FWIW, I was only able to reproduce the problem which I was seeing on
lenny+openvz (running the same workload on lenny+chroot, or
squeeze+openvz didn't trigger it).
The fix you attached does sound like a plausible fix for the issue I was
seeing (having spent a day or two peering at the code and sp
Ben Hutchings writes ("Re: Lockups under heavy disk IO; md (RAID) resync/check
implicated"):
> There is a change in Linux 3.3, also intended to go into Linux 3.2.14,
> which looks like a fix for bug #584881.
Thanks. I haven't experienced the bug in production in squeeze.
I will try to set up a t
There is a change in Linux 3.3, also intended to go into Linux 3.2.14,
which looks like a fix for bug #584881.
I'm attaching a backported version of this bug fix for Debian 6.0
'squeeze', which you may wish to test. You can build a kernel package
with this patch by following the instructions at
<
Related:
https://bugzilla.kernel.org/show_bug.cgi?id=12905
--
To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org
Archive:
http://lists.debian.org/7ebf2d89f525c3b724aca5d197887aea.squir...@mstier.de
On Fri, 2010-07-23 at 23:58 +0100, Ian Jackson wrote:
> I wrote:
> > ... I'm going to compile the kernel again without that particular
> > warning (and with kgdb support) and see if I can dig out anything
> > interesting.
>
> My attempt to compile the kernel with kgdb support failed. Something
>
I wrote:
> ... I'm going to compile the kernel again without that particular
> warning (and with kgdb support) and see if I can dig out anything
> interesting.
My attempt to compile the kernel with kgdb support failed. Something
in the Debian kernel packaging thingy complained like this:
ABI h
On Tue, 2010-07-20 at 22:51 +0100, Ian Jackson wrote:
> Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
> resync/check implicated"):
> > Please try 2.6.34 from experimental.
>
> I've now replicated the problem on my coffee table
Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
resync/check implicated"):
> On Fri, 2010-06-25 at 11:50 +0100, Ian Jackson wrote:
> > No, I think there are two meanings of the word "barrier". AFAICT md
> > has its own thing wh
On Fri, 2010-06-25 at 11:50 +0100, Ian Jackson wrote:
> Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
> resync/check implicated"):
> > I/O barriers are block I/O operations (not specific to md) that inhibit
> > reordering of read
Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
resync/check implicated"):
> I/O barriers are block I/O operations (not specific to md) that inhibit
> reordering of read and write operations. They certainly should not be
> blocking operations.
On Thu, 2010-06-24 at 11:17 +0100, Ian Jackson wrote:
> Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
> resync/check implicated"):
[...]
> > > Search the web suggests that symptoms very similar to mine are not
> > > uncommon, inclu
Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
resync/check implicated"):
> Even if you can't get a process dump, you can get some useful
> information with:
Right, thanks.
> 'd' - show locks held
> 'l' - show backtra
On Mon, 2010-06-21 at 11:11 +0100, Ian Jackson wrote:
> Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
> resync/check implicated"):
> > We really need to see the kernel messages reporting soft-lockup.
>
> There aren't any. Or, if
Ben Hutchings writes ("Re: Bug#584881: Lockups under heavy disk IO; md (RAID)
resync/check implicated"):
> We really need to see the kernel messages reporting soft-lockup.
There aren't any. Or, if there are, it isn't printing them to the
serial console. Perhaps it is t
On Mon, 2010-06-07 at 10:53 +0100, Ian Jackson wrote:
> Package: linux-image-2.6.26-2-686-bigmem
> Version: 2.6.26-21lenny4
>
> I keep getting soft lockups; the symptoms appear to be that user
> processes become deadlocked when they try to access the disk, but the
> kernel doesn't notice that anyt
Package: linux-image-2.6.26-2-686-bigmem
Version: 2.6.26-21lenny4
I keep getting soft lockups; the symptoms appear to be that user
processes become deadlocked when they try to access the disk, but the
kernel doesn't notice that anything is wrong.
It appears that the lockups happen when:
(a) my s
16 matches
Mail list logo
