store-gateway: introduce more postings strategies

cmd/mimir/config-descriptor.json

@@ -7211,6 +7211,27 @@
               "fieldFlag": "blocks-storage.bucket-store.series-selection-strategy",
               "fieldType": "string",
               "fieldCategory": "experimental"
+            },
+            {
+              "kind": "block",
+              "name": "series_selection_strategies",
+              "required": false,
+              "desc": "",
+              "blockEntries": [
+                {
+                  "kind": "field",
+                  "name": "worst_case_series_preference",
+                  "required": false,
+                  "desc": "This option is only used when blocks-storage.bucket-store.series-selection-strategy=worst-case. Increasing the series preference results in fetching more series than postings. Must be a positive floating point number.",
+                  "fieldValue": null,
+                  "fieldDefaultValue": 1,
+                  "fieldFlag": "blocks-storage.bucket-store.series-selection-strategies.worst-case-series-preference",
+                  "fieldType": "float",
+                  "fieldCategory": "experimental"
+                }
+              ],
+              "fieldValue": null,
+              "fieldDefaultValue": null
             }
           ],
           "fieldValue": null,

cmd/mimir/help-all.txt.tmpl

@@ -611,6 +611,8 @@ Usage of ./cmd/mimir/mimir:
     	Controls what is the ratio of postings offsets that the store will hold in memory. (default 32)
   -blocks-storage.bucket-store.series-hash-cache-max-size-bytes uint
     	Max size - in bytes - of the in-memory series hash cache. The cache is shared across all tenants and it's used only when query sharding is enabled. (default 1073741824)
+  -blocks-storage.bucket-store.series-selection-strategies.worst-case-series-preference float
+    	[experimental] This option is only used when blocks-storage.bucket-store.series-selection-strategy=worst-case. Increasing the series preference results in fetching more series than postings. Must be a positive floating point number. (default 1)
   -blocks-storage.bucket-store.series-selection-strategy string
     	[experimental] This option controls the strategy to selection of series and deferring application of matchers. A more aggressive strategy will fetch less posting lists at the cost of more series. This is useful when querying large blocks in which many series share the same label name and value. Supported values (most aggressive to least aggressive): speculative, worst-case, worst-case-small-posting-lists, all. (default "all")
   -blocks-storage.bucket-store.sync-dir string

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

@@ -3283,6 +3283,14 @@ bucket_store:
   # CLI flag: -blocks-storage.bucket-store.series-selection-strategy
   [series_selection_strategy: <string> | default = "all"]
 
+  series_selection_strategies:
+    # (experimental) This option is only used when
+    # blocks-storage.bucket-store.series-selection-strategy=worst-case.
+    # Increasing the series preference results in fetching more series than
+    # postings. Must be a positive floating point number.
+    # CLI flag: -blocks-storage.bucket-store.series-selection-strategies.worst-case-series-preference
+    [worst_case_series_preference: <float> | default = 1]
+
 tsdb:
   # Directory to store TSDBs (including WAL) in the ingesters. This directory is
   # required to be persisted between restarts.

pkg/storage/tsdb/config.go

@@ -97,9 +97,10 @@ const (
 	maxTSDBOpeningConcurrencyOnStartupFlag    = "blocks-storage.tsdb.max-tsdb-opening-concurrency-on-startup"
 	defaultMaxTSDBOpeningConcurrencyOnStartup = 10
 
-	maxChunksBytesPoolFlag = "blocks-storage.bucket-store.max-chunk-pool-bytes"
-	minBucketSizeBytesFlag = "blocks-storage.bucket-store.chunk-pool-min-bucket-size-bytes"
-	maxBucketSizeBytesFlag = "blocks-storage.bucket-store.chunk-pool-max-bucket-size-bytes"
+	maxChunksBytesPoolFlag      = "blocks-storage.bucket-store.max-chunk-pool-bytes"
+	minBucketSizeBytesFlag      = "blocks-storage.bucket-store.chunk-pool-min-bucket-size-bytes"
+	maxBucketSizeBytesFlag      = "blocks-storage.bucket-store.chunk-pool-max-bucket-size-bytes"
+	seriesSelectionStrategyFlag = "blocks-storage.bucket-store.series-selection-strategy"
 )
 
 // Validation errors
@@ -376,6 +377,9 @@ type BucketStoreConfig struct {
 	StreamingBatchSize          int    `yaml:"streaming_series_batch_size" category:"advanced"`
 	ChunkRangesPerSeries        int    `yaml:"fine_grained_chunks_caching_ranges_per_series" category:"experimental"`
 	SeriesSelectionStrategyName string `yaml:"series_selection_strategy" category:"experimental"`
+	SelectionStrategies         struct {
+		WorstCaseSeriesPreference float64 `yaml:"worst_case_series_preference" category:"experimental"`
+	} `yaml:"series_selection_strategies"`
 }
 
 const (
@@ -420,7 +424,8 @@ func (cfg *BucketStoreConfig) RegisterFlags(f *flag.FlagSet, logger log.Logger)
 	f.Uint64Var(&cfg.PartitionerMaxGapBytes, "blocks-storage.bucket-store.partitioner-max-gap-bytes", DefaultPartitionerMaxGapSize, "Max size - in bytes - of a gap for which the partitioner aggregates together two bucket GET object requests.")
 	f.IntVar(&cfg.StreamingBatchSize, "blocks-storage.bucket-store.batch-series-size", 5000, "This option controls how many series to fetch per batch. The batch size must be greater than 0.")
 	f.IntVar(&cfg.ChunkRangesPerSeries, "blocks-storage.bucket-store.fine-grained-chunks-caching-ranges-per-series", 1, "This option controls into how many ranges the chunks of each series from each block are split. This value is effectively the number of chunks cache items per series per block when -blocks-storage.bucket-store.chunks-cache.fine-grained-chunks-caching-enabled is enabled.")
-	f.StringVar(&cfg.SeriesSelectionStrategyName, "blocks-storage.bucket-store.series-selection-strategy", AllPostingsStrategy, "This option controls the strategy to selection of series and deferring application of matchers. A more aggressive strategy will fetch less posting lists at the cost of more series. This is useful when querying large blocks in which many series share the same label name and value. Supported values (most aggressive to least aggressive): "+strings.Join(validSeriesSelectionStrategies, ", ")+".")
+	f.StringVar(&cfg.SeriesSelectionStrategyName, seriesSelectionStrategyFlag, AllPostingsStrategy, "This option controls the strategy to selection of series and deferring application of matchers. A more aggressive strategy will fetch less posting lists at the cost of more series. This is useful when querying large blocks in which many series share the same label name and value. Supported values (most aggressive to least aggressive): "+strings.Join(validSeriesSelectionStrategies, ", ")+".")
+	f.Float64Var(&cfg.SelectionStrategies.WorstCaseSeriesPreference, "blocks-storage.bucket-store.series-selection-strategies.worst-case-series-preference", 1.0, "This option is only used when "+seriesSelectionStrategyFlag+"="+WorstCasePostingsStrategy+". Increasing the series preference results in fetching more series than postings. Must be a positive floating point number.")
 }
 
 // Validate the config.
@@ -452,6 +457,9 @@ func (cfg *BucketStoreConfig) Validate(logger log.Logger) error {
 	if !util.StringsContain(validSeriesSelectionStrategies, cfg.SeriesSelectionStrategyName) {
 		return errors.New("invalid series-selection-strategy, set one of " + strings.Join(validSeriesSelectionStrategies, ", "))
 	}
+	if cfg.SelectionStrategies.WorstCaseSeriesPreference <= 0 {
+		return errors.New("invalid worst-case series preference; must be positive")
+	}
 	return nil
 }
 

pkg/storegateway/bucket_stores.go

@@ -469,7 +469,7 @@ func (u *BucketStores) getOrCreateStore(userID string) (*BucketStore, error) {
 		u.syncDirForUser(userID),
 		u.cfg.BucketStore.StreamingBatchSize,
 		u.cfg.BucketStore.ChunkRangesPerSeries,
-		selectPostingsStrategy(u.logger, u.cfg.BucketStore.SeriesSelectionStrategyName),
+		selectPostingsStrategy(u.logger, u.cfg.BucketStore.SeriesSelectionStrategyName, u.cfg.BucketStore.SelectionStrategies.WorstCaseSeriesPreference),
 		NewChunksLimiterFactory(func() uint64 {
 			return uint64(u.limits.MaxChunksPerQuery(userID))
 		}),
@@ -496,14 +496,14 @@ func (u *BucketStores) getOrCreateStore(userID string) (*BucketStore, error) {
 	return bs, nil
 }
 
-func selectPostingsStrategy(l log.Logger, name string) postingsSelectionStrategy {
+func selectPostingsStrategy(l log.Logger, name string, worstCaseSeriesPreference float64) postingsSelectionStrategy {
 	switch name {
 	case tsdb.AllPostingsStrategy:
 		return selectAllStrategy{}
 	case tsdb.SpeculativePostingsStrategy:
 		return speculativeFetchedDataStrategy{}
 	case tsdb.WorstCasePostingsStrategy:
-		return worstCaseFetchedDataStrategy{postingListActualSizeFactor: 1.0}
+		return worstCaseFetchedDataStrategy{postingListActualSizeFactor: worstCaseSeriesPreference}
 	case tsdb.WorstCaseSmallPostingListsPostingsStrategy:
 		return worstCaseFetchedDataStrategy{postingListActualSizeFactor: 0.3}
 	default: