app/vmagent,lib/persistentqueue: show warning message if --remoteWrite.maxDiskUsagePerURL flag lower than 500MB (#4196)

* app/vmagent,lib/persistentqueue: show warning message if `--remoteWrite.maxDiskUsagePerURL` flag lower than 500MB

* app/vmagent,lib/persistentqueue: linter fix

* app/vmagent,lib/persistentqueue: fix comment

app/vmagent/README.md

@@ -1485,7 +1485,7 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -remoteWrite.maxDailySeries int
      The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter
   -remoteWrite.maxDiskUsagePerURL array
-     The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500MB. Disk usage is unlimited if the value is set to 0
+     The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks. It is recommended to set the value for this flag to a multiple of the block size 500MB. Disk usage is unlimited if the value is set to 0
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB.
      Supports array of values separated by comma or specified via multiple flags.
   -remoteWrite.maxHourlySeries int

app/vmagent/remotewrite/remotewrite.go

@@ -47,7 +47,7 @@ var (
 		"It is hidden by default, since it can contain sensitive info such as auth key")
 	maxPendingBytesPerURL = flagutil.NewArrayBytes("remoteWrite.maxDiskUsagePerURL", "The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath "+
 		"for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. "+
-		"Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500MB. "+
+		"Buffered data is stored in ~500MB chunks. It is recommended to set the value for this flag to a multiple of the block size 500MB. "+
 		"Disk usage is unlimited if the value is set to 0")
 	significantFigures = flagutil.NewArrayInt("remoteWrite.significantFigures", "The number of significant figures to leave in metric values before writing them "+
 		"to remote storage. See https://en.wikipedia.org/wiki/Significant_figures . Zero value saves all the significant figures. "+
@@ -523,6 +523,9 @@ func newRemoteWriteCtx(argIdx int, at *auth.Token, remoteWriteURL *url.URL, maxI
 	h := xxhash.Sum64([]byte(pqURL.String()))
 	queuePath := filepath.Join(*tmpDataPath, persistentQueueDirname, fmt.Sprintf("%d_%016X", argIdx+1, h))
 	maxPendingBytes := maxPendingBytesPerURL.GetOptionalArgOrDefault(argIdx, 0)
+	if maxPendingBytes != 0 && maxPendingBytes < persistentqueue.DefaultChunkFileSize {
+		logger.Warnf("specified flag `--remoteWrite.maxDiskUsagePerURL` is lower than buffered data chunks. It is recommended to set the value for this flag to a multiple of the block size 500MB.")
+	}
 	fq := persistentqueue.MustOpenFastQueue(queuePath, sanitizedURL, maxInmemoryBlocks, maxPendingBytes)
 	_ = metrics.GetOrCreateGauge(fmt.Sprintf(`vmagent_remotewrite_pending_data_bytes{path=%q, url=%q}`, queuePath, sanitizedURL), func() float64 {
 		return float64(fq.GetPendingBytes())

docs/vmagent.md

@@ -1489,7 +1489,7 @@ See the docs at https://docs.victoriametrics.com/vmagent.html .
   -remoteWrite.maxDailySeries int
      The maximum number of unique series vmagent can send to remote storage systems during the last 24 hours. Excess series are logged and dropped. This can be useful for limiting series churn rate. See https://docs.victoriametrics.com/vmagent.html#cardinality-limiter
   -remoteWrite.maxDiskUsagePerURL array
-     The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks, so the minimum practical value for this flag is 500MB. Disk usage is unlimited if the value is set to 0
+     The maximum file-based buffer size in bytes at -remoteWrite.tmpDataPath for each -remoteWrite.url. When buffer size reaches the configured maximum, then old data is dropped when adding new data to the buffer. Buffered data is stored in ~500MB chunks. It is recommended to set the value for this flag to a multiple of the block size 500MB. Disk usage is unlimited if the value is set to 0
      Supports the following optional suffixes for size values: KB, MB, GB, TB, KiB, MiB, GiB, TiB.
      Supports array of values separated by comma or specified via multiple flags.
   -remoteWrite.maxHourlySeries int

lib/persistentqueue/persistentqueue.go

@@ -22,7 +22,8 @@ import (
 // MaxBlockSize is the maximum size of the block persistent queue can work with.
 const MaxBlockSize = 32 * 1024 * 1024
 
-const defaultChunkFileSize = (MaxBlockSize + 8) * 16
+// DefaultChunkFileSize represents default chunk file size
+const DefaultChunkFileSize = (MaxBlockSize + 8) * 16
 
 var chunkFileNameRegex = regexp.MustCompile("^[0-9A-F]{16}$")
 
@@ -122,7 +123,7 @@ func mustOpen(path, name string, maxPendingBytes int64) *queue {
 	if maxPendingBytes < 0 {
 		maxPendingBytes = 0
 	}
-	return mustOpenInternal(path, name, defaultChunkFileSize, MaxBlockSize, uint64(maxPendingBytes))
+	return mustOpenInternal(path, name, DefaultChunkFileSize, MaxBlockSize, uint64(maxPendingBytes))
 }
 
 func mustOpenInternal(path, name string, chunkFileSize, maxBlockSize, maxPendingBytes uint64) *queue {

lib/persistentqueue/persistentqueue_test.go

@@ -53,7 +53,7 @@ func TestQueueOpen(t *testing.T) {
 		path := "queue-open-too-new-chunk"
 		mustCreateDir(path)
 		mustCreateEmptyMetainfo(path, "foobar")
-		mustCreateFile(filepath.Join(path, fmt.Sprintf("%016X", 100*uint64(defaultChunkFileSize))), "asdf")
+		mustCreateFile(filepath.Join(path, fmt.Sprintf("%016X", 100*uint64(DefaultChunkFileSize))), "asdf")
 		q := mustOpen(path, "foobar", 0)
 		q.MustClose()
 		mustDeleteDir(path)
@@ -63,8 +63,8 @@ func TestQueueOpen(t *testing.T) {
 		mustCreateDir(path)
 		mi := &metainfo{
 			Name:         "foobar",
-			ReaderOffset: defaultChunkFileSize,
+			ReaderOffset: DefaultChunkFileSize,
-			WriterOffset: defaultChunkFileSize,
+			WriterOffset: DefaultChunkFileSize,
 		}
 		if err := mi.WriteToFile(filepath.Join(path, metainfoFilename)); err != nil {
 			t.Fatalf("unexpected error: %s", err)
@@ -79,7 +79,7 @@ func TestQueueOpen(t *testing.T) {
 		mustCreateDir(path)
 		mi := &metainfo{
 			Name:         "foobar",
-			ReaderOffset: defaultChunkFileSize + 123,
+			ReaderOffset: DefaultChunkFileSize + 123,
 		}
 		if err := mi.WriteToFile(filepath.Join(path, metainfoFilename)); err != nil {
 			t.Fatalf("unexpected error: %s", err)