Prometheus Node_exporter 之 Disk Datail /proc/diskstats

Disk Datail /proc/diskstats

1. Disk IOps Completed

type: Graph
Unit: I/O ops/sec(iops)
Label: IO read(-)/write(+)
{{device}} - Reads completed: 每个磁盘分区每秒读完成次数

metrics:

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

{{device}} - Writes completed: 每个磁盘分区每秒写完成次数

metrics:

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

2. Disk R/W Data

type: Graph
Unit: bytes/sec
Label: Bytes read(-)/write(+)
{{device}} - Read bytes 每个磁盘分区每秒读取的比特数

metrics:

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

{{device}} - Written bytes 每个磁盘分区每秒写入的比特数

metrics:

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

3. Disk R/W Time

type: Graph
Unit: Milliseconds(ms)
Label: Millisec. read(-)/write(+)
{{device}} - Read time ms 每个磁盘分区读花费的毫秒数

metrics:

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

{{device}} - Write time ms 每个磁盘分区写操作花费的毫秒数

metrics:

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

4. Disk IOs Weighted

type: Graph
Unit: Milliseconds(ms)
Label: Milliseconds
{{device}} - IO time weighted 每个磁盘分区输入/输出操作花费的加权毫秒数

metrics:

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

5. Disk R/W Merged

type: Graph
Unit: I/O ops/sec(iops)
Label: I/Os
{{device}} - Read merged 每个磁盘分区每秒合并读完成次数

metrics:

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

{{device}} - Write merged 每个磁盘分区每秒合并写完成次数

metrics:

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

6. Milliseconds Spent Doing I/Os

type: Graph
Unit: Milliseconds(ms)
Label: Milliseconds
{{device}} - IO time ms 每个磁盘分区输入/输出操作花费的毫秒数

metrics:

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

7. Disk IOs Current in Progress

type: Graph
Unit: I/O ops/sec(iops)
Label: I/Os
{{device}} - IO now 每个磁盘分区每秒正在处理的输入/输出请求数

metrics:

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

8. Open Error File

type: Graph
Unit: short
Label: Errors
Textfile scrape error (1 = true) 1如果打开或读取文件时出错，否则为0

metrics:

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