[DRBD-user] Syncer aborted. Connection lost.

Eugene Crosser crosser at rol.ru
Tue Mar 23 20:14:34 CET 2004


On Tue, 2004-03-23 at 20:10, Eugene Crosser wrote:

> > > Please could someone knowledgeble tell me why this may happen?
> > > Under load (local massive quota update by a script plus cpio of a big
> > > tree from an NFS client) synchronization is repeatedly restarted after
> > > ~1% completion:

I have some follow-up information:  I figured that it was not actually
quota editing that triggered the problem, it was "sync" command issued
on every 1000th update in the script.  After the system actively works
for about an hour (with quota updating or just regular file operations),
"sync" begins to take several minutes to complete, "top" shows that it
uses 99% cpu and system response becomes very very slow.

So maybe(?) this is not drbd problem per se, but a sync() run on
actively updated ext3 filesystem (with quota).  OTOH it may be because
sync creates a load pattern that drbd device is not prepared to...

Eugene
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
Url : http://lists.linbit.com/pipermail/drbd-user/attachments/20040323/653fe5b8/attachment.pgp 


More information about the drbd-user mailing list