telegraf采集监控数据组件

一. telegraf 介绍

github托管链接： https://github.com/influxdata/telegraf/tree/master/plugins

支持多种平台监控扩展性强

image-20230525094014181

image-20230525100058719

监控交换机等数通设备时mibs文件映射见leancould

mibs下载链接：
http://lc-j2rHZR7P.cn-e1.lcfile.com/qP4oqwLcYwP7UPcDlvlV6IMOxyQwBY6u/mibs.zip

image-20230612214348411

二. telegraf部署 （ 建议采用容器化的方式部署 ）

1. 二进制部署 ( 比较简单了解即可 )

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
#!/bin/bash
set -e
version=1.20.4
tarball=telegraf-${version}_linux_amd64.tar.gz
wget https://dl.influxdata.com/telegraf/releases/$tarball
tar xzvf $tarball

mkdir -p /opt/telegraf
cp -far telegraf-${version}/usr/bin/telegraf /opt/telegraf

cat <<EOF > /opt/telegraf/telegraf.conf
[global_tags]
[agent]
  interval = "10s"
  flush_interval = "10s"
  round_interval = true
  metric_batch_size = 1000
  metric_buffer_limit = 10000
  collection_jitter = "0s"
  flush_jitter = "0s"
  precision = ""
  hostname = ""   # 填为自己的服务器IP
  omit_hostname = false
  
[[inputs.cpu]]
  percpu = true
  totalcpu = true
  collect_cpu_time = false
  report_active = true
[[inputs.disk]]
  ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
[[inputs.diskio]]
[[inputs.kernel]]
[[inputs.mem]]
[[inputs.processes]]
[[inputs.system]]
  fielddrop = ["uptime_format"]
[[inputs.net]]
  ignore_protocol_stats = true
  
[[outputs.prometheus_client]]
listen = ":9273"
metric_version = 2
path="/metrics"
string_as_label = true
export_timestamp = true  

EOF

cat <<EOF > /etc/systemd/system/telegraf.service
[Unit]
Description="telegraf"
After=network.target

[Service]
Type=simple

ExecStart=/opt/telegraf/telegraf --config telegraf.conf
WorkingDirectory=/opt/telegraf
SuccessExitStatus=0
LimitNOFILE=65536
StandardOutput=syslog
StandardError=syslog
SyslogIdentifier=telegraf
KillMode=process
KillSignal=SIGQUIT
TimeoutStopSec=5
Restart=always

[Install]
WantedBy=multi-user.target
EOF
systemctl daemon-reload
systemctl enable telegraf
systemctl restart telegraf
systemctl status telegraf

2. 容器化部署

( 此处镜像选择zznn阿里云私有镜像 集成oracle客户端 以及python环境 方便使用telegraf的exec模块启用脚本监控 )

部署脚本(docker-compose.yml)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
version: "3.0"
services:
  telegraf-py:   #采集工具一个
    image: registry.cn-hangzhou.aliyuncs.com/zznn/mycentos:telegraf_oracle-py
    restart: always
    container_name: telegraf-py
    hostname: telegraf
    environment:
      TZ: Asia/Shanghai
    ports:
      - 9273:9273
    volumes:
      - ./telegraf.conf:/opt/telegraf-1.20.4/etc/telegraf/telegraf.conf
      # - ./telegraf/telegraf.d/:/etc/telegraf/telegraf.d/
      # - ./telegraf/mibs/:/usr/share/snmp/mibs/
      # - ./telegraf/etc:/etc/snmp/
    command: /opt/telegraf-1.20.4/usr/bin/telegraf --config /opt/telegraf-1.20.4/etc/telegraf/telegraf.conf --config-directory /opt/telegraf-1.20.4/etc/telegraf/telegraf.d
    networks:
      - tpng  
 
  # 下方为普罗米修斯见下篇 (prometheus influxdb选其一)
  prometheus:   
    image: prom/prometheus:latest
    restart: always
    container_name: prometheus
    hostname: prometheus
    environment:
      TZ: Asia/Shanghai
    ports:
      - 9090:9090
    user: root
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./data/monitor/prometheus:/prometheus/data:rw
      #- /data/monitor/prometheus:/prometheus/data:rw
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--storage.tsdb.retention.time=15d"
      #- "--web.console.libraries=/usr/share/prometheus/console_libraries"
      #- "--web.console.templates=/usr/share/prometheus/consoles"
      #- "--enable-feature=remote-write-receiver"
      #- "--query.lookback-delta=2m"
    networks:
      - tpng

  influxdb:
    image: tutum/influxdb 
           # registry.cn-hangzhou.aliyuncs.com/zznn/mycentos:tutum-influxdb
    container_name: influx
    # environment:
    #   - INFLUXDB_ADMIN_ENABLED:"true"
    ports:
      - "8083:8083"
      - "8086:8086"
    expose:
      - 8090
      - 8099
    # volumes:
    #   - influxdb-storage:/var/lib/influxdb
    networks:
      - tpng    

  grafana:
    image: grafana/grafana:7.0.4 #低版本8.3.3
            # 阿里云：registry.cn-hangzhou.aliyuncs.com/zznn/mycentos:grafana7.0.4
    container_name: grafana
    hostname: grafana
    restart: unless-stopped
    ports:
      - 3000:3000
    user: root
    volumes:
      #- grafana-storage:/var/lib/grafana
      - ./grafana.ini:/etc/grafana/grafana.ini
      - ./data/monitor/grafana:/var/lib/grafana:rw
    environment:
      GF_SECURITY_ADMIN_PASSWORD: "admin"
      GF_USERS_ALLOW_SIGN_UP: "false"
      TZ: Asia/Shanghai
      GF_RENDERING_SERVER_URL: http://renderer:8081/render
      GF_RENDERING_CALLBACK_URL: http://grafana:3000/
      GF_LOG_FILTERS: rendering:debug
    networks:
      - tpng  
      
  renderer:
    image: grafana/grafana-image-renderer:2.0.0
            # 阿里云：registry.cn-hangzhou.aliyuncs.com/zznn/mycentos:grafana-image-renderer2.0.0
    restart: always
    ports:
      - "8081:8081"
    environment:
      - GF_RENDERER_PLUGIN_TZ=Asia/Shanghai
      - GF_RENDERER_PLUGIN_IGNORE_HTTPS_ERRORS=true
    networks:
      - tpng  

networks:
  tpng:
    driver: bridge

telegraf-py版功能

image-20230525095815596

具体监控方案见下篇。