vmalert: allow omitting -replay.timeTo in replay mode, default valu… (#6575)

…e is the current timestamp

address https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6492

---------

Signed-off-by: hagen1778 <roman@victoriametrics.com>
Co-authored-by: hagen1778 <roman@victoriametrics.com>
(cherry picked from commit 3169524fb7)

app/vmalert/Makefile

@@ -101,8 +101,7 @@ replay-vmalert: vmalert
 		-remoteWrite.url=http://localhost:8428 \
 		-external.label=cluster=east-1 \
 		-external.label=replica=a \
-		-replay.timeFrom=2021-05-11T07:21:43Z \
-		-replay.timeTo=2021-05-29T18:40:43Z
+		-replay.timeFrom=2024-06-01T00:00:00Z
 
 vmalert-linux-amd64:
 	APP_NAME=vmalert CGO_ENABLED=1 GOOS=linux GOARCH=amd64 $(MAKE) app-local-goos-goarch

app/vmalert/main.go

@@ -132,7 +132,7 @@ func main() {
 		validateTplFn = notifier.ValidateTemplates
 	}
 
-	if *replayFrom != "" || *replayTo != "" {
+	if *replayFrom != "" {
 		rw, err := remotewrite.Init(context.Background())
 		if err != nil {
 			logger.Fatalf("failed to init remoteWrite: %s", err)

app/vmalert/replay.go

@@ -15,9 +15,10 @@ import (
 
 var (
 	replayFrom = flag.String("replay.timeFrom", "",
-		"The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'")
+		"The time filter in RFC3339 format to start the replay from. E.g. '2020-01-01T20:07:00Z'")
 	replayTo = flag.String("replay.timeTo", "",
-		"The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'")
+		"The time filter in RFC3339 format to finish the replay by. E.g. '2020-01-01T20:07:00Z'. "+
+			"By default, is set to the current time.")
 	replayRulesDelay = flag.Duration("replay.rulesDelay", time.Second,
 		"Delay between rules evaluation within the group. Could be important if there are chained rules inside the group "+
 			"and processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule."+
@@ -36,14 +37,20 @@ func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewri
 	}
 	tFrom, err := time.Parse(time.RFC3339, *replayFrom)
 	if err != nil {
-		return fmt.Errorf("failed to parse %q: %w", *replayFrom, err)
+		return fmt.Errorf("failed to parse replay.timeFrom=%q: %w", *replayFrom, err)
 	}
-	tTo, err := time.Parse(time.RFC3339, *replayTo)
-	if err != nil {
-		return fmt.Errorf("failed to parse %q: %w", *replayTo, err)
+
+	// use tFrom location for default value, otherwise filters could have different locations
+	tTo := time.Now().In(tFrom.Location())
+	if *replayTo != "" {
+		tTo, err = time.Parse(time.RFC3339, *replayTo)
+		if err != nil {
+			return fmt.Errorf("failed to parse replay.timeTo=%q: %w", *replayTo, err)
+		}
 	}
+
 	if !tTo.After(tFrom) {
-		return fmt.Errorf("replay.timeTo must be bigger than replay.timeFrom")
+		return fmt.Errorf("replay.timeTo=%v must be bigger than replay.timeFrom=%v", tTo, tFrom)
 	}
 	labels := make(map[string]string)
 	for _, s := range *externalLabels {

docs/CHANGELOG.md

@@ -47,6 +47,7 @@ See also [LTS releases](https://docs.victoriametrics.com/lts-releases/).
   * These and other metrics were reflected on the [vmagent dashboard](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/dashboards/vmagent.json) in `stream aggregation` section.
 * FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent/) and [Single-node VictoriaMetrics](https://docs.victoriametrics.com/): add `-graphite.sanitizeMetricName` cmd-line flag for sanitizing metrics ingested via [Graphite protocol](https://docs.victoriametrics.com/#how-to-send-data-from-graphite-compatible-agents-such-as-statsd). See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6077).
 * FEATURE: [VictoriaMetrics cluster](https://docs.victoriametrics.com/cluster-victoriametrics/): do not retry RPC calls to vmstorage nodes if [complexity limits](https://docs.victoriametrics.com/#resource-usage-limits) were exceeded.
+* FEATURE: [vmalert](https://docs.victoriametrics.com/vmalert/): make `-replay.timeTo` optional in [replay mode](https://docs.victoriametrics.com/vmalert/#rules-backfilling). When omitted, the current timestamp will be used. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6492).
 
 * BUGFIX: [docker-compose](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#docker-compose-environment-for-victoriametrics): fix incorrect link to vmui from [VictoriaMetrics plugin in Grafana](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#grafana).
 * BUGFIX: [docker-compose](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#docker-compose-environment-for-victoriametrics): fix incorrect link to vmui from [VictoriaMetrics plugin in Grafana](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#grafana).

docs/vmalert.md

@@ -737,8 +737,8 @@ To run vmalert in `replay` mode:
 ./bin/vmalert -rule=path/to/your.rules \        # path to files with rules you usually use with vmalert
     -datasource.url=http://localhost:8428 \     # Prometheus HTTP API compatible datasource
     -remoteWrite.url=http://localhost:8428 \    # remote write compatible storage to persist results
-    -replay.timeFrom=2021-05-11T07:21:43Z \     # time from begin replay
-    -replay.timeTo=2021-05-29T18:40:43Z         # time to finish replay
+    -replay.timeFrom=2021-05-11T07:21:43Z \     # to start replay from
+    -replay.timeTo=2021-05-29T18:40:43Z         # to finish replay by, is optional
 ```
 
 The output of the command will look like the following:
@@ -770,12 +770,12 @@ max range per request:  8h20m0s
 ```
 
 In `replay` mode all groups are executed sequentially one-by-one. Rules within the group are
-executed sequentially as well (`concurrency` setting is ignored). Vmalert sends rule's expression
+executed sequentially as well (`concurrency` setting is ignored). vmalert sends rule's expression
 to [/query_range](https://docs.victoriametrics.com/keyconcepts/#range-query) endpoint
 of the configured `-datasource.url`. Returned data is then processed according to the rule type and
 backfilled to `-remoteWrite.url` via [remote Write protocol](https://prometheus.io/docs/prometheus/latest/storage/#remote-storage-integrations).
-Vmalert respects `evaluationInterval` value set by flag or per-group during the replay.
-Vmalert automatically disables caching on VictoriaMetrics side by sending `nocache=1` param. It allows
+vmalert respects `evaluationInterval` value set by flag or per-group during the replay.
+vmalert automatically disables caching on VictoriaMetrics side by sending `nocache=1` param. It allows
 to prevent cache pollution and unwanted time range boundaries adjustment during backfilling.
 
 #### Recording rules
@@ -1408,9 +1408,9 @@ The shortlist of configuration flags is the following:
   -replay.rulesDelay duration
      Delay between rules evaluation within the group. Could be important if there are chained rules inside the group and processing need to wait for previous rule results to be persisted by remote storage before evaluating the next rule.Keep it equal or bigger than -remoteWrite.flushInterval. (default 1s)
   -replay.timeFrom string
-     The time filter in RFC3339 format to select time series with timestamp equal or higher than provided value. E.g. '2020-01-01T20:07:00Z'
+     The time filter in RFC3339 format to start the replay from. E.g. '2020-01-01T20:07:00Z'
   -replay.timeTo string
-     The time filter in RFC3339 format to select timeseries with timestamp equal or lower than provided value. E.g. '2020-01-01T20:07:00Z'
+     The time filter in RFC3339 format to finish the replay by. E.g. '2020-01-01T20:07:00Z'. By default, is set to the current time.
   -rule array
      Path to the files or http url with alerting and/or recording rules.
      Supports hierarchical patterns and regexpes.