From: Nick Piggin <npiggin@suse.de>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Jens Axboe <jens.axboe@oracle.com>,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
chris.mason@oracle.com, david@fromorbit.com, hch@infradead.org,
akpm@linux-foundation.org, jack@suse.cz,
yanmin_zhang@linux.intel.com,
Christoph Lameter <cl@linux-foundation.org>,
Matthew Wilcox <willy@linux.intel.com>
Subject: Re: [PATCH 03/13] scsi: unify allocation of scsi command and sense buffer
Date: Mon, 25 May 2009 13:32:51 +0200 [thread overview]
Message-ID: <20090525113251.GC24071@wotan.suse.de> (raw)
In-Reply-To: <84144f020905250115m1dffb51er51f8f339ab58a704@mail.gmail.com>
On Mon, May 25, 2009 at 11:15:42AM +0300, Pekka Enberg wrote:
> On Mon, May 25, 2009 at 10:30 AM, Jens Axboe <jens.axboe@oracle.com> wrote:
> > Fold the sense buffer into the command, thereby eliminating a slab
> > allocation and free per command.
> >
> > Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
>
> Interesting. I wonder how this affects the SLAB vs. SLUB regression
> people are seeing on high end machines in OLTP benchmarks.
It could improve it. I think these (bios, requests, commands etc) allocations
are what SLUB has trouble with in that workload, so eliminating one of them
should help it. I guess it will help the other allocators as well, but maybe
a smaller relative improvement?
next prev parent reply other threads:[~2009-05-25 11:32 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-05-25 7:30 [PATCH 0/12] Per-bdi writeback flusher threads #5 Jens Axboe
2009-05-25 7:30 ` [PATCH 01/13] libata: get rid of ATA_MAX_QUEUE loop in ata_qc_complete_multiple() Jens Axboe
2009-05-25 7:30 ` [PATCH 01/12] ntfs: remove old debug check for dirty data in ntfs_put_super() Jens Axboe
2009-05-25 7:30 ` [PATCH 02/13] block: add static rq allocation cache Jens Axboe
2009-05-25 7:30 ` [PATCH 02/12] btrfs: properly register fs backing device Jens Axboe
2009-05-25 7:30 ` [PATCH 03/13] scsi: unify allocation of scsi command and sense buffer Jens Axboe
2009-05-25 7:41 ` Christoph Hellwig
2009-05-25 7:46 ` Jens Axboe
2009-05-25 7:50 ` Christoph Hellwig
2009-05-25 7:54 ` Jens Axboe
2009-05-25 10:33 ` Boaz Harrosh
2009-05-25 10:42 ` Christoph Hellwig
2009-05-25 10:49 ` Jens Axboe
2009-05-26 4:36 ` FUJITA Tomonori
2009-05-26 5:08 ` FUJITA Tomonori
2009-05-25 8:15 ` Pekka Enberg
2009-05-25 11:32 ` Nick Piggin [this message]
2009-05-25 9:28 ` Boaz Harrosh
2009-05-26 1:45 ` Roland Dreier
2009-05-26 4:36 ` FUJITA Tomonori
2009-05-26 6:29 ` Jens Axboe
2009-05-26 7:25 ` FUJITA Tomonori
2009-05-26 7:32 ` Jens Axboe
2009-05-26 7:38 ` FUJITA Tomonori
2009-05-26 14:47 ` James Bottomley
2009-05-26 15:13 ` Matthew Wilcox
2009-05-26 15:31 ` FUJITA Tomonori
2009-05-26 16:05 ` Boaz Harrosh
2009-05-27 1:36 ` FUJITA Tomonori
2009-05-27 7:54 ` Boaz Harrosh
2009-05-27 8:26 ` FUJITA Tomonori
2009-05-27 9:11 ` Boaz Harrosh
2009-05-26 16:12 ` Boaz Harrosh
2009-05-26 16:28 ` Boaz Harrosh
2009-05-26 7:56 ` FUJITA Tomonori
2009-05-26 5:23 ` FUJITA Tomonori
2009-05-25 7:30 ` [PATCH 03/12] writeback: move dirty inodes from super_block to backing_dev_info Jens Axboe
2009-05-25 7:30 ` [PATCH 04/13] scsi: get rid of lock in __scsi_put_command() Jens Axboe
2009-05-25 7:30 ` [PATCH 04/12] writeback: switch to per-bdi threads for flushing data Jens Axboe
2009-05-25 7:30 ` [PATCH 05/13] aio: mostly crap Jens Axboe
2009-05-25 9:09 ` Jan Kara
2009-05-25 7:30 ` [PATCH 05/12] writeback: get rid of pdflush completely Jens Axboe
2009-05-25 7:30 ` [PATCH 06/13] block: move elevator ops into the queue Jens Axboe
2009-05-25 7:30 ` [PATCH 06/12] writeback: separate the flushing state/task from the bdi Jens Axboe
2009-05-25 7:30 ` [PATCH 07/13] block: avoid indirect calls to enter cfq io scheduler Jens Axboe
2009-05-26 9:02 ` Nikanth K
2009-05-25 7:30 ` [PATCH 07/12] writeback: support > 1 flusher thread per bdi Jens Axboe
2009-05-25 7:30 ` [PATCH 08/13] block: change the tag sync vs async restriction logic Jens Axboe
2009-05-25 7:30 ` [PATCH 08/12] writeback: include default_backing_dev_info in writeback Jens Axboe
2009-05-25 7:31 ` [PATCH 09/13] libata: switch to using block layer tagging support Jens Axboe
2009-05-25 7:31 ` [PATCH 09/12] writeback: allow sleepy exit of default writeback task Jens Axboe
2009-05-25 7:31 ` [PATCH 10/13] block: add function for waiting for a specific free tag Jens Axboe
2009-05-25 7:31 ` [PATCH 10/12] writeback: add some debug inode list counters to bdi stats Jens Axboe
2009-05-25 7:31 ` [PATCH 11/13] block: disallow merging of read-ahead bits into normal request Jens Axboe
2009-05-25 7:31 ` [PATCH 11/12] writeback: add name to backing_dev_info Jens Axboe
2009-05-25 7:31 ` [PATCH 12/13] block: first cut at implementing a NAPI approach for block devices Jens Axboe
2009-05-25 7:31 ` [PATCH 12/12] writeback: check for registered bdi in flusher add and inode dirty Jens Axboe
2009-05-25 7:31 ` [PATCH 13/13] block: unlocked completion test patch Jens Axboe
2009-05-25 7:33 ` [PATCH 0/12] Per-bdi writeback flusher threads #5 Jens Axboe
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=20090525113251.GC24071@wotan.suse.de \
--to=npiggin@suse.de \
--cc=akpm@linux-foundation.org \
--cc=chris.mason@oracle.com \
--cc=cl@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=jens.axboe@oracle.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=penberg@cs.helsinki.fi \
--cc=willy@linux.intel.com \
--cc=yanmin_zhang@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;
as well as URLs for NNTP newsgroup(s).