使用influxdb以及Grafana监控vCenter的操作步骤

1. 下载安装介质

---

• 计划telegraf和influxdb 使用rpm包进行安装。Grafana使用docker容器方式安装

下载路径为：
https://repos.influxdata.com/rhel/7Server/x86_64/stable/
其实可以根据仓库自己查找就可以了。
拉取镜像为：
docker pull grafana/grafana
注意2021.8时的版本信息为：
influxdb-1.8.9.x86_64.rpm
telegraf-1.19.2-1.x86_64.rpm
grafana 8.1的版本
注意 influxdb2的版本变化比较大 资料比较少一些。

---

2. 安装介质

---

yum localinstall *.rpm
需要注意的是,设置为开机启动相关。

3. influxdb参数文件设置

• influxdb的设置
• 注意安装完之后需要启动数据库
• systemctl enable influxdb && systemctl restart influxdb 启动数据库即可。

注意可以通过influx 命令登录进数据库，一开始设置完没有密码可以直接登录，但是用有密码之后必须使用命令进行登录了。
influxdb 是一个时序数据库可以通过telegraf 等工具push监控数据进来，然后交由grafana进行图形化展示。
# 显示用户
SHOW USERS
# 创建用户
CREATE USER "username" WITH PASSWORD 'password'
# 赋予用户管理员权限
GRANT ALL PRIVILEGES TO username
# 创建管理员权限的用户
CREATE USER <username> WITH PASSWORD '<password>' WITH ALL PRIVILEGES
# 修改用户密码
SET PASSWORD FOR username = 'password'
# 撤消权限
REVOKE ALL ON mydb FROM username
# 查看权限
SHOW GRANTS FOR username
# 删除用户
DROP USER "username"

• 注意设置好权限之后就可以进行telegraf的处理了。

---

4. telegraf的配置文件

• • systemctl enable influxdb && systemctl restart influxdb 启动数据库即可。

vim /etc/telegraf/vm187.conf
添加内容为：
[global_tags]
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 10000
collection_jitter = "0s"
flush_interval = "10s"
flush_jitter = "0s"
precision = ""
hostname = ""
omit_hostname = false
[[outputs.influxdb]]
#这里需要修改。
urls = ["http://127.0.0.1:8086"]
database = "vm187"
timeout = "0s"
username = "influxdb"
password = "上一步创建的密码"
[[inputs.vsphere]]
# 这里需要设置为密码
  vcenters = [ "https://yourvmcenterip/sdk" ]
  username = "administrator@vsphere.local"
  password = "yourvcenterpassword"
   vm_metric_include = [
     "cpu.demand.average",
     "cpu.idle.summation",
     "cpu.latency.average",
     "cpu.readiness.average",
     "cpu.ready.summation",
     "cpu.run.summation",
     "cpu.usagemhz.average",
     "cpu.used.summation",
     "cpu.wait.summation",
     "mem.active.average",
     "mem.granted.average",
     "mem.latency.average",
     "mem.swapin.average",
     "mem.swapinRate.average",
     "mem.swapout.average",
     "mem.swapoutRate.average",
     "mem.usage.average",
     "mem.vmmemctl.average",
     "net.bytesRx.average",
     "net.bytesTx.average",
     "net.droppedRx.summation",
     "net.droppedTx.summation",
     "net.usage.average",
     "power.power.average",
     "virtualDisk.numberReadAveraged.average",
     "virtualDisk.numberWriteAveraged.average",
     "virtualDisk.read.average",
     "virtualDisk.readOIO.latest",
     "virtualDisk.throughput.usage.average",
     "virtualDisk.totalReadLatency.average",
     "virtualDisk.totalWriteLatency.average",
     "virtualDisk.write.average",
     "virtualDisk.writeOIO.latest",
     "sys.uptime.latest",
   ]
   host_metric_include = [
     "cpu.coreUtilization.average",
     "cpu.costop.summation",
     "cpu.demand.average",
     "cpu.idle.summation",
     "cpu.latency.average",
     "cpu.readiness.average",
     "cpu.ready.summation",
     "cpu.swapwait.summation",
     "cpu.usage.average",
     "cpu.usagemhz.average",
     "cpu.used.summation",
     "cpu.utilization.average",
     "cpu.wait.summation",
     "disk.deviceReadLatency.average",
     "disk.deviceWriteLatency.average",
     "disk.kernelReadLatency.average",
     "disk.kernelWriteLatency.average",
     "disk.numberReadAveraged.average",
     "disk.numberWriteAveraged.average",
     "disk.read.average",
     "disk.totalReadLatency.average",
     "disk.totalWriteLatency.average",
     "disk.write.average",
     "mem.active.average",
     "mem.latency.average",
     "mem.state.latest",
     "mem.swapin.average",
     "mem.swapinRate.average",
     "mem.swapout.average",
     "mem.swapoutRate.average",
     "mem.totalCapacity.average",
     "mem.usage.average",
     "mem.vmmemctl.average",
     "net.bytesRx.average",
     "net.bytesTx.average",
     "net.droppedRx.summation",
     "net.droppedTx.summation",
     "net.errorsRx.summation",
     "net.errorsTx.summation",
     "net.usage.average",
     "power.power.average",
     "storageAdapter.numberReadAveraged.average",
     "storageAdapter.numberWriteAveraged.average",
     "storageAdapter.read.average",
     "storageAdapter.write.average",
     "sys.uptime.latest",
   ]
cluster_metric_include = []
datastore_metric_include = []
  datacenter_metric_include = []
  datacenter_metric_exclude = [ "*" ]
insecure_skip_verify = true

• 设置完之后需要启动telegraf

nohup telegraf -config /etc/telegraf/vm187.conf &
后台运行即可。

• 注意我设置的是最小化的参数。

---

5. docker 运行grafana

docker run -d   -p 3000:3000   --name=grafana   -v /opt/grafana-storage:/var/lib/grafana   grafana/grafana
注意需要进行持久化避免重启之后数据丢失

---

6.添加influxdb 的数据源

注意需要输入创建的用户和密码
端口选择为8086

7. 添加grafana的json文件或者是执行导入即可。

• 先展示一下效果
  
  
• 使用的配置文件为：

https://grafana.com/grafana/dashboards/6171