public inbox for linux-nfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Vladislav Bolkhovitin <vst@vlnb.net>
To: Wu Fengguang <wfg@linux.intel.com>
Cc: Jens Axboe <jens.axboe@oracle.com>,
	Jeff Moyer <jmoyer@redhat.com>,
	"Vitaly V. Bursov" <vitalyb@telenet.dn.ua>,
	linux-kernel@vger.kernel.org, linux-nfs@vger.kernel.org,
	lukasz.jurewicz@gmail.com
Subject: Re: Slow file transfer speeds with CFQ IO scheduler in some cases
Date: Fri, 20 Mar 2009 11:53:34 +0300	[thread overview]
Message-ID: <49C3598E.4010704@vlnb.net> (raw)
In-Reply-To: <49C2846D.5030500@vlnb.net>

Vladislav Bolkhovitin, on 03/19/2009 08:44 PM wrote:
>   6. Unexpected result. In case, when all IO threads work in the same IO 
> context with CFQ increasing RA size *decreases* throughput. I think this 
> is, because RA requests performed as single big READ requests, while 
> requests coming from remote clients are much smaller in size (up to 
> 256K), so, when the read by RA data transferred to the remote client on 
> 100MB/s speed, the backstorage media gets rotated a bit, so the next 
> read request must wait the rotation latency (~0.1ms on 7200RPM).
                                                ^^^^^^^^^^^^^^^^^
Oops, it's RP*M*, hence the full rotation latency is in 60 times more, 
i.e. 8.3 ms.

Sorry,
Vlad


  reply	other threads:[~2009-03-20  8:52 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20081112190227.GS26778@kernel.dk>
     [not found] ` <1226566313.199910.29888@de>
     [not found]   ` <492BDAA9.4090405@vlnb.net>
     [not found]     ` <20081125113048.GB16422@localhost>
     [not found]       ` <492BE47B.3010802@vlnb.net>
     [not found]         ` <20081125114908.GA16545@localhost>
     [not found]           ` <492BE97A.3050606@vlnb.net>
     [not found]             ` <492BEAE8.9050809@vlnb.net>
     [not found]               ` <20081125121534.GA16778@localhost>
     [not found]                 ` <492EDCFB.7080302@vlnb.net>
     [not found]                   ` <492EDCFB.7080302-d+Crzxg7Rs0@public.gmane.org>
2008-11-28  0:48                     ` Slow file transfer speeds with CFQ IO scheduler in some cases Wu Fengguang
2009-02-12 18:35                       ` Vladislav Bolkhovitin
2009-02-13  1:57                         ` Wu Fengguang
2009-02-13 20:08                           ` Vladislav Bolkhovitin
     [not found]                             ` <4995D339.5050502-d+Crzxg7Rs0@public.gmane.org>
2009-02-16  2:34                               ` Wu Fengguang
2009-02-17 19:03                                 ` Vladislav Bolkhovitin
2009-02-18 18:14                                   ` Vladislav Bolkhovitin
2009-02-19  1:35                                   ` Wu Fengguang
2009-02-17 19:01                           ` Vladislav Bolkhovitin
2009-02-19  2:05                             ` Wu Fengguang
2009-03-19 17:44                               ` Vladislav Bolkhovitin
2009-03-20  8:53                                 ` Vladislav Bolkhovitin [this message]
2009-03-23  1:42                                 ` Wu Fengguang
2009-04-21 18:18                                   ` Vladislav Bolkhovitin
2009-04-24  8:43                                     ` Wu Fengguang
2009-05-12 18:13                                       ` Vladislav Bolkhovitin
     [not found]                         ` <49946BE6.1040005-d+Crzxg7Rs0@public.gmane.org>
2009-02-17 19:01                           ` Vladislav Bolkhovitin
     [not found]                             ` <499B0979.8050006-d+Crzxg7Rs0@public.gmane.org>
2009-02-19  1:38                               ` Wu Fengguang

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=49C3598E.4010704@vlnb.net \
    --to=vst@vlnb.net \
    --cc=jens.axboe@oracle.com \
    --cc=jmoyer@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=lukasz.jurewicz@gmail.com \
    --cc=vitalyb@telenet.dn.ua \
    --cc=wfg@linux.intel.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