Filesystem I/O is CPU-bound in rc7 and rc8
in [Kernel]
|
Prev: PROPOSAL READ ATTACHMENT AND GET BACK TO ME
Next: [PATCH 2/4] firewire: ohci: enable cycle timer fix on ALi and NEC controllers
From: James Cloos on 20 Feb 2010 11:30 >>>>> "Dave" == Dave Airlie <airlied(a)gmail.com> writes: >> >> OK. �I do use radeon kms (r100). Dave> I've just sent a pull req to Linus Dave> http://bugzilla.kernel.org/show_bug.cgi?id=15328 Dave> this Dave> http://bugzilla.kernel.org/attachment.cgi?id=25107 Dave> patch. I'll give that a try as soon as I can schedule a reboot. Dave> The relevant piece of dmesg is at the top ;-), where Dave> it states if you have PAT support or not, but I Dave> suspect if you try this patch it'll fix it. Oh. I thought you were referring to errors.... Anyway, no, the p3m does not support PAT: [ 0.000000] PAT not supported by CPU. -JimC -- James Cloos <cloos(a)jhcloos.com> OpenPGP: 1024D/ED7DAEA6 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: James Cloos on 20 Feb 2010 21:20
>>>>> "Dave" == Dave Airlie <airlied(a)gmail.com> writes: Dave> I've just sent a pull req to Linus Dave> http://bugzilla.kernel.org/show_bug.cgi?id=15328 Dave> this Dave> http://bugzilla.kernel.org/attachment.cgi?id=25107 Dave> patch. That patch does indeed fix the regression here. Thanks! It looks like my report is a dup of bug 15328. -JimC -- James Cloos <cloos(a)jhcloos.com> OpenPGP: 1024D/ED7DAEA6 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |