CentOS7上docker部署prometheus+grafana
- 全部关闭防火墙和selinux：
systemctl stop firewalld && systemctl disable firewalld
sed -i 's/=enforcing/=disabled/g' /etc/selinux/config && setenforce 0
- 安装docker
curl http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo -o /etc/yum.repos.d/docker.repo
yum makecache fast
yum install -y docker-ce
systemctl start docker && systemctl enable docker
- node-export:
docker pull prom/node-exporter:latest
docker run -d -p 9100:9100 --name node-exporter prom/node-exporter:latest
docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
95252704e558 prom/node-exporter:latest "/bin/node_exporter" 3 seconds ago Up 2 seconds 0.0.0.0:9100->9100/tcp node-exporter
netstat -lntp |grep docker
tcp6 0 0 :::9100 :::* LISTEN 9076/docker-proxy
- alertmanager：
mkdir /home/prom && cd /home/prom
docker pull prom/alertmanager:latest
docker pull timonwong/prometheus-webhook-dingtalk #钉钉告警
vim config.yml
targets:
webhook:
url: https://oapi.dingtalk.com/robot/send?access_token=xxxxxxxxxxxx #修改为钉钉机器人的webhook
mention:
all: true
vim alertmanager.yml
global:
resolve_timeout: 5m
smtp_smarthost: 'smtp.163.com:465' #邮箱smtp服务器代理，启用SSL发信, 端口一般是465
smtp_from: '[email protected]' #发送邮箱名称
smtp_auth_username: '[email protected]' #邮箱名称
smtp_auth_password: 'password' #邮箱密码或授权码
smtp_require_tls: false
route:
receiver: 'default'
group_wait: 10s
group_interval: 1m
repeat_interval: 1h
group_by: ['alertname']
inhibit_rules:
- source_match:
severity: 'critical'
target_match:
severity: 'warning'
equal: ['alertname', 'instance']
receivers:
- name: 'default'
email_configs:
- to: '[email protected]'
send_resolved: true
webhook_configs:
- url: 'http://192.168.20.218:8060/dingtalk/webhook/send'
send_resolved: true
docker run -d -p 8060:8060 -v /home/prom/config.yml:/etc/prometheus-webhook-dingtalk/config.yml --name alertdingtalk timonwong/prometheus-webhook-dingtalk
docker run -d -p 9093:9093 -p 9094:9094 -v /home/prom/alertmanager.yml:/etc/alertmanager/alertmanager.yml --name alertmanager prom/alertmanager:latest
docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
bed08b1b251d prom/alertmanager:latest "/bin/alertmanager -…" 3 seconds ago Up 2 seconds 0.0.0.0:9093-9094->9093-9094/tcp alertmanager
1449d7d0a445 timonwong/prometheus-webhook-dingtalk "/bin/prometheus-web…" 21 seconds ago Up 20 seconds 0.0.0.0:8060->8060/tcp alertdingtalk
cf90ea931188 prom/node-exporter:latest "/bin/node_exporter" 23 minutes ago Up 23 minutes 0.0.0.0:9100->9100/tcp node-exporter
netstat -lntp |grep docker
tcp6 0 0 :::9100 :::* LISTEN 14970/docker-proxy
tcp6 0 0 :::8060 :::* LISTEN 17666/docker-proxy
tcp6 0 0 :::9093 :::* LISTEN 17808/docker-proxy
tcp6 0 0 :::9094 :::* LISTEN 17794/docker-proxy
- prometheus：
mkdir -p /home/prom/data && chmod 777 /home/prom/data && cd /home/prom
docker pull prom/prometheus:latest
vim alert-rules.yml
groups:
- name: node-alert
rules:
- alert: NodeDown
expr: up{job="node"} == 0
for: 5m
labels:
severity: critical
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} down"
description: "Instance: {{ $labels.instance }} 已经宕机 5分钟"
value: "{{ $value }}"
- alert: NodeCpuHigh
expr: (1 - avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="idle"}[5m]))) * 100 > 80
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} cpu使用率过高"
description: "CPU 使用率超过 80%"
value: "{{ $value }}"
- alert: NodeCpuIowaitHigh
expr: avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="iowait"}[5m])) * 100 > 50
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} cpu iowait 使用率过高"
description: "CPU iowait 使用率超过 50%"
value: "{{ $value }}"
- alert: NodeLoad5High
expr: node_load5 > (count by (instance) (node_cpu_seconds_total{job="node",mode='system'})) * 1.2
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} load(5m) 过高"
description: "Load(5m) 过高，超出cpu核数 1.2倍"
value: "{{ $value }}"
- alert: NodeMemoryHigh
expr: (1 - node_memory_MemAvailable_bytes{job="node"} / node_memory_MemTotal_bytes{job="node"}) * 100 > 90
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} memory 使用率过高"
description: "Memory 使用率超过 90%"
value: "{{ $value }}"
- alert: NodeDiskRootHigh
expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"}) * 100 > 90
for: 10m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk(/ 分区) 使用率过高"
description: "Disk(/ 分区) 使用率超过 90%"
value: "{{ $value }}"
- alert: NodeDiskBootHigh
expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"}) * 100 > 80
for: 10m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk(/boot 分区) 使用率过高"
description: "Disk(/boot 分区) 使用率超过 80%"
value: "{{ $value }}"
- alert: NodeDiskReadHigh
expr: irate(node_disk_read_bytes_total{job="node"}[5m]) > 20 * (1024 ^ 2)
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk 读取字节数 速率过高"
description: "Disk 读取字节数 速率超过 20 MB/s"
value: "{{ $value }}"
- alert: NodeDiskWriteHigh
expr: irate(node_disk_written_bytes_total{job="node"}[5m]) > 20 * (1024 ^ 2)
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk 写入字节数 速率过高"
description: "Disk 写入字节数 速率超过 20 MB/s"
value: "{{ $value }}"
- alert: NodeDiskReadRateCountHigh
expr: irate(node_disk_reads_completed_total{job="node"}[5m]) > 3000
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk iops 每秒读取速率过高"
description: "Disk iops 每秒读取速率超过 3000 iops"
value: "{{ $value }}"
- alert: NodeDiskWriteRateCountHigh
expr: irate(node_disk_writes_completed_total{job="node"}[5m]) > 3000
for: 5m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk iops 每秒写入速率过高"
description: "Disk iops 每秒写入速率超过 3000 iops"
value: "{{ $value }}"
- alert: NodeInodeRootUsedPercentHigh
expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/"}) * 100 > 80
for: 10m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk(/ 分区) inode 使用率过高"
description: "Disk (/ 分区) inode 使用率超过 80%"
value: "{{ $value }}"
- alert: NodeInodeBootUsedPercentHigh
expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/boot"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/boot"}) * 100 > 80
for: 10m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} disk(/boot 分区) inode 使用率过高"
description: "Disk (/boot 分区) inode 使用率超过 80%"
value: "{{ $value }}"
- alert: NodeFilefdAllocatedPercentHigh
expr: node_filefd_allocated{job="node"} / node_filefd_maximum{job="node"} * 100 > 80
for: 10m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} filefd 打开百分比过高"
description: "Filefd 打开百分比 超过 80%"
value: "{{ $value }}"
- alert: NodeNetworkNetinBitRateHigh
expr: avg by (instance) (irate(node_network_receive_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
for: 3m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} network 接收比特数 速率过高"
description: "Network 接收比特数 速率超过 20MB/s"
value: "{{ $value }}"
- alert: NodeNetworkNetoutBitRateHigh
expr: avg by (instance) (irate(node_network_transmit_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
for: 3m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} network 发送比特数 速率过高"
description: "Network 发送比特数 速率超过 20MB/s"
value: "{{ $value }}"
- alert: NodeNetworkNetinPacketErrorRateHigh
expr: avg by (instance) (irate(node_network_receive_errs_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
for: 3m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} 接收错误包 速率过高"
description: "Network 接收错误包 速率超过 15个/秒"
value: "{{ $value }}"
- alert: NodeNetworkNetoutPacketErrorRateHigh
expr: avg by (instance) (irate(node_network_transmit_packets_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
for: 3m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} 发送错误包 速率过高"
description: "Network 发送错误包 速率超过 15个/秒"
value: "{{ $value }}"
- alert: NodeProcessBlockedHigh
expr: node_procs_blocked{job="node"} > 10
for: 10m
labels:
severity: warning
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} 当前被阻塞的任务的数量过多"
description: "Process 当前被阻塞的任务的数量超过 10个"
value: "{{ $value }}"
- alert: NodeTimeOffsetHigh
expr: abs(node_timex_offset_seconds{job="node"}) > 3 * 60
for: 2m
labels:
severity: info
instance: "{{ $labels.instance }}"
annotations:
summary: "instance: {{ $labels.instance }} 时间偏差过大"
description: "Time 节点的时间偏差超过 3m"
value: "{{ $value }}"
vim prometheus.yml
global:
scrape_interval: 15s
evaluation_interval: 15s
alerting:
alertmanagers:
- static_configs:
- targets:
- 192.168.20.218:9093
rule_files:
- "*rules.yml"
scrape_configs:
- job_name: 'prometheus'
static_configs:
- targets: ['192.168.20.218:9090']
- job_name: 'node'
static_configs:
- targets: ['192.168.20.211:9100','192.168.20.240:9100','192.168.20.218:9100']
- job_name: 'alertmanager'
static_configs:
- targets: ['192.168.20.218:9093']
docker run -d -p 9090:9090 \
-v /home/prom/prometheus.yml:/etc/prometheus/prometheus.yml \
-v /home/prom/alert-rules.yml:/etc/prometheus/alert-rules.yml \
-v /home/prom/data:/prometheus --name prometheus prom/prometheus:latest
docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
0a15519b970c prom/prometheus:latest "/bin/prometheus --c…" 3 seconds ago Up 2 seconds 0.0.0.0:9090->9090/tcp prometheus
95252704e558 prom/node-exporter:latest "/bin/node_exporter" 16 hours ago Up 16 hours 0.0.0.0:9100->9100/tcp node-exporter
netstat -lntp |grep docker
tcp6 0 0 :::9090 :::* LISTEN 9701/docker-proxy
tcp6 0 0 :::9100 :::* LISTEN 9076/docker-proxy
-
访问 http://192.168.20.218:9090
-
安装redis_exporter服务端(https://github.com/oliver006/redis_exporter)
docker run -d --restart=always --name redis_exporter -p 9121:9121 oliver006/redis_exporter --redis.addr=192.168.20.240:6379 --redis.password=3vRgLpTMLHhMSCflL1iq
- 添加prometheus配置项
vim prometheus.yml
- job_name: redis_exporter
scrape_interval: 5s
static_configs:
- targets: ['192.168.20.218:9121']
labels:
instance: redis
重启prometheus
docker restart prometheus
- 安装influxdb(这里安装的是1.8.0版本的，2.0版本需要用户名密码设置)
docker run -d --name influxdb -p 8086:8086 -v /home/prom/influxdb_data:/var/lib/influxdb influxdb:1.8.10
安装完成后需要进入到容器里创建一个jmeter数据库
docker exec -it influxdb influx
Connected to http://localhost:8086 version 1.8.10
InfluxDB shell version: 1.8.10
> create database jmeter;
>exit
- jmeter配置
在jmeter里添加“Backend Listener”，具体配置信息如下图:
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-kz8LOPBI-1656659097931)(jmeter-influxdb.jpg)]
在grafana里导入5496模板
- 安装grafana:
mkdir -p /home/prom/grafana && chmod 777 /home/prom/grafana
docker pull grafana/grafana:latest
docker run -d -p 3000:3000 -v /home/prom/grafana:/var/lib/grafana --name=grafana grafana/grafana:latest
docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
17d5c5d415b5 grafana/grafana:latest "/run.sh" 4 seconds ago Up 3 seconds 0.0.0.0:3000->3000/tcp grafana
bd53df9eb9fa prom/node-exporter:latest "/bin/node_exporter" 16 hours ago Up 16 hours 0.0.0.0:9100->9100/tcp node-exporter
netstat -lntp |grep docker
tcp6 0 0 :::9100 :::* LISTEN 6558/docker-proxy
tcp6 0 0 :::3000 :::* LISTEN 13123/docker-proxy
grafana容器配置文件：/etc/grafana/grafana.ini。
访问IP:3000，初始账号密码为admin/admin，会要求更改密码。
选择数据源Prometheus——http://ip:9090，导入模板8919，
| Grafana模板ID | 描述 |
|---|---|
| 8919 | node_export |
| 11835 | redis_export |
| 5496 | jmeter_dashboards |
| 10467、14694、14510 | windows_exprot |
-
参考文档:
https://blog.csdn.net/miss1181248983/article/details/107415551
https://blog.csdn.net/wang_jing_jing/article/details/123222461
https://blog.csdn.net/weixin_39118023/article/details/124608554 -
遇到问题
- 报错：dial tcp 192.168.20.218:9093: connect: no route to host
- 解决方法：
iptables -P INPUT ACCEPT
iptables -P FORWARD ACCEPT
iptables -P OUTPUT ACCEPT
iptables -F
- 如果上面操作完还是不行那就是路由信息配置有问题了，使用命令查看路由信息（主要是网关和DNS配置信息）
ip route
确认网关与DNS配置没有问题，如果有问题可以修改“网上信息”。如ens192网卡
vim /etc/sysconfig/network-scripts/ifcfg-ens192
- 监测每台服务都需要安装node_export
docker run -d -p 9100:9100 --name node-exporter prom/node-exporter:latest
3.监测每台服务都需要安装redis_export
nohup ./redis_exporter -redis.addr=192.168.20.240:6379 -redis.password=3vRgLpTMLHhMSCflL1iq -web.listen-address :9121 &
cat > /usr/lib/systemd/system/redis_exporter.service <<EOF
[Unit]
Description=redis_exporter
Documentation=https://github.com/oliver006/redis_exporter
After=network.target
[Service]
Type=simple
User=prometheus
ExecStart=/usr/local/redis_exporter/redis_exporter -redis.addr 192.168.20.240:6379 -redis.password 3vRgLpTMLHhMSCflL1iq
Restart=on-failure
[Install]
WantedBy=multi-user.target
EOF