Prometheus Node_exporter 之 System Detail

System Detail

1. Context Switches / Interrupts

type: Graph
Unit: short
Label: Counter
Context switches - CPU 的 context switch 平均次数(5分钟内)

metrics:

irate(node_context_switches_total{instance=~"$node:$port",job=~"$job"}[5m])

Interrupts - 服务的平均中断总数(5分钟内)

metrics:

irate(node_intr_total{instance=~"$node:$port",job=~"$job"}[5m])

2. System Load

type: Graph
Unit: short
Label: Load
Load 1m - 系统1分钟内的平均负载

metrics:

node_load1{instance=~"$node:$port",job=~"$job"}

Load 5m - 系统5分钟内的平均负载

metrics:

node_load5{instance=~"$node:$port",job=~"$job"}

Load 15m - 系统15分钟内的平均负载

metrics:

node_load15{instance=~"$node:$port",job=~"$job"}

3. Interrupts Detail /proc/interrupts

type: Graph
Unit: short
Label: Counter
{{ type }} - {{ info }} - 当前系统的软中断列表和对应的中断号平均中断次数(5分钟内)

metrics:

irate(node_interrupts_total{instance=~"$node:$port",job=~"$job"}[5m])

4. File Descriptors

type: Graph
Unit: short
Label: Descriptors
Maximum open file descriptors - 最大打开文件描述符数

metrics:

process_max_fds{instance=~"$node:$port",job=~"$job"}

Open file descriptors - 打开文件描述符的数量

metrics:

process_open_fds{instance=~"$node:$port",job=~"$job"}

5. Entropy

type: Graph
Unit: short
Label: Entropy
Entropy available to random number generators

metrics:

node_entropy_available_bits{instance=~"$node:$port",job=~"$job"}

6. Processes State

type: Graph
Unit: short
Label: Processes
Processes blocked - 当前被阻塞的任务的数目 /proc/stat procs_blocked

metrics:

node_procs_blocked{instance=~"$node:$port",job=~"$job"}

Processes in runnable state - 当前运行队列的任务的数目 /proc/stat procs_running

metrics:

node_procs_running{instance=~"$node:$port",job=~"$job"}

7. Processes Forks

type: Graph
Unit: short
Label: Forks / sec
Processes forks second - 每秒创建的进程个数

metrics:

rate(node_forks_total{instance=~"$node:$port",job=~"$job"}[5m])

8. Processes Memory

type: Graph
Unit: bytes
Label: Bytes
进程占用的虚拟内存的大小:

metrics:

process_virtual_memory_bytes{instance=~"$node:$port",job=~"$job"}

进程常驻内存大小:

metrics:

process_resident_memory_bytes{instance=~"$node:$port",job=~"$job"}

9. Time Syncronized Status

type: Graph
Unit: short
Label: Counter
Is clock synchronized to a reliable server:时钟是否与一个可靠的服务器同步:

metrics:

node_timex_sync_status{instance=~"$node:$port",job=~"$job"}

Local clock frequency adjustment: 本地时钟调整频率:

metrics:

node_timex_frequency_adjustment_ratio{instance=~"$node:$port",job=~"$job"}

10. Time Syncronized Drift

type: Graph
Unit: seconds
Label: Seconds
Estimated error in seconds:估算误差(秒):

metrics:

node_timex_estimated_error_seconds{instance=~"$node:$port",job=~"$job"}

Time offset in between local system and reference clock:本地系统和参考时钟之间的时间偏移:

metrics:

node_timex_offset_seconds{instance=~"$node:$port",job=~"$job"}

Maximum error in seconds: 最大误差(秒):

metrics:

node_timex_maxerror_seconds{instance=~"$node:$port",job=~"$job"}

11. Hardware temperature monitor 硬件的温度监控

type: Graph
Unit: Celsius(摄氏度)
Label: Temperature
{{ chip }} {{ sensor }} temp -

metrics:

node_hwmon_temp_celsius{instance=~"$node:$port",job=~"$job"}

{{ chip }} {{ sensor }} Critical Alarm

metrics:

node_hwmon_temp_crit_alarm_celsius{instance=~"$node:$port",job=~"$job"}

{{ chip }} {{ sensor }} Critical

metrics:

node_hwmon_temp_crit_celsius{instance=~"$node:$port",job=~"$job"}

{{ chip }} {{ sensor }} Critical Historical

metrics:

node_hwmon_temp_crit_hyst_celsius{instance=~"$node:$port",job=~"$job"}

{{ chip }} {{ sensor }} Max

metrics:

node_hwmon_temp_max_celsius{instance=~"$node:$port",job=~"$job"}