Hello list, today I noticed huge differences between the hardware clocks in our cluster. Some details:
root@www01:~# hwclock;date Do 03 Jan 2013 09:32:09 CET -0.626096 seconds Do 3. Jan 09:34:54 CET 2013 root@www02:~# hwclock;date Do 03 Jan 2013 09:32:09 CET -0.626091 seconds Do 3. Jan 09:34:54 CET 2013 root@www03:~# hwclock;date Do 03 Jan 2013 09:34:54 CET -0.625820 seconds Do 3. Jan 09:34:54 CET 2013 root@storage:~# hwclock;date Do 03 Jan 2013 08:34:54 CET -0.641532 seconds Do 3. Jan 09:34:54 CET 2013 The server 'storage' is the server which provides the iscsi device to www01-03. Because the cluster was very unstable during load peaks, I want to ask you what kind of effects it will have to ocfs2 if the hwclocks are asynchronous like shown above. Thanks in advance Jakob _______________________________________________ Ocfs2-users mailing list Ocfs2-users@oss.oracle.com https://oss.oracle.com/mailman/listinfo/ocfs2-users
