sql: add new index_recommendation column

docs/generated/settings/settings-for-tenants.txt

@@ -283,4 +283,4 @@ trace.jaeger.agent	string		the address of a Jaeger agent to receive traces using
 trace.opentelemetry.collector	string		address of an OpenTelemetry trace collector to receive traces using the otel gRPC protocol, as <host>:<port>. If no port is specified, 4317 will be used.
 trace.span_registry.enabled	boolean	true	if set, ongoing traces can be seen at https://<ui>/#/debug/tracez
 trace.zipkin.collector	string		the address of a Zipkin instance to receive traces, as <host>:<port>. If no port is specified, 9411 will be used.
-version	version	22.1-30	set the active cluster version in the format '<major>.<minor>'
+version	version	22.1-32	set the active cluster version in the format '<major>.<minor>'

docs/generated/settings/settings.html

@@ -214,6 +214,6 @@
 <tr><td><code>trace.opentelemetry.collector</code></td><td>string</td><td><code></code></td><td>address of an OpenTelemetry trace collector to receive traces using the otel gRPC protocol, as <host>:<port>. If no port is specified, 4317 will be used.</td></tr>
 <tr><td><code>trace.span_registry.enabled</code></td><td>boolean</td><td><code>true</code></td><td>if set, ongoing traces can be seen at https://<ui>/#/debug/tracez</td></tr>
 <tr><td><code>trace.zipkin.collector</code></td><td>string</td><td><code></code></td><td>the address of a Zipkin instance to receive traces, as <host>:<port>. If no port is specified, 9411 will be used.</td></tr>
-<tr><td><code>version</code></td><td>version</td><td><code>22.1-30</code></td><td>set the active cluster version in the format '<major>.<minor>'</td></tr>
+<tr><td><code>version</code></td><td>version</td><td><code>22.1-32</code></td><td>set the active cluster version in the format '<major>.<minor>'</td></tr>
 </tbody>
 </table>

pkg/ccl/logictestccl/testdata/logic_test/crdb_internal_tenant

@@ -195,10 +195,10 @@ SELECT * FROM crdb_internal.leases WHERE node_id < 0
 ----
 node_id  table_id  name  parent_id  expiration  deleted
 
-query ITTTTTIIITRRRRRRRRRRRRRRRRRRRRRRRRRRBBTTTT colnames
+query ITTTTTIIITRRRRRRRRRRRRRRRRRRRRRRRRRRBBTTTTT colnames
 SELECT * FROM crdb_internal.node_statement_statistics WHERE node_id < 0
 ----
-node_id  application_name  flags  statement_id  key  anonymized  count  first_attempt_count  max_retries  last_error  rows_avg  rows_var  parse_lat_avg  parse_lat_var  plan_lat_avg  plan_lat_var  run_lat_avg  run_lat_var  service_lat_avg  service_lat_var  overhead_lat_avg  overhead_lat_var  bytes_read_avg  bytes_read_var  rows_read_avg  rows_read_var  network_bytes_avg  network_bytes_var  network_msgs_avg  network_msgs_var  max_mem_usage_avg  max_mem_usage_var  max_disk_usage_avg  max_disk_usage_var  contention_time_avg  contention_time_var  implicit_txn  full_scan  sample_plan  database_name  exec_node_ids  txn_fingerprint_id
+node_id  application_name  flags  statement_id  key  anonymized  count  first_attempt_count  max_retries  last_error  rows_avg  rows_var  parse_lat_avg  parse_lat_var  plan_lat_avg  plan_lat_var  run_lat_avg  run_lat_var  service_lat_avg  service_lat_var  overhead_lat_avg  overhead_lat_var  bytes_read_avg  bytes_read_var  rows_read_avg  rows_read_var  network_bytes_avg  network_bytes_var  network_msgs_avg  network_msgs_var  max_mem_usage_avg  max_mem_usage_var  max_disk_usage_avg  max_disk_usage_var  contention_time_avg  contention_time_var  implicit_txn  full_scan  sample_plan  database_name  exec_node_ids  txn_fingerprint_id index_recommendations
 
 query ITTTIIRRRRRRRRRRRRRRRRRR colnames
 SELECT * FROM crdb_internal.node_transaction_statistics WHERE node_id < 0

pkg/clusterversion/cockroach_versions.go

@@ -331,6 +331,9 @@ const (
 	AlterSystemSQLInstancesAddLocality
 	// SystemExternalConnectionsTable adds system.external_connections table.
 	SystemExternalConnectionsTable
+	// AlterSystemStatementStatisticsAddIndexRecommendations adds an
+	// index_recommendations column to the system.statement_statistics table.
+	AlterSystemStatementStatisticsAddIndexRecommendations
 
 	// *************************************************
 	// Step (1): Add new versions here.
@@ -572,6 +575,10 @@ var versionsSingleton = keyedVersions{
 		Key:     SystemExternalConnectionsTable,
 		Version: roachpb.Version{Major: 22, Minor: 1, Internal: 30},
 	},
+	{
+		Key:     AlterSystemStatementStatisticsAddIndexRecommendations,
+		Version: roachpb.Version{Major: 22, Minor: 1, Internal: 32},
+	},
 
 	// *************************************************
 	// Step (2): Add new versions here.

pkg/roachpb/app_stats.go

@@ -155,6 +155,7 @@ func (s *StatementStatistics) Add(other *StatementStatistics) {
 	s.RowsWritten.Add(other.RowsWritten, s.Count, other.Count)
 	s.Nodes = util.CombineUniqueInt64(s.Nodes, other.Nodes)
 	s.PlanGists = util.CombineUniqueString(s.PlanGists, other.PlanGists)
+	s.IndexRecommendations = util.CombineUniqueString(s.IndexRecommendations, other.IndexRecommendations)
 
 	s.ExecStats.Add(other.ExecStats)
 

pkg/roachpb/app_stats.proto

@@ -104,12 +104,15 @@ message StatementStatistics {
   // Nodes is the ordered list of nodes ids on which the statement was executed.
   repeated int64 nodes = 24;
 
-  // plan_gists is list of a compressed version of plan that can be converted (lossily)
+  // plan_gists is the list of a compressed version of plan that can be converted (lossily)
   // back into a logical plan.
   // Each statement contain only one plan gist, but the same statement fingerprint id
   // can contain more than one value.
   repeated string plan_gists = 26;
 
+  // index_recommendations is the list of index recommendations generated for the statement fingerprint.
+  repeated string index_recommendations = 27;
+
   // Note: be sure to update `sql/app_stats.go` when adding/removing fields here!
 
   reserved 13, 14, 17, 18, 19, 20;

pkg/sql/catalog/systemschema/system.go

@@ -481,6 +481,8 @@ CREATE TABLE system.statement_statistics (
       mod(fnv32(crdb_internal.datums_to_bytes(aggregated_ts, app_name, fingerprint_id, node_id, plan_hash, transaction_fingerprint_id)), 8:::INT8)
     ) STORED,
 
+    index_recommendations STRING[] NOT NULL DEFAULT (array[]::STRING[]),
+
     CONSTRAINT "primary" PRIMARY KEY (aggregated_ts, fingerprint_id, transaction_fingerprint_id, plan_hash, app_name, node_id)
       USING HASH WITH (bucket_count=8),
     INDEX "fingerprint_stats_idx" (fingerprint_id, transaction_fingerprint_id),
@@ -495,7 +497,8 @@ CREATE TABLE system.statement_statistics (
 			agg_interval,
 			metadata,
 			statistics,
-			plan
+			plan,
+			index_recommendations
 		)
 )
 `
@@ -1983,6 +1986,8 @@ var (
 			},
 		))
 
+	defaultIndexRec = "ARRAY[]:::STRING[]"
+
 	// StatementStatisticsTable is the descriptor for the SQL statement stats table.
 	// It stores statistics for statement fingerprints.
 	StatementStatisticsTable = registerSystemTable(
@@ -2009,6 +2014,7 @@ var (
 					ComputeExpr: &sqlStmtHashComputeExpr,
 					Hidden:      true,
 				},
+				{Name: "index_recommendations", ID: 12, Type: types.StringArray, Nullable: false, DefaultExpr: &defaultIndexRec},
 			},
 			[]descpb.ColumnFamilyDescriptor{
 				{
@@ -2017,9 +2023,9 @@ var (
 					ColumnNames: []string{
 						"crdb_internal_aggregated_ts_app_name_fingerprint_id_node_id_plan_hash_transaction_fingerprint_id_shard_8",
 						"aggregated_ts", "fingerprint_id", "transaction_fingerprint_id", "plan_hash", "app_name", "node_id",
-						"agg_interval", "metadata", "statistics", "plan",
+						"agg_interval", "metadata", "statistics", "plan", "index_recommendations",
 					},
-					ColumnIDs:       []descpb.ColumnID{11, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10},
+					ColumnIDs:       []descpb.ColumnID{11, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12},
 					DefaultColumnID: 0,
 				},
 			},

pkg/sql/catalog/systemschema_test/testdata/bootstrap

@@ -306,6 +306,7 @@ CREATE TABLE public.statement_statistics (
 	statistics JSONB NOT NULL,
 	plan JSONB NOT NULL,
 	crdb_internal_aggregated_ts_app_name_fingerprint_id_node_id_plan_hash_transaction_fingerprint_id_shard_8 INT4 NOT VISIBLE NOT NULL AS (mod(fnv32(crdb_internal.datums_to_bytes(aggregated_ts, app_name, fingerprint_id, node_id, plan_hash, transaction_fingerprint_id)), 8:::INT8)) STORED,
+	index_recommendations STRING[] NOT NULL DEFAULT ARRAY[]:::STRING[],
 	CONSTRAINT "primary" PRIMARY KEY (aggregated_ts ASC, fingerprint_id ASC, transaction_fingerprint_id ASC, plan_hash ASC, app_name ASC, node_id ASC) USING HASH WITH (bucket_count=8),
 	INDEX fingerprint_stats_idx (fingerprint_id ASC, transaction_fingerprint_id ASC)
 );

pkg/sql/crdb_internal.go

@@ -1103,7 +1103,8 @@ CREATE TABLE crdb_internal.node_statement_statistics (
   sample_plan         JSONB,
   database_name       STRING NOT NULL,
   exec_node_ids       INT[] NOT NULL,
-  txn_fingerprint_id  STRING
+  txn_fingerprint_id  STRING,
+  index_recommendations STRING[] NOT NULL
 )`,
 	populate: func(ctx context.Context, p *planner, _ catalog.DatabaseDescriptor, addRow func(...tree.Datum) error) error {
 		hasViewActivityOrViewActivityRedacted, err := p.HasViewActivityOrViewActivityRedactedRole(ctx)
@@ -1156,6 +1157,13 @@ CREATE TABLE crdb_internal.node_statement_statistics (
 
 			}
 
+			indexRecommendations := tree.NewDArray(types.String)
+			for _, recommendation := range stats.Stats.IndexRecommendations {
+				if err := indexRecommendations.Append(tree.NewDString(recommendation)); err != nil {
+					return err
+				}
+			}
+
 			err := addRow(
 				tree.NewDInt(tree.DInt(nodeID)),                           // node_id
 				tree.NewDString(stats.Key.App),                            // application_name
@@ -1199,6 +1207,7 @@ CREATE TABLE crdb_internal.node_statement_statistics (
 				tree.NewDString(stats.Key.Database), // database_name
 				execNodeIDs,                         // exec_node_ids
 				txnFingerprintID,                    // txn_fingerprint_id
+				indexRecommendations,                // index_recommendations
 			)
 			if err != nil {
 				return err
@@ -5371,7 +5380,8 @@ CREATE TABLE crdb_internal.cluster_statement_statistics (
     metadata                   JSONB NOT NULL,
     statistics                 JSONB NOT NULL,
     sampled_plan               JSONB NOT NULL,
-    aggregation_interval       INTERVAL NOT NULL
+    aggregation_interval       INTERVAL NOT NULL,
+    index_recommendations      STRING[] NOT NULL
 );`,
 	generator: func(ctx context.Context, p *planner, db catalog.DatabaseDescriptor, stopper *stop.Stopper) (virtualTableGenerator, cleanupFunc, error) {
 		// TODO(azhng): we want to eventually implement memory accounting within the
@@ -5402,7 +5412,7 @@ CREATE TABLE crdb_internal.cluster_statement_statistics (
 		curAggTs := s.ComputeAggregatedTs()
 		aggInterval := s.GetAggregationInterval()
 
-		row := make(tree.Datums, 8 /* number of columns for this virtual table */)
+		row := make(tree.Datums, 9 /* number of columns for this virtual table */)
 		worker := func(ctx context.Context, pusher rowPusher) error {
 			return memSQLStats.IterateStatementStats(ctx, &sqlstats.IteratorOptions{
 				SortedAppNames: true,
@@ -5437,6 +5447,13 @@ CREATE TABLE crdb_internal.cluster_statement_statistics (
 					duration.MakeDuration(aggInterval.Nanoseconds(), 0, 0),
 					types.DefaultIntervalTypeMetadata)
 
+				indexRecommendations := tree.NewDArray(types.String)
+				for _, recommendation := range statistics.Stats.IndexRecommendations {
+					if err := indexRecommendations.Append(tree.NewDString(recommendation)); err != nil {
+						return err
+					}
+				}
+
 				row = row[:0]
 				row = append(row,
 					aggregatedTs,                        // aggregated_ts
@@ -5448,6 +5465,7 @@ CREATE TABLE crdb_internal.cluster_statement_statistics (
 					tree.NewDJSON(statisticsJSON),       // statistics
 					tree.NewDJSON(plan),                 // plan
 					aggInterval,                         // aggregation_interval
+					indexRecommendations,                // index_recommendations
 				)
 
 				return pusher.pushRow(row...)
@@ -5473,7 +5491,8 @@ SELECT
   max(metadata) as metadata,
   crdb_internal.merge_statement_stats(array_agg(statistics)),
   max(sampled_plan),
-  aggregation_interval
+  aggregation_interval,
+  array_remove(array_agg(index_rec), NULL) AS index_recommendations
 FROM (
   SELECT
       aggregated_ts,
@@ -5484,7 +5503,8 @@ FROM (
       metadata,
       statistics,
       sampled_plan,
-      aggregation_interval
+      aggregation_interval,
+      index_recommendations
   FROM
       crdb_internal.cluster_statement_statistics
   UNION ALL
@@ -5497,10 +5517,12 @@ FROM (
           metadata,
           statistics,
           plan,
-          agg_interval
+          agg_interval,
+          index_recommendations
       FROM
           system.statement_statistics
 )
+LEFT JOIN LATERAL unnest(index_recommendations) AS index_rec ON true
 GROUP BY
   aggregated_ts,
   fingerprint_id,
@@ -5518,6 +5540,7 @@ GROUP BY
 		{Name: "statistics", Typ: types.Jsonb},
 		{Name: "sampled_plan", Typ: types.Jsonb},
 		{Name: "aggregation_interval", Typ: types.Interval},
+		{Name: "index_recommendations", Typ: types.StringArray},
 	},
 }
 

pkg/sql/executor_statement_metrics.go

@@ -168,23 +168,24 @@ func (ex *connExecutor) recordStatementSummary(
 	}
 
 	recordedStmtStats := sqlstats.RecordedStmtStats{
-		SessionID:       ex.sessionID,
-		StatementID:     planner.stmt.QueryID,
-		AutoRetryCount:  automaticRetryCount,
-		RowsAffected:    rowsAffected,
-		ParseLatency:    parseLat,
-		PlanLatency:     planLat,
-		RunLatency:      runLat,
-		ServiceLatency:  svcLat,
-		OverheadLatency: execOverhead,
-		BytesRead:       stats.bytesRead,
-		RowsRead:        stats.rowsRead,
-		RowsWritten:     stats.rowsWritten,
-		Nodes:           getNodesFromPlanner(planner),
-		StatementType:   stmt.AST.StatementType(),
-		Plan:            planner.instrumentation.PlanForStats(ctx),
-		PlanGist:        planner.instrumentation.planGist.String(),
-		StatementError:  stmtErr,
+		SessionID:            ex.sessionID,
+		StatementID:          planner.stmt.QueryID,
+		AutoRetryCount:       automaticRetryCount,
+		RowsAffected:         rowsAffected,
+		ParseLatency:         parseLat,
+		PlanLatency:          planLat,
+		RunLatency:           runLat,
+		ServiceLatency:       svcLat,
+		OverheadLatency:      execOverhead,
+		BytesRead:            stats.bytesRead,
+		RowsRead:             stats.rowsRead,
+		RowsWritten:          stats.rowsWritten,
+		Nodes:                getNodesFromPlanner(planner),
+		StatementType:        stmt.AST.StatementType(),
+		Plan:                 planner.instrumentation.PlanForStats(ctx),
+		PlanGist:             planner.instrumentation.planGist.String(),
+		StatementError:       stmtErr,
+		IndexRecommendations: planner.instrumentation.indexRecommendations,
 	}
 
 	stmtFingerprintID, err :=

pkg/sql/logictest/testdata/logic_test/crdb_internal

@@ -315,10 +315,10 @@ SELECT * FROM crdb_internal.leases WHERE node_id < 0
 ----
 node_id  table_id  name  parent_id  expiration  deleted
 
-query ITTTTTIIITRRRRRRRRRRRRRRRRRRRRRRRRRRBBTTTT colnames
+query ITTTTTIIITRRRRRRRRRRRRRRRRRRRRRRRRRRBBTTTTT colnames
 SELECT * FROM crdb_internal.node_statement_statistics WHERE node_id < 0
 ----
-node_id  application_name  flags  statement_id  key  anonymized  count  first_attempt_count  max_retries  last_error  rows_avg  rows_var  parse_lat_avg  parse_lat_var  plan_lat_avg  plan_lat_var  run_lat_avg  run_lat_var  service_lat_avg  service_lat_var  overhead_lat_avg  overhead_lat_var  bytes_read_avg  bytes_read_var  rows_read_avg  rows_read_var  network_bytes_avg  network_bytes_var  network_msgs_avg  network_msgs_var  max_mem_usage_avg  max_mem_usage_var  max_disk_usage_avg  max_disk_usage_var  contention_time_avg  contention_time_var  implicit_txn  full_scan  sample_plan  database_name  exec_node_ids  txn_fingerprint_id
+node_id  application_name  flags  statement_id  key  anonymized  count  first_attempt_count  max_retries  last_error  rows_avg  rows_var  parse_lat_avg  parse_lat_var  plan_lat_avg  plan_lat_var  run_lat_avg  run_lat_var  service_lat_avg  service_lat_var  overhead_lat_avg  overhead_lat_var  bytes_read_avg  bytes_read_var  rows_read_avg  rows_read_var  network_bytes_avg  network_bytes_var  network_msgs_avg  network_msgs_var  max_mem_usage_avg  max_mem_usage_var  max_disk_usage_avg  max_disk_usage_var  contention_time_avg  contention_time_var  implicit_txn  full_scan  sample_plan  database_name  exec_node_ids  txn_fingerprint_id index_recommendations
 
 query ITTTIIRRRRRRRRRRRRRRRRRR colnames
 SELECT * FROM crdb_internal.node_transaction_statistics WHERE node_id < 0