[OpenAFS-devel] Problems on 8-way Itanium2 system

Derrick J Brashear shadow@dementia.org
Sat, 29 Jan 2005 13:14:22 -0500 (EST)


On Fri, 28 Jan 2005, Alf Wachsmann wrote:

> Hi,
>
> we have problems with the stability of AFS on our 72 CPU SGI Altix
> system running a 2.4.21-sgi302r24 kernel with OpenAFS-1.2.10.
>
> We are able to reproduce the hangs on an 8 CPU configuration.
> A backtrace show something like this:

That's a very strange looking backtrace. In particular, while it's an afs 
client process, nothing in the stack is afs specific at all. What do the 
tracebacks look like for the other processes on the machine? And can you 
reduce still further to 2 processors and reproduce?

> Stack traceback for pid 1868
> 0xe0000030f7ea8000     1868        1  1    6   R  0xe0000030f7ea85a0 *afs_background
> 0xe000000004408c20 ia64_spinlock_contention+0x20
>        args (0xe00008b4f5cfc780, 0x1, 0xe00008b4f5cfc9f4, 0xe00008b4f5cfc9f0, 0xe0000030f7eafc40)
>        kernel .text 0xe000000004400000 0xe000000004408c00 0xe000000004408c50
>        r31 (spinlock address) 0xe000000004ea4380 kernel_flag
> 0xe0000000045f03b0 ext2_new_block+0x11d0
>        kernel .text 0xe000000004400000 0xe0000000045ef1e0 0xe0000000045f0d80
> 0xe00000000515b200 sn_latency_matrix+0x5d570
>        args (0xe00005b4f2ece000, 0x1000, 0xe0000030f4496408, 0x534f2370000, 0xa0007fed45f752b0)
>        kernel .bss 0xe000000005067500 0xe0000000050fdc90 0xe0000000058fdc90
> 0xe0000000045f0470 ext2_new_block+0x1290
>        args (0xa00000003abaca08, 0xa00000003abc0ab0, 0x80000, 0xa00000003b0ba3f8, 0xa00000003abc0d30)
>        kernel .text 0xe000000004400000 0xe0000000045ef1e0 0xe0000000045f0d80
>
> Has anyone else seen this problem? Is there a fix or workaround?
>
> Many thanks,
>                Alf.
>
> -----------------------------------------------------------------------
>  Alf Wachsmann                       | e-mail: alfw@slac.stanford.edu
>  SLAC Computing Service              | Phone:  +1-650-926-4802
>  2575 Sand Hill Road, M/S 97         | FAX:    +1-650-926-3329
>  Menlo Park, CA 94025, USA           | Office: Bldg. 50/323
> -----------------------------------------------------------------------
>                http://www.slac.stanford.edu/~alfw (PGP)
> -----------------------------------------------------------------------
> _______________________________________________
> OpenAFS-devel mailing list
> OpenAFS-devel@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-devel
>
>