03 . Prometheus监控容器和HTTP探针应用及服务发现

# HELP node_cpu Seconds the cpus spent in each mode.
# TYPE node_cpu counter
node_cpu{cpu="cpu0",mode="idle"} 362812.7890625
# HELP node_load1 1m load average.
# TYPE node_load1 gauge
node_load1 3.0703125

# HELP <metrics_name> <doc_string>

# TYPE <metrics_name> <metrics_type>

metric_name [
  "{" label_name "=" `"` label_value `"` { "," label_name "=" `"` label_value `"` } [ "," ] "}"
] value [ timestamp ]

# A histogram, which has a pretty complex representation in the text format:
# HELP http_request_duration_seconds A histogram of the request duration.
# TYPE http_request_duration_seconds histogram
http_request_duration_seconds_bucket{le="0.05"} 24054
http_request_duration_seconds_bucket{le="0.1"} 33444
http_request_duration_seconds_bucket{le="0.2"} 100392
http_request_duration_seconds_bucket{le="+Inf"} 144320
http_request_duration_seconds_sum 53423
http_request_duration_seconds_count 144320

# Finally a summary, which has a complex representation, too:
# HELP rpc_duration_seconds A summary of the RPC duration in seconds.
# TYPE rpc_duration_seconds summary
rpc_duration_seconds{quantile="0.01"} 3102
rpc_duration_seconds{quantile="0.05"} 3272
rpc_duration_seconds{quantile="0.5"} 4773
rpc_duration_seconds_sum 1.7560473e+07
rpc_duration_seconds_count 2693

HTTP/1.1 200 OK
Content-Encoding: gzip
Content-Length: 2906
Content-Type: text/plain; version=0.0.4
Date: Sat, 17 Mar 2018 08:47:06 GMT

# 安装一些必要的系统工具
sudo yum install -y yum-utils device-mapper-persistent-data lvm2
# 添加软件源信息
# docker 官方源
sudo yum-config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.repo

# 阿里云源
sudo yum-config-manager --add-repo http://mirrors.aliyun.com/docker-ce/linux/centos/docker-ce.repo

sudo yum makecache fast

# CentOS7安装 Docker-ce
yum -y install docker-ce   


mkdir /etc/docker
vim /etc/docker/daemon.json
{
"registry-mirrors": ["https://registry.docker-cn.com"]
}

# 启动Docker后台服务
systemctl start docker && systemctl enable docker
systemctl daemon-reload                 # 守护进程重启

# 运行一个nginx做测试
docker run -itd nginx

docker stats
CONTAINER           CPU %      MEM USAGE / LIMIT     MEM %      NET I/O         BLOCK I/O   PIDS
9a1648bec3b2        0.30%      196KiB / 3.855GiB     0.00%      828B / 0B       827kB / 0B  1
# 除了使用命令以外，用户还可以通过docker提供的http api查看容器的监控统计信息.

docker run 
  --volume=/:/rootfs:ro 
  --volume=/var/run:/var/run:rw 
  --volume=/sys:/sys:ro 
  --volume=/var/lib/docker/:/var/lib/docker:ro 
  --publish=8080:8080 
  --detach=true 
  --name=cadvisor 
  google/cadvisor:latest
# 通过访问http://localhost:8080可以查看，当前主机上容器的运行状态.

  - job_name: 'docker'
    static_configs:
    - targets: ['172.19.0.27:8080']

systemctl restart prometheus

sum(irate(container_cpu_usage_seconds_total{image!=""}[1m])) without (cpu)

container_memory_usage_bytes{image!=""}

sum(rate(container_network_receive_bytes_total{image!=""}[1m])) without (interface)

sum(rate(container_network_transmit_bytes_total{image!=""}[1m])) without (interface)

sum(rate(container_fs_reads_bytes_total{image!=""}[1m])) without (device)

# 为了方便看出效果，我们使用dd命令
docker exec -it 628d /bin/bash
dd if=/dev/zero of=test bs=1M count=1000

sum(rate(container_fs_writes_bytes_total{image!=""}[1m])) without (device)

tar xvf blackbox_exporter-0.16.0.linux-amd64.tar.gz -C /usr/local/prometheus/
mv blackbox_exporter-0.16.0.linux-amd64/ blackbox_exporter
useradd prometheus
chown -R prometheus:prometheus /usr/local/prometheus/

vim /usr/lib/systemd/system/blackbox_exporter.service
[Unit]
Description=blackbox_exporter
After=network.target

[Service]
Type=simple
User=prometheus
ExecStart=/usr/local/prometheus/blackbox_exporter/blackbox_exporter --config.file=/usr/local/prometheus/blackbox_exporter/blackbox.yml
Restart=on-failure

[Install]
WantedBy=multi-user.target

systemctl enable blackbox_exporter.service
systemctl start blackbox_exporter.service

# 探针类型：http、 tcp、 dns、 icmp.
prober: <prober_string>
# 超时时间
[ timeout: <duration> ]
# 探针的详细配置，最多只能配置其中的一个
[ http: <http_probe> ]
[ tcp: <tcp_probe> ]
[ dns: <dns_probe> ]
[ icmp: <icmp_probe> ]

modules:
  http_2xx:
    prober: http
    http:
      method: GET
  http_post_2xx:
    prober: http
    http:
      method: POST

blackbox_exporter --config.file=/etc/prometheus/blackbox.yml
or
systemctl restart blackbox_exporter.service

# HELP probe_dns_lookup_time_seconds Returns the time taken for probe dns lookup in seconds
# TYPE probe_dns_lookup_time_seconds gauge
probe_dns_lookup_time_seconds 0.004359875
# HELP probe_duration_seconds Returns how long the probe took to complete in seconds
# TYPE probe_duration_seconds gauge
probe_duration_seconds 0.046153996
# HELP probe_failed_due_to_regex Indicates if probe failed due to regex
# TYPE probe_failed_due_to_regex gauge
probe_failed_due_to_regex 0
# HELP probe_http_content_length Length of http content response
# TYPE probe_http_content_length gauge
probe_http_content_length 81
# HELP probe_http_duration_seconds Duration of http request by phase, summed over all redirects
# TYPE probe_http_duration_seconds gauge
probe_http_duration_seconds{phase="connect"} 0.00105657
probe_http_duration_seconds{phase="processing"} 0.039457402
probe_http_duration_seconds{phase="resolve"} 0.004359875
probe_http_duration_seconds{phase="tls"} 0
probe_http_duration_seconds{phase="transfer"} 0.000337184
# HELP probe_http_last_modified_timestamp_seconds Returns the Last-Modified HTTP 
response header in unixtime
# TYPE probe_http_last_modified_timestamp_seconds gauge
probe_http_last_modified_timestamp_seconds 1.26330408e+09
# HELP probe_http_redirects The number of redirects
# TYPE probe_http_redirects gauge
probe_http_redirects 0
# HELP probe_http_ssl Indicates if SSL was used for the final redirect
# TYPE probe_http_ssl gauge
probe_http_ssl 0
# HELP probe_http_status_code Response HTTP status code
# TYPE probe_http_status_code gauge
probe_http_status_code 200
# HELP probe_http_uncompressed_body_length Length of uncompressed response body
# TYPE probe_http_uncompressed_body_length gauge
probe_http_uncompressed_body_length 81
# HELP probe_http_version Returns the version of HTTP of the probe response
# TYPE probe_http_version gauge
probe_http_version 1.1
# HELP probe_ip_protocol Specifies whether probe ip protocol is IP4 or IP6
# TYPE probe_ip_protocol gauge
probe_ip_protocol 4
# HELP probe_success Displays whether or not the probe was a success
# TYPE probe_success gauge
probe_success 1

  - job_name: 'baidu_http2xx_probe'
    params:
      module:
      - http_2xx
      target:
      - baidu.com
    metrics_path: /probe
    static_configs:
    - targets: ['172.19.0.27:9115']

  - job_name: 'prometheus_http2xx_probe'
    params:
      module:
      - http_2xx
      target:
      - prometheus.io
    metrics_path: /probe
    static_configs:
    - targets: ['172.19.0.27:9115']

systemctl restart prometheus

  - job_name: 'blackbox'
    metrics_path: /probe
    params:
      module: [http_2xx]
    static_configs:
      - targets:
        - http://prometheus.io    # Target to probe with http.
        - https://prometheus.io   # Target to probe with https.
        - http://example.com:8080 # Target to probe with http on port 8080.
    relabel_configs:
      - source_labels: [__address__]
        target_label: __param_target
      - source_labels: [__param_target]
        target_label: instance
      - target_label: __address__
        replacement: 172.19.0.27:9115

* 第一步， 根据Target实例的地址，写入__param_target标签中，__param_<name>形式的标签来表示,
	# 在采集任务时会在请求目标地址中添加<name>参数，等同于params的设置.
* 第二步,  获取__param_target的值，并覆写到instance标签中.
* 第三步,  覆写Target实例的__address__标签值为BlockBox Exporter实例的访问地址.

modules:
  http_2xx_example:
    prober: http
    http:

http_post_2xx:
    prober: http
    timeout: 5s
    http:
      method: POST
      headers:
        Content-Type: application/json
      body: '{}'

http_basic_auth_example:
    prober: http
    timeout: 5s
    http:
      method: POST
      headers:
        Host: "login.example.com"
      basic_auth:
        username: "username"
        password: "mysecret"

 http_custom_ca_example:
    prober: http
    http:
      method: GET
      tls_config:
        ca_file: "/certs/my_cert.crt"

  http_2xx_example:
    prober: http
    timeout: 5s
    http:
      valid_http_versions: ["HTTP/1.1", "HTTP/2"]
      valid_status_codes: []

# HELP probe_http_ssl Indicates if SSL was used for the final redirect
# TYPE probe_http_ssl gauge
probe_http_ssl 0

  http_2xx_example:
    prober: http
    timeout: 5s
    http:
      valid_status_codes: []
      method: GET
      no_follow_redirects: false
      fail_if_ssl: false
      fail_if_not_ssl: false

  http_2xx_example:
    prober: http
    timeout: 5s
    http:
      method: GET
      fail_if_matches_regexp:
        - "Could not connect to database"
      fail_if_not_matches_regexp:
        - "Download the latest version here"

# HELP probe_ip_protocol Specifies whether probe ip protocol is IP4 or IP6
# TYPE probe_ip_protocol gauge
probe_ip_protocol 6

cat prometheus.yml 
global:
  scrape_interval:     35s
  evaluation_interval: 35s
  query_log_file: "prometheus.log"

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - "localhost:9093"

rule_files:
  - "rules/*.yml"
scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']
  - job_name: 'node'
    basic_auth:
      username: "youmen"
      password: "youmen"
    file_sd_configs:
      - files:
          - sd/file/node/*.yaml
          - sd/file/node/*.json

[
  {"targets":["121.36.43.223:9100"]}
]

- targets: ["121.36.43.223:9100","49.233.69.195:9100"]