app/{vmagent,victoria-metrics}: add -dryRun option and make more clear handling for -promscrape.config.dryRun

app/victoria-metrics/main.go

@@ -17,6 +17,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/procutil"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promscrape"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
 )
 
@@ -25,6 +26,8 @@ var (
 	minScrapeInterval = flag.Duration("dedup.minScrapeInterval", 0, "Remove superflouos samples from time series if they are located closer to each other than this duration. "+
 		"This may be useful for reducing overhead when multiple identically configured Prometheus instances write data to the same VictoriaMetrics. "+
 		"Deduplication is disabled if the -dedup.minScrapeInterval is 0")
+	dryRun = flag.Bool("dryRun", false, "Whether to check only -promscrape.config and then exit. "+
+		"Unknown config entries are allowed in -promscrape.config by default. This can be changed with -promscrape.config.strictParse")
 )
 
 func main() {
@@ -34,6 +37,18 @@ func main() {
 	buildinfo.Init()
 	logger.Init()
 	cgroup.UpdateGOMAXPROCSToCPUQuota()
+
+	if promscrape.IsDryRun() {
+		*dryRun = true
+	}
+	if *dryRun {
+		if err := promscrape.CheckConfig(); err != nil {
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
+		}
+		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		return
+	}
+
 	logger.Infof("starting VictoriaMetrics at %q...", *httpListenAddr)
 	startTime := time.Now()
 	storage.SetMinScrapeIntervalForDeduplication(*minScrapeInterval)

app/vmagent/main.go

@@ -69,12 +69,19 @@ func main() {
 	logger.Init()
 	cgroup.UpdateGOMAXPROCSToCPUQuota()
 
+	if promscrape.IsDryRun() {
+		if err := promscrape.CheckConfig(); err != nil {
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
+		}
+		logger.Infof("-promscrape.config is ok; exitting with 0 status code")
+		return
+	}
 	if *dryRun {
 		if err := remotewrite.CheckRelabelConfigs(); err != nil {
 			logger.Fatalf("error when checking relabel configs: %s", err)
 		}
 		if err := promscrape.CheckConfig(); err != nil {
-			logger.Fatalf("error when checking Prometheus config: %s", err)
+			logger.Fatalf("error when checking -promscrape.config: %s", err)
 		}
 		logger.Infof("all the configs are ok; exitting with 0 status code")
 		return

docs/CHANGELOG.md

@@ -20,6 +20,7 @@ See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/851
   Slow query logging is controlled with `-search.logSlowQueryDuration` command-line flag.
 * FEATURE: add `/tags/delSeries` handler from Graphite Tags API. See https://victoriametrics.github.io/#graphite-tags-api-usage
 * FEATURE: log metric name plus all its labels when the metric timestamp is out of the configured retention. This should simplify detecting the source of metrics with unexpected timestamps.
+* FEATURE: add `-dryRun` command-line flag to single-node VictoriaMetrics in order to check config file pointed by `-promscrape.config`.
 
 * BUGFIX: properly parse Prometheus metrics with [exemplars](https://github.com/OpenObservability/OpenMetrics/blob/master/OpenMetrics.md#exemplars-1) such as `foo 123 # {bar="baz"} 1`.
 * BUGFIX: properly parse "infinity" values in [OpenMetrics format](https://github.com/OpenObservability/OpenMetrics/blob/master/OpenMetrics.md#abnf).

lib/promscrape/config.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"io/ioutil"
 	"net/url"
-	"os"
 	"path/filepath"
 	"strings"
 	"sync/atomic"
@@ -134,16 +133,14 @@ func loadConfig(path string) (cfg *Config, data []byte, err error) {
 	if err := cfgObj.parse(data, path); err != nil {
 		return nil, nil, fmt.Errorf("cannot parse Prometheus config from %q: %w", path, err)
 	}
-	if *dryRun {
-		// This is a dirty hack for checking Prometheus config only.
-		// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/362
-		// and https://github.com/VictoriaMetrics/VictoriaMetrics/issues/508 for details.
-		logger.Infof("Success: the config at %q has no errors; exitting with 0 status code", path)
-		os.Exit(0)
-	}
 	return &cfgObj, data, nil
 }
 
+// IsDryRun returns true if -promscrape.config.dryRun command-line flag is set
+func IsDryRun() bool {
+	return *dryRun
+}
+
 func (cfg *Config) parse(data []byte, path string) error {
 	if err := unmarshalMaybeStrict(data, cfg); err != nil {
 		return fmt.Errorf("cannot unmarshal data: %w", err)