Merge branch 'public-single-node' into pmm-6401-read-prometheus-data-files

README.md

@@ -1279,6 +1279,7 @@ The most interesting metrics are:
 
 VictoriaMetrics also exposes currently running queries with their execution times at `/api/v1/status/active_queries` page.
 
+See the example of alerting rules for VM components [here](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/deployment/docker/alerts.yml).
 
 ## Troubleshooting
 

app/vmagent/remotewrite/statconn.go

@@ -5,9 +5,9 @@ import (
 	"net"
 	"strings"
 	"sync/atomic"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
-	"github.com/VictoriaMetrics/fasthttp"
 	"github.com/VictoriaMetrics/metrics"
 )
 
@@ -15,11 +15,10 @@ func statDial(network, addr string) (conn net.Conn, err error) {
 	if !strings.HasPrefix(network, "tcp") {
 		return nil, fmt.Errorf("unexpected network passed to statDial: %q; it must start from `tcp`", network)
 	}
-	if netutil.TCP6Enabled() {
-		conn, err = fasthttp.DialDualStack(addr)
-	} else {
-		conn, err = fasthttp.Dial(addr)
+	if !netutil.TCP6Enabled() {
+		network = "tcp4"
 	}
+	conn, err = net.DialTimeout(network, addr, 5*time.Second)
 	dialsTotal.Inc()
 	if err != nil {
 		dialErrors.Inc()

app/vmalert/config/testdata/rules2-good.rules

@@ -17,6 +17,7 @@ groups:
           (up == 1)
         labels:
           job: '{{ $labels.job }}'
+          dynamic: '{{ $x := query "up" | first | value }}{{ if eq 1.0 $x }}one{{ else }}unknown{{ end }}'
         annotations:
           description: Job {{ $labels.job }} is up!
           summary: All instances up {{ range query "up" }}

app/vmalert/notifier/template_func.go

@@ -178,7 +178,9 @@ func InitTemplateFunc(externalURL *url.URL) {
 		// it is present here only for validation purposes, when there is no
 		// provided datasource.
 		"query": func(q string) ([]datasource.Metric, error) {
-			return nil, nil
+			// return non-empty slice to pass validation with chained functions in template
+			// see issue #989 for details
+			return []datasource.Metric{{}}, nil
 		},
 		"first": func(metrics []datasource.Metric) (datasource.Metric, error) {
 			if len(metrics) > 0 {

deployment/docker/alerts.yml

@@ -1,23 +1,174 @@
+# File contains default list of alerts for vm-single and vmagent services.
+# The alerts below are just recommendations and may require some updates
+# and threshold calibration according to every specific setup.
 groups:
-  - name: groupGorSingleAlert
+  - name: serviceHealth
     rules:
-      - alert: VMRows
-        for: 10s
-        expr: vm_rows > 0
+      # note the `job` filter and update accordingly to your setup
+      - alert: TooManyRestarts
+        expr: changes(process_start_time_seconds{job=~"victoriametrics|vmagent|vmalert"}[15m]) > 2
         labels:
-          label: bar
-          host: "{{ $labels.instance }}"
+          severity: critical
         annotations:
-          summary: "{{ $value|humanize }}"
-          description: "{{$labels}}"
-  - name: TestGroup
+          summary: "{{ $labels.job }} too many restarts (instance {{ $labels.instance }})"
+          description: "Job {{ $labels.job }} has restarted more than twice in the last 15 minutes.
+            It might be crashlooping."
+
+  # Alerts group for VM single assumes that Grafana dashboard
+  # https://grafana.com/grafana/dashboards/10229 is installed.
+  # Pls update the `dashboard` annotation according to your setup.
+  - name: vmsingle
+    interval: 30s
+    concurrency: 2
     rules:
-      - alert: Conns
-        expr: sum(vm_tcplistener_conns) by(instance) > 1
-        for: 5s
+      - alert: DiskRunsOutOfSpaceIn3Days
+        expr: |
+          vm_free_disk_space_bytes / ignoring(path) (
+           (
+            sum(rate(vm_rows_added_to_storage_total[1d])) -
+            sum(rate(vm_deduplicated_samples_total[1d])) without(type)
+           )
+          *
+           (
+            sum(vm_data_size_bytes{type!="indexdb"}) /
+            sum(vm_rows{type!="indexdb"})
+           )
+          ) < 3 * 24 * 3600
+        for: 30m
+        labels:
+          severity: critical
         annotations:
-          summary: "Too high connection number for {{$labels.instance}}"
-          description: "It is {{ $value }} connections for {{$labels.instance}}"
-      - alert: ExampleAlertAlwaysFiring
-        expr: sum by(job)
-          (up == 1)
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=73&var-instance={{ $labels.instance }}"
+          summary: "Instance {{ $labels.instance }} will run out of disk space soon"
+          description: "Taking into account current ingestion rate, free disk space will be enough only
+            for {{ $value | humanizeDuration }} on instance {{ $labels.instance }}.\n
+            Consider to limit the ingestion rate, decrease retention or scale the disk space if possible."
+
+      - alert: RequestErrorsToAPI
+        expr: increase(vm_http_request_errors_total[5m]) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=35&var-instance={{ $labels.instance }}"
+          summary: "Too many errors served for path {{ $labels.path }} (instance {{ $labels.instance }})"
+          description: "Requests to path {{ $labels.path }} are receiving errors.
+            Please verify if clients are sending correct requests."
+
+      - alert: ConcurrentFlushesHitTheLimit
+        expr: vm_concurrent_addrows_current >= vm_concurrent_addrows_capacity
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=59&var-instance={{ $labels.instance }}"
+          summary: "VictoriMetrics on instance {{ $labels.instance }} is constantly hitting concurrent flushes limit"
+          description: "The limit of concurrent flushes on instance {{ $labels.instance }} is equal to number of CPUs.\n
+            When VictoriaMetrics constantly hits the limit it means that storage is overloaded and requires more CPU."
+
+      - alert: TooManyLogs
+        expr: sum(increase(vm_log_messages_total{level!="info"}[5m])) by (job, instance) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=67&var-instance={{ $labels.instance }}"
+          summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
+          description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n
+           Worth to check logs for specific error messages."
+
+      - alert: RowsRejectedOnIngestion
+        expr: sum(rate(vm_rows_ignored_total[5m])) by (instance, reason) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=58&var-instance={{ $labels.instance }}"
+          summary: "Some rows are rejected on \"{{ $labels.instance }}\" on ingestion attempt"
+          description: "VM is rejecting to ingest rows on \"{{ $labels.instance }}\" due to the
+            following reason: \"{{ $labels.reason }}\""
+
+      - alert: TooHighChurnRate
+        expr: |
+          (
+             sum(rate(vm_new_timeseries_created_total[5m])) by(instance)
+             /
+             sum(rate(vm_rows_inserted_total[5m])) by (instance)
+           ) > 0.1
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=66&var-instance={{ $labels.instance }}"
+          summary: "Churn rate is more than 10% on \"{{ $labels.instance }}\" for the last 15m"
+          description: "VM constantly creates new time series on \"{{ $labels.instance }}\".\n
+            This effect is known as Churn Rate.\n
+            High Churn Rate tightly connected with database performance and may
+            result in unexpected OOM's or slow queries."
+
+      - alert: TooHighSlowInsertsRate
+        expr: |
+          (
+             sum(rate(vm_slow_row_inserts_total[5m])) by(instance)
+             /
+             sum(rate(vm_rows_inserted_total[5m])) by (instance)
+           ) > 0.5
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=68&var-instance={{ $labels.instance }}"
+          summary: "Percentage of slow inserts is more than 50% on \"{{ $labels.instance }}\" for the last 15m"
+          description: "High rate of slow inserts on \"{{ $labels.instance }}\" may be a sign of resource exhaustion
+            for the current load. It is likely more RAM is needed for optimal handling of the current number of active time series."
+
+  # Alerts group for vmagent assumes that Grafana dashboard
+  # https://grafana.com/grafana/dashboards/12683 is installed.
+  # Pls update the `dashboard` annotation according to your setup.
+  - name: vmagent
+    interval: 30s
+    concurrency: 2
+    rules:
+      - alert: PersistentQueueIsDroppingData
+        expr: sum(increase(vm_persistentqueue_bytes_dropped_total[5m])) by (job, instance) > 0
+        for: 10m
+        labels:
+          severity: critical
+        annotations:
+          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=49&var-instance={{ $labels.instance }}"
+          summary: "Instance {{ $labels.instance }} is dropping data from persistent queue"
+          description: "Vmagent dropped {{ $value | humanize1024 }} from persistent queue
+              on instance {{ $labels.instance }} for the last 10m."
+
+      - alert: TooManyScrapeErrors
+        expr: sum(increase(vm_promscrape_scrapes_failed_total[5m])) by (job, instance) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=31&var-instance={{ $labels.instance }}"
+          summary: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} fails to scrape targets for last 15m"
+
+      - alert: TooManyWriteErrors
+        expr: |
+          (sum(increase(vm_ingestserver_request_errors_total[5m])) by (job, instance)
+          +
+          sum(increase(vmagent_http_request_errors_total[5m])) by (job, instance)) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=77&var-instance={{ $labels.instance }}"
+          summary: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} responds with errors to write requests for last 15m."
+
+      - alert: TooManyRemoteWriteErrors
+        expr: sum(rate(vmagent_remotewrite_retries_count_total[5m])) by(job, instance, url) > 0
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=61&var-instance={{ $labels.instance }}"
+          summary: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} fails to push to remote storage"
+          description: "Vmagent fails to push data via remote write protocol to destination \"{{ $labels.url }}\"\n
+            Ensure that destination is up and reachable."
+

deployment/docker/prometheus.yml

@@ -1,5 +1,5 @@
 global:
-  scrape_interval:     10s
+  scrape_interval: 10s
 
 scrape_configs:
   - job_name: 'vmagent'

docs/CHANGELOG.md

@@ -2,6 +2,8 @@
 
 # tip
 
+* BUGFIX: vmagent: prevent from `dialing to the given TCP address time out` error when scraping big number of unavailable targets. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/987
+
 * FEATURE: disable final merge for data for the previous month at the beginning of new month, since it may result in high disk IO and CPU usage. Final merge can be enabled by setting `-finalMergeDelay` command-line flag to positive duration.
 
 

go.mod

@@ -7,7 +7,7 @@ require (
 
 	// Do not use the original github.com/valyala/fasthttp because of issues
 	// like https://github.com/valyala/fasthttp/commit/996610f021ff45fdc98c2ce7884d5fa4e7f9199b
-	github.com/VictoriaMetrics/fasthttp v1.0.9
+	github.com/VictoriaMetrics/fasthttp v1.0.11
 	github.com/VictoriaMetrics/metrics v1.12.3
 	github.com/VictoriaMetrics/metricsql v0.9.1
 	github.com/aws/aws-sdk-go v1.36.23

go.sum

@@ -81,8 +81,8 @@ github.com/Shopify/sarama v1.19.0/go.mod h1:FVkBWblsNy7DGZRfXLU0O9RCGt5g3g3yEuWX
 github.com/Shopify/toxiproxy v2.1.4+incompatible/go.mod h1:OXgGpZ6Cli1/URJOF1DMxUHB2q5Ap20/P/eIdh4G0pI=
 github.com/VictoriaMetrics/fastcache v1.5.7 h1:4y6y0G8PRzszQUYIQHHssv/jgPHAb5qQuuDNdCbyAgw=
 github.com/VictoriaMetrics/fastcache v1.5.7/go.mod h1:ptDBkNMQI4RtmVo8VS/XwRY6RoTu1dAWCbrk+6WsEM8=
-github.com/VictoriaMetrics/fasthttp v1.0.9 h1:Fja1tfcNMNoUD7RJDYpjGx2CsSfXkUbISKY4kNafdN4=
-github.com/VictoriaMetrics/fasthttp v1.0.9/go.mod h1:3SeUL4zwB/p/a9aEeRc6gdlbrtNHXBJR6N376EgiSHU=
+github.com/VictoriaMetrics/fasthttp v1.0.11 h1:6XOvE1pF/EhW8qoi7V5qJQJ2rhNV+UGrb1/a9vMbTiw=
+github.com/VictoriaMetrics/fasthttp v1.0.11/go.mod h1:3SeUL4zwB/p/a9aEeRc6gdlbrtNHXBJR6N376EgiSHU=
 github.com/VictoriaMetrics/metrics v1.12.2/go.mod h1:Z1tSfPfngDn12bTfZSCqArT3OPY3u88J12hSoOhuiRE=
 github.com/VictoriaMetrics/metrics v1.12.3 h1:Fe6JHC6MSEKa+BtLhPN8WIvS+HKPzMc2evEpNeCGy7I=
 github.com/VictoriaMetrics/metrics v1.12.3/go.mod h1:Z1tSfPfngDn12bTfZSCqArT3OPY3u88J12hSoOhuiRE=

lib/proxy/proxy.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"net"
 	"net/url"
+	"time"
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/fasthttp"
@@ -80,10 +81,12 @@ func (u *URL) NewDialFunc(tlsConfig *tls.Config) (fasthttp.DialFunc, error) {
 }
 
 func defaultDialFunc(addr string) (net.Conn, error) {
+	network := "tcp4"
 	if netutil.TCP6Enabled() {
-		return fasthttp.DialDualStack(addr)
+		network = "tcp"
 	}
-	return fasthttp.Dial(addr)
+	// Do not use fasthttp.Dial because of https://github.com/VictoriaMetrics/VictoriaMetrics/issues/987
+	return net.DialTimeout(network, addr, 5*time.Second)
 }
 
 // sendConnectRequest sends CONNECT request to proxyConn for the given addr and authHeader and returns the established connection to dstAddr.

vendor/modules.txt

@@ -10,7 +10,7 @@ cloud.google.com/go/internal/version
 cloud.google.com/go/storage
 # github.com/VictoriaMetrics/fastcache v1.5.7
 github.com/VictoriaMetrics/fastcache
-# github.com/VictoriaMetrics/fasthttp v1.0.9
+# github.com/VictoriaMetrics/fasthttp v1.0.11
 github.com/VictoriaMetrics/fasthttp
 github.com/VictoriaMetrics/fasthttp/fasthttputil
 github.com/VictoriaMetrics/fasthttp/stackless