panxiao81/homelab-infra
1
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases Wiki Activity

清理已停用的 VictoriaMetrics Compose 配置并记录旧数据卷删除
yaml / yaml (pull_request) Successful in 15s
Details

Browse Source
This commit is contained in:
panxiao81
2026-09-16 15:53:00 +00:00
parent f36e8a1733
commit d9486b4c8c
19 changed files with 14 additions and 20491 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/victoriametrics/alertmanager.yaml
-5
View File
@@ -1,5 +0,0 @@
route:
receiver: blackhole
receivers:
- name: blackhole
apps/victoriametrics/compose.yaml
-94
View File
@@ -1,94 +0,0 @@
services:
# Metrics collector.
# It scrapes targets defined in --promscrape.config
# And forward them to --remoteWrite.url
vmagent:
image: victoriametrics/vmagent:v1.132.0
depends_on:
- "victoriametrics"
ports:
- 8429:8429
volumes:
- vmagentdata:/vmagentdata
- ./prometheus.yaml:/etc/prometheus/prometheus.yml
command:
- "--promscrape.config=/etc/prometheus/prometheus.yml"
- "--remoteWrite.url=http://victoriametrics:8428/api/v1/write"
restart: always
# VictoriaMetrics instance, a single process responsible for
# storing metrics and serve read requests.
victoriametrics:
image: victoriametrics/victoria-metrics:v1.132.0
ports:
- 8428:8428
- 8089:8089
- 8089:8089/udp
- 2003:2003
- 2003:2003/udp
- 4242:4242
volumes:
- vmdata:/storage
command:
- "--storageDataPath=/storage"
- "--graphiteListenAddr=:2003"
- "--opentsdbListenAddr=:4242"
- "--httpListenAddr=:8428"
- "--influxListenAddr=:8089"
- "--vmalert.proxyURL=http://vmalert:8880"
restart: always
grafana:
image: grafana/grafana:12.2.0
depends_on:
- "victoriametrics"
ports:
- 3000:3000
volumes:
- grafanadata:/var/lib/grafana
- ./provisioning/datasources/prometheus-datasource/single.yml:/etc/grafana/provisioning/datasources/single.yml
- ./provisioning/dashboards:/etc/grafana/provisioning/dashboards
- ./provisioning/dashboards/victoriametrics.json:/var/lib/grafana/dashboards/vm.json
- ./provisioning/dashboards/vmagent.json:/var/lib/grafana/dashboards/vmagent.json
- ./provisioning/dashboards/vmalert.json:/var/lib/grafana/dashboards/vmalert.json
restart: always
# vmalert executes alerting and recording rules
vmalert:
image: victoriametrics/vmalert:v1.132.0
depends_on:
- "victoriametrics"
- "alertmanager"
ports:
- 8880:8880
volumes:
- ./rules/alerts.yml:/etc/alerts/alerts.yml
- ./rules/alerts-health.yml:/etc/alerts/alerts-health.yml
- ./rules/alerts-vmagent.yml:/etc/alerts/alerts-vmagent.yml
- ./rules/alerts-vmalert.yml:/etc/alerts/alerts-vmalert.yml
command:
- "--datasource.url=http://victoriametrics:8428/"
- "--remoteRead.url=http://victoriametrics:8428/"
- "--remoteWrite.url=http://vmagent:8429/"
- "--notifier.url=http://alertmanager:9093/"
- "--rule=/etc/alerts/*.yml"
# display source of alerts in grafana
- "--external.url=http://127.0.0.1:3000" #grafana outside container
- '--external.alert.source=explore?orgId=1&left={"datasource":"VictoriaMetrics","queries":[{"expr":{{.Expr|jsonEscape|queryEscape}},"refId":"A"}],"range":{"from":"{{ .ActiveAt.UnixMilli }}","to":"now"}}'
restart: always
# alertmanager receives alerting notifications from vmalert
# and distributes them according to --config.file.
alertmanager:
image: prom/alertmanager:v0.28.1
volumes:
- ./alertmanager.yaml:/config/alertmanager.yml
command:
- "--config.file=/config/alertmanager.yml"
ports:
- 9093:9093
restart: always
volumes:
vmagentdata: {}
vmdata: {}
grafanadata: {}
apps/victoriametrics/prometheus.yaml
-16
View File
@@ -1,16 +0,0 @@
global:
scrape_interval: 10s
scrape_configs:
- job_name: vmagent
static_configs:
- targets:
- vmagent:8429
- job_name: vmalert
static_configs:
- targets:
- vmalert:8880
- job_name: victoriametrics
static_configs:
- targets:
- victoriametrics:8428
apps/victoriametrics/provisioning/dashboards/dashboard.yml
-9
View File
@@ -1,9 +0,0 @@
apiVersion: 1
providers:
- name: Prometheus
orgId: 1
folder: ''
type: file
options:
path: /var/lib/grafana/dashboards
apps/victoriametrics/provisioning/dashboards/datasources/prometheus-datasource/single.yml
-11
View File
@@ -1,11 +0,0 @@
apiVersion: 1
datasources:
- name: VictoriaMetrics
type: prometheus
access: proxy
url: http://victoriametrics:8428
isDefault: true
jsonData:
prometheusType: Prometheus
prometheusVersion: 2.24.0
apps/victoriametrics/provisioning/dashboards/victoriametrics.json
-7264
View File
File diff suppressed because it is too large Load Diff
apps/victoriametrics/provisioning/datasources/prometheus-datasource/single.yml
-11
View File
@@ -1,11 +0,0 @@
apiVersion: 1
datasources:
- name: VictoriaMetrics
type: prometheus
access: proxy
url: http://victoriametrics:8428
isDefault: true
jsonData:
prometheusType: Prometheus
prometheusVersion: 2.24.0
apps/victoriametrics/rules/alerts-health.yml
-149
View File
@@ -1,149 +0,0 @@
# File contains default list of alerts for various VM components.
# The following alerts are recommended for use for any VM installation.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
- name: vm-health
# note the `job` filter and update accordingly to your setup
rules:
- alert: TooManyRestarts
expr: changes(process_start_time_seconds{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"}[15m]) > 2
labels:
severity: critical
annotations:
summary: "{{ $labels.job }} too many restarts (instance {{ $labels.instance }})"
description: >
Job {{ $labels.job }} (instance {{ $labels.instance }}) has restarted more than twice in the last 15 minutes.
It might be crashlooping.
- alert: ServiceDown
expr: up{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"} == 0
for: 2m
labels:
severity: critical
annotations:
summary: "Service {{ $labels.job }} is down on {{ $labels.instance }}"
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes."
- alert: ProcessNearFDLimits
expr: (process_max_fds - process_open_fds) < 100
for: 5m
labels:
severity: critical
annotations:
summary: "Number of free file descriptors is less than 100 for \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") for the last 5m"
description: |
Exhausting OS file descriptors limit can cause severe degradation of the process.
Consider to increase the limit as fast as possible.
- alert: TooHighMemoryUsage
expr: (min_over_time(process_resident_memory_anon_bytes[10m]) / vm_available_memory_bytes) > 0.8
for: 5m
labels:
severity: critical
annotations:
summary: "It is more than 80% of memory used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\")"
description: |
Too high memory usage may result into multiple issues such as OOMs or degraded performance.
Consider to either increase available memory or decrease the load on the process.
- alert: TooHighCPUUsage
expr: rate(process_cpu_seconds_total[5m]) / process_cpu_cores_available > 0.9
for: 5m
labels:
severity: critical
annotations:
summary: "More than 90% of CPU is used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") during the last 5m"
description: >
Too high CPU usage may be a sign of insufficient resources and make process unstable.
Consider to either increase available CPU resources or decrease the load on the process.
- alert: TooHighGoroutineSchedulingLatency
expr: histogram_quantile(0.99, sum(rate(go_sched_latencies_seconds_bucket{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"}[5m])) by (le, job, instance)) > 0.1
for: 15m
labels:
severity: critical
annotations:
summary: "\"{{ $labels.job }}\"(\"{{ $labels.instance }}\") has insufficient CPU resources for >15m"
description: >
Go runtime is unable to schedule goroutines execution in acceptable time. This is usually a sign of
insufficient CPU resources or CPU throttling. Verify that service has enough CPU resources. Otherwise,
the service could work unreliably with delays in processing.
- alert: TooManyLogs
expr: sum(increase(vm_log_messages_total{level="error"}[5m])) without (app_version, location) > 0
for: 15m
labels:
severity: warning
annotations:
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.
Worth to check logs for specific error messages.
- alert: TooManyTSIDMisses
expr: increase(vm_missing_tsids_for_metric_id_total[5m]) > 0
for: 15m
labels:
severity: critical
annotations:
summary: "Unexpected TSID misses for job \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes"
description: |
Unexpected TSID misses for \"{{ $labels.job }}\" ({{ $labels.instance }}) for the last 15 minutes.
If this happens after unclean shutdown of VictoriaMetrics process (via \"kill -9\", OOM or power off),
then this is OK - the alert must go away in a few minutes after the restart.
Otherwise this may point to the corruption of index data.
- alert: ConcurrentInsertsHitTheLimit
expr: avg_over_time(vm_concurrent_insert_current[1m]) >= vm_concurrent_insert_capacity
for: 15m
labels:
severity: warning
annotations:
summary: "{{ $labels.job }} on instance {{ $labels.instance }} is constantly hitting concurrent inserts limit"
description: |
The limit of concurrent inserts on instance {{ $labels.instance }} depends on the number of CPUs.
Usually, when component constantly hits the limit it is likely the component is overloaded and requires more CPU.
In some cases for components like vmagent or vminsert the alert might trigger if there are too many clients
making write attempts. If vmagent's or vminsert's CPU usage and network saturation are at normal level, then
it might be worth adjusting `-maxConcurrentInserts` cmd-line flag.
- alert: IndexDBRecordsDrop
expr: increase(vm_indexdb_items_dropped_total[5m]) > 0
labels:
severity: critical
annotations:
summary: "IndexDB skipped registering items during data ingestion with reason={{ $labels.reason }}."
description: |
VictoriaMetrics could skip registering new timeseries during ingestion if they fail the validation process.
For example, `reason=too_long_item` means that time series cannot exceed 64KB. Please, reduce the number
of labels or label values for such series. Or enforce these limits via `-maxLabelsPerTimeseries` and
`-maxLabelValueLen` command-line flags.
- alert: RowsRejectedOnIngestion
expr: rate(vm_rows_ignored_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "Some rows are rejected on \"{{ $labels.instance }}\" on ingestion attempt"
description: "Ingested rows on instance \"{{ $labels.instance }}\" are rejected due to the
following reason: \"{{ $labels.reason }}\""
- alert: TooHighQueryLoad
expr: increase(vm_concurrent_select_limit_timeout_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "Read queries fail with timeout for {{ $labels.job }} on instance {{ $labels.instance }}"
description: |
Instance {{ $labels.instance }} ({{ $labels.job }}) is failing to serve read queries during last 15m.
Concurrency limit `-search.maxConcurrentRequests` was reached on this instance and extra queries were
put into the queue for `-search.maxQueueDuration` interval. But even after waiting in the queue these queries weren't served.
This happens if instance is overloaded with the current workload, or datasource is too slow to respond.
Possible solutions are the following:
* reduce the query load;
* increase compute resources or number of replicas;
* adjust limits `-search.maxConcurrentRequests` and `-search.maxQueueDuration`.
See more at https://docs.victoriametrics.com/victoriametrics/troubleshooting/#slow-queries
apps/victoriametrics/rules/alerts-vmagent.yml
-172
View File
@@ -1,172 +0,0 @@
# File contains default list of alerts for vmagent service.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
# 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])) without (path) > 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: RejectedRemoteWriteDataBlocksAreDropped
expr: sum(increase(vmagent_remotewrite_packets_dropped_total[5m])) without (url) > 0
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=79&var-instance={{ $labels.instance }}"
summary: "Vmagent is dropping data blocks that are rejected by remote storage"
description: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} drops the rejected by
remote-write server data blocks. Check the logs to find the reason for rejects."
- alert: TooManyScrapeErrors
expr: increase(vm_promscrape_scrapes_failed_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=31&var-instance={{ $labels.instance }}"
summary: "Vmagent fails to scrape one or more targets"
description: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} fails to scrape targets for last 15m"
- alert: ScrapePoolHasNoTargets
expr: sum(vm_promscrape_scrape_pool_targets) without (status, instance, pod) == 0
for: 30m
labels:
severity: warning
annotations:
summary: "Vmagent has scrape_pool with 0 configured/discovered targets"
description: "Vmagent \"{{ $labels.job }}\" has scrape_pool \"{{ $labels.scrape_job }}\"
with 0 discovered targets. It is likely a misconfiguration. Please follow https://docs.victoriametrics.com/victoriametrics/vmagent/#debugging-scrape-targets
to troubleshoot the scraping config."
- alert: TooManyWriteErrors
expr: |
(sum(increase(vm_ingestserver_request_errors_total[5m])) without (name,net,type)
+
sum(increase(vmagent_http_request_errors_total[5m])) without (path,protocol)) > 0
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=77&var-instance={{ $labels.instance }}"
summary: "Vmagent responds with too many errors on data ingestion protocols"
description: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} responds with errors to write requests for last 15m."
- alert: TooManyRemoteWriteErrors
expr: rate(vmagent_remotewrite_retries_count_total[5m]) > 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."
- alert: RemoteWriteConnectionIsSaturated
expr: |
(
rate(vmagent_remotewrite_send_duration_seconds_total[5m])
/
vmagent_remotewrite_queues
) > 0.9
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=84&var-instance={{ $labels.instance }}"
summary: "Remote write connection from \"{{ $labels.job }}\" (instance {{ $labels.instance }}) to {{ $labels.url }} is saturated"
description: "The remote write connection between vmagent \"{{ $labels.job }}\" (instance {{ $labels.instance }}) and destination \"{{ $labels.url }}\"
is saturated by more than 90% and vmagent won't be able to keep up.\n
There could be the following reasons for this:\n
* vmagent can't send data fast enough through the existing network connections. Increase `-remoteWrite.queues` cmd-line flag value to establish more connections per destination.\n
* remote destination can't accept data fast enough. Check if remote destination has enough resources for processing."
- alert: PersistentQueueForWritesIsSaturated
expr: rate(vm_persistentqueue_write_duration_seconds_total[5m]) > 0.9
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=98&var-instance={{ $labels.instance }}"
summary: "Persistent queue writes for instance {{ $labels.instance }} are saturated"
description: "Persistent queue writes for vmagent \"{{ $labels.job }}\" (instance {{ $labels.instance }})
are saturated by more than 90% and vmagent won't be able to keep up with flushing data on disk.
In this case, consider to decrease load on the vmagent or improve the disk throughput."
- alert: PersistentQueueForReadsIsSaturated
expr: rate(vm_persistentqueue_read_duration_seconds_total[5m]) > 0.9
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=99&var-instance={{ $labels.instance }}"
summary: "Persistent queue reads for instance {{ $labels.instance }} are saturated"
description: "Persistent queue reads for vmagent \"{{ $labels.job }}\" (instance {{ $labels.instance }})
are saturated by more than 90% and vmagent won't be able to keep up with reading data from the disk.
In this case, consider to decrease load on the vmagent or improve the disk throughput."
- alert: SeriesLimitHourReached
expr: (vmagent_hourly_series_limit_current_series / vmagent_hourly_series_limit_max_series) > 0.9
labels:
severity: critical
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=88&var-instance={{ $labels.instance }}"
summary: "Instance {{ $labels.instance }} reached 90% of the limit"
description: "Max series limit set via -remoteWrite.maxHourlySeries flag is close to reaching the max value.
Then samples for new time series will be dropped instead of sending them to remote storage systems."
- alert: SeriesLimitDayReached
expr: (vmagent_daily_series_limit_current_series / vmagent_daily_series_limit_max_series) > 0.9
labels:
severity: critical
annotations:
dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=90&var-instance={{ $labels.instance }}"
summary: "Instance {{ $labels.instance }} reached 90% of the limit"
description: "Max series limit set via -remoteWrite.maxDailySeries flag is close to reaching the max value.
Then samples for new time series will be dropped instead of sending them to remote storage systems."
- alert: ConfigurationReloadFailure
expr: |
vm_promscrape_config_last_reload_successful != 1
or
vmagent_relabel_config_last_reload_successful != 1
labels:
severity: warning
annotations:
summary: "Configuration reload failed for vmagent instance {{ $labels.instance }}"
description: "Configuration hot-reload failed for vmagent on instance {{ $labels.instance }}.
Check vmagent's logs for detailed error message."
- alert: StreamAggrFlushTimeout
expr: |
increase(vm_streamaggr_flush_timeouts_total[5m]) > 0
labels:
severity: warning
annotations:
summary: "Streaming aggregation at \"{{ $labels.job }}\" (instance {{ $labels.instance }}) can't be finished within the configured aggregation interval."
description: "Stream aggregation process can't keep up with the load and might produce incorrect aggregation results. Check logs for more details.
Possible solutions: increase aggregation interval; aggregate smaller number of series; reduce samples' ingestion rate to stream aggregation."
- alert: StreamAggrDedupFlushTimeout
expr: |
increase(vm_streamaggr_dedup_flush_timeouts_total[5m]) > 0
labels:
severity: warning
annotations:
summary: "Deduplication \"{{ $labels.job }}\" (instance {{ $labels.instance }}) can't be finished within configured deduplication interval."
description: "Deduplication process can't keep up with the load and might produce incorrect results. Check docs https://docs.victoriametrics.com/victoriametrics/stream-aggregation/#deduplication and logs for more details.
Possible solutions: increase deduplication interval; deduplicate smaller number of series; reduce samples' ingestion rate."
apps/victoriametrics/rules/alerts-vmalert.yml
-96
View File
@@ -1,96 +0,0 @@
# File contains default list of alerts for vmalert service.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
# Alerts group for vmalert assumes that Grafana dashboard
# https://grafana.com/grafana/dashboards/14950 is installed.
# Pls update the `dashboard` annotation according to your setup.
- name: vmalert
interval: 30s
rules:
- alert: ConfigurationReloadFailure
expr: vmalert_config_last_reload_successful != 1
labels:
severity: warning
annotations:
summary: "Configuration reload failed for vmalert instance {{ $labels.instance }}"
description: "Configuration hot-reload failed for vmalert on instance {{ $labels.instance }}.
Check vmalert's logs for detailed error message."
- alert: AlertingRulesError
expr: sum(increase(vmalert_alerting_rules_errors_total[5m])) without(id) > 0
for: 5m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/LzldHAVnz?viewPanel=13&var-instance={{ $labels.instance }}&var-file={{ $labels.file }}&var-group={{ $labels.group }}"
summary: "Alerting rules are failing for vmalert instance {{ $labels.instance }}"
description: "Alerting rules execution is failing for \"{{ $labels.alertname }}\" from group \"{{ $labels.group }}\" in file \"{{ $labels.file }}\".
Check vmalert's logs for detailed error message."
- alert: RecordingRulesError
expr: sum(increase(vmalert_recording_rules_errors_total[5m])) without(id) > 0
for: 5m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/LzldHAVnz?viewPanel=30&var-instance={{ $labels.instance }}&var-file={{ $labels.file }}&var-group={{ $labels.group }}"
summary: "Recording rules are failing for vmalert instance {{ $labels.instance }}"
description: "Recording rules execution is failing for \"{{ $labels.recording }}\" from group \"{{ $labels.group }}\" in file \"{{ $labels.file }}\".
Check vmalert's logs for detailed error message."
- alert: RecordingRulesNoData
expr: sum(vmalert_recording_rules_last_evaluation_samples) without(id) < 1
for: 30m
labels:
severity: info
annotations:
dashboard: "http://localhost:3000/d/LzldHAVnz?viewPanel=33&var-file={{ $labels.file }}&var-group={{ $labels.group }}"
summary: "Recording rule {{ $labels.recording }} ({{ $labels.group }}) produces no data"
description: "Recording rule \"{{ $labels.recording }}\" from group \"{{ $labels.group }}\ in file \"{{ $labels.file }}\"
produces 0 samples over the last 30min. It might be caused by a misconfiguration
or incorrect query expression."
- alert: TooManyMissedIterations
expr: increase(vmalert_iteration_missed_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "vmalert instance {{ $labels.instance }} is missing rules evaluations"
description: "vmalert instance {{ $labels.instance }} is missing rules evaluations for group \"{{ $labels.group }}\" in file \"{{ $labels.file }}\".
The group evaluation time takes longer than the configured evaluation interval. This may result in missed
alerting notifications or recording rules samples. Try increasing evaluation interval or concurrency of
group \"{{ $labels.group }}\". See https://docs.victoriametrics.com/victoriametrics/vmalert/#groups.
If rule expressions are taking longer than expected, please see https://docs.victoriametrics.com/victoriametrics/troubleshooting/#slow-queries."
- alert: RemoteWriteErrors
expr: increase(vmalert_remotewrite_errors_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "vmalert instance {{ $labels.instance }} is failing to push metrics to remote write URL"
description: "vmalert instance {{ $labels.instance }} is failing to push metrics generated via alerting
or recording rules to the configured remote write URL. Check vmalert's logs for detailed error message."
- alert: RemoteWriteDroppingData
expr: increase(vmalert_remotewrite_dropped_rows_total[5m]) > 0
for: 5m
labels:
severity: critical
annotations:
summary: "vmalert instance {{ $labels.instance }} is dropping data sent to remote write URL"
description: "vmalert instance {{ $labels.instance }} is failing to send results of alerting or recording rules
to the configured remote write URL. This may result into gaps in recording rules or alerts state.
Check vmalert's logs for detailed error message."
- alert: AlertmanagerErrors
expr: increase(vmalert_alerts_send_errors_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "vmalert instance {{ $labels.instance }} is failing to send notifications to Alertmanager"
description: "vmalert instance {{ $labels.instance }} is failing to send alert notifications to \"{{ $labels.addr }}\".
Check vmalert's logs for detailed error message."
apps/victoriametrics/rules/alerts.yml
-138
View File
@@ -1,138 +0,0 @@
# File contains default list of alerts for VictoriaMetrics single server.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
# 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: DiskRunsOutOfSpaceIn3Days
expr: |
sum(vm_free_disk_space_bytes) without(path) /
(
(rate(vm_rows_added_to_storage_total[1d]) - sum(rate(vm_deduplicated_samples_total[1d])) without(type)) * (
sum(vm_data_size_bytes{type!~"indexdb.*"}) without(type) /
sum(vm_rows{type!~"indexdb.*"}) without(type)
)
+
rate(vm_new_timeseries_created_total[1d]) * (
sum(vm_data_size_bytes{type="indexdb/file"}) without(type)/
sum(vm_rows{type="indexdb/file"}) without(type)
)
) < 3 * 24 * 3600 > 0
for: 30m
labels:
severity: critical
annotations:
dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=53&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: NodeBecomesReadonlyIn3Days
expr: |
sum(vm_free_disk_space_bytes - vm_free_disk_space_limit_bytes) without(path) /
(
(rate(vm_rows_added_to_storage_total[1d]) - sum(rate(vm_deduplicated_samples_total[1d])) without(type)) * (
sum(vm_data_size_bytes{type!~"indexdb.*"}) without(type) /
sum(vm_rows{type!~"indexdb.*"}) without(type)
)
+
rate(vm_new_timeseries_created_total[1d]) * (
sum(vm_data_size_bytes{type="indexdb/file"}) without(type) /
sum(vm_rows{type="indexdb/file"}) without(type)
)
) < 3 * 24 * 3600 > 0
for: 30m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/oS7Bi_0Wz?viewPanel=53&var-instance={{ $labels.instance }}"
summary: "Instance {{ $labels.instance }} will become read-only in 3 days"
description: "Taking into account current ingestion rate and free disk space
instance {{ $labels.instance }} is writable for {{ $value | humanizeDuration }}.\n
Consider to limit the ingestion rate, decrease retention or scale the disk space up if possible."
- alert: DiskRunsOutOfSpace
expr: |
sum(vm_data_size_bytes) by(job, instance) /
(
sum(vm_free_disk_space_bytes) by(job, instance) +
sum(vm_data_size_bytes) by(job, instance)
) > 0.8
for: 30m
labels:
severity: critical
annotations:
dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=53&var-instance={{ $labels.instance }}"
summary: "Instance {{ $labels.instance }} (job={{ $labels.job }}) will run out of disk space soon"
description: "Disk utilisation on instance {{ $labels.instance }} is more than 80%.\n
Having less than 20% of free disk space could cripple merge processes and overall performance.
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: 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 is tightly connected with database performance and may
result in unexpected OOM's or slow queries."
- alert: TooHighChurnRate24h
expr: |
sum(increase(vm_new_timeseries_created_total[24h])) by(instance)
>
(sum(vm_cache_entries{type="storage/hour_metric_ids"}) by(instance) * 3)
for: 15m
labels:
severity: warning
annotations:
dashboard: "http://localhost:3000/d/wNf0q_kZk?viewPanel=66&var-instance={{ $labels.instance }}"
summary: "Too high number of new series on \"{{ $labels.instance }}\" created over last 24h"
description: "The number of created new time series over last 24h is 3x times higher than
current number of active series on \"{{ $labels.instance }}\".\n
This effect is known as Churn Rate.\n
High Churn Rate is 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)
) > 0.05
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 5% 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.
See also https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3976#issuecomment-1476883183"
apps/victoriametrics/vmagent.json
-8260
View File
File diff suppressed because it is too large Load Diff
apps/victoriametrics/vmalert.json
-4255
View File
File diff suppressed because it is too large Load Diff
platform/observability/README.md
+9 -6
View File
@@ -2,7 +2,8 @@
Metrics, logs, and traces for the cluster — one VictoriaMetrics-ecosystem stack,
operator-driven, running in the `monitoring` namespace. Replaces the standalone
Docker Compose stack in `../../apps/victoriametrics/`.
Docker Compose monitoring stack. The retired stack and its three Docker data volumes
were removed on 2026-09-16 with the maintainer's explicit approval.
## Grafana 当前入口（2026-09-16）
@@ -94,7 +95,7 @@ observability/
operator/ victoria-metrics-operator (Helm)
metrics/
vmsingle|vmagent|vmalert|vmalertmanager.yaml core CRs
rules/ VMRules ported from ../../apps/victoriametrics/rules
rules/ VMRules migrated from the retired Compose stack (source in Git history)
exporters/ node-exporter (+VMNodeScrape), kube-state-metrics (Helm)
scrapes/ kubelet + cAdvisor VMNodeScrapes
logs/ VLSingle CR + victoria-logs-collector (Helm)
@@ -105,8 +106,8 @@ observability/
## Docker hosts
The Compose services on Docker hosts (`../../apps/vlmcsd`, `../../apps/ps3netsrv`, `../../apps/netboot`, ...
and the legacy `../../apps/victoriametrics` stack) are monitored too:
The Compose services on Docker hosts (`../../apps/vlmcsd`, `../../apps/ps3netsrv`, `../../apps/netboot`, ...)
are monitored too:
- **Metrics — pull, nothing exposed.** Each host runs `docker-hosts/compose.yaml`
(cAdvisor `:8080` + node-exporter `:9100`). The cluster's vmagent scrapes their LAN
@@ -177,7 +178,9 @@ cd grafana && ./helm.sh && cd ..
vmalert (14950), node-exporter (1860), cAdvisor now that those exporters exist.
- Wire real Alertmanager receivers in `metrics/vmalertmanager.yaml` (email via
`../../apps/smtp-relay/`), replacing the ported `blackhole`.
- Once parity is confirmed, decommission the Compose stack: `../../apps/victoriametrics/`
(`docker compose down`), and retire that folder.
- 旧 Compose 监控栈已于 2026-09-16 按维护者要求清理：原先已无容器，本次移除
旧配置及 `victoriametrics_vmdata`、`victoriametrics_vmagentdata`、
`victoriametrics_grafanadata` 三个无引用 Docker 卷。没有创建备份或迁移旧数据，
Kubernetes 监控资源未修改。旧配置仍可从 Git 历史查阅，旧卷中的数据已删除。
- Add app instrumentation: point `OTEL_EXPORTER_OTLP_ENDPOINT` at
`otel-collector.monitoring.svc:4317`.
platform/observability/metrics/rules/vm-health.yaml
+1 -1
View File
@@ -1,4 +1,4 @@
# Ported from ../../../../apps/victoriametrics/rules/alerts-health.yml
# 告警规则从已退役的 Compose 栈迁入，原始版本保留在 Git 历史。
apiVersion: operator.victoriametrics.com/v1beta1
kind: VMRule
metadata:
platform/observability/metrics/rules/vmagent.yaml
+1 -1
View File
@@ -1,4 +1,4 @@
# Ported from ../../../../apps/victoriametrics/rules/alerts-vmagent.yml
# 告警规则从已退役的 Compose 栈迁入，原始版本保留在 Git 历史。
apiVersion: operator.victoriametrics.com/v1beta1
kind: VMRule
metadata:
platform/observability/metrics/rules/vmalert.yaml
+1 -1
View File
@@ -1,4 +1,4 @@
# Ported from ../../../../apps/victoriametrics/rules/alerts-vmalert.yml
# 告警规则从已退役的 Compose 栈迁入，原始版本保留在 Git 历史。
apiVersion: operator.victoriametrics.com/v1beta1
kind: VMRule
metadata:
platform/observability/metrics/rules/vmsingle.yaml
+1 -1
View File
@@ -1,4 +1,4 @@
# Ported from ../../../../apps/victoriametrics/rules/alerts.yml
# 告警规则从已退役的 Compose 栈迁入，原始版本保留在 Git 历史。
apiVersion: operator.victoriametrics.com/v1beta1
kind: VMRule
metadata:
platform/observability/metrics/vmalertmanager.yaml
+1 -1
View File
@@ -1,4 +1,4 @@
# Alert router/notifier. Ported 1:1 from ../../../apps/victoriametrics/alertmanager.yaml,
# Alert router/notifier. Migrated from the retired Compose stack (see Git history),
# which currently blackholes everything. Wire real receivers here (email via the
# in-cluster smtp-relay, or a webhook) when you want notifications.
apiVersion: operator.victoriametrics.com/v1beta1