[DRBD-user] DRBD stuck after a strong network failure

Cyril Bouthors cyril at bouthors.org
Tue May 9 10:12:35 CEST 2006

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.


On  8 May 2006, Lars Ellenberg wrote:

> only one drbdsetup per /dev/drbdX is allowed at any time. thats why
> the other two are in "down_interruptible" state, they wait for the
> ioctl semaphore.

I understand.

> I'm sorry, this is not debuggable this way. I cannot even tell where
> drbd does hang, if it hangs. Maybe it hangs in some lower level
> kernel function, that is not supposed to hang. Maybe it is something
> in our kernel 2.4 compatibility layer. There is not enought
> information for me to give any specific diagnosis, and unless you
> are able to get some "stack traces" (via kernel
> debugger/sysrq/whatever) to see where exactly which kernel threads
> are waiting on each other (which I assume is the case), I can not
> help you here.

I'm quite a newbie to kernel hacking, could you please give me a
procedure in order for me to provide you with accurate debugging
information next time?

I'd really like to help you fix this issue.

> The best I can do is recommend to use a 2.6 kernel, and see if it
> gets better.

I've already tried to switch my ~50 nodes to Linux 2.6 but it just
kept on crashing and crashing.

If this DRBD crash happens too often, I'll reconsider switching to
Linux 2.6, maybe the bugs I've been hit by are now fixed...
-- 
Cyril Bouthors
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 188 bytes
Desc: not available
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20060509/8382b742/attachment.pgp>


More information about the drbd-user mailing list