tag:blogger.com,1999:blog-6977755959349847093.post8268826782652592538..comments2024-03-01T21:53:15.921-08:00Comments on The Pith of Performance: Virtualization SpectrumNeil Guntherhttp://www.blogger.com/profile/11441377418482735926noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-6977755959349847093.post-27455484025329022112007-02-26T18:21:00.000-08:002007-02-26T18:21:00.000-08:00[ Actually, that's 3 questions ;) ]You're always f...[ Actually, that's 3 questions ;) ]<BR/><BR/>You're always free to ignore performance. Any VM comes with overheads that depend significantly on the type of applications you are running. But you may still choose to implement your apps on say a VMM for reasons other than performance, e.g., server consolidation, internal politics, etc.<BR/><BR/>Whether or not my VM spectrum paradigm is practical or not will have to be judged by others. Recognizing that such a classification scheme <B>is</B> possible is already a practical step in the right direction, IMHO.<BR/><BR/>As a general proposition, hardware <B>is</B> cheap. However, if your application is single-threaded (rather than hyperthreaded), a truck-load of cheap PCs won't buy you one iota of performance.Neil Guntherhttps://www.blogger.com/profile/11441377418482735926noreply@blogger.comtag:blogger.com,1999:blog-6977755959349847093.post-5920298048424837602007-02-26T17:55:00.000-08:002007-02-26T17:55:00.000-08:00A couple of questions:* What's the problem with ju...A couple of questions:<BR/><BR/>* What's the problem with just <I>ignoring</I> the performance of a VM? What do I, or any vendor, gain from gathering and using these stats?<BR/><BR/>* Does this taxonomy have practical applications?<BR/><BR/>* Why won't "just add more hardware" work? After all, servers, disk and bandwidth are very cheap.steve jenkinhttps://www.blogger.com/profile/16064724730975745470noreply@blogger.com