Re: Kernel deadlock when running on top of squashfs

2010-07-19 Thread Nikolaus Rath
Nikolaus Rath writes: > sf...@users.sourceforge.net writes: >> Hello Nikolaus, >> >> Nikolaus Rath: >>> I have set up diskless fat clients with kernel 2.6.32. The root filesystem >>> is aufs. Underlying the aufs is an rw tmpfs and a ro squashfs, the later >>> mounted from NBD. >>> >>> The probl

Re: Kernel deadlock when running on top of squashfs

2010-07-13 Thread sfjro
Nikolaus Rath: > > Do you mean all stopped at the similar function, ie. block I/O? > > Since the system becomes totally inaccessible, I have no idea what these > processes are up to. What I mean is that I get kernel messages of the for= > m > > Jul 10 14:11:38 beta kernel: [25560.688091] INFO: tas

Re: Kernel deadlock when running on top of squashfs

2010-07-13 Thread Nikolaus Rath
sf...@users.sourceforge.net writes: > Hello Nikolaus, > > Nikolaus Rath: >> I have set up diskless fat clients with kernel 2.6.32. The root filesystem >> is aufs. Underlying the aufs is an rw tmpfs and a ro squashfs, the later >> mounted from NBD. >> >> The problems is that the fat clients work

Re: Kernel deadlock when running on top of squashfs

2010-07-13 Thread Nikolaus Rath
On 07/12/2010 08:58 PM, sf...@users.sourceforge.net wrote: > Nikolaus Rath: >> There are lots of other tasks here, but aufsd is not among them. > > Do you mean all stopped at the similar function, ie. block I/O? Since the system becomes totally inaccessible, I have no idea what these processes ar

Re: Kernel deadlock when running on top of squashfs

2010-07-12 Thread sfjro
Nikolaus Rath: > There are lots of other tasks here, but aufsd is not among them. Do you mean all stopped at the similar function, ie. block I/O? J. R. Okajima -- This SF.net email is sponsored by Sprint What will you

Re: Kernel deadlock when running on top of squashfs

2010-07-12 Thread sfjro
"Ian Stakenvicius, Aerobiology Research": > If you take a look at your syslog, I bet you will see at least one > additional hung task, that being an aufsd process. I usually see four > or five hung processes (i have a quad-core processor, you may see less > if you have fewer cores?), most of whic

Re: Kernel deadlock when running on top of squashfs

2010-07-12 Thread Nikolaus Rath
On 07/12/2010 10:52 AM, Ian Stakenvicius, Aerobiology Research wrote: > On 11/07/10 12:57 PM, Nikolaus Rath wrote: >> Hello, >> >> I have set up diskless fat clients with kernel 2.6.32. The root filesystem >> is aufs. Underlying the aufs is an rw tmpfs and a ro squashfs, the later >> mounted from

Re: Kernel deadlock when running on top of squashfs

2010-07-12 Thread Ian Stakenvicius, Aerobiology Research
On 11/07/10 12:57 PM, Nikolaus Rath wrote: > Hello, > > I have set up diskless fat clients with kernel 2.6.32. The root filesystem is > aufs. Underlying the aufs is an rw tmpfs and a ro squashfs, the later mounted > from NBD. > > The problems is that the fat clients work fine for a little while,

Re: Kernel deadlock when running on top of squashfs

2010-07-11 Thread sfjro
Hello Nikolaus, Nikolaus Rath: > I have set up diskless fat clients with kernel 2.6.32. The root filesystem is > aufs. Underlying the aufs is an rw tmpfs and a ro squashfs, the later mounted > from NBD. > > The problems is that the fat clients work fine for a little while, but then > reproduc

Kernel deadlock when running on top of squashfs

2010-07-11 Thread Nikolaus Rath
Hello, I have set up diskless fat clients with kernel 2.6.32. The root filesystem is aufs. Underlying the aufs is an rw tmpfs and a ro squashfs, the later mounted from NBD. The problems is that the fat clients work fine for a little while, but then reproducibly freeze completely within a few h