lkml.org 
[lkml]   [2011]   [Dec]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] VFS: br_write_lock locks on possible CPUs other than online CPUs
On Mon, Dec 19, 2011 at 04:11:42AM +0000, Al Viro wrote:
> On Mon, Dec 19, 2011 at 11:36:15AM +0800, mengcong wrote:
> > In a heavily loaded system, when frequently turning on and off CPUs, the
> > kernel will detect soft-lockups on multiple CPUs. The detailed bug report
> > is at https://lkml.org/lkml/2011/8/24/185.
> >
> > The root cause is that brlock functions, i.e. br_write_lock() and
> > br_write_unlock(), only locks/unlocks the per-CPU spinlock of CPUs that
> > are online, which means, if one online CPU is locked and then goes
> > offline, any later unlocking operation happens during its offline state
> > will not touch it; and when it goes online again, it has the incorrect
> > brlock state. This has been verified in current kernel.
> >
> > I can reproduce this bug on the intact 3.1 kernel. After my patch applied,
> > I've ran an 8-hours long test(test script provided by the bug reporter),
> > and no soft lockup happened again.
>
> Argh... OK, that's seriously nasty. I agree that this is broken, but
> your patch makes br_write_lock() very costly on kernels build with
> huge number of possible CPUs, even when it's run on a box with few
> CPUs ;-/

I fixed this problem with the XFS per-cpu superblock counters
(bit lock + counters in per-cpu structs) back in 2006. It basically
uses a lglock-like local/global locking structure and iterates them
using for_each_online_cpu().

I fixed it simply by registering a hotplug notifier and
draining/reinitialising counters on the appropriate event under a
global lock context. i.e. make CPU hotplug serialise against
concurrent lock operations. See commit e8234a68 ("[XFS] Add support
for hotplug CPUs...")

Cheers,

Dave.
--
Dave Chinner
david@fromorbit.com


\
 
 \ /
  Last update: 2011-12-19 06:03    [W:0.205 / U:0.276 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site