Re: help understanding the output of fio

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi Felix -

It might be helpful to share your job file or fio command line. Not sure, I'm a neophyte as well with many questions such as what happens when the number of jobs is less than the iodepth.

On 4/3/24 00:35, Felix Rubio wrote:
Hi everybody,

I have started recently to use fio, and I am getting the following output for sequential writes:

write_throughput_i: (groupid=0, jobs=16): err= 0: pid=2301660: Tue Apr 2 21:03:41 2024   write: IOPS=2, BW=5613KiB/s (5748kB/s)(2048MiB/373607msec); 0 zone resets
     slat (msec): min=41549, max=373605, avg=260175.71, stdev=76630.63
     clat (nsec): min=17445, max=31004, avg=20350.31, stdev=3744.64
      lat (msec): min=235566, max=373605, avg=318209.63, stdev=32743.17
     clat percentiles (nsec):
      |  1.00th=[17536],  5.00th=[17536], 10.00th=[17792], 20.00th=[17792],
      | 30.00th=[18048], 40.00th=[18304], 50.00th=[18304], 60.00th=[18816],
      | 70.00th=[21632], 80.00th=[22144], 90.00th=[27008], 95.00th=[31104],
      | 99.00th=[31104], 99.50th=[31104], 99.90th=[31104], 99.95th=[31104],
      | 99.99th=[31104]
   bw (  MiB/s): min= 2051, max= 2051, per=100.00%, avg=2051.84, stdev= 0.00, samples=16    iops        : min= 2048, max= 2048, avg=2048.00, stdev= 0.00, samples=16
   lat (usec)   : 20=68.75%, 50=31.25%
   cpu          : usr=0.00%, sys=0.02%, ctx=8350, majf=13, minf=633
  IO depths    : 1=0.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=100.0%      submit    : 0=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=100.0%, >=64=0.0%      complete  : 0=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=100.0%, >=64=0.0%
      issued rwts: total=0,1024,0,0 short=0,0,0,0 dropped=0,0,0,0
      latency   : target=0, window=0, percentile=100.00%, depth=64

Run status group 0 (all jobs):
  WRITE: bw=5613KiB/s (5748kB/s), 5613KiB/s-5613KiB/s (5748kB/s-5748kB/s), io=2048MiB (2147MB), run=373607-373607msec

Should I understand this correctly, the submission latency (slat) is at minimum 41.5 seconds? I am experiencing problems with my SSD disk (the performance is pretty low, which this seems to confirm), but now I am wondering if this could be a problem with my OS and not my disk, being the slat the submission latency?

Thank you




[Index of Archives]     [Linux Kernel]     [Linux SCSI]     [Linux IDE]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux SCSI]

  Powered by Linux