On Sun, Aug 22, 2010 at 8:01 PM, Alan Warren <bluemoonsh...@gmail.com> wrote: > Is there a proper venu for debugging such matters, or should I just wait for > this kernel to go prime-time?
Can you reliably reproduce the problem? If so, and you have a kernel that works git-bisect should allow you to pinpoint the offending commit. By the sounds of it though, this could be related to the problems Linux has when under heavy I/O, in which case you best bet would be to look to the upstream git as there are supposed to be fixes in it. Cheers, RobbieAB.