Merge branch 'main' into kavirajk/sane-init-config-packaging

.github/workflows/checks.yml

@@ -0,0 +1,20 @@
+name: Checks
+on: [push]
+jobs:
+  checks:
+    runs-on: ubuntu-latest
+    env:
+      BUILD_IN_CONTAINER: false 
+    container:
+      image: grafana/loki-build-image:0.32.0
+    steps:
+      - uses: actions/checkout@v4
+      - run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+      - run: make lint
+      - run: make check-doc
+      - run: make check-mod
+      - run: make validate-example-configs
+      - run: make check-example-config-doc
+      - run: make check-drone-drift
+      - run: make check-generated-files
+      - run: make test

CHANGELOG.md

@@ -6,7 +6,8 @@
 
 ##### Enhancements
 
-* [11363](https://github.com/grafana/loki/pull/11477) **MichelHollands**: support GET for /ingester/shutdown
+* [11571](https://github.com/grafana/loki/pull/11571) **MichelHollands**: Add a metrics.go log line for requests from querier to ingester 
+* [11477](https://github.com/grafana/loki/pull/11477) **MichelHollands**: support GET for /ingester/shutdown
 * [11363](https://github.com/grafana/loki/pull/11363) **kavirajk**: bugfix(memcached): Make memcached batch fetch truely context aware.
 * [11319](https://github.com/grafana/loki/pull/11319) **someStrangerFromTheAbyss**: Helm: Add extraContainers to the write pods.
 * [11243](https://github.com/grafana/loki/pull/11243) **kavirajk**: Inflight-logging: Add extra metadata to inflight requests logging.
@@ -42,10 +43,17 @@
 * [10956](https://github.com/grafana/loki/pull/10956) **jeschkies** do not wrap requests but send pure Protobuf from frontend v2 via scheduler to querier when `-frontend.encoding=protobuf`.
 * [10417](https://github.com/grafana/loki/pull/10417) **jeschkies** shard `quantile_over_time` range queries using probabilistic data structures.
 * [11284](https://github.com/grafana/loki/pull/11284) **ashwanthgoli** Config: Adds `frontend.max-query-capacity` to tune per-tenant query capacity.
+* [11539](https://github.com/grafana/loki/pull/11539) **kaviraj,ashwanthgoli** Support caching /series and /labels query results
+* [11545](https://github.com/grafana/loki/pull/11545) **dannykopping** Force correct memcached timeout when fetching chunks.
+* [11589](https://github.com/grafana/loki/pull/11589) **ashwanthgoli** Results Cache: Adds `query_length_served` cache stat to measure the length of the query served from cache.
 
 ##### Fixes
 * [11074](https://github.com/grafana/loki/pull/11074) **hainenber** Fix panic in lambda-promtail due to mishandling of empty DROP_LABELS env var.
 * [11195](https://github.com/grafana/loki/pull/11195) **canuteson** Generate tsdb_shipper storage_config even if using_boltdb_shipper is false
+* [9831](https://github.com/grafana/loki/pull/9831) **sijmenhuizenga**: Fix Promtail excludepath not evaluated on newly added files.
+* [11551](https://github.com/grafana/loki/pull/11551) **dannykopping** Do not reflect label names in request metrics' "route" label.
+* [11601](https://github.com/grafana/loki/pull/11601) **dannykopping** Ruler: Fixed a panic that can be caused by concurrent read-write access of tenant configs when there are a large amount of rules.
+* [11606](https://github.com/grafana/loki/pull/11606) **dannykopping** Fixed regression adding newlines to HTTP error response bodies which may break client integrations.
 
 ##### Changes
 
@@ -72,6 +80,7 @@
 
 * [10677](https://github.com/grafana/loki/pull/10677) **chaudum** Remove deprecated `stream_lag_labels` setting from both the `options` and `client` configuration sections.
 * [10689](https://github.com/grafana/loki/pull/10689) **dylanguedes**: Ingester: Make jitter to be 20% of flush check period instead of 1%.
+* [11420](https://github.com/grafana/loki/pull/11420) **zry98**: Show a clearer reason in "disable watchConfig" log message when server is disabled.
 
 ##### Fixes
 

clients/pkg/promtail/promtail.go

@@ -255,25 +255,29 @@ func (p *Promtail) watchConfig() {
 		level.Warn(p.logger).Log("msg", "disable watchConfig", "reason", "Promtail newConfig func is Empty")
 		return
 	}
-	promtailServer, ok := p.server.(*server.PromtailServer)
-	if !ok {
-		level.Warn(p.logger).Log("msg", "disable watchConfig", "reason", "promtailServer cast fail")
+	switch srv := p.server.(type) {
+	case *server.NoopServer:
+		level.Warn(p.logger).Log("msg", "disable watchConfig", "reason", "Promtail server is disabled")
 		return
-	}
-	level.Warn(p.logger).Log("msg", "enable watchConfig")
-	hup := make(chan os.Signal, 1)
-	signal.Notify(hup, syscall.SIGHUP)
-	for {
-		select {
-		case <-hup:
-			_ = p.reload()
-		case rc := <-promtailServer.Reload():
-			if err := p.reload(); err != nil {
-				rc <- err
-			} else {
-				rc <- nil
+	case *server.PromtailServer:
+		level.Warn(p.logger).Log("msg", "enable watchConfig")
+		hup := make(chan os.Signal, 1)
+		signal.Notify(hup, syscall.SIGHUP)
+		for {
+			select {
+			case <-hup:
+				_ = p.reload()
+			case rc := <-srv.Reload():
+				if err := p.reload(); err != nil {
+					rc <- err
+				} else {
+					rc <- nil
+				}
 			}
 		}
+	default:
+		level.Warn(p.logger).Log("msg", "disable watchConfig", "reason", "Unknown Promtail server type")
+		return
 	}
 }
 

clients/pkg/promtail/server/server.go

@@ -321,25 +321,25 @@ func computeExternalURL(u string, port int) (*url.URL, error) {
 	return eu, nil
 }
 
-type noopServer struct {
+type NoopServer struct {
 	log  log.Logger
 	sigs chan os.Signal
 }
 
-func newNoopServer(log log.Logger) *noopServer {
-	return &noopServer{
+func newNoopServer(log log.Logger) *NoopServer {
+	return &NoopServer{
 		log:  log,
 		sigs: make(chan os.Signal, 1),
 	}
 }
 
-func (s *noopServer) Run() error {
+func (s *NoopServer) Run() error {
 	signal.Notify(s.sigs, syscall.SIGINT, syscall.SIGTERM)
 	sig := <-s.sigs
 	level.Info(s.log).Log("msg", "received shutdown signal", "sig", sig)
 	return nil
 }
 
-func (s *noopServer) Shutdown() {
+func (s *NoopServer) Shutdown() {
 	s.sigs <- syscall.SIGTERM
 }

clients/pkg/promtail/targets/file/filetarget.go

@@ -350,6 +350,20 @@ func (t *FileTarget) startTailing(ps []string) {
 			continue
 		}
 
+		if t.pathExclude != "" {
+			matched, err := doublestar.Match(t.pathExclude, p)
+			if err != nil {
+				level.Error(t.logger).Log("msg", "ignoring file, exclude pattern match failed", "error", err, "filename", p, "pathExclude", t.pathExclude)
+				t.metrics.totalBytes.DeleteLabelValues(p)
+				continue
+			}
+			if matched {
+				level.Info(t.logger).Log("msg", "ignoring file", "error", "file matches exclude pattern", "filename", p, "pathExclude", t.pathExclude)
+				t.metrics.totalBytes.DeleteLabelValues(p)
+				continue
+			}
+		}
+
 		var reader Reader
 		if t.decompressCfg != nil && t.decompressCfg.Enabled {
 			level.Debug(t.logger).Log("msg", "reading from compressed file", "filename", p)

clients/pkg/promtail/targets/file/filetarget_test.go

@@ -475,6 +475,7 @@ func TestHandleFileCreationEvent(t *testing.T) {
 	positionsFileName := filepath.Join(dirName, "positions.yml")
 	logDir := filepath.Join(dirName, "log")
 	logFile := filepath.Join(logDir, "test1.log")
+	logFileIgnored := filepath.Join(logDir, "test.donot.log")
 
 	if err := os.MkdirAll(logDir, 0750); err != nil {
 		t.Fatal(err)
@@ -511,7 +512,8 @@ func TestHandleFileCreationEvent(t *testing.T) {
 		}
 	}()
 
-	target, err := NewFileTarget(metrics, logger, client, ps, path, "", nil, nil, &Config{
+	pathExclude := "**/*.donot.log"
+	target, err := NewFileTarget(metrics, logger, client, ps, path, pathExclude, nil, nil, &Config{
 		// To handle file creation event from channel, set enough long time as sync period
 		SyncPeriod: 10 * time.Minute,
 	}, DefaultWatchConig, fakeFileHandler, fakeTargetHandler, "", nil)
@@ -523,10 +525,18 @@ func TestHandleFileCreationEvent(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
+	_, err = os.Create(logFileIgnored)
+	if err != nil {
+		t.Fatal(err)
+	}
 	fakeFileHandler <- fsnotify.Event{
 		Name: logFile,
 		Op:   fsnotify.Create,
 	}
+	fakeFileHandler <- fsnotify.Event{
+		Name: logFileIgnored,
+		Op:   fsnotify.Create,
+	}
 	requireEventually(t, func() bool {
 		return len(target.readers) == 1
 	}, "Expected tails to be 1 at this point in the test...")

cmd/loki/loki-local-with-memcached.yaml

@@ -0,0 +1,87 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+  grpc_listen_port: 9096
+
+common:
+  instance_addr: 127.0.0.1
+  path_prefix: /tmp/loki
+  storage:
+    filesystem:
+      chunks_directory: /tmp/loki/chunks
+      rules_directory: /tmp/loki/rules
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+query_range:
+  align_queries_with_step: true
+  cache_index_stats_results: true
+  cache_results: true
+  cache_volume_results: true
+  cache_series_results: true
+  series_results_cache:
+    cache:
+      default_validity: 12h
+      memcached_client:
+        consistent_hash: true
+        addresses: "dns+localhost:11211"
+        max_idle_conns: 16
+        timeout: 500ms
+        update_interval: 1m
+  index_stats_results_cache:
+    cache:
+      default_validity: 12h
+      memcached_client:
+        consistent_hash: true
+        addresses: "dns+localhost:11211"
+        max_idle_conns: 16
+        timeout: 500ms
+        update_interval: 1m
+  max_retries: 5
+  results_cache:
+    cache:
+      default_validity: 12h
+      memcached_client:
+        consistent_hash: true
+        addresses: "dns+localhost:11211"
+        max_idle_conns: 16
+        timeout: 500ms
+        update_interval: 1m
+  volume_results_cache:
+    cache:
+      default_validity: 12h
+      memcached_client:
+        consistent_hash: true
+        addresses: "dns+localhost:11211"
+        max_idle_conns: 16
+        timeout: 500ms
+        update_interval: 1m
+
+schema_config:
+  configs:
+    - from: 2020-10-24
+      store: tsdb
+      object_store: filesystem
+      schema: v12
+      index:
+        prefix: index_
+        period: 24h
+
+ruler:
+  alertmanager_url: http://localhost:9093
+
+# By default, Loki will send anonymous, but uniquely-identifiable usage and configuration
+# analytics to Grafana Labs. These statistics are sent to https://stats.grafana.org/
+#
+# Statistics help us better understand how Loki is used, and they show us performance
+# levels for most users. This helps us prioritize features and documentation.
+# For more information on what's sent, look at
+# https://github.com/grafana/loki/blob/main/pkg/analytics/stats.go
+# Refer to the buildReport method to see what goes into a report.
+#
+# If you would like to disable reporting, uncomment the following lines:
+#analytics:
+#  reporting_enabled: false

cmd/migrate/main.go

@@ -309,8 +309,7 @@ func (m *chunkMover) moveChunks(ctx context.Context, threadID int, syncRangeCh <
 			start := time.Now()
 			var totalBytes uint64
 			var totalChunks uint64
-			//log.Printf("%d processing sync range %d - Start: %v, End: %v\n", threadID, sr.number, time.Unix(0, sr.from).UTC(), time.Unix(0, sr.to).UTC())
-			schemaGroups, fetchers, err := m.source.GetChunks(m.ctx, m.sourceUser, model.TimeFromUnixNano(sr.from), model.TimeFromUnixNano(sr.to), m.matchers...)
+			schemaGroups, fetchers, err := m.source.GetChunks(m.ctx, m.sourceUser, model.TimeFromUnixNano(sr.from), model.TimeFromUnixNano(sr.to), chunk.NewPredicate(m.matchers, nil))
 			if err != nil {
 				log.Println(threadID, "Error querying index for chunk refs:", err)
 				errCh <- err

docs/sources/configure/_index.md

@@ -880,6 +880,40 @@ volume_results_cache:
   # compression. Supported values are: 'snappy' and ''.
   # CLI flag: -frontend.volume-results-cache.compression
   [compression: <string> | default = ""]
+
+# Cache series query results.
+# CLI flag: -querier.cache-series-results
+[cache_series_results: <boolean> | default = false]
+
+# If series_results_cache is not configured and cache_series_results is true,
+# the config for the results cache is used.
+series_results_cache:
+  # The cache block configures the cache backend.
+  # The CLI flags prefix for this block configuration is:
+  # frontend.series-results-cache
+  [cache: <cache_config>]
+
+  # Use compression in cache. The default is an empty value '', which disables
+  # compression. Supported values are: 'snappy' and ''.
+  # CLI flag: -frontend.series-results-cache.compression
+  [compression: <string> | default = ""]
+
+# Cache label query results.
+# CLI flag: -querier.cache-label-results
+[cache_label_results: <boolean> | default = false]
+
+# If label_results_cache is not configured and cache_label_results is true, the
+# config for the results cache is used.
+label_results_cache:
+  # The cache block configures the cache backend.
+  # The CLI flags prefix for this block configuration is:
+  # frontend.label-results-cache
+  [cache: <cache_config>]
+
+  # Use compression in cache. The default is an empty value '', which disables
+  # compression. Supported values are: 'snappy' and ''.
+  # CLI flag: -frontend.label-results-cache.compression
+  [compression: <string> | default = ""]
 ```
 
 ### ruler
@@ -2844,6 +2878,12 @@ The `limits_config` block configures global and per-tenant limits in Loki.
 # CLI flag: -querier.split-queries-by-interval
 [split_queries_by_interval: <duration> | default = 1h]
 
+# Split metadata queries by a time interval and execute in parallel. The value 0
+# disables splitting metadata queries by time. This also determines how cache
+# keys are chosen when label/series result caching is enabled.
+# CLI flag: -querier.split-metadata-queries-by-interval
+[split_metadata_queries_by_interval: <duration> | default = 1d]
+
 # Limit queries that can be sharded. Queries within the time range of now and
 # now minus this sharding lookback are not sharded. The default value of 0s
 # disables the lookback, causing sharding of all queries at all times.
@@ -3044,13 +3084,6 @@ shard_streams:
 # CLI flag: -bloom-compactor.max-table-age
 [bloom_compactor_max_table_age: <duration> | default = 168h]
 
-# The minimum age of a table before it is compacted. Do not compact tables newer
-# than the the configured time. Default to 1 hour. 0s means no limit. This is
-# useful to avoid compacting tables that will be updated with out-of-order
-# writes.
-# CLI flag: -bloom-compactor.min-table-age
-[bloom_compactor_min_table_age: <duration> | default = 1h]
-
 # Whether to compact chunks into bloom filters.
 # CLI flag: -bloom-compactor.enable-compaction
 [bloom_compactor_enable_compaction: <boolean> | default = false]
@@ -4283,6 +4316,8 @@ The cache block configures the cache backend. The supported CLI flags `<prefix>`
 - `bloom-gateway-client.cache`
 - `frontend`
 - `frontend.index-stats-results-cache`
+- `frontend.label-results-cache`
+- `frontend.series-results-cache`
 - `frontend.volume-results-cache`
 - `store.chunks-cache`
 - `store.index-cache-read`

docs/sources/configure/bp-configure.md

@@ -1,7 +1,7 @@
 ---
 title: Configuration best practices
 menuTitle:  Best practices
-description: Grafana Loki configuration best practices
+description: Describes configuration best practices for Grafana Loki.
 weight:  100
 ---
 # Configuration best practices

docs/sources/get-started/_index.md

@@ -2,7 +2,7 @@
 title: Get started with Grafana Loki
 menuTitle: Get started
 weight: 200
-description: Overview of the steps for getting started using Loki to collect logs.
+description: Provides an overview of the steps for implementing Grafana Loki to collect and view logs.
 ---
 
 # Get started with Grafana Loki

docs/sources/get-started/architecture.md

@@ -1,7 +1,7 @@
 ---
 title: Loki architecture
 menutitle: Architecture
-description: Grafana Loki's architecture.
+description: Describes Grafana Loki's architecture.
 weight: 300
 aliases:
     - ../architecture/