mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: James Bottomley <James.Bottomley@HansenPartnership.com>
To: Ross Walker <rswwalker@gmail.com>
Cc: Bart Van Assche <bart.vanassche@gmail.com>,
	"Ross S. W. Walker" <RWalker@medallion.com>,
	Vladislav Bolkhovitin <vst@vlnb.net>,
	"linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>,
	iSCSI Enterprise Target Developer List 
	<iscsitarget-devel@lists.sourceforge.net>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"stgt@vger.kernel.org" <stgt@vger.kernel.org>,
	scst-devel <scst-devel@lists.sourceforge.net>
Subject: Re: [Iscsitarget-devel] [Scst-devel] ISCSI-SCST performance (withalso IET and STGT data)
Date: Wed, 01 Apr 2009 20:23:43 +0000	[thread overview]
Message-ID: <1238617423.3318.82.camel@mulgrave.int.hansenpartnership.com> (raw)
In-Reply-To: <FA7F6940-CD5C-4460-9777-2F7AE3657B8E@gmail.com>

On Wed, 2009-04-01 at 08:20 -0400, Ross Walker wrote:
> On Apr 1, 2009, at 2:29 AM, Bart Van Assche <bart.vanassche@gmail.com>  
> wrote:
> 
> > On Tue, Mar 31, 2009 at 8:43 PM, Ross S. W. Walker
> > <RWalker@medallion.com> wrote:
> >> IET just needs to fix how it does it workload with CFQ which
> >> somehow SCST has overcome. Of course SCST tweaks the Linux kernel to
> >> gain some extra speed.
> >
> > I'm not familiar with the implementation details of CFQ, but I know
> > that one of the changes between SCST 1.0.0 and SCST 1.0.1 is that the
> > default number of kernel threads of the scst_vdisk kernel module has
> > been increased to 5. Could this explain the performance difference
> > between SCST and IET for FILEIO and BLOCKIO ?
> 
> Thank for the update. IET has used 8 threads per target for ages now,  
> I don't think it is that.
> 
> It may be how the I/O threads are forked in SCST that causes them to  
> be in the same I/O context with each other.
> 
> I'm pretty sure implementing a version of the patch that was used for  
> the dump command (found on the LKML) will fix this.
> 
> But thanks goes to Vlad for pointing this dificiency out so we can fix  
> it to help make IET even better.

SCST explicitly fiddles with the io context to get this to happen.  It
has a hack to block to export alloc_io_context:

http://marc.info/?t=122893564800003

James



  reply	other threads:[~2009-04-01 20:24 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-03-30 17:33 ISCSI-SCST performance (with also " Vladislav Bolkhovitin
     [not found] ` <e2e108260903301106y2b750c23kfab978567f3de3a0@mail.gmail.com>
2009-03-30 18:33   ` [Scst-devel] " Vladislav Bolkhovitin
2009-03-30 18:53     ` Bart Van Assche
2009-03-31 17:37       ` Vladislav Bolkhovitin
2009-03-31 18:43         ` [Iscsitarget-devel] [Scst-devel] ISCSI-SCST performance (withalso " Ross S. W. Walker
2009-04-01  6:29           ` Bart Van Assche
2009-04-01 12:20             ` Ross Walker
2009-04-01 20:23               ` James Bottomley [this message]
2009-04-02  7:38                 ` [Scst-devel] [Iscsitarget-devel] ISCSI-SCST performance (with also " Vladislav Bolkhovitin
2009-04-02  9:02                   ` Vladislav Bolkhovitin
2009-04-02 14:06                     ` Ross S. W. Walker
2009-04-02 14:14                       ` Ross S. W. Walker
2009-04-02 15:36                       ` Vladislav Bolkhovitin
2009-04-02 17:19                         ` Ross S. W. Walker
2009-04-01 20:14 ` Bart Van Assche
2009-04-02 17:16   ` [Scst-devel] " Vladislav Bolkhovitin
2009-04-03 17:08     ` Bart Van Assche
2009-04-03 17:13       ` [Scst-devel] ISCSI-SCST performance (with also IET and STGTdata) Sufficool, Stanley
2009-04-03 17:52         ` Bart Van Assche
2009-04-04  8:04     ` [Scst-devel] ISCSI-SCST performance (with also IET and STGT data) Bart Van Assche
2009-04-17 18:11       ` Vladislav Bolkhovitin

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=1238617423.3318.82.camel@mulgrave.int.hansenpartnership.com \
    --to=james.bottomley@hansenpartnership.com \
    --cc=RWalker@medallion.com \
    --cc=bart.vanassche@gmail.com \
    --cc=iscsitarget-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=rswwalker@gmail.com \
    --cc=scst-devel@lists.sourceforge.net \
    --cc=stgt@vger.kernel.org \
    --cc=vst@vlnb.net \
    /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

all inboxes | Powered by JetHome®