[CTDB and GFS] test: scenario and some results

Ignacio Coupeau icoupeau at unav.es
Fri Jul 13 16:25:46 GMT 2007


Volker Lendecke wrote:
> On Fri, Jul 13, 2007 at 01:36:58PM +0200, Ignacio Coupeau wrote:
>> I tested the SAMBA cluster CTDB with GFS6.1. The main purpose of this
>> test was the LB ability of the CTDB.
>>
>> The numeric results are very poor with concurrence (as usual with GFS).
>> The load balancing issue: well for CTDB, bad for my hardware.
> 
> Thanks for testing this!
> 
> How do you want to proceed from here?

As our main target is the high availability and load balance, I going to 
test now with the Nortel 2216 L7 switch instead ServerIron.

I need check that:

1. the client traffic are balanced (sticky) to the same node in the 
whole session (or we have a very bad business with the performance);

2. if a samba node stops (not only if the hardware stops) the traffic is 
redirected to another samba node;

3. the performance with several distributed clients (heavy load) is 
manageable

4. the pilot may work with acceptable performance in a VMWare 
environment with distributed charge

5. optionally, test the gfs2 with a (possible) Red Hat 5.x; for now (in 
the RH5) the gfs2 is a bit weak;

After this I can put some of the services (students shares, for example) 
in production. I'm a samba user since 1.8prealpha+ldap days ;-)

Ignacio

-- 
________________________________________________________
Dr. Ignacio Coupeau
Systems and Network Services Director
IT Services
University of Navarra           http://www.unav.edu/
Pamplona, SPAIN                 http://www.unav.es/SI/


More information about the samba-technical mailing list