vmalert: parse multi doc yaml (#6995)

### Describe Your Changes

This PR adds the feature to parse a multi yaml doc following the
`\n---\n`
The issue is
[6753](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6753)

### Checklist

The following checks are **mandatory**:

- [x] My change adheres [VictoriaMetrics contributing
guidelines](https://docs.victoriametrics.com/contributing/).

---------

Signed-off-by: kirti purohit <kirti.purohit@hpe.com>
Co-authored-by: kirti purohit <kirti.purohit@hpe.com>
Co-authored-by: Jiekun <jiekun@victoriametrics.com>
Co-authored-by: hagen1778 <roman@victoriametrics.com>

app/vmalert/config/config.go

@@ -1,19 +1,20 @@
 package config
 
 import (
+	"bytes"
 	"crypto/md5"
 	"fmt"
 	"hash/fnv"
+	"io"
 	"net/url"
 	"sort"
 	"strings"
 
-	"gopkg.in/yaml.v2"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config/log"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/envtemplate"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
+	"gopkg.in/yaml.v2"
 )
 
 // Group contains list of Rules grouped into
@@ -298,16 +299,30 @@ func parseConfig(data []byte) ([]Group, error) {
 	if err != nil {
 		return nil, fmt.Errorf("cannot expand environment vars: %w", err)
 	}
-	g := struct {
+
+	var result []Group
+	type cfgFile struct {
 		Groups []Group `yaml:"groups"`
 		// Catches all undefined fields and must be empty after parsing.
 		XXX map[string]any `yaml:",inline"`
-	}{}
-	err = yaml.Unmarshal(data, &g)
-	if err != nil {
-		return nil, err
 	}
-	return g.Groups, checkOverflow(g.XXX, "config")
+
+	decoder := yaml.NewDecoder(bytes.NewReader(data))
+	for {
+		var cf cfgFile
+		if err = decoder.Decode(&cf); err != nil {
+			if err == io.EOF { // EOF indicates no more documents to read
+				break
+			}
+			return nil, err
+		}
+		if err = checkOverflow(cf.XXX, "config"); err != nil {
+			return nil, err
+		}
+		result = append(result, cf.Groups...)
+	}
+
+	return result, nil
 }
 
 func checkOverflow(m map[string]any, ctx string) error {

app/vmalert/config/config_test.go

@@ -9,11 +9,10 @@ import (
 	"testing"
 	"time"
 
-	"gopkg.in/yaml.v2"
-
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/notifier"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/templates"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutils"
+	"gopkg.in/yaml.v2"
 )
 
 func TestMain(m *testing.M) {
@@ -40,6 +39,34 @@ groups:
 		w.Write([]byte(`
 groups:
   - name: TestGroup
+    rules:
+      - record: conns
+        expr: max(vm_tcplistener_conns)`))
+	})
+	mux.HandleFunc("/good-multi-doc", func(w http.ResponseWriter, _ *http.Request) {
+		w.Write([]byte(`
+groups:
+  - name: foo
+    rules:
+      - record: conns
+        expr: max(vm_tcplistener_conns)
+---
+groups:
+  - name: bar
+    rules:
+      - record: conns
+        expr: max(vm_tcplistener_conns)`))
+	})
+	mux.HandleFunc("/bad-multi-doc", func(w http.ResponseWriter, _ *http.Request) {
+		w.Write([]byte(`
+bad_field:
+  - name: foo
+    rules:
+      - record: conns
+        expr: max(vm_tcplistener_conns)
+---
+groups:
+  - name: bar
     rules:
       - record: conns
         expr: max(vm_tcplistener_conns)`))
@@ -48,13 +75,23 @@ groups:
 	srv := httptest.NewServer(mux)
 	defer srv.Close()
 
-	if _, err := Parse([]string{srv.URL + "/good-alert", srv.URL + "/good-rr"}, notifier.ValidateTemplates, true); err != nil {
-		t.Fatalf("error parsing URLs %s", err)
+	f := func(urls []string, expErr bool) {
+		for i, u := range urls {
+			urls[i] = srv.URL + u
+		}
+		_, err := Parse(urls, notifier.ValidateTemplates, true)
+		if err != nil && !expErr {
+			t.Fatalf("error parsing URLs %s", err)
+		}
+		if err == nil && expErr {
+			t.Fatalf("expecting error parsing URLs but got none")
+		}
 	}
 
-	if _, err := Parse([]string{srv.URL + "/bad"}, notifier.ValidateTemplates, true); err == nil {
-		t.Fatalf("expected parsing error: %s", err)
-	}
+	f([]string{"/good-alert", "/good-rr", "/good-multi-doc"}, false)
+	f([]string{"/bad"}, true)
+	f([]string{"/bad-multi-doc"}, true)
+	f([]string{"/good-alert", "/bad"}, true)
 }
 
 func TestParse_Success(t *testing.T) {
@@ -86,6 +123,8 @@ func TestParse_Failure(t *testing.T) {
 	f([]string{"testdata/dir/rules4-bad.rules"}, "either `record` or `alert` must be set")
 	f([]string{"testdata/rules/rules1-bad.rules"}, "bad graphite expr")
 	f([]string{"testdata/dir/rules6-bad.rules"}, "missing ':' in header")
+	f([]string{"testdata/rules/rules-multi-doc-bad.rules"}, "unknown fields")
+	f([]string{"testdata/rules/rules-multi-doc-duplicates-bad.rules"}, "duplicate")
 	f([]string{"http://unreachable-url"}, "failed to")
 }
 

app/vmalert/config/testdata/rules/rules-multi-doc-bad.rules

@@ -0,0 +1,29 @@
+groups:
+  - name: groupTest
+    rules:
+      - alert: VMRows
+        for: 1ms
+        expr: vm_rows > 0
+        labels:
+          label: bar
+          host: "{{ $labels.instance }}"
+        annotations:
+          summary: "{{ $value }}"
+invalid-field-1: invalid-value-1
+invalid-field-2: invalid-value-2
+---
+groups:
+  - name: TestGroup
+    interval: 2s
+    concurrency: 2
+    type: graphite
+    rules:
+      - alert: Conns
+        expr: filterSeries(sumSeries(host.receiver.interface.cons),'last','>', 500)
+        for: 3m
+
+        annotations:
+          summary: Too high connection number for {{$labels.instance}}
+          description: "It is {{ $value }} connections for {{$labels.instance}}"
+invalid-field-2: invalid-value-2
+invalid-field-3: invalid-value-3

app/vmalert/config/testdata/rules/rules-multi-doc-duplicates-bad.rules

@@ -0,0 +1,11 @@
+groups:
+  - name: foo
+    rules:
+      - alert: VMRows
+        expr: vm_rows > 0
+---
+groups:
+  - name: foo
+    rules:
+      - alert: VMRows
+        expr: vm_rows > 0

app/vmalert/config/testdata/rules/rules-multi-doc-good.rules

@@ -0,0 +1,15 @@
+
+---
+groups:
+  - name: groupTest
+    rules:
+      - alert: VMRows
+        for: 1ms
+        expr: vm_rows > 0
+        labels:
+          label: bar
+          host: "{{ $labels.instance }}"
+        annotations:
+          summary: "{{ $value }}"
+---
+groups:

app/vmalert/config/testdata/rules/rules-multi-doc2-good.rules

@@ -0,0 +1,46 @@
+---
+groups:
+  - name: groupTest
+    rules:
+      - alert: VMRows
+        for: 1ms
+        expr: vm_rows > 0
+        labels:
+          label: bar
+          host: "{{ $labels.instance }}"
+        annotations:
+          summary: "{{ $value }}"
+  - name: groupTest-2
+    rules:
+      - alert: VMRows-2
+        for: 1ms
+        expr: vm_rows_2 > 0
+        labels:
+          label: bar2
+          host: "{{ $labels.instance }}"
+        annotations:
+          summary: "\n markdown result is : \n---\n # header\n body: \n text \n----\n"
+---
+groups:
+  - name: groupTest-3
+    rules:
+      - alert: VMRows-3
+        for: 1ms
+        expr: vm_rows_3 > 0
+        labels:
+          label: bar_3
+          host: "{{ $labels.instance }}"
+        annotations:
+          summary: "{{ $value }}"
+  - name: groupTest-4
+    rules:
+      - alert: VMRows-4
+        for: 1ms
+        expr: vm_rows_4 > 0
+        labels:
+          label: bar4
+          host: "{{ $labels.instance }}"
+        annotations:
+          summary: "{{ $value }}"
+---
+groups:

app/vmalert/main.go

@@ -31,14 +31,14 @@ import (
 )
 
 var (
-	rulePath = flagutil.NewArrayString("rule", `Path to the files or http url with alerting and/or recording rules.
+	rulePath = flagutil.NewArrayString("rule", `Path to the files or http url with alerting and/or recording rules in YAML format.
 Supports hierarchical patterns and regexpes.
 Examples:
  -rule="/path/to/file". Path to a single file with alerting rules.
  -rule="http://<some-server-addr>/path/to/rules". HTTP URL to a page with alerting rules.
  -rule="dir/*.yaml" -rule="/*.yaml" -rule="gcs://vmalert-rules/tenant_%{TENANT_ID}/prod". 
  -rule="dir/**/*.yaml". Includes all the .yaml files in "dir" subfolders recursively.
-Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
+Rule files support YAML multi-document. Files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.
 
 Enterprise version of vmalert supports S3 and GCS paths to rules.
 For example: gs://bucket/path/to/rules, s3://bucket/path/to/rules

docs/changelog/CHANGELOG.md

@@ -20,6 +20,7 @@ See also [LTS releases](https://docs.victoriametrics.com/lts-releases/).
 
 * FEATURE: add Darwin binaries for [VictoriaMetrics cluster](https://docs.victoriametrics.com/cluster-victoriametrics/) to the release flow. The binaries will be available in the new release.
 * FEATURE: [vmagent](https://docs.victoriametrics.com/vmagent/): allow using HTTP/2 client for Kubernetes service discovery if `-promscrape.kubernetes.useHTTP2Client` cmd-line flag is set. This could help to reduce the amount of opened connections to the Kubernetes API server. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/5971) for the details.
+* FEATURE: [vmalert](https://docs.victoriametrics.com/vmalert/): `-rule` cmd-line flag now supports multi-document YAML files. This could be usefule when rules are retrieved from via HTTP where multiple rule files were merged together in one response. See [this issue](https://github.com/VictoriaMetrics/VictoriaMetrics/issues/6753). Thanks to @Irene-123 for [the pull request](https://github.com/VictoriaMetrics/VictoriaMetrics/pull/6995).
 
 ## [v1.104.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.104.0)
 

docs/vmalert.md

@@ -1427,14 +1427,14 @@ The shortlist of configuration flags is the following:
   -replay.timeTo string
      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.
+     Path to the files or http url with alerting and/or recording rules in YAML format.
      Supports hierarchical patterns and regexpes.
      Examples:
       -rule="/path/to/file". Path to a single file with alerting rules.
       -rule="http://<some-server-addr>/path/to/rules". HTTP URL to a page with alerting rules.
       -rule="dir/*.yaml" -rule="/*.yaml" -rule="gcs://vmalert-rules/tenant_%{TENANT_ID}/prod". 
       -rule="dir/**/*.yaml". Includes all the .yaml files in "dir" subfolders recursively.
-     Rule files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.   
+     Rule files support YAML multi-document. Files may contain %{ENV_VAR} placeholders, which are substituted by the corresponding env vars.  
      Enterprise version of vmalert supports S3 and GCS paths to rules.
      For example: gs://bucket/path/to/rules, s3://bucket/path/to/rules
      S3 and GCS paths support only matching by prefix, e.g. s3://bucket/dir/rule_ matches