exit vmagent if there is config syntax error in scrape_config_files when -promscrape.config.strictParse=true (#5560)

docs/CHANGELOG.md

@@ -56,6 +56,7 @@ The sandbox cluster installation is running under the constant load generated by
 * BUGFIX: [MetricsQL](https://docs.victoriametrics.com/MetricsQL.html): properly handle queries, which wrap [rollup functions](https://docs.victoriametrics.com/MetricsQL.html#rollup-functions) with multiple arguments without explicitly specified lookbehind window in square brackets into [aggregate functions](https://docs.victoriametrics.com/MetricsQL.html#aggregate-functions). For example, `sum(quantile_over_time(0.5, process_resident_memory_bytes))` was resulting to `expecting at least 2 args to ...; got 1 args` error. Thanks to @atykhyy for [the pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5414).
 * BUGFIX: [vmctl](https://docs.victoriametrics.com/vmctl.html): retry on import errors in `vm-native` mode. Before, retries happened only on writes into a network connection between source and destination. But errors returned by server after all the data was transmitted were logged, but not retried.
 * BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent.html): properly assume role with [AWS IRSA authorization](https://docs.aws.amazon.com/eks/latest/userguide/iam-roles-for-service-accounts.html). Previously role chaining was not supported. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3822) for details.
+* BUGFIX: [vmagent](https://docs.victoriametrics.com/vmagent.html): exit if there is config syntax error in [`scrape_config_files`](https://docs.victoriametrics.com/vmagent.html#loading-scrape-configs-from-multiple-files) when `-promscrape.config.strictParse=true`. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5508).
 * BUGFIX: [vmui](https://docs.victoriametrics.com/#vmui): fix a link for the statistic inaccuracy explanation in the cardinality explorer tool. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5460).
 * BUGFIX: all: fix potential panic during components shutdown when [metrics push](https://docs.victoriametrics.com/#push-metrics) is configured. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5548). Thanks to @zhdd99 for the [pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/5549).
 

lib/promscrape/config.go

@@ -438,7 +438,7 @@ func loadConfig(path string) (*Config, error) {
 	return &c, nil
 }
 
-func mustLoadScrapeConfigFiles(baseDir string, scrapeConfigFiles []string) []*ScrapeConfig {
+func mustLoadScrapeConfigFiles(baseDir string, scrapeConfigFiles []string, isStrict bool) ([]*ScrapeConfig, error) {
 	var scrapeConfigs []*ScrapeConfig
 	for _, filePath := range scrapeConfigFiles {
 		filePath := fs.GetFilepath(baseDir, filePath)
@@ -464,14 +464,20 @@ func mustLoadScrapeConfigFiles(baseDir string, scrapeConfigFiles []string) []*Sc
 				continue
 			}
 			var scs []*ScrapeConfig
-			if err = yaml.UnmarshalStrict(data, &scs); err != nil {
+			if isStrict {
-				logger.Errorf("skipping %q at `scrape_config_files` because of failure to parse it: %s", path, err)
+				if err = yaml.UnmarshalStrict(data, &scs); err != nil {
-				continue
+					return nil, fmt.Errorf("cannot unmarshal data from `scrape_config_files` %s: %w; pass -promscrape.config.strictParse=false command-line flag for ignoring unknown fields in yaml config", path, err)
+				}
+			} else {
+				if err = yaml.Unmarshal(data, &scs); err != nil {
+					logger.Errorf("skipping %q at `scrape_config_files` because of failure to parse it: %s", path, err)
+					continue
+				}
 			}
 			scrapeConfigs = append(scrapeConfigs, scs...)
 		}
 	}
-	return scrapeConfigs
+	return scrapeConfigs, nil
 }
 
 // IsDryRun returns true if -promscrape.config.dryRun command-line flag is set
@@ -492,7 +498,10 @@ func (cfg *Config) parseData(data []byte, path string) error {
 	cfg.baseDir = filepath.Dir(absPath)
 
 	// Load cfg.ScrapeConfigFiles into c.ScrapeConfigs
-	scs := mustLoadScrapeConfigFiles(cfg.baseDir, cfg.ScrapeConfigFiles)
+	scs, err := mustLoadScrapeConfigFiles(cfg.baseDir, cfg.ScrapeConfigFiles, *strictParse)
+	if err != nil {
+		return err
+	}
 	cfg.ScrapeConfigFiles = nil
 	cfg.ScrapeConfigs = append(cfg.ScrapeConfigs, scs...)