Re: Yet another SDET hang (73-mm3) ... yawn

[Andrew Morton]

"Martin J. Bligh" <[e-mail]> wrote:
>
> 2.5.73-mm3 + feral + highpte (ext2)
> 
> Seems to be all wedged up on io_schedule. Not sure if it was
> highpte that caused this or not, but I'd done one run on ext2
> and one on ext3 without it, and they worked fine.

highpte, or highpmd?

I assume the latter.  But either way, it would be an odd correlation.

It looks more like the block layer or device driver blew a fuse.  The usual
deal: make it repeatable, then try `elevator=deadline', then try a
different driver..

Oh, and write OpenSDET while you're at it.  grr.