Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Tim Evers schrieb: > Hi, > > I have a iSCSI SAN server using drbd in the backend. This results in atm > 32 logical volumes each with drbd on top and exported via iscsi. > > During normal operation everything is fine. But if I fire up a new drbd > device (drbdadm up res or drbdadm adjust res) sometimes (about 1 out of > ten times) the machine crashes with kernel panic. In the meantime I have investigated the problem further and was able to make a partial snapshot of the trace resulting from the crash: At first I tried to simulate the problem with a test machine running the exact copy of the production machines software (Linux Version, Kernel, iscsi-target and drbd) while only having 1 raid controller. In this configuration I was not able to reproduce the error while posting heavy load through iscsi and local disk activity and simultaneously creating, modifying and removing drbd devices. Last night I configured aroung 40 new drbd devices on the production machine and got a crash after about 35 configured devices. I made a screenshot from my kvm screen during the crash: http://www.massaker.de/crash_trace_small.png The crash happened while issuing a 'drbd adjust res' on a ressource which was immediately before initialized by 'drbdadm create-md res'. This was done before about 35 times without problem in the same sequence. Can anyone see anything useful in this one? Any hint on the cause (I think it definitely looks like a drbd problem)? Or any hint on how to track the problem down further? Best regards Tim