From: Chris Mason <chris.mason@oracle.com>
To: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: James Bottomley <James.Bottomley@suse.de>,
Boaz Harrosh <bharrosh@panasas.com>,
Andrew Morton <akpm@linux-foundation.org>,
Jeff Moyer <jmoyer@redhat.com>, Ric Wheeler <rwheeler@redhat.com>,
linux-scsi@vger.kernel.org
Subject: Re: DIF/DIX updates for 2.6.32
Date: Thu, 27 Aug 2009 16:05:01 -0400 [thread overview]
Message-ID: <20090827200501.GA4940@think> (raw)
In-Reply-To: <yq1ws4p6n4u.fsf@sermon.lab.mkp.net>
On Thu, Aug 27, 2009 at 04:02:41PM -0400, Martin K. Petersen wrote:
> >>>>> "James" == James Bottomley <James.Bottomley@suse.de> writes:
>
> >> This is not an option on a mirror system, and the performance
> >> gain/lose is dependent on the round trip speed. If for every digest
> >> error I have an error recovery cycle, delays, and stalls. Then no it
> >> is not better. Not to mention some iscsi-targets that reset and the
> >> all session must be re-established.
>
> James> Your suggestion of putting processes to sleep while I/O is
> James> pending will degrade performance for everyone; that's not really
> James> an acceptable tradeoff for improving one corner case.
>
[ changing pages in flight ]
>
> In my opinion ext[234] should simply be fixed. If there's a significant
> performance hit on those filesystems we could make the wait conditional
> on a block_device flag.
I agree here. It is pretty trivial in the filesystem to wait for pages
in flight, and it shouldn't be the job of the lower layers to double
buffer 100% of the time.
-chris
next prev parent reply other threads:[~2009-08-27 20:06 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-26 6:17 DIF/DIX updates for 2.6.32 Martin K. Petersen
2009-08-26 6:17 ` [PATCH 1/5] SCSI: Add support for 32-byte CDBs Martin K. Petersen
2009-08-26 12:16 ` Boaz Harrosh
2009-08-27 6:38 ` Martin K. Petersen
2009-08-26 6:17 ` [PATCH 2/5] SCSI: Deprecate SCSI_PROT_*_CONVERT operations Martin K. Petersen
2009-08-26 6:17 ` [PATCH 3/5] sd: Detach DIF from block integrity infrastructure Martin K. Petersen
2009-08-26 6:18 ` [PATCH 4/5] sd: Support disks formatted with DIF Type 2 Martin K. Petersen
2009-08-26 12:26 ` Boaz Harrosh
2009-08-27 6:41 ` Martin K. Petersen
2009-08-26 6:18 ` [PATCH 5/5] scsi_debug: Implement support for " Martin K. Petersen
2009-08-26 12:40 ` Boaz Harrosh
2009-08-27 6:58 ` Martin K. Petersen
2009-08-27 9:35 ` Boaz Harrosh
2009-08-27 13:41 ` James Bottomley
2009-08-27 14:20 ` Boaz Harrosh
2009-08-27 14:30 ` James Bottomley
2009-08-27 14:47 ` Boaz Harrosh
2009-08-27 14:54 ` James Bottomley
2009-08-27 15:17 ` Douglas Gilbert
2009-08-27 15:39 ` Boaz Harrosh
2009-08-26 11:54 ` DIF/DIX updates for 2.6.32 Boaz Harrosh
2009-08-27 6:34 ` Martin K. Petersen
2009-08-27 9:49 ` Boaz Harrosh
2009-08-27 13:46 ` James Bottomley
2009-08-27 14:40 ` Boaz Harrosh
2009-08-27 14:51 ` James Bottomley
2009-08-27 15:18 ` Boaz Harrosh
2009-08-27 15:22 ` James Bottomley
2009-08-27 20:02 ` Martin K. Petersen
2009-08-27 20:05 ` Chris Mason [this message]
-- strict thread matches above, loose matches on Subject: below --
2009-09-04 8:36 Martin K. Petersen
2009-09-11 19:20 Martin K. Petersen
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=20090827200501.GA4940@think \
--to=chris.mason@oracle.com \
--cc=James.Bottomley@suse.de \
--cc=akpm@linux-foundation.org \
--cc=bharrosh@panasas.com \
--cc=jmoyer@redhat.com \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=rwheeler@redhat.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).