zfs -> ufs rsync: livelock in wdrain state

Dmitry Morozovsky marck at rinet.ru
Wed Jan 9 21:47:37 UTC 2013


On Tue, 8 Jan 2013, Dmitry Morozovsky wrote:

> > Are there any kernel messages about the disk system ?
> > 
> > The wdrain means that the amount of the dirty buffers accumulated exceeds
> > the allowed maximum. The transient 'wdrain' state is normal on a machine
> > doing lot of writes to a filesystem using buffer cache, say UFS. Failure
> > to clean the dirty buffers is usually related to the disk i/o stalling.
> > 
> > It cannot be denied that a bug could cause stuck 'wdrain' state, but
> > in the last five or so years all the cases I investigated were due to
> > disks.
> 
> Yes, it seems so:
> 
> root at moose:~# camcontrol devlist
> load: 0.03  cmd: camcontrol 49735 [devfs] 2.68r 0.00u 0.00s 0% 820k
> 
> and then machine is in well known "hardly alive" state: TCP connects 
> established, process switching does not go.
> 
> Will investigate the hardware, thank you.

It seems flaky eSATA cable was the source of drive sometimes get lost.

Sorry for the noise.

-- 
Sincerely,
D.Marck                                     [DM5020, MCK-RIPE, DM3-RIPN]
[ FreeBSD committer:                                 marck at FreeBSD.org ]
------------------------------------------------------------------------
*** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck at rinet.ru ***
------------------------------------------------------------------------


More information about the freebsd-fs mailing list