Head Guru Posted March 30, 2007 Posted March 30, 2007 http://www.webperformanceinc.com/library/r...ance/index.html Quote
TCH-Dick Posted March 30, 2007 Posted March 30, 2007 Interesting. I would like to see the same tests using Virtuozzo or OpenVZ. Quote
TCH-Andy Posted March 30, 2007 Posted March 30, 2007 I'm not surprised by the main Virtual results. I was a little surprised that hyperthreading on / off made no difference on the VPS case - although clearly made a difference, as expected, on a standard machine. Quote
click Posted March 30, 2007 Posted March 30, 2007 It looks as though VMWare wasn't using hyperthreading at all. I wonder if there wasn't a configuration/compatibility issue somewhere or if the results could be duplicated on another machine/OS. The virtual machine didn't do too bad when hyperthreading was turned off. I guess you would see the benefits of hyperthreading when running multiple lower demand virtual servers on one machine but it seemed to do surprisingly poorly running a single server. I hardly think the hardware abstraction/easy upgrade path, etc is worth a 43% performance hit. Quote
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.