Merge branch 'main' into vldmr/helm-gomaxprocs

Author: narqo

.github/workflows/update-vendored-mimir-prometheus.yml

@@ -72,7 +72,7 @@ jobs:
         uses: actions/setup-go@v5
         with:
           # We only use this to run `go mod` commands, so it doesn't need to follow the version used in the Dockerfile.
-          go-version: "1.24.4"
+          go-version: "1.24.6"
 
       # This job uses "mimir-vendoring bot" instead of "github-actions bot" (secrets.GITHUB_TOKEN)
       # because any events triggered by the later don't spawn GitHub actions.

.golangci.yml

@@ -75,8 +75,14 @@ linters:
         - name: redefines-builtin-id
           disabled: true
     staticcheck:
+      # Replicate the default, except to not disable ST1016.
       checks:
-        - ST1016
+        - all
+        - -ST1000
+        - -ST1003
+        - -ST1020
+        - -ST1021
+        - -ST1022
   exclusions:
     presets:
       - comments

CHANGELOG.md

@@ -11,13 +11,19 @@
 * [CHANGE] Memcached: Remove experimental `-<prefix>.memcached.addresses-provider` flag to use alternate DNS service discovery backends. The more reliable backend introduced in 2.16.0 (#10895) is now the default. As a result of this change, DNS-based cache service discovery no longer supports search domains. #12175
 * [CHANGE] Query-frontend: Remove the CLI flag `-query-frontend.downstream-url` and corresponding YAML configuration and the ability to use the query-frontend to proxy arbitrary Prometheus backends. #12191
 * [CHANGE] Query-frontend: Remove experimental instant query splitting feature. #12267
-* [FEATURE] Distributor, ruler: Add experimental `-validation.name-validation-scheme` option to specify the validation scheme for metric and label names. #12215
+* [CHANGE] Distributor: Remove deprecated global HA tracker timeout configuration flags. #12321
+* [FEATURE] Distributor, ruler: Add experimental `-validation.name-validation-scheme` flag to specify the validation scheme for metric and label names. #12215
+* [FEATURE] Distributor: Add experimental `-distributor.otel-translation-strategy` flag to support configuring the metric and label name translation strategy in the OTLP endpoint. #12284 #12306
+* [ENHANCEMENT] Query-scheduler/query-frontend: Add native histogram definitions to `cortex_query_{scheduler|frontend}_queue_duration_seconds`. #12288
+* [ENHANCEMENT] Compactor: Add `-compactor.update-blocks-concurrency` flag to control concurrency for updating block metadata during bucket index updates, separate from deletion marker concurrency. #12117
 * [ENHANCEMENT] Stagger head compaction intervals across zones to prevent compactions from aligning simultaneously, which could otherwise cause strong consistency queries to fail when experimental ingest storage is enabled. #12090
 * [ENHANCEMENT] Querier: Add native histogram definition to `cortex_bucket_index_load_duration_seconds`. #12094
 * [ENHANCEMENT] MQE: Add support for applying common subexpression elimination to range vector expressions in instant queries. #12236
+* [ENHANCEMENT] Ingester: Improve the performance of active series custom trackers matchers. #12184
 * [BUGFIX] Querier: Samples with the same timestamp are merged deterministically. Previously, this could lead to flapping query results when an out-of-order sample is ingested that conflicts with a previously ingested in-order sample's value. #8673
 * [BUGFIX] Store-gateway: Fix potential goroutine leak by passing the scoped context in LabelValues. #12048
 * [BUGFIX] Distributor: Fix pooled memory reuse bug that can cause corrupt data to appear in the err-mimir-label-value-too-long error message. #12048
+* [BUGFIX] Querier: Fix timeout responding to query-frontend when response size is very close to `-querier.frontend-client.grpc-max-send-msg-size`. #12261
 
 ### Jsonnet
 

Makefile

@@ -247,7 +247,7 @@ mimir-build-image/$(UPTODATE): mimir-build-image/*
 # All the boiler plate for building golang follows:
 SUDO := $(shell docker info >/dev/null 2>&1 || echo "sudo -E")
 BUILD_IN_CONTAINER ?= true
-LATEST_BUILD_IMAGE_TAG ?= pr12036-d9b5f13dc5
+LATEST_BUILD_IMAGE_TAG ?= pr12352-27854ede92
 
 # TTY is parameterized to allow CI and scripts to run builds,
 # as it currently disallows TTY devices.
@@ -415,13 +415,6 @@ lint: check-makefiles
 		github.com/prometheus/client_golang/prometheus.{NewCounter,NewCounterVec,NewCounterFunc,NewGauge,NewGaugeVec,NewGaugeFunc,NewSummary,NewSummaryVec,NewHistogram,NewHistogramVec}=github.com/prometheus/client_golang/prometheus/promauto.With" \
 		./pkg/...
 
-	# Use the faster slices.Sort where we can.
-	# Note that we don't automatically suggest replacing sort.Float64s() with slices.Sort() as the documentation for slices.Sort()
-	# at the time of writing warns that slices.Sort() may not correctly handle NaN values.
-	faillint -paths \
-		"sort.{Strings,Ints}=slices.Sort" \
-		./pkg/... ./cmd/... ./tools/... ./integration/...
-
 	# Use the faster slices.IsSortedFunc where we can.
 	faillint -paths \
 		"sort.{SliceIsSorted}=slices.IsSortedFunc" \

cmd/metaconvert/Dockerfile

@@ -3,7 +3,7 @@
 # Provenance-includes-license: Apache-2.0
 # Provenance-includes-copyright: The Cortex Authors.
 
-FROM       alpine:3.22.0
+FROM       alpine:3.22.1
 ARG        EXTRA_PACKAGES
 RUN        apk add --no-cache ca-certificates tzdata $EXTRA_PACKAGES
 # Expose TARGETOS and TARGETARCH variables. These are supported by Docker when using BuildKit, but must be "enabled" using ARG.

cmd/mimir/Dockerfile.continuous-test

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-only
 
-FROM       alpine:3.22.0
+FROM       alpine:3.22.1
 ARG        EXTRA_PACKAGES
 RUN        apk add --no-cache ca-certificates tzdata $EXTRA_PACKAGES
 # Expose TARGETOS and TARGETARCH variables. These are supported by Docker when using BuildKit, but must be "enabled" using ARG.

cmd/mimir/config-descriptor.json

@@ -729,7 +729,7 @@
           "kind": "field",
           "name": "trace_request_exclude_headers_list",
           "required": false,
-          "desc": "Comma separated list of headers to exclude from tracing spans. Only used if server.trace-request-headers is true. The following headers are always excluded: Authorization, Cookie, X-Csrf-Token.",
+          "desc": "Comma separated list of headers to exclude from tracing spans. Only used if server.trace-request-headers is true. The following headers are always excluded: Authorization, Cookie, X-Access-Token, X-Csrf-Token, X-Grafana-Id.",
           "fieldValue": null,
           "fieldDefaultValue": "",
           "fieldFlag": "server.trace-request-headers-exclude-list",
@@ -1284,36 +1284,6 @@
               ],
               "fieldValue": null,
               "fieldDefaultValue": null
-            },
-            {
-              "kind": "field",
-              "name": "ha_tracker_update_timeout",
-              "required": false,
-              "desc": "Deprecated. Use limits.ha_tracker_update_timeout.",
-              "fieldValue": null,
-              "fieldDefaultValue": null,
-              "fieldType": "duration",
-              "fieldCategory": "advanced"
-            },
-            {
-              "kind": "field",
-              "name": "ha_tracker_update_timeout_jitter_max",
-              "required": false,
-              "desc": "Deprecated. Use limits.ha_tracker_update_timeout_jitter_max.",
-              "fieldValue": null,
-              "fieldDefaultValue": null,
-              "fieldType": "duration",
-              "fieldCategory": "advanced"
-            },
-            {
-              "kind": "field",
-              "name": "ha_tracker_failover_timeout",
-              "required": false,
-              "desc": "Deprecated. Use limits.ha_tracker_failover_timeout.",
-              "fieldValue": null,
-              "fieldDefaultValue": null,
-              "fieldType": "duration",
-              "fieldCategory": "advanced"
             }
           ],
           "fieldValue": null,
@@ -6014,6 +5984,17 @@
           "fieldType": "boolean",
           "fieldCategory": "experimental"
         },
+        {
+          "kind": "field",
+          "name": "otel_translation_strategy",
+          "required": false,
+          "desc": "Translation strategy to apply in OTLP endpoint for metric and label names. If unspecified (the default), the strategy is derived from -validation.name-validation-scheme and -distributor.otel-metric-suffixes-enabled. Supported values: \"\", UnderscoreEscapingWithSuffixes, UnderscoreEscapingWithoutSuffixes, NoUTF8EscapingWithSuffixes, NoTranslation.",
+          "fieldValue": null,
+          "fieldDefaultValue": "",
+          "fieldFlag": "distributor.otel-translation-strategy",
+          "fieldType": "string",
+          "fieldCategory": "experimental"
+        },
         {
           "kind": "field",
           "name": "ingest_storage_read_consistency",
@@ -10743,6 +10724,17 @@
           "fieldType": "int",
           "fieldCategory": "advanced"
         },
+        {
+          "kind": "field",
+          "name": "update_blocks_concurrency",
+          "required": false,
+          "desc": "Number of Go routines to use when updating blocks metadata during bucket index updates.",
+          "fieldValue": null,
+          "fieldDefaultValue": 1,
+          "fieldFlag": "compactor.update-blocks-concurrency",
+          "fieldType": "int",
+          "fieldCategory": "advanced"
+        },
         {
           "kind": "field",
           "name": "enabled_tenants",

cmd/mimir/help-all.txt.tmpl

@@ -1141,6 +1141,8 @@ Usage of ./cmd/mimir/mimir:
     	Number of symbols flushers used when doing split compaction. (default 1)
   -compactor.tenant-cleanup-delay duration
     	For tenants marked for deletion, this is the time between deletion of the last block, and doing final cleanup (marker files, debug files) of the tenant. (default 6h0m0s)
+  -compactor.update-blocks-concurrency int
+    	Number of Go routines to use when updating blocks metadata during bucket index updates. (default 1)
   -compactor.upload-sparse-index-headers
     	[experimental] If enabled, the compactor constructs and uploads sparse index headers to object storage during each compaction cycle. This allows store-gateway instances to use the sparse headers from object storage instead of recreating them locally.
   -config.expand-env
@@ -1271,6 +1273,8 @@ Usage of ./cmd/mimir/mimir:
     	[experimental] Optionally specify OTel resource attributes to promote to labels.
   -distributor.otel-promote-scope-metadata
     	[experimental] Whether to promote OTel scope metadata (scope name, version, schema URL, attributes) to corresponding metric labels, prefixed with otel_scope_.
+  -distributor.otel-translation-strategy value
+    	[experimental] Translation strategy to apply in OTLP endpoint for metric and label names. If unspecified (the default), the strategy is derived from -validation.name-validation-scheme and -distributor.otel-metric-suffixes-enabled. Supported values: "", UnderscoreEscapingWithSuffixes, UnderscoreEscapingWithoutSuffixes, NoUTF8EscapingWithSuffixes, NoTranslation.
   -distributor.remote-timeout duration
     	Timeout for downstream ingesters. (default 2s)
   -distributor.request-burst-size int
@@ -3086,7 +3090,7 @@ Usage of ./cmd/mimir/mimir:
   -server.trace-request-headers
     	Optionally add request headers to tracing spans.
   -server.trace-request-headers-exclude-list string
-    	Comma separated list of headers to exclude from tracing spans. Only used if server.trace-request-headers is true. The following headers are always excluded: Authorization, Cookie, X-Csrf-Token.
+    	Comma separated list of headers to exclude from tracing spans. Only used if server.trace-request-headers is true. The following headers are always excluded: Authorization, Cookie, X-Access-Token, X-Csrf-Token, X-Grafana-Id.
   -shutdown-delay duration
     	How long to wait between SIGTERM and shutdown. After receiving SIGTERM, Mimir will report not-ready status via /ready endpoint.
   -store-gateway.disabled-tenants comma-separated-list-of-strings

cmd/mimir/help.txt.tmpl

@@ -818,7 +818,7 @@ Usage of ./cmd/mimir/mimir:
   -server.trace-request-headers
     	Optionally add request headers to tracing spans.
   -server.trace-request-headers-exclude-list string
-    	Comma separated list of headers to exclude from tracing spans. Only used if server.trace-request-headers is true. The following headers are always excluded: Authorization, Cookie, X-Csrf-Token.
+    	Comma separated list of headers to exclude from tracing spans. Only used if server.trace-request-headers is true. The following headers are always excluded: Authorization, Cookie, X-Access-Token, X-Csrf-Token, X-Grafana-Id.
   -store-gateway.sharding-ring.consul.hostname string
     	Hostname and port of Consul. (default "localhost:8500")
   -store-gateway.sharding-ring.etcd.endpoints string

cmd/mimirtool/Dockerfile

@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
 
-FROM       alpine:3.22.0
+FROM       alpine:3.22.1
 ARG        EXTRA_PACKAGES
 RUN        apk add --no-cache ca-certificates tzdata $EXTRA_PACKAGES
 # Expose TARGETOS and TARGETARCH variables. These are supported by Docker when using BuildKit, but must be "enabled" using ARG.