Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Hi everyone :) I am testing the new cluster i have setup and last night something wrong happened, the nodes have their nfs mounted directory that hangs. So, after some investigation, i was able to reproduce the situation, here's my syslog (server side) (The server also mounts the share) Feb 2 12:03:02 localhost kernel: drbd0: sock was shut down by peer Feb 2 12:03:02 localhost kernel: drbd0: drbd0_receiver [2531]: cstate Connected --> BrokenPipe Feb 2 12:03:02 localhost kernel: drbd0: short read expecting header on sock: r=0 Feb 2 12:03:02 localhost kernel: drbd0: meta connection shut down by peer. Feb 2 12:03:02 localhost kernel: drbd0: asender terminated Feb 2 12:03:02 localhost kernel: drbd0: worker terminated Feb 2 12:03:02 localhost kernel: drbd0: drbd0_receiver [2531]: cstate BrokenPipe --> Unconnected Feb 2 12:03:02 localhost kernel: drbd0: Connection lost. Feb 2 12:03:02 localhost kernel: drbd0: drbd0_receiver [2531]: cstate Unconnecte d --> WFConnection Feb 2 12:03:08 localhost kernel: nfs: server fs-cluster not responding, still tr ying Feb 2 12:03:11 localhost kernel: nfs: server fs-cluster not responding, still tr ying Any idea what's going on ? qwould it be a bandwidth issue ? it's only 10/100 interfaces on this server and the one that mirrors the drbd disk... Thanks. Pierre. -- Boston Cybertech http://www.bostoncybertech.com Boston Network and Computers consultants