deployment/docker/rules: fixed expression for vmalert rules

Previously, vmselect may crash if there is not enough free disk space to store tmp files from vmstorage. vmselect stores data blocks received from vmstorage if response size exceeds in-memory limit.
 It reduced vmselect availability, because it makes impossible to serve small queries. And huge query may crash vmselect for all users.

 So this commit adds a error check instead. If there is not enough disk space, vmselect will stop query execution and return error back to user.

fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4688

app/vmselect/netstorage/tmp_blocks_file.go

@@ -62,6 +62,9 @@ type tmpBlocksFile struct {
 	r *fs.ReaderAt
 
 	offset uint64
+
+	// err stores the first error occurred while writing the temporary blocks file.
+	err error
 }
 
 func getTmpBlocksFile() *tmpBlocksFile {
@@ -82,6 +85,7 @@ func putTmpBlocksFile(tbf *tmpBlocksFile) {
 	tbf.f = nil
 	tbf.r = nil
 	tbf.offset = 0
+	tbf.err = nil
 	tmpBlocksFilePool.Put(tbf)
 }
 
@@ -109,6 +113,10 @@ var (
 // and this must be handled.
 func (tbf *tmpBlocksFile) WriteBlockRefData(b []byte) (tmpBlockAddr, error) {
 	var addr tmpBlockAddr
+	if tbf.err != nil {
+		// Do not write anything to the tbf after the first failed write
+		return addr, tbf.err
+	}
 	addr.offset = tbf.offset
 	addr.size = len(b)
 	tbf.offset += uint64(addr.size)
@@ -122,7 +130,8 @@ func (tbf *tmpBlocksFile) WriteBlockRefData(b []byte) (tmpBlockAddr, error) {
 	if tbf.f == nil {
 		f, err := os.CreateTemp(tmpBlocksDir, "")
 		if err != nil {
-			return addr, err
+			tbf.err = fmt.Errorf("cannot create temporary blocks file at %q: %w", tmpBlocksDir, err)
+			return addr, tbf.err
 		}
 		tbf.f = f
 		tmpBlocksFilesCreated.Inc()
@@ -130,7 +139,9 @@ func (tbf *tmpBlocksFile) WriteBlockRefData(b []byte) (tmpBlockAddr, error) {
 	_, err := tbf.f.Write(tbf.buf)
 	tbf.buf = append(tbf.buf[:0], b...)
 	if err != nil {
-		return addr, fmt.Errorf("cannot write block to %q: %w", tbf.f.Name(), err)
+		// The blocks buffered at tbf.buf could be partially lost, mark the tbf as unusable.
+		tbf.err = fmt.Errorf("cannot write block to %q: %w", tbf.f.Name(), err)
+		return addr, tbf.err
 	}
 	return addr, nil
 }
@@ -141,12 +152,16 @@ func (tbf *tmpBlocksFile) Len() uint64 {
 }
 
 func (tbf *tmpBlocksFile) Finalize() error {
+	if tbf.err != nil {
+		return tbf.err
+	}
 	if tbf.f == nil {
 		return nil
 	}
 	fname := tbf.f.Name()
 	if _, err := tbf.f.Write(tbf.buf); err != nil {
-		return fmt.Errorf("cannot write the remaining %d bytes to %q: %w", len(tbf.buf), fname, err)
+		tbf.err = fmt.Errorf("cannot write the remaining %d bytes to %q: %w", len(tbf.buf), fname, err)
+		return tbf.err
 	}
 	tbf.buf = tbf.buf[:0]
 	r := fs.NewReaderAt(tbf.f)
@@ -166,6 +181,10 @@ func (tbf *tmpBlocksFile) Finalize() error {
 }
 
 func (tbf *tmpBlocksFile) MustReadBlockRefAt(partRef storage.PartRef, addr tmpBlockAddr) storage.BlockRef {
+	if tbf.err != nil {
+		// This should never happen, since Finalize() already returns the error for such a tbf.
+		logger.Panicf("BUG: cannot read block at %s from the temporary blocks file with the failed write: %s", addr, tbf.err)
+	}
 	var buf []byte
 	if tbf.r == nil {
 		buf = tbf.buf[addr.offset : addr.offset+uint64(addr.size)]

deployment/docker/rules/alerts-vmalert.yml

@@ -126,10 +126,10 @@ groups:
           (
             vmalert_alerting_rules_last_evaluation_samples
               > on(group,file) group_left()
-            (vmalert_group_rule_results_limit * 0.9)
+            max by (group,file) (vmalert_group_rule_results_limit * 0.9)
           )
             and on(group,file)
-          (vmalert_group_rule_results_limit > 0)
+          (max by (group,file) (vmalert_group_rule_results_limit) > 0)
         for: 5m
         labels:
           severity: warning
@@ -144,10 +144,10 @@ groups:
           (
             vmalert_recording_rules_last_evaluation_samples
               > on(group,file) group_left()
-            (vmalert_group_rule_results_limit * 0.9)
+            max by (group,file) (vmalert_group_rule_results_limit * 0.9)
           )
             and on(group,file)
-          (vmalert_group_rule_results_limit > 0)
+          (max by (group,file) (vmalert_group_rule_results_limit) > 0)
         for: 5m
         labels:
           severity: warning

docs/victoriametrics/changelog/CHANGELOG.md

@@ -33,6 +33,7 @@ See also [LTS releases](https://docs.victoriametrics.com/victoriametrics/lts-rel
 * BUGFIX: [vmagent](https://docs.victoriametrics.com/victoriametrics/vmagent/) and `vminsert` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fix infinite loop in the OpenTelemetry Firehose ingestion endpoint (`/opentelemetry/api/v1/push`) when receiving a malformed record with an incomplete varint in the `data` field. Previously this caused the goroutine to spin forever, permanently consuming CPU until the process was restarted.
 * BUGFIX: [vmalert-tool](https://docs.victoriametrics.com/victoriametrics/vmalert-tool/): reuse connections to `-remoteWrite.url` when writing the results of recording rules and alerts. Previously every series was sent over a new connection, which left a lot of sockets in `TIME_WAIT` state and could exhaust the ephemeral port range. The number of idle connections can be tuned via the new `-remoteWrite.maxIdleConnections` command-line flag. Thanks @evkuzin for contribution.
 * BUGFIX: [vmsingle](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/) and `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): prevent process crash in `sort_by_label_numeric()` and `sort_by_label_numeric_desc()` when a label value contains a number with 309 or more digits. See [#11423](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/11423).
+* BUGFIX: `vmselect` in [VictoriaMetrics cluster](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/): fail the query request directly when there is not enough disk space to store temporary search results. Previously, such queries could lead to vmselect crash. See [#4688](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4688).
 
 ## [v1.150.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.150.0)