Merge branch 'master' into distributor-inflight-client-limit-5xx

Signed-off-by: Anna Tran <[email protected]>

Author: anna-tran

CHANGELOG.md

@@ -33,13 +33,15 @@
 * [ENHANCEMENT] Distributor: Add new `cortex_reduced_resolution_histogram_samples_total` metric to track the number of histogram samples which resolution was reduced. #6182
 * [ENHANCEMENT] StoreGateway: Implement metadata API limit in queryable. #6195
 * [ENHANCEMENT] Ingester: Add matchers to ingester LabelNames() and LabelNamesStream() RPC. #6209
+* [ENHANCEMENT] KV: Add TLS configs to consul. #6374
 * [ENHANCEMENT] Ingester/Store Gateway Clients: Introduce an experimental HealthCheck handler to quickly fail requests directed to unhealthy targets. #6225 #6257
 * [ENHANCEMENT] Upgrade build image and Go version to 1.23.2. #6261 #6262
 * [ENHANCEMENT] Ingester: Introduce a new experimental feature for caching expanded postings on the ingester. #6296
 * [ENHANCEMENT] Querier/Ruler: Expose `store_gateway_consistency_check_max_attempts` for max retries when querying store gateway in consistency check. #6276
 * [ENHANCEMENT] StoreGateway: Add new `cortex_bucket_store_chunk_pool_inuse_bytes` metric to track the usage in chunk pool. #6310
 * [ENHANCEMENT] Distributor: Add new `cortex_distributor_inflight_client_requests` metric to track number of ingester client inflight requests. #6358
 * [ENHANCEMENT] Distributor: Expose `cortex_label_size_bytes` native histogram metric. #6372
+* [ENHANCEMENT] Add new option `-server.grpc_server-num-stream-workers` to configure the number of worker goroutines that should be used to process incoming streams. #6386
 * [ENHANCEMENT] Distributor: Return HTTP 5XX instead of HTTP 4XX when instance limits are hit. #6358
 * [BUGFIX] Runtime-config: Handle absolute file paths when working directory is not / #6224
 * [BUGFIX] Ruler: Allow rule evaluation to complete during shutdown. #6326

docs/configuration/config-file-reference.md

@@ -2445,7 +2445,7 @@ The `consul_config` configures the consul client. The supported CLI flags `<pref
 # CLI flag: -<prefix>.consul.acl-token
 [acl_token: <string> | default = ""]
 
-# HTTP timeout when talking to Consul
+# HTTP timeout when talking to Consul.
 # CLI flag: -<prefix>.consul.client-timeout
 [http_client_timeout: <duration> | default = 20s]
 
@@ -2461,6 +2461,33 @@ The `consul_config` configures the consul client. The supported CLI flags `<pref
 # Burst size used in rate limit. Values less than 1 are treated as 1.
 # CLI flag: -<prefix>.consul.watch-burst-size
 [watch_burst_size: <int> | default = 1]
+
+# Enable TLS.
+# CLI flag: -<prefix>.consul.tls-enabled
+[tls_enabled: <boolean> | default = false]
+
+# Path to the client certificate file, which will be used for authenticating
+# with the server. Also requires the key path to be configured.
+# CLI flag: -<prefix>.consul.tls-cert-path
+[tls_cert_path: <string> | default = ""]
+
+# Path to the key file for the client certificate. Also requires the client
+# certificate to be configured.
+# CLI flag: -<prefix>.consul.tls-key-path
+[tls_key_path: <string> | default = ""]
+
+# Path to the CA certificates file to validate server certificate against. If
+# not set, the host's root CA certificates are used.
+# CLI flag: -<prefix>.consul.tls-ca-path
+[tls_ca_path: <string> | default = ""]
+
+# Override the expected name on the server certificate.
+# CLI flag: -<prefix>.consul.tls-server-name
+[tls_server_name: <string> | default = ""]
+
+# Skip validating server certificate.
+# CLI flag: -<prefix>.consul.tls-insecure-skip-verify
+[tls_insecure_skip_verify: <boolean> | default = false]
 ```
 
 ### `distributor_config`
@@ -5390,6 +5417,12 @@ grpc_tls_config:
 # CLI flag: -server.grpc-max-concurrent-streams
 [grpc_server_max_concurrent_streams: <int> | default = 100]
 
+# Number of worker goroutines that should be used to process incoming
+# streams.Setting this 0 (default) will disable workers and spawn a new
+# goroutine for each stream.
+# CLI flag: -server.grpc_server-num-stream-workers
+[grpc_server_num_stream_workers: <int> | default = 0]
+
 # The duration after which an idle connection should be closed. Default:
 # infinity
 # CLI flag: -server.grpc.keepalive.max-connection-idle

go.mod

@@ -51,9 +51,9 @@ require (
 	github.com/sony/gobreaker v1.0.0
 	github.com/spf13/afero v1.11.0
 	github.com/stretchr/testify v1.10.0
-	github.com/thanos-io/objstore v0.0.0-20241028150459-cfdd0e50390d
-	github.com/thanos-io/promql-engine v0.0.0-20240921092401-37747eddbd31
-	github.com/thanos-io/thanos v0.35.2-0.20241118113652-f998fc59c171
+	github.com/thanos-io/objstore v0.0.0-20241111205755-d1dd89d41f97
+	github.com/thanos-io/promql-engine v0.0.0-20241106100125-097e6e9f425a
+	github.com/thanos-io/thanos v0.37.0
 	github.com/uber/jaeger-client-go v2.30.0+incompatible
 	github.com/weaveworks/common v0.0.0-20230728070032-dd9e68f319d5
 	go.etcd.io/etcd/api/v3 v3.5.17
@@ -80,7 +80,7 @@ require (
 	github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3
 	github.com/cespare/xxhash/v2 v2.3.0
 	github.com/google/go-cmp v0.6.0
-	github.com/sercand/kuberesolver/v4 v4.0.0
+	github.com/sercand/kuberesolver/v5 v5.1.1
 	go.opentelemetry.io/collector/pdata v1.20.0
 	golang.org/x/exp v0.0.0-20240613232115-7f521ea00fb8
 	google.golang.org/protobuf v1.35.2
@@ -246,6 +246,9 @@ require (
 	k8s.io/utils v0.0.0-20240711033017-18e509b52bc8 // indirect
 )
 
+// Using cortex fork of weaveworks/common
+replace github.com/weaveworks/common => github.com/cortexproject/weaveworks-common v0.0.0-20241129212437-96019edf21f1
+
 // Override since git.apache.org is down.  The docs say to fetch from github.
 replace git.apache.org/thrift.git => github.com/apache/thrift v0.0.0-20180902110319-2566ecd5d999
 
@@ -270,8 +273,5 @@ replace github.com/google/gnostic => github.com/googleapis/gnostic v0.6.9
 // https://github.com/thanos-io/thanos/blob/fdeea3917591fc363a329cbe23af37c6fff0b5f0/go.mod#L265
 replace gopkg.in/alecthomas/kingpin.v2 => github.com/alecthomas/kingpin v1.3.8-0.20210301060133-17f40c25f497
 
-// Pin kuberesolver/v5 to support new grpc version. Need to upgrade kuberesolver version on weaveworks/common.
-replace github.com/sercand/kuberesolver/v4 => github.com/sercand/kuberesolver/v5 v5.1.1
-
 // gRPC 1.66 introduced memory pooling which breaks Cortex queries. Pin 1.65.0 until we have a fix.
 replace google.golang.org/grpc => google.golang.org/grpc v1.65.0