On Fri, Mar 27, 2009 at 10:14 AM, Steven S. Critchfield <[email protected]>wrote:
> > 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] > I am presuming that using vserver you don't have the ability to migrate a running machine / instance to different hardware? Andy --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
