[receiver/sqlserver] Add collection interval for top query

.chloggen/top-query-collection-interval.yaml

@@ -0,0 +1,29 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: sqlserverreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add configuration option `top_query_collection.collection_interval` for top query collection to make the collection less frequent.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [40002]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: |
+  - This change only applies to the `top_query_collection` feature.
+  - The default value is `60s`
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]

receiver/sqlserverreceiver/README.md

@@ -47,6 +47,13 @@ Top-Query collection specific options (only useful when top-query collection are
   - Queries that were finished execution outside the lookback window are not included in the collection. Increasing the lookback window (in seconds) will be useful for capturing long-running queries.
 - `max_query_sample_count` (optional, example = `5000`, default = `1000`): The maximum number of records to fetch in a single run.
 - `top_query_count`: (optional, example = `100`, default = `200`): The maximum number of active queries to report (to the next consumer) in a single run.
+- `collection_interval`: (optional, default = `60s`): The interval at which top queries should be emitted by this receiver.
+  - This value can only guarantee that the top queries are collected at most once in this interval.
+    - For instance, you have global `collection_interval` as `10s` and `top_query_collection.collection_interval` as `60s`.
+      - In this case, the default receiver scraper will still try to run in every 10 seconds.
+      - However, the top queries collection will only run after 60 seconds have passed since the last collection.
+    - For instance, you have global `collection_interval` as `10s` and `top_query_collection.collection_interval` as `5s`.
+      - In this case, `top_query_collection.collection_internal` will make no effects to the collection
 - `enabled`: (optional, default = `false`): Enable collection of top queries.
   - e.g. `sqlserver` receiver will fetch 1000 (value: `max_query_sample_count`) queries from database and report the top 200 (value: `top_query_count`) which used the most CPU time.
 

receiver/sqlserverreceiver/config.go

@@ -5,6 +5,7 @@ package sqlserverreceiver // import "github.com/open-telemetry/opentelemetry-col
 
 import (
 	"errors"
+	"time"
 
 	"go.opentelemetry.io/collector/config/configopaque"
 	"go.opentelemetry.io/collector/scraper/scraperhelper"
@@ -23,10 +24,11 @@ type TopQueryCollection struct {
 	// The query statement will also be reported, hence, it is not ideal to send it as a metric. Hence
 	// we are reporting them as logs.
 	// The `N` is configured via `TopQueryCount`
-	Enabled             bool `mapstructure:"enabled"`
-	LookbackTime        uint `mapstructure:"lookback_time"`
-	MaxQuerySampleCount uint `mapstructure:"max_query_sample_count"`
-	TopQueryCount       uint `mapstructure:"top_query_count"`
+	Enabled             bool          `mapstructure:"enabled"`
+	LookbackTime        uint          `mapstructure:"lookback_time"`
+	MaxQuerySampleCount uint          `mapstructure:"max_query_sample_count"`
+	TopQueryCount       uint          `mapstructure:"top_query_count"`
+	CollectionInterval  time.Duration `mapstructure:"collection_interval"`
 }
 
 // Config defines configuration for a sqlserver receiver.
@@ -72,6 +74,10 @@ func (cfg *Config) Validate() error {
 		return errors.New("`top_query_count` must be less than or equal to `max_query_sample_count`")
 	}
 
+	if cfg.TopQueryCollection.CollectionInterval < 0 {
+		return errors.New("`top_query_collection.collection_interval` must not be less than 0")
+	}
+
 	cfg.isDirectDBConnectionEnabled, err = directDBConnectionEnabled(cfg)
 
 	return err

receiver/sqlserverreceiver/factory.go

@@ -61,6 +61,7 @@ func createDefaultConfig() component.Config {
 			LookbackTime:        uint(2 * cfg.CollectionInterval / time.Second),
 			MaxQuerySampleCount: 1000,
 			TopQueryCount:       200,
+			CollectionInterval:  time.Minute,
 		},
 	}
 }

receiver/sqlserverreceiver/factory_test.go

@@ -48,6 +48,7 @@ func TestFactory(t *testing.T) {
 						LookbackTime:        uint(2 * 10),
 						MaxQuerySampleCount: 1000,
 						TopQueryCount:       200,
+						CollectionInterval:  time.Minute,
 					},
 					QuerySample: QuerySample{
 						Enabled:         false,

receiver/sqlserverreceiver/scraper.go

@@ -37,19 +37,20 @@ const (
 )
 
 type sqlServerScraperHelper struct {
-	id                 component.ID
-	config             *Config
-	sqlQuery           string
-	instanceName       string
-	clientProviderFunc sqlquery.ClientProviderFunc
-	dbProviderFunc     sqlquery.DbProviderFunc
-	logger             *zap.Logger
-	telemetry          sqlquery.TelemetryConfig
-	client             sqlquery.DbClient
-	db                 *sql.DB
-	mb                 *metadata.MetricsBuilder
-	lb                 *metadata.LogsBuilder
-	cache              *lru.Cache[string, int64]
+	id                     component.ID
+	config                 *Config
+	sqlQuery               string
+	instanceName           string
+	clientProviderFunc     sqlquery.ClientProviderFunc
+	dbProviderFunc         sqlquery.DbProviderFunc
+	logger                 *zap.Logger
+	telemetry              sqlquery.TelemetryConfig
+	client                 sqlquery.DbClient
+	db                     *sql.DB
+	mb                     *metadata.MetricsBuilder
+	lb                     *metadata.LogsBuilder
+	cache                  *lru.Cache[string, int64]
+	lastExecutionTimestamp time.Time
 }
 
 var (
@@ -67,16 +68,17 @@ func newSQLServerScraper(id component.ID,
 	cache *lru.Cache[string, int64],
 ) *sqlServerScraperHelper {
 	return &sqlServerScraperHelper{
-		id:                 id,
-		config:             cfg,
-		sqlQuery:           query,
-		logger:             params.Logger,
-		telemetry:          telemetry,
-		dbProviderFunc:     dbProviderFunc,
-		clientProviderFunc: clientProviderFunc,
-		mb:                 metadata.NewMetricsBuilder(cfg.MetricsBuilderConfig, params),
-		lb:                 metadata.NewLogsBuilder(cfg.LogsBuilderConfig, params),
-		cache:              cache,
+		id:                     id,
+		config:                 cfg,
+		sqlQuery:               query,
+		logger:                 params.Logger,
+		telemetry:              telemetry,
+		dbProviderFunc:         dbProviderFunc,
+		clientProviderFunc:     clientProviderFunc,
+		mb:                     metadata.NewMetricsBuilder(cfg.MetricsBuilderConfig, params),
+		lb:                     metadata.NewLogsBuilder(cfg.LogsBuilderConfig, params),
+		cache:                  cache,
+		lastExecutionTimestamp: time.Unix(0, 0),
 	}
 }
 
@@ -121,6 +123,10 @@ func (s *sqlServerScraperHelper) ScrapeLogs(ctx context.Context) (plog.Logs, err
 	var resources pcommon.Resource
 	switch s.sqlQuery {
 	case getSQLServerQueryTextAndPlanQuery():
+		if s.lastExecutionTimestamp.Add(s.config.TopQueryCollection.CollectionInterval).After(time.Now()) {
+			s.logger.Debug("Skipping the collection of top queries because the current time has not yet exceeded the last execution time plus the specified collection interval")
+			return plog.NewLogs(), nil
+		}
 		resources, err = s.recordDatabaseQueryTextAndPlan(ctx, s.config.TopQueryCount)
 	case getSQLServerQuerySamplesQuery():
 		resources, err = s.recordDatabaseSampleQuery(ctx)
@@ -596,7 +602,9 @@ func (s *sqlServerScraperHelper) recordDatabaseQueryTextAndPlan(ctx context.Cont
 	sort.Slice(totalElapsedTimeDiffsMicrosecond, func(i, j int) bool { return totalElapsedTimeDiffsMicrosecond[i] > totalElapsedTimeDiffsMicrosecond[j] })
 
 	resourcesAdded := false
-	timestamp := pcommon.NewTimestampFromTime(time.Now())
+	now := time.Now()
+	timestamp := pcommon.NewTimestampFromTime(now)
+	s.lastExecutionTimestamp = now
 	for i, row := range rows {
 		// skipping the rest of the rows as totalElapsedTimeDiffs is sorted in descending order
 		if totalElapsedTimeDiffsMicrosecond[i] == 0 {

receiver/sqlserverreceiver/scraper_test.go

@@ -346,6 +346,7 @@ func TestQueryTextAndPlanQuery(t *testing.T) {
 
 	configureAllScraperMetrics(cfg, false)
 	cfg.TopQueryCollection.Enabled = true
+	cfg.TopQueryCollection.CollectionInterval = cfg.ControllerConfig.CollectionInterval
 
 	scrapers := setupSQLServerLogsScrapers(receivertest.NewNopSettings(metadata.Type), cfg)
 	assert.NotNil(t, scrapers)