app/vmselect/netstorage: properly process -search.maxSamplesPerQuery limit (#4472)

Properly return the error to user when `-search.maxSamplesPerQuery` limit is exceeded.
Before, user could have received a partial response instead.

Signed-off-by: hagen1778 <roman@victoriametrics.com>

app/vmselect/netstorage/netstorage.go

@@ -1498,6 +1498,16 @@ func SearchMetricNames(qt *querytracer.Tracer, denyPartialResponse bool, sq *sto
 	return metricNames, isPartial, nil
 }
 
+// limitExceededErr error generated by vmselect
+// on checking complexity limits during processing responses
+// from storage nodes.
+type limitExceededErr struct {
+	err error
+}
+
+// Error satisfies error interface
+func (e limitExceededErr) Error() string { return e.err.Error() }
+
 // ProcessSearchQuery performs sq until the given deadline.
 //
 // Results.RunParallel or Results.Cancel must be called on the returned Results.
@@ -1522,9 +1532,9 @@ func ProcessSearchQuery(qt *querytracer.Tracer, denyPartialResponse bool, sq *st
 		blocksRead.Add(workerID, 1)
 		n := samples.Add(workerID, uint64(mb.Block.RowsCount()))
 		if *maxSamplesPerQuery > 0 && n > maxSamplesPerWorker && samples.GetTotal() > uint64(*maxSamplesPerQuery) {
-			return fmt.Errorf("cannot select more than -search.maxSamplesPerQuery=%d samples; possible solutions: "+
+			return &limitExceededErr{err: fmt.Errorf("cannot select more than -search.maxSamplesPerQuery=%d samples; possible solutions: "+
 				"to increase the -search.maxSamplesPerQuery; to reduce time range for the query; "+
-				"to use more specific label filters in order to select lower number of series", *maxSamplesPerQuery)
+				"to use more specific label filters in order to select lower number of series", *maxSamplesPerQuery)}
 		}
 		if err := tbfw.RegisterAndWriteBlock(mb, workerID); err != nil {
 			return fmt.Errorf("cannot write MetricBlock to temporary blocks file: %w", err)
@@ -1718,6 +1728,13 @@ func (snr *storageNodesRequest) collectResults(partialResultsCounter *metrics.Co
 				snr.finishQueryTracers("cancel request because of error in other vmstorage nodes")
 				return false, err
 			}
+			var limitErr *limitExceededErr
+			if errors.As(err, &limitErr) {
+				// Immediately return the error, since complexity limits are already exceeded,
+				// and we don't need to process the rest of results.
+				snr.finishQueryTracers("cancel request because query complexity limit was exceeded")
+				return false, err
+			}
 			errsPartial = append(errsPartial, err)
 			if snr.denyPartialResponse && len(errsPartial) >= *replicationFactor {
 				// Return the error to the caller if partial responses are denied

docs/CHANGELOG.md

@@ -36,6 +36,7 @@ The following tip changes can be tested by building VictoriaMetrics components f
   Remove redundant limit from [Prometheus api/v1/series](https://docs.victoriametrics.com/Single-server-VictoriaMetrics.html#prometheus-querying-api-usage). See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4339).
 * BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent.html): fix panic on vmagent shutdown which could lead to loosing aggregation results which were not flushed to remote yet. See [this](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4407) for details.
 * BUGFIX: [vmbackupmanager](https://docs.victoriametrics.com/vmbackupmanager.html): fix an issue with `vmbackupmanager` not being able to restore data from a backup stored in GCS. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4420) for details.
+* BUGFIX: properly return the error to user when `-search.maxSamplesPerQuery` limit is exceeded. Before, user could have received a partial response instead.
 
 ## [v1.91.2](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.91.2)