app/vmselect/promql: add any(x) by (y) aggregate function, which returns any time series from q for each group y

app/vmselect/promql/aggr.go

@@ -43,6 +43,7 @@ var aggrFuncs = map[string]aggrFunc{
 	"bottomk_max":    newAggrFuncRangeTopK(maxValue, true),
 	"bottomk_avg":    newAggrFuncRangeTopK(avgValue, true),
 	"bottomk_median": newAggrFuncRangeTopK(medianValue, true),
+	"any":            newAggrFunc(aggrFuncAny),
 }
 
 type aggrFunc func(afa *aggrFuncArg) ([]*timeseries, error)
@@ -118,6 +119,10 @@ func aggrFuncExt(afe func(tss []*timeseries) []*timeseries, argOrig []*timeserie
 	return rvs, nil
 }
 
+func aggrFuncAny(tss []*timeseries) []*timeseries {
+	return tss[:1]
+}
+
 func aggrFuncSum(tss []*timeseries) []*timeseries {
 	if len(tss) == 1 {
 		// Fast path - nothing to sum.

app/vmselect/promql/aggr_incremental.go

@@ -48,6 +48,11 @@ var incrementalAggrFuncCallbacksMap = map[string]*incrementalAggrFuncCallbacks{
 		mergeAggrFunc:    mergeAggrGeomean,
 		finalizeAggrFunc: finalizeAggrGeomean,
 	},
+	"any": {
+		updateAggrFunc:   updateAggrAny,
+		mergeAggrFunc:    mergeAggrAny,
+		finalizeAggrFunc: finalizeAggrCommon,
+	},
 }
 
 type incrementalAggrFuncContext struct {
@@ -458,3 +463,25 @@ func finalizeAggrGeomean(iac *incrementalAggrContext) {
 		dstValues[i] = math.Pow(dstValues[i], 1/v)
 	}
 }
+
+func updateAggrAny(iac *incrementalAggrContext, values []float64) {
+	dstValues := iac.ts.Values
+	dstCounts := iac.values
+	if dstCounts[0] > 0 {
+		return
+	}
+	dstCounts[0] = 1
+	dstValues = append(dstValues[:0], values...)
+}
+
+func mergeAggrAny(dst, src *incrementalAggrContext) {
+	srcValues := src.ts.Values
+	dstValues := dst.ts.Values
+	srcCounts := src.values
+	dstCounts := dst.values
+	if dstCounts[0] > 0 {
+		return
+	}
+	dstCounts[0] = srcCounts[0]
+	dstValues = append(dstValues[:0], srcValues...)
+}

app/vmselect/promql/exec_test.go

@@ -3793,6 +3793,17 @@ func TestExecSuccess(t *testing.T) {
 		resultExpected := []netstorage.Result{r1, r2}
 		f(q, resultExpected)
 	})
+	t.Run(`any()`, func(t *testing.T) {
+		t.Parallel()
+		q := `any(label_set(10, "foo", "bar") or label_set(time()/150, "baz", "sss"))`
+		r := netstorage.Result{
+			MetricName: metricNameExpected,
+			Values:     []float64{10, 10, 10, 10, 10, 10},
+			Timestamps: timestampsExpected,
+		}
+		resultExpected := []netstorage.Result{r}
+		f(q, resultExpected)
+	})
 	t.Run(`topk(-1)`, func(t *testing.T) {
 		t.Parallel()
 		q := `sort(topk(-1, label_set(10, "foo", "bar") or label_set(time()/150, "baz", "sss")))`

docs/MetricsQL.md

@@ -22,7 +22,7 @@ Feel free [filing a feature request](https://github.com/VictoriaMetrics/Victoria
 This functionality can be tried at [an editable Grafana dashboard](http://play-grafana.victoriametrics.com:3000/d/4ome8yJmz/node-exporter-on-victoriametrics-demo).
 
 - [`WITH` templates](https://play.victoriametrics.com/promql/expand-with-exprs). This feature simplifies writing and managing complex queries. Go to [`WITH` templates playground](https://victoriametrics.com/promql/expand-with-exprs) and try it.
-- Aggregate functions support optional `limit N` suffix in order to limit the number of output series. For example, `sum(x) by (y) limit 10` limits
+- All the aggregate functions support optional `limit N` suffix in order to limit the number of output series. For example, `sum(x) by (y) limit 10` limits
   the number of output time series after the aggregation to 10. All the other time series are dropped.
 - Metric names and metric labels may contain escaped chars. For instance, `foo\-bar{baz\=aa="b"}` is valid expression. It returns time series with name `foo-bar` containing label `baz=aa` with value `b`. Additionally, `\xXX` escape sequence is supported, where `XX` is hexadecimal representation of escaped char.
 - `offset`, range duration and step value for range vector may refer to the current step aka `$__interval` value from Grafana.
@@ -74,6 +74,8 @@ This functionality can be tried at [an editable Grafana dashboard](http://play-g
 - `median_over_time(m[d])` - calculates median values for `m` over `d` time window. Shorthand to `quantile_over_time(0.5, m[d])`.
 - `median(q)` - median aggregate. Shorthand to `quantile(0.5, q)`.
 - `limitk(k, q)` - limits the number of time series returned from `q` to `k`.
+- `any(q) by (x)` - returns any time series from `q` for each group in `x`. Note that `any()` removes all the labels except of those listed in `by (x)`.
+  Use `limitk(1, q)` if you need retaining all the labels from `q`.
 - `keep_last_value(q)` - fills missing data (gaps) in `q` with the previous non-empty value.
 - `keep_next_value(q)` - fills missing data (gaps) in `q` with the next non-empty value.
 - `distinct_over_time(m[d])` - returns distinct number of values for `m` data points over `d` duration.

go.mod

@@ -9,7 +9,7 @@ require (
 	// like https://github.com/valyala/fasthttp/commit/996610f021ff45fdc98c2ce7884d5fa4e7f9199b
 	github.com/VictoriaMetrics/fasthttp v1.0.1
 	github.com/VictoriaMetrics/metrics v1.11.2
-	github.com/VictoriaMetrics/metricsql v0.2.0
+	github.com/VictoriaMetrics/metricsql v0.2.1
 	github.com/aws/aws-sdk-go v1.30.25
 	github.com/cespare/xxhash/v2 v2.1.1
 	github.com/golang/protobuf v1.4.1 // indirect

go.sum

@@ -45,8 +45,8 @@ github.com/VictoriaMetrics/fasthttp v1.0.1 h1:I7YdbswTIW63WxoFoUOSNxeOEGB46rdKUL
 github.com/VictoriaMetrics/fasthttp v1.0.1/go.mod h1:BqgsieH90PR7x97c89j+eqZDloKkDhAEQTwhLw6jw/4=
 github.com/VictoriaMetrics/metrics v1.11.2 h1:t/ceLP6SvagUqypCKU7cI7+tQn54+TIV/tGoxihHvx8=
 github.com/VictoriaMetrics/metrics v1.11.2/go.mod h1:LU2j9qq7xqZYXz8tF3/RQnB2z2MbZms5TDiIg9/NHiQ=
-github.com/VictoriaMetrics/metricsql v0.2.0 h1:tGWPFSCqDRKYLuc99lNmxa0md9uyWHVycbumGLAM4V0=
+github.com/VictoriaMetrics/metricsql v0.2.1 h1:OI/W2QCFiQiFULVN3ZiC/iCqZFt25rXp/O7P2NiAwYU=
-github.com/VictoriaMetrics/metricsql v0.2.0/go.mod h1:UIjd9S0W1UnTWlJdM0wLS+2pfuPqjwqKoK8yTos+WyE=
+github.com/VictoriaMetrics/metricsql v0.2.1/go.mod h1:UIjd9S0W1UnTWlJdM0wLS+2pfuPqjwqKoK8yTos+WyE=
 github.com/allegro/bigcache v1.2.1-0.20190218064605-e24eb225f156 h1:eMwmnE/GDgah4HI848JfFxHt+iPb26b4zyfspmqY0/8=
 github.com/allegro/bigcache v1.2.1-0.20190218064605-e24eb225f156/go.mod h1:Cb/ax3seSYIx7SuZdm2G2xzfwmv3TPSk2ucNfQESPXM=
 github.com/aws/aws-sdk-go v1.30.25 h1:89NXJkfpjnMEnsxkP8MVX+LDsoiLCSqevraLb5y4Mjk=

vendor/github.com/VictoriaMetrics/metricsql/aggr.go

@@ -33,6 +33,7 @@ var aggrFuncs = map[string]bool{
 	"bottomk_max":    true,
 	"bottomk_avg":    true,
 	"bottomk_median": true,
+	"any":            true,
 }
 
 func isAggrFunc(s string) bool {

vendor/modules.txt

@@ -18,7 +18,7 @@ github.com/VictoriaMetrics/fasthttp/fasthttputil
 github.com/VictoriaMetrics/fasthttp/stackless
 # github.com/VictoriaMetrics/metrics v1.11.2
 github.com/VictoriaMetrics/metrics
-# github.com/VictoriaMetrics/metricsql v0.2.0
+# github.com/VictoriaMetrics/metricsql v0.2.1
 github.com/VictoriaMetrics/metricsql
 github.com/VictoriaMetrics/metricsql/binaryop
 # github.com/aws/aws-sdk-go v1.30.25