Messages in this thread | | | Date | Wed, 23 Feb 2011 04:17:44 +1030 | From | Arthur Marsh <> | Subject | Re: [Alsa-user] new source of MIDI playback slow-down identified - 5a03b051ed87e72b959f32a86054e1142ac4cf55 thp: use compaction in kswapd for GFP_ATOMIC order > 0 |
| |
Andrea Arcangeli wrote, on 23/02/11 02:45: > On Tue, Feb 22, 2011 at 02:40:47PM +0100, Andrea Arcangeli wrote: >> spin_lock_irq(&zone->lru_lock); >> for (; low_pfn< end_pfn; low_pfn++) { >> struct page *page; >> + >> + cond_resched(); >> + > > my bad, see the above spin_lock_irq oops... > > I attached two replacement patches to apply in order (both of them > should be applied at the same time on top of git upstream, and they > shouldn't lockup this time).
OK, these patches applied together against upstream didn't cause a crash but I did observe:
significant slowdowns of MIDI playback (moreso than in previous cases, and with less than 20 Meg of swap file in use);
kswapd0 sharing equal top place in CPU usage at times (e.g. 20 percent).
If I should try only one of the patches or something else entirely, please let me know.
Regards,
Arthur.
| |