linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jens Axboe <jaxboe@fusionio.com>
To: <dedekind1@gmail.com>
Cc: <linux-kernel@vger.kernel.org>, <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCHv6 00/15] kill unnecessary bdi wakeups + cleanups
Date: Wed, 4 Aug 2010 13:34:15 +0200	[thread overview]
Message-ID: <4C595037.4050408@fusionio.com> (raw)
In-Reply-To: <4C580FFF.2000605@kernel.dk>

On 2010-08-03 14:47, Jens Axboe wrote:
> On 2010-08-03 14:37, Artem Bityutskiy wrote:
>> On Tue, 2010-08-03 at 14:27 +0200, Jens Axboe wrote:
>>> On 2010-07-25 13:29, Artem Bityutskiy wrote:
>>>> Hi,
>>>>
>>>> here is v6 of the patch series which clean-ups bdi threads and substantially
>>>> lessens amount of unnecessary kernel wake-ups, which is very important on
>>>> battery-powered devices.
>>>>
>>>> This patch-set is also available at:
>>>> git://git.infradead.org/users/dedekind/misc-2.6.git flushers_v6
>>>
>>> Thanks Artem, for sticking around long enough to get this into
>>> shape. I have finally merged it.
>>
>> Thanks, but
>>
>>>> 1. Use 'spin_lock_bh' for the 'bdi->wb_lock' (changed patch N12)
>>>
>>> I'd rather not, question is how to avoid it. Either just wakeup the
>>> default thread, or punt the lock-and-check bdi->wb.task to a thread.
>>
>> you merged this change, do you want me to send a separate patch which
>> undo the 'spin_lock_bh' change? I'll think about how to avoid this and
>> come back.
> 
> Yes, it's not a huge thing, but it would be nice to get rid of. So I
> figured it was better to merge it and not have you respin the series yet
> again.

There is a spinlock bug in the current code, you nest _bh locks on lock
but not always on unlock. I fixed it up as per the below:

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0b8ee66..08d3575 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -415,7 +415,8 @@ static int bdi_forker_thread(void *ptr)
 				break;
 			}
 
-			spin_lock_bh(&bdi->wb_lock);
+			spin_lock(&bdi->wb_lock);
+
 			/*
 			 * If there is no work to do and the bdi thread was
 			 * inactive long enough - kill it. The wb_lock is taken
@@ -432,7 +433,7 @@ static int bdi_forker_thread(void *ptr)
 				action = KILL_THREAD;
 				break;
 			}
-			spin_unlock_bh(&bdi->wb_lock);
+			spin_unlock(&bdi->wb_lock);
 		}
 		spin_unlock_bh(&bdi_lock);
 

-- 
Jens Axboe


Confidentiality Notice: This e-mail message, its contents and any attachments to it are confidential to the intended recipient, and may contain information that is privileged and/or exempt from disclosure under applicable law. If you are not the intended recipient, please immediately notify the sender and destroy the original e-mail message and any attachments (and any copies that may have been made) from your system or otherwise. Any unauthorized use, copying, disclosure or distribution of this information is strictly prohibited.

  reply	other threads:[~2010-08-04 11:34 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-07-25 11:29 [PATCHv6 00/15] kill unnecessary bdi wakeups + cleanups Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 01/15] writeback: harmonize writeback threads naming Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 02/15] writeback: fix possible race when creating bdi threads Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 03/15] writeback: do not lose wake-ups in the forker thread - 1 Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 04/15] writeback: do not lose wake-ups in the forker thread - 2 Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 05/15] writeback: do not lose wake-ups in bdi threads Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 06/15] writeback: simplify bdi code a little Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 07/15] writeback: do not remove bdi from bdi_list Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 08/15] writeback: move last_active to bdi Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 09/15] writeback: restructure bdi forker loop a little Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 10/15] writeback: move bdi threads exiting logic to the forker thread Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 11/15] writeback: prevent unnecessary bdi threads wakeups Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 12/15] writeback: optimize periodic bdi thread wakeups Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 13/15] writeback: remove unnecessary init_timer call Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 14/15] writeback: add new tracepoints Artem Bityutskiy
2010-07-25 11:29 ` [PATCHv6 15/15] writeback: cleanup bdi_register Artem Bityutskiy
2010-08-03  4:44 ` [PATCHv6 00/15] kill unnecessary bdi wakeups + cleanups Artem Bityutskiy
2010-08-03 12:27 ` Jens Axboe
2010-08-03 12:37   ` Artem Bityutskiy
2010-08-03 12:47     ` Jens Axboe
2010-08-04 11:34       ` Jens Axboe [this message]
2010-08-05  9:35         ` Artem Bityutskiy
2010-08-03 14:11   ` Artem Bityutskiy

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=4C595037.4050408@fusionio.com \
    --to=jaxboe@fusionio.com \
    --cc=dedekind1@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.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).