prometheusを動かしてみる

Copy
$ mkdir prometheus
$ cd prometheus
$ wget https://github.com/prometheus/prometheus/releases/download/v2.46.0/prometheus-2.46.0.linux-amd64.tar.gz
$ tar xfz prometheus-2.46.0.linux-amd64.tar.gz
$ cd prometheus-2.46.0.linux-amd64/
[dsh92@localhost prometheus-2.46.0.linux-amd64]$ ls -aF
./  ../  LICENSE  NOTICE  console_libraries/  consoles/  prometheus*  prometheus.yml  promtool*

Copy
$ ./prometheus

Copy
$ ps -aux
USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
dsh92    29408  0.3  0.5 800084 43968 pts/1    Sl+  18:09   0:00 ./prometheus

Copy
$ sudo firewall-cmd --add-port=9090/tcp --permanent
success
$ sudo firewall-cmd --reload
success

Copy
$ wget https://github.com/prometheus/node_exporter/releases/download/v1.5.0/node_exporter-1.5.0.linux-amd64.tar.gz
$ tar zxvf ./node_exporter-1.5.0.linux-amd64.tar.gz
$ cd ./node_exporter-1.5.0.linux-amd64
$ ./node_exporter --web.listen-address=:9100

Copy
$ ps -aux
USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
root       55476  0.0  0.6 725440 23172 pts/0    Sl+  00:22   0:00 ./node_exporter --web.listen-address=:9100

Copy
$ curl -s http://localhost:9100/metrics  | head
$ HELP go_gc_duration_seconds A summary of the pause duration of garbage collection cycles.
$ TYPE go_gc_duration_seconds summary
go_gc_duration_seconds{quantile="0"} 0
go_gc_duration_seconds{quantile="0.25"} 0
go_gc_duration_seconds{quantile="0.5"} 0
go_gc_duration_seconds{quantile="0.75"} 0
go_gc_duration_seconds{quantile="1"} 0
go_gc_duration_seconds_sum 0
go_gc_duration_seconds_count 0
$ HELP go_goroutines Number of goroutines that currently exist.

Copy
$ sudo firewall-cmd --add-port=9100/tcp --permanent
success
$ sudo firewall-cmd --reload
success

Copy
# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ["localhost:9090"]
"prometheus.yml" 29L, 934C

Copy
# my global config
global:
  scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # scrape_timeout is set to the global default (10s).

# Alertmanager configuration
alerting:
  alertmanagers:
    - static_configs:
        - targets:
          # - alertmanager:9093

# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"

# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: "prometheus"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
      - targets: ["localhost:9090"]

  - job_name: "kasou2_node"

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    #下記を追加
    static_configs:
      - targets: [{仮想マシン2のIPアドレス}:9100"]

Copy
$ ./prometheus

Copy
$ curl http://192.168.0.11:9090/api/v1/query?query=up
{
  "status": "success",
  "data": {
    "resultType": "vector",
    "result": [
      {
        "metric": {
          "__name__": "up",
          "instance": "192.168.0.12:9100",
          "job": "kasou2_node"
        },
        "value": [1691252773.755, "1"]
      },
      {
        "metric": {
          "__name__": "up",
          "instance": "localhost:9090",
          "job": "prometheus"
        },
        "value": [1691252773.755, "1"]
      }
    ]
  }
}