我有很多人。 1个节点。Prometheus服务看不到服务whoami。但是它确实看到了他自己。我也确实通过“ curl 127.0.0.1:800”从whoami服务接收数据。
docker-stack.yml
version: '3.7'
volumes:
prometheus_data: {}
grafana_data: {}
services:
prom:
image: prom/prometheus
volumes:
- ./prometheus/:/etc/prometheus/
- prometheus_data:/prometheus
command:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--web.console.libraries=/usr/share/prometheus/console_libraries'
- '--web.console.templates=/usr/share/prometheus/consoles'
ports:
- 8080:9090
deploy:
replicas: 1
update_config:
parallelism: 2
delay: 10s
restart_policy:
condition: on-failure
grafana:
image: grafana/grafana
ports:
- "3000:3000"
deploy:
update_config:
parallelism: 2
delay: 10s
restart_policy:
condition: on-failure
whoami:
image: containous/whoami
ports:
- "800:80"
deploy:
replicas: 1
update_config:
parallelism: 2
delay: 10s
restart_policy:
condition: on-failure
telegraf:
image: telegraf
ports:
- "998:998"
deploy:
replicas: 1
update_config:
parallelism: 2
delay: 10s
restart_policy:
condition: on-failure
alertmanager:
image: prom/alertmanager
ports:
- 9093:9093
deploy:
replicas: 1
update_config:
parallelism: 2
delay: 10s
restart_policy:
condition: on-failure
prometheus.yml:
# my global config
global:
scrape_interval: 15s # By default, scrape targets every 15 seconds.
evaluation_interval: 15s # By default, scrape targets every 15 seconds.
# scrape_timeout is set to the global default (10s).
# Attach these labels to any time series or alerts when communicating with
# external systems (federation, remote storage, Alertmanager).
external_labels:
monitor: 'my-project'
# Load and evaluate rules in this file every 'evaluation_interval' seconds.
rule_files:
- 'alert.rules'
# - "first.rules"
# - "second.rules"
# alert
alerting:
alertmanagers:
- scheme: http
static_configs:
- targets:
- "alertmanager:9093"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
- job_name: 'prometheus'
# Override the global default and scrape targets from this job every 5 seconds.
scrape_interval: 5s
static_configs:
- targets: ['127.0.0.1:9090']
- job_name: 'cadvisor'
# Override the global default and scrape targets from this job every 5 seconds.
scrape_interval: 5s
dns_sd_configs:
- names:
- 'tasks.cadvisor'
type: 'A'
port: 8080
# static_configs:
# - targets: ['cadvisor:8080']
- job_name: 'node-exporter'
# Override the global default and scrape targets from this job every 5 seconds.
scrape_interval: 5s
dns_sd_configs:
- names:
- 'tasks.node-exporter'
type: 'A'
port: 9100
# static_configs:
# - targets: ['node-exporter:9100']
- job_name: 'whoami'
# Override the global default and scrape targets from this job every 5 seconds.
scrape_interval: 5s
dns_sd_configs:
- names:
- 'tasks.whoami'
type: 'A'
port: 800
static_configs:
- targets: ['127.0.0.1:800']
OMG。该网站告诉我,我应该添加更多文本,因为我的帖子大部分是代码,并且缺少文本。不知道我还能添加什么要求...