IDE
in [Kernel]
|
From: Linus Torvalds on 8 Apr 2010 11:10 On Thu, 8 Apr 2010, David Miller wrote: > > 2) taskfile ops with CFQ scheduler bomb because the taskfile > code allocates a request then changes it's direction (e.g. > READ vs. WRITE) and this makes CFQ explode. Fix by allocating > the correct request type from the beginning. From Mikulas Patocka. Hmm. Isn't this -stable material too? At least ide-taskfile.c hasn't changed since 2.6.33? Or is the cfq behavior new, and nobody simply cared before? I looked a bit at the cfq changes since 2.6.33, and none of them seemed to be relevant. But I didn't look very closely. Hmm? Linus -- 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: David Miller on 8 Apr 2010 14:20 From: Linus Torvalds <torvalds(a)linux-foundation.org> Date: Thu, 8 Apr 2010 08:02:45 -0700 (PDT) > > > On Thu, 8 Apr 2010, David Miller wrote: >> >> 2) taskfile ops with CFQ scheduler bomb because the taskfile >> code allocates a request then changes it's direction (e.g. >> READ vs. WRITE) and this makes CFQ explode. Fix by allocating >> the correct request type from the beginning. From Mikulas Patocka. > > Hmm. Isn't this -stable material too? At least ide-taskfile.c hasn't > changed since 2.6.33? Absolutely and it's in my queue of things to send to Greg KH and co. once you suck this in. -- 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/
|
Pages: 1 Prev: [PATCH 5/6] perf: cleanup some Documentation Next: I need your Swiftly reply |