[DRBD-user] lockup on primary node

Helmut Wollmersdorfer helmut.wollmersdorfer at gmx.at
Sat Jul 17 04:06:28 CEST 2004

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


John Lange schrieb:

> However, pinging across the Gigabit interfaces during a resync still
> results in about 60% packet loss. 

Sounds bad.

> Is there a way to ensure that all console messages dmesg are also sent
> to my ssh sessions? 

cat /var/log/dmesg

> As the interfaces usually stay up there is a good
> chance that I could capture the messages. Or any other tips that would
> help me do this remotely?

Stop drbd.
Then test your connection on full speed e.g. using a tool like bing.
I tried to use eth1394 (IP over firewire) for cluster connection, but 
this did not stand my bing tests - it hangs after few hours.
If you can reproduce the hangs without drbd, you definitely can exclude 
drbd.

Helmut Wollmersdorfer





More information about the drbd-user mailing list