[Linux-cluster] Ext3/ext4 in a clustered environement

[Nicolas Ross]

[...]

>> => It works pretty well for now, but when it comes to data update (via 
>> rsync)
>> => and backup (also via rsync), the node doing the rsync crawls to a 
>> stop, all
>> => 16 logical cores are used at 100% system, and it sometimes freezes the 
>> file
>> => system for other services on other nodes.
>>
>> Ouch!
>>
> So the question is what is using all this cpu time? Is this being used
> by rsync, or by some of the gfs2/dlm system daemons or even by some
> other threads?

It is used by gfs2/dlm, or some other process, and 100% system cpu, not user 
cpu. At that time, my rsync process is stalled, if I try to ctrl-z it, it's 
no joy, only when cpu cools down that my ctrl-z works.

Previously it was suggested I use nice and mostly ionice, it did help alot, 
but I still see good spikes in cpu, but now my servers still responds...