Just as a example of the reduced overhead for using vserver...

I just converted our backup server from vmware to vserver. Under
vmware, 46 processes as reported by top are running just after boot
up. I think it normally ran at 51, but I had to disable the network
on it to not conflict with the vserver version running. As a vserver
there is only 14 processes running.

Currently I have converted 5 guests from vmware to vserver. So far
we are having less IO contention or IO wait time. The CPUs are not
having nearly the level of load that had under vmware. Also memory
usage is not nearly as bad as it was under vmware. 

If my above example is representative of the conversion process, we
are saving 30 processes plus a kernel for every virtual machine we
convert. So now I am down 5 kernels and 150 processes. Makes sense
why all my performance metrics are looking so much better. Oh, and
this doesn't even account for the host side processes that are not
needed for vmware anymore.

So this goes back to my suggestion that if you are running a lot of
linux machines that don't have specialized hardware, you really 
should check into vserver.
-- 
Steven Critchfield [email protected]

--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups 
"NLUG" group.
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to 
[email protected]
For more options, visit this group at 
http://groups.google.com/group/nlug-talk?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to