prometheus 基于consul、file实现服务发现
安装consul
consul官网：https://www.consul.io/
Consul 是分布式 k/v 数据存储集群，目前常用于服务的服务注册和发现。
官网下载
下载链接1 https://www.consul.io/downloads
下载链接2
环境：
192.168.100.9、192.168.100.10、192.168.100.11
安装consul
root@consul1:/usr/local\# unzip consul_1.13.1_linux_amd64.zip
root@consul1:/usr/local\# mv consul /usr/local/bin/
root@consul1:/usr/local\# scp /usr/local/bin/consul 192.168.100.10:/usr/local/bin/
root@consul1:/usr/local\# scp /usr/local/bin/consul 192.168.100.11:/usr/local/bin/
mkdir /data/consul/data -p
mkdir /data/consul/logs -p
consul命令参数：
consul agent -server #使用 server 模式运行 consul 服务
-bootstrap #首次部署使用初始化模式
-bind #设置群集通信的监听地址
-client #设置客户端访问的监听地址
-data-dir #指定数据保存路径
-ui #启用内置静态 web UI 服务器
-node #此节点的名称,群集中必须唯一
-datacenter=dc1 #集群名称，默认是 dc1
-join #加入到已有 consul 集群环境
-bootstrap-expect #在一个datacenter中期望提供的server节点数目，当该值提供的时候，consul一直等到达到指定sever数目的时候才会引导整个集群，该标记不能和bootstrap共用（推荐使用的方式）
-config-dir #配置文件目录，里面所有以.json结尾的文件都会被加载
-log-rotate-bytes=102400000 #指定日志大小,100MB（字节）
主节点配置
root@consul1:/data/consul/logs\# vim /etc/systemd/system/consul.service
[Unit]
Description=consul server
After=network.target
[Service]
Type=simple
User=root
ExecStart=/usr/local/bin/consul agent -server -bootstrap-expect=3 -bind=192.168.100.9 -client=192.168.100.9 -data-dir=/data/consul/data -ui -node=192.168.100.9 -datacenter=dc1 -log-rotate-bytes=102400000 -log-file=/data/consul/logs/
ExecReload=/bin/kill -HUP $MAINPID
KillSignal=SIGTERM
[Install]
WantedBy=multi-user.target
从节点配置
consul2配置
root@consul2:~\# vim /etc/systemd/system/consul.service
[Unit]
Description=consul server
After=network.target
[Service]
Type=simple
User=root
ExecStart=/usr/local/bin/consul agent -server -bootstrap-expect=3 -bind=192.168.100.10 -client=192.168.100.10 -data-dir=/data/consul/data -ui -node=192.168.100.10 -datacenter=dc1 -join=192.168.100.9 -log-rotate-bytes=102400000 -log-file=/data/consul/logs/
ExecReload=/bin/kill -HUP $MAINPID
KillSignal=SIGTERM
[Install]
WantedBy=multi-user.target
consul3配置
root@consul3:~\# cat /etc/systemd/system/consul.service
[Unit]
Description=consul server
After=network.target
[Service]
Type=simple
User=root
ExecStart=/usr/local/bin/consul agent -server -bootstrap-expect=3 -bind=192.168.100.11 -client=192.168.100.11 -data-dir=/data/consul/data -ui -node=192.168.100.11 -datacenter=dc1 -join=192.168.100.9 -log-rotate-bytes=102400000 -log-file=/data/consul/logs/
ExecReload=/bin/kill -HUP $MAINPID
KillSignal=SIGTERM
[Install]
WantedBy=multi-user.target
systemctl daemon-reload && systemctl start consul && systemctl enable consul
浏览器访问consul主节点：IP:8500
测试写入数据
1、服务发现node-exporter
通过 consul 的 API 写入数据，添加k8s三个prometheus 的node-exporter服务地址
curl -X PUT -d '{"id": "node-exporter1","name": "node-exporter1","address":"192.168.100.3","port":9100,"tags": ["node-exporter"],"checks": [{"http":"http://192.168.100.3:9100/","interval": "5s"}]}' http://192.168.100.9:8500/v1/agent/service/register
curl -X PUT -d '{"id": "node-exporter2","name": "node-exporter2","address":"192.168.100.4","port":9100,"tags": ["node-exporter"],"checks": [{"http":"http://192.168.100.4:9100/","interval": "5s"}]}' http://192.168.100.9:8500/v1/agent/service/register
curl -X PUT -d '{"id": "node-exporter3","name": "node-exporter3","address":"192.168.100.5","port":9100,"tags": ["node-exporter"],"checks": [{"http":"http://192.168.100.5:9100/","interval": "5s"}]}' http://192.168.100.9:8500/v1/agent/service/register
2、服务发现cadvisor
通过 consul 的 API 写入数据，添加k8s三个prometheus 的cadvisor服务地址
curl -X PUT -d '{"id": "cadvisor1","name": "cadvisor1","address":"192.168.100.3","port":8080,"tags": ["cadvisor"],"checks": [{"http":"http://192.168.100.3:8080/","interval": "5s"}]}' http://192.168.100.9:8500/v1/agent/service/register
curl -X PUT -d '{"id": "cadvisor2","name": "cadvisor2","address":"192.168.100.4","port":8080,"tags": ["cadvisor"],"checks": [{"http":"http://192.168.100.4:8080/","interval": "5s"}]}' http://192.168.100.9:8500/v1/agent/service/register
curl -X PUT -d '{"id": "cadvisor3","name": "cadvisor3","address":"192.168.100.5","port":8080,"tags": ["cadvisor"],"checks": [{"http":"http://192.168.100.5:8080/","interval": "5s"}]}' http://192.168.100.9:8500/v1/agent/service/register
服务详细
删除服务
PUT请求URI /v1/agent/service/deregister/{服务ID}
curl -XPUT http://192.168.100.9:8500/v1/agent/service/deregister/node-exporter3
配置prometheus到consul发现服务
prometheus官网：https://prometheus.io/docs/prometheus/latest/configuration/configuration/#consul_sd_config
主要配置字段
static_configs: #配置数据源
consul_sd_configs: #指定基于 consul 服务发现的配置
rebel_configs： #重新标记
services: [] #表示匹配 consul 中所有的 service
consul_sd_configs配置字段
metrics_path: /metrics #指定的是k8s中的node-exporter的metrics指标URI
scheme: http #指定的是k8s中node-exporter的scheme模式，不是consul的scheme
refresh_interval: 15s #间隔15s从consul服务发现，默认30s
honor_labels: true
#honor_labels 控制 Prometheus 如何处理已经存在于已抓取数据中的标签与 Prometheus 将附加服务器端的标签之间的冲突（"job"和"instance"标签，手动配置的目标标签以及服务发现实现生成的标签）。如果 honor_labels 设置为"true"，则保留已抓取数据的标签值并忽略冲突的 prometheus 服务器端标签来解决标签冲突，另外如果被采集端有标签但是值为空、则使用 prometheus 本地标签值，如果被采集端没有此标签、但是 prometheus 配置了，那也使用 prometheus 的配置的标签值。如果 honor_labels 设置为 "false" ，则通过将已抓取数据中的冲突标签重命名为 "exported_<original-label>"（例如"exported_instance"，"exported_job"）然后附加服务器端标签来解决标签冲突。
1、k8s部署prometheus-server 的配置yaml
root@master1:~/yaml# cat prometheus-consul-cfg.yaml
kind: ConfigMap
apiVersion: v1
metadata:
labels:
app: prometheus
name: prometheus-config
namespace: monitoring
data:
prometheus.yml: |
global:
scrape_interval: 15s
scrape_timeout: 10s
evaluation_interval: 1m
scrape_configs:
- job_name: consul
honor_labels: true #则保留已抓取数据的标签值并忽略冲突的 prometheus 服务器端标签来解决标签冲突
metrics_path: /metrics #指定的是k8s中的node-exporter的metrics指标URI
scheme: http #指定的是k8s中node-exporter的scheme模式，不是consul的scheme
consul_sd_configs:
- server: 192.168.100.9:8500
services: []
- server: 192.168.100.10:8500
services: []
- server: 192.168.100.11:8500
services: []
- refresh_interval: 15s #间隔15s从consul服务发现，默认30s
relabel_configs:
- source_labels: ['__meta_consul_tags']
target_label: 'product' #将__meta_consul_tags替换为新的标签product
- source_labels: ['__meta_consul_dc']
target_label: 'idc' #将__meta_consul_dc标签替换为新的标签idc
- source_labels: ['__meta_consul_service']
regex: "consul" #取消发现consul的服务
action: drop
浏览器访问验证prometheus-server
root@prometheus:/etc/profile.d\# cd /usr/local/prometheus
root@prometheus:/usr/local/prometheus\# vim prometheus.yml
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "first_rules.yml"
# - "second_rules.yml"
# 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"
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ["localhost:9090"]
#配置consul服务发现，从而抓取监控指标
- job_name: consul
honor_labels: true
metrics_path: /metrics
scheme: http
consul_sd_configs:
- server: 192.168.100.9:8500
services: []
- server: 192.168.100.10:8500
services: []
- server: 192.168.100.11:8500
services: []
- refresh_interval: 15s
relabel_configs:
- source_labels: ['__meta_consul_tags']
target_label: 'product'
- source_labels: ['__meta_consul_dc']
target_label: 'idc'
- source_labels: ['__meta_consul_service']
regex: "consul"
action: drop
浏览器访问：
file_sd_configs
prometheus-server可以从指定的文件中动态发现监控指标服务，并且文件如果发生修改prometheus-server也无需重新服务，可以动态从文件中抓取获取到对应的target
https://prometheus.io/docs/prometheus/latest/configuration/configuration/#file_sd_config
编辑 file_sd_configs 配置文件：
在prometheus目录下创建一个存放file_sd_configs目录
root@prometheus:/usr/local/prometheus\# mkdir file_sd创建file_sd_configs 配置文件添加prometheus服务发现的target(node_exporter)
root@prometheus:/usr/local/prometheus\# vim file_sd/target.json
[
{
"targets": [ "192.168.100.3:9100", "192.168.100.4:9100", "192.168.100.5:9100" ]
}
]
root@prometheus:/usr/local/prometheus\# vim file_sd/cadvisor.json
[
{
"targets": [ "192.168.100.3:8080", "192.168.100.4:8080", "192.168.100.5:8080" ]
}
]修改prometheus服务配置文件
root@prometheus:/usr/local/prometheus\# cat prometheus.yml
# my global config
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "first_rules.yml"
# - "second_rules.yml"
# 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"
# metrics_path defaults to '/metrics'
# scheme defaults to 'http'.
static_configs:
- targets: ["localhost:9090"]
- job_name: "file_sd_my_server"
file_sd_configs:
- files:
- /usr/local/prometheus/file_sd/target.json #服务发现node-exporter
- /usr/local/prometheus/file_sd/cadvisor.json #服务发现cadvisor
refresh_interval: 10s #间隔10s从文件服务发现，默认5min浏览器访问prometheus-server验证
本文来自博客园，作者：PunchLinux，转载请注明原文链接：https://www.cnblogs.com/punchlinux/p/16856615.html
