From: Alasdair G Kergon <agk-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>,
Kent Overstreet
<koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
Subject: Re: [dm-devel] [PATCH v10 4/8] block: Add bio_reset()
Date: Sat, 8 Sep 2012 00:14:33 +0100 [thread overview]
Message-ID: <20120907231433.GE10309@agk-dp.fab.redhat.com> (raw)
In-Reply-To: <504A78B0.8010105-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
As I indicated already in this discussion, dm started to use
merge_bvec_fn as a cheap way of avoiding splitting and this improved
overall efficiency. Often it's better to pay the small price of calling
that function to ensure the bio is created the right size in the first
place so it won't have to get split later.
I'm as yet unconvinced that removing merge_bvec_fn would be an overall
win. Some of Kent's other changes that make splitting cheaper will
improve the balance in some situations, but that might be handled by
simplifying the merge_bvec_fn calculations in those situations.
(Or changing the mechanism to avoid repeating performing the mapping
when it hasn't changed.)
IOW Any proposal to remove merge_bvec_fn from dm needs careful
evaluation to ensure it doesn't introduce any significant
performance regressions for some sets of users.
Alasdair
next prev parent reply other threads:[~2012-09-07 23:14 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-06 22:34 [PATCH v10 0/8] Block cleanups Kent Overstreet
2012-09-06 22:34 ` [PATCH v10 1/8] block: Generalized bio pool freeing Kent Overstreet
[not found] ` <1346970902-10931-2-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-14 18:28 ` [dm-devel] " Alasdair G Kergon
[not found] ` <20120914182828.GK15728-FDJ95KluN3Z0klwcnFlA1dvLeJWuRmrY@public.gmane.org>
2012-09-17 20:51 ` Kent Overstreet
[not found] ` <20120917205139.GB14492-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-18 16:31 ` Alasdair G Kergon
2012-09-14 18:36 ` Alasdair G Kergon
2012-09-06 22:34 ` [PATCH v10 2/8] block: Ues bi_pool for bio_integrity_alloc() Kent Overstreet
2012-09-06 22:34 ` [PATCH v10 3/8] dm: Use bioset's front_pad for dm_rq_clone_bio_info Kent Overstreet
2012-09-06 22:34 ` [PATCH v10 4/8] block: Add bio_reset() Kent Overstreet
[not found] ` <1346970902-10931-5-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-07 1:34 ` Jens Axboe
2012-09-07 20:58 ` Kent Overstreet
[not found] ` <20120907205823.GD16360-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-07 21:55 ` Jens Axboe
[not found] ` <504A6D57.1030607-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
2012-09-07 22:06 ` Jens Axboe
[not found] ` <504A6FF5.3090603-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
2012-09-07 22:25 ` Kent Overstreet
[not found] ` <20120907222522.GE16360-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-07 22:44 ` Jens Axboe
[not found] ` <504A78B0.8010105-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>
2012-09-07 23:14 ` Alasdair G Kergon [this message]
[not found] ` <20120907231433.GE10309-FDJ95KluN3Z0klwcnFlA1dvLeJWuRmrY@public.gmane.org>
2012-09-07 23:25 ` [dm-devel] " Kent Overstreet
2012-09-06 22:34 ` [PATCH v10 5/8] pktcdvd: Switch to bio_kmalloc() Kent Overstreet
2012-09-06 22:35 ` [PATCH v10 6/8] block: Kill bi_destructor Kent Overstreet
[not found] ` <1346970902-10931-7-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-06 23:42 ` Tejun Heo
2012-09-06 22:35 ` [PATCH v10 7/8] block: Consolidate bio_alloc_bioset(), bio_kmalloc() Kent Overstreet
[not found] ` <1346970902-10931-8-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-06 23:45 ` Tejun Heo
2012-09-06 22:35 ` [PATCH v10 8/8] block: Add bio_clone_bioset(), bio_clone_kmalloc() Kent Overstreet
[not found] ` <1346970902-10931-9-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-06 23:46 ` Tejun Heo
2012-09-14 21:50 ` [dm-devel] " Alasdair G Kergon
[not found] ` <20120914215059.GQ15728-FDJ95KluN3Z0klwcnFlA1dvLeJWuRmrY@public.gmane.org>
2012-09-17 20:42 ` Kent Overstreet
[not found] ` <20120917204227.GA14492-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-18 16:15 ` Alasdair G Kergon
[not found] ` <1346970902-10931-1-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-06 23:48 ` [PATCH v10 0/8] Block cleanups Tejun Heo
[not found] ` <20120906234805.GD9426-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-09-07 1:37 ` Jens Axboe
2012-09-07 20:44 ` Kent Overstreet
2012-09-11 4:43 ` NeilBrown
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=20120907231433.GE10309@agk-dp.fab.redhat.com \
--to=agk-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
--cc=axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org \
--cc=dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
/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).