Prometheus 极速概览

global:
  # How frequently to scrape targets by default.
  # 抓 target 的频率
  [ scrape_interval: <duration> | default = 1m ]

  # How long until a scrape request times out.
  # 超时时间
  [ scrape_timeout: <duration> | default = 10s ]

  # How frequently to evaluate rules.
  # 计算 rule 的频率
  [ evaluation_interval: <duration> | default = 1m ]

  # The labels to add to any time series or alerts when communicating with
  # external systems (federation, remote storage, Alertmanager).
  external_labels:
    [ <labelname>: <labelvalue> ... ]

  # File to which PromQL queries are logged.
  # Reloading the configuration will reopen the file.
  [ query_log_file: <string> ]

# Rule files specifies a list of globs. Rules and alerts are read from
# all matching files.
# 一组 glob（带通配符的文件地址），读取文件中的规则和告警
rule_files:
  [ - <filepath_glob> ... ]

# A list of scrape configurations.
# 抓取配置，可以分组配置 exporter
scrape_configs:
  [ - <scrape_config> ... ]

# Alerting specifies settings related to the Alertmanager.
alerting:
  alert_relabel_configs:
    [ - <relabel_config> ... ]
  alertmanagers:
    [ - <alertmanager_config> ... ]

# Settings related to the remote write feature.
remote_write:
  [ - <remote_write> ... ]

# Settings related to the remote read feature.
remote_read:
  [ - <remote_read> ... ]

# HELP node_disk_io_time_seconds_total Total seconds spent doing I/Os.
# TYPE node_disk_io_time_seconds_total counter
node_disk_io_time_seconds_total{device="dm-0"} 903.864
node_disk_io_time_seconds_total{device="sda"} 903.688
node_disk_io_time_seconds_total{device="sr0"} 0.156
node_disk_io_time_seconds_total{device="sr1"} 0.124
# HELP node_disk_io_time_weighted_seconds_total The weighted # of seconds spent doing I/Os.
# TYPE node_disk_io_time_weighted_seconds_total counter
node_disk_io_time_weighted_seconds_total{device="dm-0"} 387.796
node_disk_io_time_weighted_seconds_total{device="sda"} 38.02
node_disk_io_time_weighted_seconds_total{device="sr0"} 0.024
node_disk_io_time_weighted_seconds_total{device="sr1"} 0.008
# HELP node_disk_read_bytes_total The total number of bytes read successfully.
# TYPE node_disk_read_bytes_total counter
node_disk_read_bytes_total{device="dm-0"} 7.86113536e+08
node_disk_read_bytes_total{device="sda"} 7.97292544e+08
node_disk_read_bytes_total{device="sr0"} 1.8208768e+07
node_disk_read_bytes_total{device="sr1"} 1.8243584e+07

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

scrape_configs:
  - job_name: 'node'
    # Override the global default and scrape targets from this job every 5 seconds.
    # 可覆盖 global 配置的抓取间隔
    scrape_interval: 5s
    static_configs:
      - targets: ['localhost:8080', 'localhost:8081']
        labels:
          group: 'production'
      - targets: ['localhost:8082']
        labels:
          group: 'canary'

groups:
  [ - <rule_group> ]

# The name of the group. Must be unique within a file.
name: <string>

# How often rules in the group are evaluated.
[ interval: <duration> | default = global.evaluation_interval ]

rules:
  [ - <rule> ... ]

# The name of the time series to output to. Must be a valid metric name.
record: <string>

# The PromQL expression to evaluate. Every evaluation cycle this is
# evaluated at the current time, and the result recorded as a new set of
# time series with the metric name as given by 'record'.
expr: <string>

# Labels to add or overwrite before storing the result.
labels: [<labelname>: <labelvalue>]

groups:
  - name: cpu-node
    rules:
      - record: job_instance_mode:node_cpu_seconds:avg_rate5m
        expr: avg by (job, instance, mode) (rate(node_cpu_seconds_total[5m]))

rule_files:
  - 'prometheus.rules.yml'

# The name of the alert. Must be a valid label value.
alert: <string>

# The PromQL expression to evaluate. Every evaluation cycle this is
# evaluated at the current time, and all resultant time series become
# pending/firing alerts.
expr: <string>

# Alerts are considered firing once they have been returned for this long.
# Alerts which have not yet fired for long enough are considered pending.
[ for: <duration> | default = 0s ]

# Labels to add or overwrite for each alert.
labels:
  [ <labelname>: <tmpl_string> ]

# Annotations to add to each alert.
annotations:
  [ <labelname>: <tmpl_string> ]

groups:
  - name: example
    rules:
      - alert: HighRequestLatency
        expr: job:request_latency_seconds:mean5m{job="myjob"} > 0.5
        for: 10m
        labels:
          severity: page
        annotations:
          summary: High request latency

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['localhost:9093']

<metric name>{<label name>=<label value>, ...}

api_http_requests_total{method="POST", handler="/messages"}