On 06/30/2011 10:43 AM, Roman Mamedov wrote: > On Thu, 30 Jun 2011 10:37:51 -0400 > Josef Bacik <josef@xxxxxxxxxx> wrote: > >> Can you do sysrq+w when this happens? The caching kthread should still >> be able to make progress, which is what we seem to be waiting on. Does >> it eventually unhang and continue on? Thanks, > > Hello, > > Unfortunately I already rebooted that server so can't check SysRq+W. > Before the reboot I waited for about 40 minutes, and the block device seemed to be 100% idle during all this time. > I got an advice on IRC to wait for a couple of hours if this happens again, which I am going to try if it does. > Oh well crud I see what happened, the caching_kthread didn't even get started, kthreadd got locked up waiting on the page lock for migration. I will try and figure out what to do for this. Thanks for reporting it, Josef -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
