On 11/12/12 16:52, vince.dug...@virginactive.co.za wrote: > When running under load (150+ busy connections) SuperClassic clearly uses > only one NUMA node (threads are spread across 16 cores), while Classic is > spread evenly across all 64 cores. CPUAffinityMask makes no difference (as > stated in the docs).
Will be very interesting to know how does linux behave in your case. Linux threads are very much process-like objects, specially compared with windows threads. > How is this going to run in V3? Will we see full use of all cores on all > processors, or will the behaviour be as in SuperClassic. Currently code, creating threads in server, was not much changed in FB3 vs FB2.5. But probably based on results of your tests we can do something... ------------------------------------------------------------------------------ Everyone hates slow websites. So do we. Make your web apps faster with AppDynamics Download AppDynamics Lite for free today: http://p.sf.net/sfu/appdyn_d2d_nov Firebird-Devel mailing list, web interface at https://lists.sourceforge.net/lists/listinfo/firebird-devel
