Этап 6: починка NO DATA в Grafana (3 причины)+relabel instance→hostname; исправлены имена garage-метрик в панелях и алертах; опыт в EXPERIENCE.md

This commit is contained in:
kpa39l
2026-09-03 08:39:53 +00:00
parent 7437864b50
commit 66ff07c52a
8 changed files with 927 additions and 189 deletions
+104 -56
View File
@@ -2,61 +2,109 @@ global:
scrape_interval: 15s
evaluation_interval: 15s
external_labels:
monitor: 'garage-cluster'
monitor: garage-cluster
rule_files:
- /etc/prometheus/alerts.yml
- /etc/prometheus/alerts.yml
scrape_configs:
# Garage node metrics (admin API on WG) — Bearer auth
- job_name: 'garage'
metrics_path: /metrics
scheme: http
authorization:
type: Bearer
credentials: c213debe864061cefe501f7791d557b6dba701710b41791b4a4a0fb036690d1d
static_configs:
- targets: ['10.8.0.1:3903', '10.8.0.2:3903', '10.8.0.4:3903']
labels:
cluster: garage
# HTTP health probe via blackbox-exporter (returns probe_success)
- job_name: 'garage_health'
metrics_path: /probe
params:
module: [http_2xx]
static_configs:
- targets: ['http://10.8.0.1:3903/health']
labels:
instance: vps01
- targets: ['http://10.8.0.2:3903/health']
labels:
instance: bigbox
- targets: ['http://10.8.0.4:3903/health']
labels:
instance: vps02
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: target
- target_label: __address__
replacement: 127.0.0.1:9115
# Node exporter on each host (system metrics via WG)
- job_name: 'node'
static_configs:
- targets: ['10.8.0.2:9100']
labels:
host: bigbox
- targets: ['10.8.0.1:9100']
labels:
host: vps01
- targets: ['10.8.0.4:9100']
labels:
host: vps02
# Prometheus self
- job_name: 'prometheus'
static_configs:
- targets: ['localhost:9090']
- job_name: garage
metrics_path: /metrics
scheme: http
authorization:
type: Bearer
credentials: c213debe864061cefe501f7791d557b6dba701710b41791b4a4a0fb036690d1d
static_configs:
- targets:
- 10.8.0.1:3903
- 10.8.0.2:3903
- 10.8.0.4:3903
labels:
cluster: garage
relabel_configs:
- source_labels:
- __address__
regex: 10.8.0.1:3903
target_label: instance
replacement: vps01:3903
- source_labels:
- __address__
regex: 10.8.0.2:3903
target_label: instance
replacement: bigbox:3903
- source_labels:
- __address__
regex: 10.8.0.4:3903
target_label: instance
replacement: vps02:3903
- job_name: garage_health
metrics_path: /probe
params:
module:
- http_2xx
static_configs:
- targets:
- http://10.8.0.1:3903/health
labels:
instance: vps01
- targets:
- http://10.8.0.2:3903/health
labels:
instance: bigbox
- targets:
- http://10.8.0.4:3903/health
labels:
instance: vps02
relabel_configs:
- source_labels:
- __address__
target_label: __param_target
- source_labels:
- __param_target
target_label: target
- target_label: __address__
replacement: 127.0.0.1:9115
- job_name: node
static_configs:
- targets:
- 10.8.0.2:9100
labels:
host: bigbox
- targets:
- 10.8.0.1:9100
labels:
host: vps01
- targets:
- 10.8.0.4:9100
labels:
host: vps02
relabel_configs:
- source_labels:
- __address__
regex: 10.8.0.2:9100
target_label: instance
replacement: bigbox:9100
- source_labels:
- __address__
regex: 10.8.0.1:9100
target_label: instance
replacement: vps01:9100
- source_labels:
- __address__
regex: 10.8.0.4:9100
target_label: instance
replacement: vps02:9100
- job_name: prometheus
static_configs:
- targets:
- localhost:9090
- job_name: tproxy
static_configs:
- targets:
- 127.0.0.1:18081
labels:
host: vps03
service: tproxy
relabel_configs:
- target_label: instance
replacement: vps03:8081
- target_label: host
replacement: vps03