On Sun, Aug 22, 2010 at 8:35 PM, Alan Warren <bluemoonsh...@gmail.com> wrote: > I think you are correct though. It does seem to only happen while the system > is under heavy I/O. > > I've never experienced anything like this in previous versions of the linux > kernel, > and resorting back to gentoo-sources-2.6.34 fixes the issue completely. > > If there are I/O fixes upstream, then I am assuming you are referring to a > cut > that is more recent then gentoo-sources-2.6.35-r2 that the Gentoo devs have > yet to provide their patches to? ( I see vanilla sources has 2.6.35 .3)
Well, the fix is in the line for 2.6.36 IIRC, so wouldn't be in an 2.6.35 kernel. That said, the problem supposedly being fixed goes back well before 2.6.34, so if that kernel works, it suggests that it is a different issue you are hitting. However... If there was a FF update, that could be triggering the bug, as FF3.5+ are pretty stinky for I/O levels.
