linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: NeilBrown <neilb@suse.de>
To: Shaohua Li <shli@kernel.org>
Cc: linux-raid@vger.kernel.org, axboe@kernel.dk,
	dan.j.williams@intel.com, shli@fusionio.com
Subject: Re: [patch 03/10 v3] raid5: add a per-stripe lock
Date: Mon, 2 Jul 2012 17:39:53 +1000	[thread overview]
Message-ID: <20120702173953.7bee26cb@notabene.brown> (raw)
In-Reply-To: <20120702031626.GE29770@kernel.org>

[-- Attachment #1: Type: text/plain, Size: 1928 bytes --]

On Mon, 2 Jul 2012 11:16:26 +0800 Shaohua Li <shli@kernel.org> wrote:


> > Then I could see what is being added and what is being removed all in the one
> > patch and I can be sure that they balance.
> 
> reworked the patch 3-5 to two patches as you suggested, and sent to you. please check.

Thanks.  That's looking really good.

However I think we can do better.  I've been looking more closely at the code
and I think that the only things that we need stripe_lock to protect are
->toread and ->towrite, together with the following bios.  e.g.
->toread->bi_next etc.

->read and ->written don't need stripe_lock protection, as they are only
manipulated by the handle_stripe state machine which uses STRIPE_ACTIVE 
and refcounts for exclusion.

So add_stripe_bio need to take the lock while adding a bio to the
->toread and  ->towrite lists, and ops_run_biodrain() and ops_run_biofill
need to take the lock while the move the list from ->to{read,write} to
->{read,written}.  But we don't need it anywhere else.  e.g. analyse_stripe
shouldn't need the lock at all.  Any change that could happen during the loop
could equally happen after the lock was released so we don't lose by not
having the lock.

There is another current user of the lock, but I think that should be
discarded as a false optimisation.
We currently try to optimise out extra calls to bitmap_startwrite and
bitmap_endwrite when we see back-to-back writes to the one stripe.  However I
suspect that is extremely unlikely and it just imposes and pointless need for
synchronisation in raid5.

We just simply call bitmap_startwrite whenever ->towrite changes from NULL to
non-NULL, and call bitmap_endwrite whenever we clear ->written, reguardless
what value ->towrite now has.

Would you like to experiment with that?  If I haven't described it well
enough I can write a patch to show what I mean.

Thanks,
NeilBrown

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 828 bytes --]

  reply	other threads:[~2012-07-02  7:39 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-25  7:24 [patch 00/10 v3] raid5: improve write performance for fast storage Shaohua Li
2012-06-25  7:24 ` [patch 01/10 v3] raid5: use wake_up_all for overlap waking Shaohua Li
2012-06-28  7:26   ` NeilBrown
2012-06-28  8:53     ` Shaohua Li
2012-06-25  7:24 ` [patch 02/10 v3] raid5: delayed stripe fix Shaohua Li
2012-07-02  0:46   ` NeilBrown
2012-07-02  0:49     ` Shaohua Li
2012-07-02  0:55       ` NeilBrown
2012-06-25  7:24 ` [patch 03/10 v3] raid5: add a per-stripe lock Shaohua Li
2012-07-02  0:50   ` NeilBrown
2012-07-02  3:16     ` Shaohua Li
2012-07-02  7:39       ` NeilBrown [this message]
2012-07-03  1:27         ` Shaohua Li
2012-07-03 12:16         ` majianpeng
2012-07-03 23:56           ` NeilBrown
2012-07-04  1:09             ` majianpeng
2012-06-25  7:24 ` [patch 04/10 v3] raid5: lockless access raid5 overrided bi_phys_segments Shaohua Li
2012-06-25  7:24 ` [patch 05/10 v3] raid5: remove some device_lock locking places Shaohua Li
2012-06-25  7:24 ` [patch 06/10 v3] raid5: reduce chance release_stripe() taking device_lock Shaohua Li
2012-07-02  0:57   ` NeilBrown
2012-06-25  7:24 ` [patch 07/10 v3] md: personality can provide unplug private data Shaohua Li
2012-07-02  1:06   ` NeilBrown
2012-06-25  7:24 ` [patch 08/10 v3] raid5: make_request use batch stripe release Shaohua Li
2012-07-02  2:31   ` NeilBrown
2012-07-02  2:59     ` Shaohua Li
2012-07-02  5:07       ` NeilBrown
2012-06-25  7:24 ` [patch 09/10 v3] raid5: raid5d handle stripe in batch way Shaohua Li
2012-07-02  2:32   ` NeilBrown
2012-06-25  7:24 ` [patch 10/10 v3] raid5: create multiple threads to handle stripes Shaohua Li
2012-07-02  2:39   ` NeilBrown
2012-07-02 20:03   ` Dan Williams
2012-07-03  8:04     ` Shaohua Li

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=20120702173953.7bee26cb@notabene.brown \
    --to=neilb@suse.de \
    --cc=axboe@kernel.dk \
    --cc=dan.j.williams@intel.com \
    --cc=linux-raid@vger.kernel.org \
    --cc=shli@fusionio.com \
    --cc=shli@kernel.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).