operations/mimir: Upstream Jsonnet changes from r334 (#11602)

* dskit: Don't depend on Memcached on startup
* operations/mimir: Set max buffered bytes in the Kafka client used by the ruler

---------

Signed-off-by: Arve Knudsen <[email protected]>
Co-authored-by: Taylor C <[email protected]>

Author: aknuds1

CHANGELOG.md

@@ -13,6 +13,7 @@
 * [CHANGE] Overrides-exporter: Don't export per-tenant overrides that are set to their default values. #11173
 * [CHANGE] gRPC/HTTP clients: Rename metric `cortex_client_request_invalid_cluster_validation_labels_total` to `cortex_client_invalid_cluster_validation_label_requests_total`. #11237
 * [CHANGE] Querier: Use Mimir Query Engine (MQE) by default. Set `-querier.query-engine=prometheus` to continue using Prometheus' engine. #11501
+* [CHANGE] Memcached: Ignore initial DNS resolution failure, meaning don't depend on Memcached on startup. #11602
 * [FEATURE] Distributor: Experimental support for Prometheus Remote-Write 2.0 protocol. Limitations: Created timestamp is ignored, per series metadata is merged on metric family level automatically, ingestion might fail if client sends ProtoBuf fields out of order. The label `version` is added to the metric `cortex_distributor_requests_in_total` with a value of either `1.0` or `2.0` depending on the detected Remote-Write protocol. #11100 #11101 #11192 #11143
 * [FEATURE] Query-frontend: expand `query-frontend.cache-errors` and `query-frontend.results-cache-ttl-for-errors` configuration options to cache non-transient response failures for instant queries. #11120
 * [FEATURE] Querier, query-frontend, ruler: Enable experimental support for duration expressions in PromQL, which are simple arithmetics on numbers in offset and range specification. #11344
@@ -97,6 +98,7 @@
 * [CHANGE] Increase the allowed number of rule groups for small, medium_small, and extra_small user tiers by 20%. #11152
 * [CHANGE] Update rollout-operator version to 0.26.0. #11232
 * [CHANGE] Memcached: Set a timeout of `500ms` for the `ruler-storage` cache instead of the default `200ms`. #11231
+* [CHANGE] Ruler: If ingest storage is enabled, set the maximum buffered bytes in the Kafka client used by the ruler based on the expected maximum rule evaluation response size, clamping it between 1 GB (default) and 4 GB. #11602
 * [FEATURE] Make ingest storage ingester HPA behavior configurable through `_config.ingest_storage_ingester_hpa_behavior`. #11168
 * [FEATURE] Add an alternate ingest storage HPA trigger that targets maximum owned series per pod. #11356
 

cmd/mimir/config-descriptor.json

@@ -7044,7 +7044,7 @@
                   "required": false,
                   "desc": "Allow client creation even if initial DNS resolution fails.",
                   "fieldValue": null,
-                  "fieldDefaultValue": false,
+                  "fieldDefaultValue": true,
                   "fieldFlag": "query-frontend.results-cache.memcached.dns-ignore-startup-failures",
                   "fieldType": "boolean",
                   "fieldCategory": "experimental"
@@ -9249,7 +9249,7 @@
                       "required": false,
                       "desc": "Allow client creation even if initial DNS resolution fails.",
                       "fieldValue": null,
-                      "fieldDefaultValue": false,
+                      "fieldDefaultValue": true,
                       "fieldFlag": "blocks-storage.bucket-store.index-cache.memcached.dns-ignore-startup-failures",
                       "fieldType": "boolean",
                       "fieldCategory": "experimental"
@@ -9812,7 +9812,7 @@
                       "required": false,
                       "desc": "Allow client creation even if initial DNS resolution fails.",
                       "fieldValue": null,
-                      "fieldDefaultValue": false,
+                      "fieldDefaultValue": true,
                       "fieldFlag": "blocks-storage.bucket-store.chunks-cache.memcached.dns-ignore-startup-failures",
                       "fieldType": "boolean",
                       "fieldCategory": "experimental"
@@ -10399,7 +10399,7 @@
                       "required": false,
                       "desc": "Allow client creation even if initial DNS resolution fails.",
                       "fieldValue": null,
-                      "fieldDefaultValue": false,
+                      "fieldDefaultValue": true,
                       "fieldFlag": "blocks-storage.bucket-store.metadata-cache.memcached.dns-ignore-startup-failures",
                       "fieldType": "boolean",
                       "fieldCategory": "experimental"
@@ -15721,7 +15721,7 @@
                   "required": false,
                   "desc": "Allow client creation even if initial DNS resolution fails.",
                   "fieldValue": null,
-                  "fieldDefaultValue": false,
+                  "fieldDefaultValue": true,
                   "fieldFlag": "ruler-storage.cache.memcached.dns-ignore-startup-failures",
                   "fieldType": "boolean",
                   "fieldCategory": "experimental"

cmd/mimir/help-all.txt.tmpl

@@ -448,7 +448,7 @@ Usage of ./cmd/mimir/mimir:
   -blocks-storage.bucket-store.chunks-cache.memcached.connect-timeout duration
     	The connection timeout. (default 200ms)
   -blocks-storage.bucket-store.chunks-cache.memcached.dns-ignore-startup-failures
-    	[experimental] Allow client creation even if initial DNS resolution fails.
+    	[experimental] Allow client creation even if initial DNS resolution fails. (default true)
   -blocks-storage.bucket-store.chunks-cache.memcached.max-async-buffer-size int
     	The maximum number of enqueued asynchronous operations allowed. (default 25000)
   -blocks-storage.bucket-store.chunks-cache.memcached.max-async-concurrency int
@@ -552,7 +552,7 @@ Usage of ./cmd/mimir/mimir:
   -blocks-storage.bucket-store.index-cache.memcached.connect-timeout duration
     	The connection timeout. (default 200ms)
   -blocks-storage.bucket-store.index-cache.memcached.dns-ignore-startup-failures
-    	[experimental] Allow client creation even if initial DNS resolution fails.
+    	[experimental] Allow client creation even if initial DNS resolution fails. (default true)
   -blocks-storage.bucket-store.index-cache.memcached.max-async-buffer-size int
     	The maximum number of enqueued asynchronous operations allowed. (default 25000)
   -blocks-storage.bucket-store.index-cache.memcached.max-async-concurrency int
@@ -674,7 +674,7 @@ Usage of ./cmd/mimir/mimir:
   -blocks-storage.bucket-store.metadata-cache.memcached.connect-timeout duration
     	The connection timeout. (default 200ms)
   -blocks-storage.bucket-store.metadata-cache.memcached.dns-ignore-startup-failures
-    	[experimental] Allow client creation even if initial DNS resolution fails.
+    	[experimental] Allow client creation even if initial DNS resolution fails. (default true)
   -blocks-storage.bucket-store.metadata-cache.memcached.max-async-buffer-size int
     	The maximum number of enqueued asynchronous operations allowed. (default 25000)
   -blocks-storage.bucket-store.metadata-cache.memcached.max-async-concurrency int
@@ -2452,7 +2452,7 @@ Usage of ./cmd/mimir/mimir:
   -query-frontend.results-cache.memcached.connect-timeout duration
     	The connection timeout. (default 200ms)
   -query-frontend.results-cache.memcached.dns-ignore-startup-failures
-    	[experimental] Allow client creation even if initial DNS resolution fails.
+    	[experimental] Allow client creation even if initial DNS resolution fails. (default true)
   -query-frontend.results-cache.memcached.max-async-buffer-size int
     	The maximum number of enqueued asynchronous operations allowed. (default 25000)
   -query-frontend.results-cache.memcached.max-async-concurrency int
@@ -2722,7 +2722,7 @@ Usage of ./cmd/mimir/mimir:
   -ruler-storage.cache.memcached.connect-timeout duration
     	The connection timeout. (default 200ms)
   -ruler-storage.cache.memcached.dns-ignore-startup-failures
-    	[experimental] Allow client creation even if initial DNS resolution fails.
+    	[experimental] Allow client creation even if initial DNS resolution fails. (default true)
   -ruler-storage.cache.memcached.max-async-buffer-size int
     	The maximum number of enqueued asynchronous operations allowed. (default 25000)
   -ruler-storage.cache.memcached.max-async-concurrency int

docs/sources/mimir/configure/configuration-parameters/index.md

@@ -5345,7 +5345,7 @@ The `memcached` block configures the Memcached-based caching backend. The suppor
 
 # (experimental) Allow client creation even if initial DNS resolution fails.
 # CLI flag: -<prefix>.memcached.dns-ignore-startup-failures
-[dns_ignore_startup_failures: <boolean> | default = false]
+[dns_ignore_startup_failures: <boolean> | default = true]
 ```
 
 ### redis

go.mod

@@ -18,7 +18,7 @@ require (
 	github.com/golang/snappy v1.0.0
 	github.com/google/gopacket v1.1.19
 	github.com/gorilla/mux v1.8.1
-	github.com/grafana/dskit v0.0.0-20250529170946-28928403e61e
+	github.com/grafana/dskit v0.0.0-20250604055755-f6c457812872
 	github.com/grafana/e2e v0.1.2-0.20250428181430-708d63bcc673
 	github.com/hashicorp/golang-lru v1.0.2 // indirect
 	github.com/influxdata/influxdb/v2 v2.7.12

go.sum

@@ -559,8 +559,8 @@ github.com/grafana-tools/sdk v0.0.0-20220919052116-6562121319fc h1:PXZQA2WCxe85T
 github.com/grafana-tools/sdk v0.0.0-20220919052116-6562121319fc/go.mod h1:AHHlOEv1+GGQ3ktHMlhuTUwo3zljV3QJbC0+8o2kn+4=
 github.com/grafana/alerting v0.0.0-20250522092815-92adaaa0147a h1:a6D8cpDxLLEgvmudcEFr02R2AoTcVSnmB+35Ows7GGY=
 github.com/grafana/alerting v0.0.0-20250522092815-92adaaa0147a/go.mod h1:pMfhRxL2LZ3Pm8iy7VcVsb9CLYuBtjFYbf1oxgx7yFA=
-github.com/grafana/dskit v0.0.0-20250529170946-28928403e61e h1:xszW9jlqA2Fsz1fXPc3aP494z3lRheGywP1pkFLuxbY=
-github.com/grafana/dskit v0.0.0-20250529170946-28928403e61e/go.mod h1:XgCfkrcj96DEvYCdTVTamQSo4vLTqoXrMZw5kUeWDAQ=
+github.com/grafana/dskit v0.0.0-20250604055755-f6c457812872 h1:XvE3CDRQHRuSxRPS+4cks08U+D4aPIcGsiR4EQxj6U0=
+github.com/grafana/dskit v0.0.0-20250604055755-f6c457812872/go.mod h1:XgCfkrcj96DEvYCdTVTamQSo4vLTqoXrMZw5kUeWDAQ=
 github.com/grafana/e2e v0.1.2-0.20250428181430-708d63bcc673 h1:Va04sDlP33f1SFUHRTho4QJfDlGTz+/HnBIpYwlqV9Q=
 github.com/grafana/e2e v0.1.2-0.20250428181430-708d63bcc673/go.mod h1:JVmqPBe8A/pZWwRoJW5ZjyALeY5OXMzPl7LrVXOdZAI=
 github.com/grafana/goautoneg v0.0.0-20240607115440-f335c04c58ce h1:WI1olbgS+sEl77qxEYbmt9TgRUz7iLqmjh8lYPpGlKQ=

operations/mimir-tests/test-ingest-storage-autoscaling-custom-stabilization-window-generated.yaml

@@ -1289,6 +1289,7 @@ spec:
         - -ingest-storage.ingestion-partition-tenant-shard-size=1
         - -ingest-storage.kafka.address=kafka.default.svc.cluster.local.:9092
         - -ingest-storage.kafka.auto-create-topic-default-partitions=1000
+        - -ingest-storage.kafka.producer-max-buffered-bytes=1073741824
         - -ingest-storage.kafka.topic=ingest
         - -ingester.partition-ring.prefix=
         - -ingester.ring.heartbeat-timeout=10m

operations/mimir-tests/test-ingest-storage-autoscaling-multiple-triggers-generated.yaml

@@ -1289,6 +1289,7 @@ spec:
         - -ingest-storage.ingestion-partition-tenant-shard-size=1
         - -ingest-storage.kafka.address=kafka.default.svc.cluster.local.:9092
         - -ingest-storage.kafka.auto-create-topic-default-partitions=1000
+        - -ingest-storage.kafka.producer-max-buffered-bytes=1073741824
         - -ingest-storage.kafka.topic=ingest
         - -ingester.partition-ring.prefix=
         - -ingester.ring.heartbeat-timeout=10m

operations/mimir-tests/test-ingest-storage-autoscaling-one-trigger-generated.yaml

@@ -1289,6 +1289,7 @@ spec:
         - -ingest-storage.ingestion-partition-tenant-shard-size=1
         - -ingest-storage.kafka.address=kafka.default.svc.cluster.local.:9092
         - -ingest-storage.kafka.auto-create-topic-default-partitions=1000
+        - -ingest-storage.kafka.producer-max-buffered-bytes=1073741824
         - -ingest-storage.kafka.topic=ingest
         - -ingester.partition-ring.prefix=
         - -ingester.ring.heartbeat-timeout=10m

operations/mimir-tests/test-ingest-storage-migration-step-10-generated.yaml

@@ -1266,6 +1266,7 @@ spec:
         - -ingest-storage.ingestion-partition-tenant-shard-size=1
         - -ingest-storage.kafka.address=kafka.default.svc.cluster.local.:9092
         - -ingest-storage.kafka.auto-create-topic-default-partitions=1000
+        - -ingest-storage.kafka.producer-max-buffered-bytes=1073741824
         - -ingest-storage.kafka.topic=ingest
         - -ingester.partition-ring.prefix=
         - -ingester.ring.heartbeat-timeout=10m