf v1.0.3-0.20190309125859-24315acbbda5/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
+github.com/kamstrup/intmap v0.5.2 h1:qnwBm1mh4XAnW9W9Ue9tZtTff8pS6+s6iKF6JRIV2Dk=
+github.com/kamstrup/intmap v0.5.2/go.mod h1:gWUVWHKzWj8xpJVFf5GC0O26bWmv3GqdnIX/LMT6Aq4=
 github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51/go.mod h1:CzGEWj7cYgsdH8dAjBGEr58BoE7ScuLd+fwFZ44+/x8=
 github.com/keybase/go-keychain v0.0.1 h1:way+bWYa6lDppZoZcgMbYsvC7GxljxrskdNInRtuthU=
 github.com/keybase/go-keychain v0.0.1/go.mod h1:PdEILRW3i9D8JcdM+FmY6RwkHGnhHxXwkPPMeUgOK1k=