Merge remote-tracking branch 'origin/main' into davidgrant/bb-obs

grafana · Oct 16, 2024 · 5a98e1d · 5a98e1d
2 parents 1fd4bb7 + e1d5ba0
commit 5a98e1d
Show file tree

Hide file tree

Showing 190 changed files with 23,536 additions and 14,181 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,7 +13,7 @@
   * `cortex_alertmanager_state_replication_failed_total`
   * `cortex_alertmanager_alerts`
   * `cortex_alertmanager_silences`
-* [FEATURE] Querier: add experimental streaming PromQL engine, enabled with `-querier.query-engine=mimir`. #9367 #9368 #9398 #9399 #9403 #9417 #9418 #9419 #9420 #9482 #9504 #9505 #9507 #9518 #9531 #9532 #9533 #9553 #9558 #9588 #9589
+* [FEATURE] Querier: add experimental streaming PromQL engine, enabled with `-querier.query-engine=mimir`. #9367 #9368 #9398 #9399 #9403 #9417 #9418 #9419 #9420 #9482 #9504 #9505 #9507 #9518 #9531 #9532 #9533 #9553 #9558 #9588 #9589 #9639
 * [FEATURE] Query-frontend: added experimental configuration options `query-frontend.cache-errors` and `query-frontend.results-cache-ttl-for-errors` to allow non-transient responses to be cached. When set to `true` error responses from hitting limits or bad data are cached for a short TTL. #9028
 * [FEATURE] gRPC: Support S2 compression. #9322
   * `-alertmanager.alertmanager-client.grpc-compression=s2`
@@ -28,6 +28,7 @@
 * [FEATURE] Alertmanager: limit added for maximum size of the Grafana configuration (`-alertmanager.max-config-size-bytes`). #9402
 * [FEATURE] Ingester: Experimental support for ingesting out-of-order native histograms. This is disabled by default and can be enabled by setting `-ingester.ooo-native-histograms-ingestion-enabled` to `true`. #7175
 * [FEATURE] Distributor: Added `-api.skip-label-count-validation-header-enabled` option to allow skipping label count validation on the HTTP write path based on `X-Mimir-SkipLabelCountValidation` header being `true` or not. #9576
+* [FEATURE] Ruler: Add experimental support for caching the contents of rule groups. This is disabled by default and can be enabled by setting `-ruler-storage.cache.rule-group-enabled`. #9595
 * [ENHANCEMENT] mimirtool: Adds bearer token support for mimirtool's analyze ruler/prometheus commands. #9587
 * [ENHANCEMENT] Ruler: Support `exclude_alerts` parameter in `<prometheus-http-prefix>/api/v1/rules` endpoint. #9300
 * [ENHANCEMENT] Distributor: add a metric to track tenants who are sending newlines in their label values called `cortex_distributor_label_values_with_newlines_total`. #9400
@@ -68,6 +69,7 @@
 
 ### Query-tee
 
+* [CHANGE] Don't compare responses for cancelled requests. #9640
 * [FEATURE] Added `-proxy.compare-skip-samples-before` to skip samples before the given time when comparing responses. The time can be in RFC3339 format (or) RFC3339 without the timezone and seconds (or) date only. #9515
 
 ### Documentation

diff --git a/cmd/mimir/config-descriptor.json b/cmd/mimir/config-descriptor.json
@@ -13669,6 +13669,17 @@
           "required": false,
           "desc": "",
           "blockEntries": [
+            {
+              "kind": "field",
+              "name": "rule_group_enabled",
+              "required": false,
+              "desc": "Enabling caching of rule group contents if a cache backend is configured.",
+              "fieldValue": null,
+              "fieldDefaultValue": false,
+              "fieldFlag": "ruler-storage.cache.rule-group-enabled",
+              "fieldType": "boolean",
+              "fieldCategory": "experimental"
+            },
             {
               "kind": "field",
               "name": "backend",

diff --git a/cmd/mimir/help-all.txt.tmpl b/cmd/mimir/help-all.txt.tmpl
@@ -2497,6 +2497,8 @@ Usage of ./cmd/mimir/mimir:
     	[deprecated] Username to use when connecting to Redis.
   -ruler-storage.cache.redis.write-timeout duration
     	[deprecated] Client write timeout. (default 3s)
+  -ruler-storage.cache.rule-group-enabled
+    	[experimental] Enabling caching of rule group contents if a cache backend is configured.
   -ruler-storage.filesystem.dir string
     	Local filesystem storage directory. (default "ruler")
   -ruler-storage.gcs.bucket-name string

diff --git a/development/mimir-monolithic-mode/docker-compose.yml b/development/mimir-monolithic-mode/docker-compose.yml
@@ -4,17 +4,17 @@ services:
     image: consul:1.15  # latest tag not supported
     command: [ "agent", "-dev" ,"-client=0.0.0.0", "-log-level=info" ]
     ports:
-      - 8500:8500
+      - 8510:8500
 
   minio:
     image: minio/minio
-    command: [ "server", "--console-address", ":9001", "/data" ]
+    command: [ "server", "--console-address", ":9101", "/data" ]
     environment:
       - MINIO_ROOT_USER=mimir
       - MINIO_ROOT_PASSWORD=supersecret
     ports:
-      - 9000:9000
-      - 9001:9001
+      - 9100:9100
+      - 9101:9101
     volumes:
       - .data-minio:/data:delegated
 
@@ -26,7 +26,7 @@ services:
     volumes:
       - ./config:/etc/prometheus
     ports:
-      - 9090:9090
+      - 9190:9090
 
   grafana:
     environment:
@@ -48,7 +48,7 @@ services:
     volumes:
       - ./config:/etc/agent-config
     ports:
-      - 9091:9091
+      - 9191:9091
 
   grafana-alloy:
     profiles:
@@ -63,15 +63,15 @@ services:
   jaeger:
     image: jaegertracing/all-in-one
     ports:
-      - 16686:16686
+      - 16681:16686
       - "14268"
 
   mimir-1:
     build:
       context:    .
       dockerfile: dev.dockerfile
     image: mimir
-    command: ["sh", "-c", "sleep 3 && exec ./mimir -config.file=./config/mimir.yaml -target=all -server.http-listen-port=8001 -server.grpc-listen-port=9001"]
+    command: ["sh", "-c", "sleep 3 && exec ./mimir -config.file=./config/mimir.yaml -target=all -server.http-listen-port=8001 -server.grpc-listen-port=9101"]
     depends_on:
       - consul
       - minio
@@ -83,7 +83,7 @@ services:
       - JAEGER_SAMPLER_PARAM=1
       - JAEGER_REPORTER_MAX_QUEUE_SIZE=1000
     ports:
-      - 8001:8001
+      - 8101:8001
     volumes:
       - ./config:/mimir/config
       - .data-mimir-1:/data:delegated
@@ -105,7 +105,7 @@ services:
       - JAEGER_SAMPLER_PARAM=1
       - JAEGER_REPORTER_MAX_QUEUE_SIZE=1000
     ports:
-      - 8002:8002
+      - 8102:8002
     volumes:
       - ./config:/mimir/config
       - .data-mimir-2:/data:delegated

diff --git a/development/mimir-read-write-mode/docker-compose.jsonnet b/development/mimir-read-write-mode/docker-compose.jsonnet
@@ -71,19 +71,19 @@ std.manifestYamlDoc({
         'QUERY_FRONTEND_HOST=mimir-read-1:8080',
         'COMPACTOR_HOST=mimir-backend-1:8080',
       ],
-      ports: ['8080:8080'],
+      ports: ['8780:8080'],
       volumes: ['../common/config:/etc/nginx/templates'],
     },
   },
 
   minio:: {
     minio: {
       image: 'minio/minio',
-      command: ['server', '--console-address', ':9001', '/data'],
+      command: ['server', '--console-address', ':9701', '/data'],
       environment: ['MINIO_ROOT_USER=mimir', 'MINIO_ROOT_PASSWORD=supersecret'],
       ports: [
-        '9000:9000',
-        '9001:9001',
+        '9700:9700',
+        '9701:9701',
       ],
       volumes: ['.data-minio:/data:delegated'],
     },
@@ -116,7 +116,7 @@ std.manifestYamlDoc({
       image: 'grafana/agent:v0.37.3',
       command: ['-config.file=/etc/agent-config/grafana-agent.yaml', '-metrics.wal-directory=/tmp', '-server.http.address=127.0.0.1:9091'],
       volumes: ['./config:/etc/agent-config'],
-      ports: ['9091:9091'],
+      ports: ['9791:9091'],
     },
   },
 
@@ -131,7 +131,7 @@ std.manifestYamlDoc({
       volumes: [
         './config:/etc/prometheus',
       ],
-      ports: ['9090:9090'],
+      ports: ['9790:9090'],
     },
   },
 
@@ -168,7 +168,7 @@ std.manifestYamlDoc({
     ],
     hostname: options.name,
     // Only publish HTTP port, but not gRPC one.
-    ports: ['%d:8080' % options.publishedHttpPort],
+    ports: ['%d:8080' % (options.publishedHttpPort + 700)],
     depends_on: options.dependsOn,
     volumes: ['./config:/mimir/config', './activity:/activity'] + options.extraVolumes,
   },

diff --git a/development/mimir-read-write-mode/docker-compose.yml b/development/mimir-read-write-mode/docker-compose.yml
@@ -15,7 +15,7 @@
       - "-server.http.address=127.0.0.1:9091"
     "image": "grafana/agent:v0.37.3"
     "ports":
-      - "9091:9091"
+      - "9791:9091"
     "volumes":
       - "./config:/etc/agent-config"
   "memcached":
@@ -35,7 +35,7 @@
     "hostname": "mimir-backend-1"
     "image": "mimir"
     "ports":
-      - "8006:8080"
+      - "8706:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -54,7 +54,7 @@
     "hostname": "mimir-backend-2"
     "image": "mimir"
     "ports":
-      - "8007:8080"
+      - "8707:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -73,7 +73,7 @@
     "hostname": "mimir-read-1"
     "image": "mimir"
     "ports":
-      - "8004:8080"
+      - "8704:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -92,7 +92,7 @@
     "hostname": "mimir-read-2"
     "image": "mimir"
     "ports":
-      - "8005:8080"
+      - "8705:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -111,7 +111,7 @@
     "hostname": "mimir-write-1"
     "image": "mimir"
     "ports":
-      - "8001:8080"
+      - "8701:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -131,7 +131,7 @@
     "hostname": "mimir-write-2"
     "image": "mimir"
     "ports":
-      - "8002:8080"
+      - "8702:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -151,7 +151,7 @@
     "hostname": "mimir-write-3"
     "image": "mimir"
     "ports":
-      - "8003:8080"
+      - "8703:8080"
     "volumes":
       - "./config:/mimir/config"
       - "./activity:/activity"
@@ -160,15 +160,15 @@
     "command":
       - "server"
       - "--console-address"
-      - ":9001"
+      - ":9701"
       - "/data"
     "environment":
       - "MINIO_ROOT_USER=mimir"
       - "MINIO_ROOT_PASSWORD=supersecret"
     "image": "minio/minio"
     "ports":
-      - "9000:9000"
-      - "9001:9001"
+      - "9700:9700"
+      - "9701:9701"
     "volumes":
       - ".data-minio:/data:delegated"
   "nginx":
@@ -182,7 +182,7 @@
     "hostname": "nginx"
     "image": "nginxinc/nginx-unprivileged:1.22-alpine"
     "ports":
-      - "8080:8080"
+      - "8780:8080"
     "volumes":
       - "../common/config:/etc/nginx/templates"
   "prometheus":
@@ -192,6 +192,6 @@
       - "--enable-feature=native-histograms"
     "image": "prom/prometheus:v2.53.0"
     "ports":
-      - "9090:9090"
+      - "9790:9090"
     "volumes":
       - "./config:/etc/prometheus"
diff --git a/docs/sources/mimir/configure/about-versioning.md b/docs/sources/mimir/configure/about-versioning.md
@@ -71,6 +71,8 @@ The following features are currently experimental:
   - Allow control over rule sync intervals.
     - `ruler.outbound-sync-queue-poll-interval`
     - `ruler.inbound-sync-queue-poll-interval`
+  - Cache rule group contents.
+    - `-ruler-storage.cache.rule-group-enabled`
 - Distributor
   - Metrics relabeling
     - `-distributor.metric-relabeling-enabled`

diff --git a/docs/sources/mimir/configure/configuration-parameters/index.md b/docs/sources/mimir/configure/configuration-parameters/index.md
@@ -2166,6 +2166,11 @@ local:
   [directory: <string> | default = ""]
 
 cache:
+  # (experimental) Enabling caching of rule group contents if a cache backend is
+  # configured.
+  # CLI flag: -ruler-storage.cache.rule-group-enabled
+  [rule_group_enabled: <boolean> | default = false]
+
   # Backend for ruler storage cache, if not empty. The cache is supported for
   # any storage backend except "local". Supported values: memcached, redis.
   # CLI flag: -ruler-storage.cache.backend

diff --git a/docs/sources/mimir/manage/mimir-runbooks/_index.md b/docs/sources/mimir/manage/mimir-runbooks/_index.md
@@ -936,7 +936,7 @@ How to **investigate**:
 
 - Check the number of endpoints matching the `gossip-ring` service:
   ```
-  kubectl --namespace <namespace> get endpoints gossip-ring
+  kubectl --namespace <namespace> get endpoints gossip-ring -ojson | jq '.subsets[].addresses | length'
   ```
 - If the number of endpoints is 1000 then it means you reached the Kubernetes limit, the endpoints get truncated and
   you could be hit by [this bug](https://github.com/kubernetes/kubernetes/issues/127370). Having more than 1000 pods

diff --git a/go.mod b/go.mod
@@ -34,7 +34,7 @@ require (
 	github.com/opentracing/opentracing-go v1.2.1-0.20220228012449-10b1cf09e00b
 	github.com/pkg/errors v0.9.1
 	github.com/prometheus/alertmanager v0.27.0
-	github.com/prometheus/client_golang v1.20.4
+	github.com/prometheus/client_golang v1.20.5
 	github.com/prometheus/client_model v0.6.1
 	github.com/prometheus/common v0.59.1
 	github.com/prometheus/prometheus v1.99.0
@@ -73,7 +73,7 @@ require (
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822
 	github.com/okzk/sdnotify v0.0.0-20240725214427-1c1fdd37c5ac
 	github.com/prometheus/procfs v0.15.1
-	github.com/shirou/gopsutil/v4 v4.24.8
+	github.com/shirou/gopsutil/v4 v4.24.9
 	github.com/thanos-io/objstore v0.0.0-20241010161353-f90c89a0ef90
 	github.com/twmb/franz-go v1.17.1
 	github.com/twmb/franz-go/pkg/kadm v1.13.0
@@ -89,7 +89,7 @@ require (
 	golang.org/x/exp v0.0.0-20241009180824-f66d83c29e7c
 	golang.org/x/term v0.25.0
 	google.golang.org/api v0.196.0
-	google.golang.org/protobuf v1.34.2
+	google.golang.org/protobuf v1.35.1
 	sigs.k8s.io/kustomize/kyaml v0.16.0
 )
 
@@ -105,6 +105,7 @@ require (
 	github.com/Masterminds/sprig/v3 v3.2.1 // indirect
 	github.com/at-wat/mqtt-go v0.19.4 // indirect
 	github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3 // indirect
+	github.com/ebitengine/purego v0.8.0 // indirect
 	github.com/go-ini/ini v1.67.0 // indirect
 	github.com/go-jose/go-jose/v4 v4.0.1 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect
@@ -127,7 +128,6 @@ require (
 	github.com/pires/go-proxyproto v0.7.0 // indirect
 	github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c // indirect
 	github.com/ryanuber/go-glob v1.0.0 // indirect
-	github.com/shoenig/go-m1cpu v0.1.6 // indirect
 	github.com/shopspring/decimal v1.2.0 // indirect
 	github.com/spf13/cast v1.5.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
@@ -226,7 +226,7 @@ require (
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
 	github.com/julienschmidt/httprouter v1.3.0 // indirect
-	github.com/klauspost/compress v1.17.10
+	github.com/klauspost/compress v1.17.11
 	github.com/klauspost/cpuid/v2 v2.2.8 // indirect
 	github.com/kylelemons/godebug v1.1.0 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
@@ -275,14 +275,14 @@ require (
 	golang.org/x/tools v0.26.0 // indirect
 	google.golang.org/genproto v0.0.0-20240903143218-8af14fe29dc1 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20240827150818-7e3bb234dfed // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20240930140551-af27646dc61f
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20241015192408-796eee8c2d53
 	k8s.io/kube-openapi v0.0.0-20240228011516-70dd3763d340 // indirect
 	k8s.io/utils v0.0.0-20230726121419-3b25d923346b // indirect
 	sigs.k8s.io/yaml v1.4.0 // indirect
 )
 
 // Using a fork of Prometheus with Mimir-specific changes.
-replace github.com/prometheus/prometheus => github.com/grafana/mimir-prometheus v0.0.0-20241015102654-eaa7eae2d877
+replace github.com/prometheus/prometheus => github.com/grafana/mimir-prometheus v0.0.0-20241016140351-5e9a771537ba
 
 // Replace memberlist with our fork which includes some fixes that haven't been
 // merged upstream yet: