一起来学ceph 07.ceph 监控

ceph 监控

环境

192.168.126.101 ceph01
192.168.126.102 ceph02
192.168.126.103 ceph03
192.168.126.104 ceph04
192.168.126.105 ceph-admin

192.168.48.11 ceph01
192.168.48.12 ceph02
192.168.48.13 ceph03
192.168.48.14 ceph04
192.168.48.15 ceph-admin

192.168.48.57 prometheus

###所有节点内核版本要求4.5以上
uname -r
5.2.2-1.el7.elrepo.x86_64

安装prometheus

官方下载地址

https://prometheus.io/download/

[root@prometheus ~]# ll -h
total 48M
-rw-r--r-- 1 root root 48M Jul 27 20:36 prometheus-2.11.1.linux-amd64.tar.gz
[root@prometheus ~]# tar xvf prometheus-2.11.1.linux-amd64.tar.gz 
[root@prometheus ~]# mv prometheus-2.11.1.linux-amd64  prometheus
[root@prometheus ~]# ll -h
total 48M
drwxr-xr-x 4 3434 3434 132 Jul 10 23:33 prometheus
-rw-r--r-- 1 root root 48M Jul 27 20:36 prometheus-2.11.1.linux-amd64.tar.gz
[root@prometheus ~]# mv prometheus  /usr/local/

创建prometheus用户

[root@prometheus prometheus]# useradd -r -d /var/lib/prometheus -m prometheus
[root@prometheus prometheus]# ls -ld /var/lib/prometheus/
drwx------ 2 prometheus prometheus 76 Jul 27 20:46 /var/lib/prometheus/

创建prometheus服务

[root@prometheus ~]# vim /usr/lib/systemd/system/prometheus.service

[Unit]
Description=The Prometheus 2 monitoring system and time series database.
Documentation=https://prometheus.io
After=network.target
[Service]
EnvironmentFile=-/etc/sysconfig/prometheus
User=prometheus
ExecStart=/usr/local/prometheus/prometheus \
        --storage.tsdb.path=/var/lib/prometheus \
        --config.file=/usr/local/prometheus/prometheus.yml \
        --web.listen-address=0.0.0.0:9090 \
        --web.external-url=
Restart=on-failure
StartLimitInterval=1
RestartSec=3
[Install]
WantedBy=multi-user.target

启动prometheus

[root@prometheus ~]# systemctl daemon-reload 
[root@prometheus ~]# systemctl start prometheus.service 
[root@prometheus ~]# ss -ntl
State       Recv-Q Send-Q                           Local Address:Port                                          Peer Address:Port              
LISTEN      0      128                                          *:22                                                       *:*                  
LISTEN      0      128                                         :::9090                                                    :::*                  
LISTEN      0      128                                         :::22                                                      :::*                  
[root@prometheus ~]# 

所有节点安装node_exporter

ll -h
total 7.8M
-rw-r--r-- 1 root root 7.8M Jul 27 20:42 node_exporter-0.18.1.linux-amd64.tar.gz
tar xvf node_exporter-0.18.1.linux-amd64.tar.gz
mv node_exporter-0.18.1.linux-amd64  node_exporter
mv node_exporter /usr/local/
useradd -r -d /var/lib/prometheus -m prometheus

[root@ceph01 ~]# vim /usr/lib/systemd/system/node_exporter.service 

[Unit]
Description=node_exporter
Documentation=https://prometheus.io/
After=network.target

[Service]
EnvironmentFile=-/etc/sysconfig/node_exporter
Type=simple
User=prometheus
ExecStart=/usr/local/node_exporter/node_exporter
Restart=on-failure

[Install]
WantedBy=multi-user.target                                     

systemctl daemon-reload 
systemctl start node_exporter.service

编辑prometheus配置文件

[root@prometheus ~]# vim /usr/local/prometheus/prometheus.yml
......
......
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: 'prometheus'
    static_configs:
    - targets: ['localhost:9090']

  - job_name: 'prometheus-node'
    static_configs:
    - targets: ['192.168.48.57:9100']

  - job_name: 'ceph01-node'
    static_configs:
    - targets: ['192.168.48.11:9100']

  - job_name: 'ceph02-node'
    static_configs:
    - targets: ['192.168.48.12:9100']
  
  - job_name: 'ceph03-node'
    static_configs:
    - targets: ['192.168.48.13:9100']

  - job_name: 'ceph04-node'
    static_configs:
    - targets: ['192.168.48.14:9100']

  - job_name: 'ceph-admin-node'
    static_configs:
    - targets: ['192.168.48.15:9100']

[root@prometheus ~]# systemctl restart prometheus.service 

监控ceph

ceph开启prometheus

[cephadm@ceph-admin ceph-cluster]$ ceph mgr module enable prometheus

mgr在ceph04上运行着

[cephadm@ceph-admin ceph-cluster]$ ceph -s
  cluster:
    id:     231d5528-bab4-49fa-9d68-d5382d2e9f6c
    health: HEALTH_OK
 
  services:
    mon: 3 daemons, quorum ceph01,ceph02,ceph03 (age 5h)
    mgr: ceph04(active, since 2m), standbys: ceph03
    mds: cephfs:2 {0=ceph02=up:active,1=ceph01=up:active} 1 up:standby
    osd: 8 osds: 8 up (since 5h), 8 in (since 5h)
    rgw: 1 daemon active (ceph01)
 
  data:
    pools:   9 pools, 352 pgs
    objects: 251 objects, 14 MiB
    usage:   8.1 GiB used, 64 GiB / 72 GiB avail
    pgs:     352 active+clean

[root@ceph04 ~]# ss -ntl | grep 9283
LISTEN     0      5           :::9283                    :::*    

prometheus编辑配置文件

[root@prometheus ~]# vim /usr/local/prometheus/prometheus.yml 
.....
.....
- job_name: 'ceph04-mgr'
    static_configs:
    - targets: ['192.168.48.14:9283']
                                     

[root@prometheus ~]# systemctl restart prometheus.service 

安装grafana

wget https://dl.grafana.com/oss/release/grafana-6.2.5-1.x86_64.rpm 
yum localinstall grafana-6.2.5-1.x86_64.rpm 
systemctl start grafana-server.service 

访问grafana

输入账号密码 admin/admin

添加数据源

导入模板

监控界面