linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: William Dauchy <william@gandi.net>
To: linux-nfs@vger.kernel.org
Cc: Trond Myklebust <trond.myklebust@primarydata.com>, william@gandi.net
Subject: Re: poor random read nfs client results using fio on v4.1.x
Date: Sat, 20 Feb 2016 16:52:54 +0100	[thread overview]
Message-ID: <20160220155254.GA3225@gandi.net> (raw)
In-Reply-To: <20160219153123.GC3351@gandi.net>

[-- Attachment #1: Type: text/plain, Size: 1964 bytes --]

On Feb19 16:31, William Dauchy wrote:
> I would expect at least the same performances in v4.1.x.
> What can I do to help debug this issue?

I overlooked my config in 4.1.x and find out KASAN and kmemleak were
enabled.
however I can't reach the results I had on 3.14.x without these debug
options.

see my updated results on 4.1.x:

random-read: (g=0): rw=randread, bs=4K-4K/4K-4K/4K-4K, ioengine=sync, iodepth=1
fio-2.1.11
Starting 1 process
Jobs: 1 (f=1): [r(1)] [100.0% done] [7136KB/0KB/0KB /s] [1784/0/0 iops] [eta 00m:00s]
random-read: (groupid=0, jobs=1): err= 0: pid=3519: Sat Feb 20 15:44:10 2016
  read : io=131072KB, bw=7617.9KB/s, iops=1904, runt= 17206msec
    clat (usec): min=281, max=2091, avg=517.56, stdev=79.68
     lat (usec): min=281, max=2092, avg=517.90, stdev=79.69
    clat percentiles (usec):
     |  1.00th=[  318],  5.00th=[  402], 10.00th=[  422], 20.00th=[  442],
     | 30.00th=[  490], 40.00th=[  506], 50.00th=[  516], 60.00th=[  524],
     | 70.00th=[  548], 80.00th=[  580], 90.00th=[  612], 95.00th=[  652],
     | 99.00th=[  716], 99.50th=[  740], 99.90th=[  772], 99.95th=[ 1208],
     | 99.99th=[ 1624]
    bw (KB  /s): min= 7080, max= 8128, per=100.00%, avg=7627.53, stdev=343.98
    lat (usec) : 500=37.34%, 750=62.32%, 1000=0.28%
    lat (msec) : 2=0.05%, 4=0.01%
  cpu          : usr=2.05%, sys=14.02%, ctx=65541, majf=0, minf=45
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued    : total=r=32768/w=0/d=0, short=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: io=131072KB, aggrb=7617KB/s, minb=7617KB/s, maxb=7617KB/s, mint=17206msec, maxt=17206msec


summary:
3.14: 9348KB/s
4.1:  7617KB/s

-- 
William

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 181 bytes --]

      reply	other threads:[~2016-02-20 15:52 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-19 15:31 poor random read nfs client results using fio on v4.1.x William Dauchy
2016-02-20 15:52 ` William Dauchy [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160220155254.GA3225@gandi.net \
    --to=william@gandi.net \
    --cc=linux-nfs@vger.kernel.org \
    --cc=trond.myklebust@primarydata.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).