Am 20.05.2014 16:32, schrieb Jonathan Rudenberg: > On 2014-03-16, 11:09 AM, Richard Weinberger wrote: >> Am 14.03.2014 15:57, schrieb Thomas Meyer: >>> >>> only some processes get stuck. >>> >>> After enabling hung task detection in the kernel I see this in the logs: >>> >>> [ 8040.100000] INFO: task jbd2/ubda-8:308 blocked for more than 120 >>> seconds. > ... >>> >>> any ideas? some synchronisation error in ext4? >> >> Hmm, maybe you suffer from the same issue this patch tries to address: >> https://lkml.org/lkml/2014/2/14/733 > > I'm running into a very similar issue on vanilla 3.14.4 and 3.15-rc5, both > appear to have that patch already applied. > > I've tested ext4, ext3, btrfs, all with the same issue: processes writing to > disk in the guest randomly hang permanently after a few minutes of uptime. > The guest reports 100% > iowait, the host has no load and is totally fine.
Can you share your UML disk image? Maybe your userspace triggers some odds. What distro is it? Does it only happen with ubd disks? IOW does NFS or hostfs work? Thanks, //richard ------------------------------------------------------------------------------ The best possible search technologies are now affordable for all companies. Download your FREE open source Enterprise Search Engine today! Our experts will assist you in its installation for $59/mo, no commitment. Test it for FREE on our Cloud platform anytime! http://pubads.g.doubleclick.net/gampad/clk?id=145328191&iu=/4140/ostg.clktrk _______________________________________________ User-mode-linux-user mailing list User-mode-linux-user@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/user-mode-linux-user
