From: Yong Zhang <yong.zhang0@gmail.com>
To: "Américo Wang" <xiyou.wangcong@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
Cypher Wu <cypher.w@gmail.com>,
linux-kernel@vger.kernel.org, netdev <netdev@vger.kernel.org>
Subject: Re: Kernel rwlock design, Multicore and IGMP
Date: Fri, 12 Nov 2010 21:00:17 +0800 [thread overview]
Message-ID: <20101112130017.GA9752@zhy> (raw)
In-Reply-To: <20101112091818.GB5949@cr0.nay.redhat.com>
On Fri, Nov 12, 2010 at 05:18:18PM +0800, Américo Wang wrote:
> On Fri, Nov 12, 2010 at 05:09:45PM +0800, Yong Zhang wrote:
> >On Fri, Nov 12, 2010 at 4:19 PM, Américo Wang <xiyou.wangcong@gmail.com> wrote:
> >> On Fri, Nov 12, 2010 at 08:27:54AM +0100, Eric Dumazet wrote:
> >>>Le vendredi 12 novembre 2010 à 15:13 +0800, Américo Wang a écrit :
> >>>> On Fri, Nov 12, 2010 at 11:32:59AM +0800, Cypher Wu wrote:
> >>>> >On Thu, Nov 11, 2010 at 11:23 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> >>>> >> Le jeudi 11 novembre 2010 à 21:49 +0800, Cypher Wu a écrit :
> >>>> >>
> >>>> >> Hi
> >>>> >>
> >>>> >> CC netdev, since you ask questions about network stuff _and_ rwlock
> >>>> >>
> >>>> >>
> >>>> >>> I'm using TILEPro and its rwlock in kernel is a liitle different than
> >>>> >>> other platforms. It have a priority for write lock that when tried it
> >>>> >>> will block the following read lock even if read lock is hold by
> >>>> >>> others. Its code can be read in Linux Kernel 2.6.36 in
> >>>> >>> arch/tile/lib/spinlock_32.c.
> >>>> >>
> >>>> >> This seems a bug to me.
> >>>> >>
> >>>> >> read_lock() can be nested. We used such a schem in the past in iptables
> >>>> >> (it can re-enter itself),
> >>>> >> and we used instead a spinlock(), but with many discussions with lkml
> >>>> >> and Linus himself if I remember well.
> >>>> >>
> >>>> >It seems not a problem that read_lock() can be nested or not since
> >>>> >rwlock doesn't have 'owner', it's just that should we give
> >>>> >write_lock() a priority than read_lock() since if there have a lot
> >>>> >read_lock()s then they'll starve write_lock().
> >>>> >We should work out a well defined behavior so all the
> >>>> >platform-dependent raw_rwlock has to design under that principle.
> >>>>
> >>>
> >>>AFAIK, Lockdep allows read_lock() to be nested.
> >>>
> >>>> It is a known weakness of rwlock, it is designed like that. :)
> >>>>
> >>>
> >>>Agreed.
> >>>
> >>
> >> Just for record, both Tile and X86 implement rwlock with a write-bias,
> >> this somewhat reduces the write-starvation problem.
> >
> >Are you sure(on x86)?
> >
> >It seems that we never realize writer-bias rwlock.
> >
>
> Try
>
> % grep RW_LOCK_BIAS -nr arch/x86
>
> *And* read the code to see how it works. :)
If read_lock()/write_lock() fails, the subtracted value(1 for
read_lock() and RW_LOCK_BIAS for write_lock()) is added back.
So reader and writer will contend on the same lock fairly.
And RW_LOCK_BIAS based rwlock is a variant of sighed-test
rwlock, so it works in the same way to highest-bit-set mode
rwlock.
Seem you're cheated by it's name(RW_LOCK_BIAS). :)
Or am I missing something?
Thanks,
Yong
>
> Note, on Tile, it uses a little different algorithm.
next prev parent reply other threads:[~2010-11-12 13:00 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <AANLkTikvT=x9eBovn2-m6HLqk7wyXSAR3sc9jCQ0C6mL@mail.gmail.com>
2010-11-11 15:23 ` Kernel rwlock design, Multicore and IGMP Eric Dumazet
2010-11-11 15:32 ` Eric Dumazet
2010-11-12 3:32 ` Cypher Wu
2010-11-12 6:28 ` Américo Wang
2010-11-12 7:13 ` Américo Wang
2010-11-12 7:27 ` Eric Dumazet
2010-11-12 8:19 ` Américo Wang
2010-11-12 9:09 ` Yong Zhang
2010-11-12 9:18 ` Américo Wang
2010-11-12 11:06 ` Cypher Wu
2010-11-13 6:35 ` Américo Wang
2010-11-12 13:00 ` Yong Zhang [this message]
2010-11-13 6:28 ` Américo Wang
2010-11-12 9:22 ` Eric Dumazet
2010-11-12 9:33 ` Américo Wang
2010-11-12 13:34 ` [PATCH net-next-2.6] igmp: RCU conversion of in_dev->mc_list Eric Dumazet
2010-11-12 14:26 ` Eric Dumazet
2010-11-12 15:46 ` [PATCH net-next-2.6 V2] " Eric Dumazet
2010-11-12 21:19 ` David Miller
2010-11-13 6:44 ` Américo Wang
2010-11-13 22:54 ` Kernel rwlock design, Multicore and IGMP Peter Zijlstra
2010-11-12 11:10 ` Cypher Wu
2010-11-12 11:25 ` Eric Dumazet
2010-11-13 22:53 ` Peter Zijlstra
[not found] ` <ZXmP8hjgLHA.4648@exchange1.tad.internal.tilera.com>
2010-11-13 23:03 ` Chris Metcalf
2010-11-15 7:22 ` Cypher Wu
2010-11-15 11:18 ` Cypher Wu
2010-11-15 11:31 ` Eric Dumazet
2010-11-17 1:30 ` Cypher Wu
2010-11-17 4:43 ` Eric Dumazet
2010-11-15 14:18 ` [PATCH] arch/tile: fix rwlock so would-be write lockers don't block new readers Chris Metcalf
2010-11-15 14:52 ` Eric Dumazet
2010-11-15 15:10 ` Chris Metcalf
2010-11-22 5:39 ` Cypher Wu
2010-11-22 13:35 ` Chris Metcalf
2010-11-23 1:36 ` Cypher Wu
2010-11-23 21:02 ` Chris Metcalf
2010-11-24 2:53 ` Cypher Wu
2010-11-24 14:09 ` Chris Metcalf
2010-11-24 16:37 ` Cypher Wu
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=20101112130017.GA9752@zhy \
--to=yong.zhang0@gmail.com \
--cc=cypher.w@gmail.com \
--cc=eric.dumazet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=xiyou.wangcong@gmail.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).