diff --git a/README.md b/README.md
index 0433f46682..fed3173d30 100644
--- a/README.md
+++ b/README.md
@@ -335,8 +335,9 @@ In order to enable application-level replication, `-replicationFactor=N` command
 This guarantees that all the data remains available for querying if up to `N-1` `vmstorage` nodes are unavailable.
 For example, when `-replicationFactor=3` is passed to `vminsert`, then it replicates all the ingested data to 3 distinct `vmstorage` nodes.
 
-When the replication is enabled, `-dedup.minScrapeInterval=1ms` command-line flag must be passed to `vmselect`
-in order to de-duplicate replicated data during queries. It is OK if `-dedup.minScrapeInterval` exceeds 1ms
+When the replication is enabled, `-replicationFactor=N` and `-dedup.minScrapeInterval=1ms` command-line flag must be passed to `vmselect` nodes.
+The `-replicationFactor=N` improves query performance when a part of vmstorage nodes respond slowly and/or temporarily unavailable.
+The `-dedup.minScrapeInterval=1ms` de-duplicates replicated data during queries. It is OK if `-dedup.minScrapeInterval` exceeds 1ms
 when [deduplication](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#deduplication) is used additionally to replication.
 
 Note that [replication doesn't save from disaster](https://medium.com/@valyala/speeding-up-backups-for-big-time-series-databases-533c1a927883),
diff --git a/app/vmselect/netstorage/netstorage.go b/app/vmselect/netstorage/netstorage.go
index c06437a8dc..54ccffc017 100644
--- a/app/vmselect/netstorage/netstorage.go
+++ b/app/vmselect/netstorage/netstorage.go
@@ -3,6 +3,7 @@ package netstorage
 import (
 	"container/heap"
 	"errors"
+	"flag"
 	"fmt"
 	"io"
 	"net/http"
@@ -27,6 +28,9 @@ import (
 	"github.com/VictoriaMetrics/metrics"
 )
 
+var replicationFactor = flag.Int("replicationFactor", 1, "How many copies of every time series is available on vmstorage nodes. "+
+	"See -replicationFactor command-line flag for vminsert nodes")
+
 // Result is a single timeseries result.
 //
 // ProcessSearchQuery returns Result slice.
@@ -1249,6 +1253,7 @@ func processSearchQuery(at *auth.Token, denyPartialResponse bool, sq *storage.Se
 
 func collectResults(denyPartialResponse bool, resultsCh <-chan interface{}, partialResultsCounter *metrics.Counter, f func(result interface{}) error) (bool, error) {
 	var errors []error
+	resultsCollected := 0
 	for i := 0; i < len(storageNodes); i++ {
 		// There is no need in timer here, since all the goroutines executing
 		// the sn.process* function must be finished until the deadline.
@@ -1258,6 +1263,16 @@ func collectResults(denyPartialResponse bool, resultsCh <-chan interface{}, part
 			errors = append(errors, err)
 			continue
 		}
+		resultsCollected++
+		if resultsCollected > len(storageNodes)-*replicationFactor {
+			// There is no need in waiting for the remaining results,
+			// because the collected results contain all the data according to the given -replicationFactor.
+			// This should speed up responses when a part of vmstorage nodes are slow and/or temporarily unavailable.
+			// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
+			//
+			// It is expected that cap(resultsCh) == len(storageNodes), otherwise goroutine leak is possible.
+			return false, nil
+		}
 	}
 	isPartial := false
 	if len(errors) > 0 {
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
index dca1d89b36..44de82a629 100644
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -6,6 +6,8 @@
   ```bash
   snap install victoriametrics
   ```
+* FEATURE: vmselect: add `-replicationFactor` command-line flag for reducing query duration when replication is enabled and a part of vmstorage nodes
+  are temporarily slow and/or temporarily unavailable. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/711
 * FEATURE: vminsert: export `vm_rpc_vmstorage_is_reachable` metric, which can be used for monitoring reachability of vmstorage nodes from vminsert nodes.
 * FEATURE: vmagent: add Netflix Eureka service discovery (aka [eureka_sd_config](https://prometheus.io/docs/prometheus/latest/configuration/configuration/#eureka_sd_config)).
 See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/851
diff --git a/docs/Cluster-VictoriaMetrics.md b/docs/Cluster-VictoriaMetrics.md
index 0433f46682..fed3173d30 100644
--- a/docs/Cluster-VictoriaMetrics.md
+++ b/docs/Cluster-VictoriaMetrics.md
@@ -335,8 +335,9 @@ In order to enable application-level replication, `-replicationFactor=N` command
 This guarantees that all the data remains available for querying if up to `N-1` `vmstorage` nodes are unavailable.
 For example, when `-replicationFactor=3` is passed to `vminsert`, then it replicates all the ingested data to 3 distinct `vmstorage` nodes.
 
-When the replication is enabled, `-dedup.minScrapeInterval=1ms` command-line flag must be passed to `vmselect`
-in order to de-duplicate replicated data during queries. It is OK if `-dedup.minScrapeInterval` exceeds 1ms
+When the replication is enabled, `-replicationFactor=N` and `-dedup.minScrapeInterval=1ms` command-line flag must be passed to `vmselect` nodes.
+The `-replicationFactor=N` improves query performance when a part of vmstorage nodes respond slowly and/or temporarily unavailable.
+The `-dedup.minScrapeInterval=1ms` de-duplicates replicated data during queries. It is OK if `-dedup.minScrapeInterval` exceeds 1ms
 when [deduplication](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/README.md#deduplication) is used additionally to replication.
 
 Note that [replication doesn't save from disaster](https://medium.com/@valyala/speeding-up-backups-for-big-time-series-databases-533c1a927883),