[Linux-cluster] gfs2_quotad:2498 blocked
rossnick-lists at cybercat.ca
Tue Mar 29 17:43:23 UTC 2011
>> It was a large, very large directory, with somewhere neer one million
>> small files, so the rsync took something like 3 to 4 hours. At some
>> point, all nodes' consoles dispalyed this :
>> gfs2_quotad:2498 blocked for more that 120 seconds.
>> "echo 0 > /proc/sys/kernel/hang_task_timeout_secs" disables this message.
>> and then some debuging info dump.
> It means you're writing data faster than GFS can handle it, so it's
> pausing on you. We see this semi-regularly here on our clusters.
> I suspect Bob Petersen's test kernel or patches from ~2-3 weeks ago will
> help you as these contain a bunch of fixes for slow writes.
Now, my server are now up into out new colo facility, I did update
gfs2-utils that was published on march 17th, amonng others, and I did not
see that message, as it was at first before the update.
More information about the Linux-cluster