https://bugzilla.novell.com/show_bug.cgi?id=239858 ------- Comment #4 from dieter.jurzitza@t-online.de 2007-05-29 12:23 MST ------- Dear Mr. Walle, maybe I am totally wrong, but: 1 have two physically separate processors sitting in one housing. They share the memory bus and other interfaces, nevertheless they are separate devices, partly even separate dice with separate cache and so on. Now, if I have two IRQ's pending I see no reason why CPU1 should not process IRQ Nr. 2 while CPU0 is busy with IRQ Nr. 1. Especially I see no difference to two CPU's in separate housings here - exept that the IRQ's go to two different pins of one physically identical IC housing instead of two different pins of two different IC housings. I never ever did performance comparisons between shared and non shared IRQ's. If one assumes sharing of IRQs beneficial - and hopefully noone would do this just because it's funny - I would guess that in the case of two CPUs in one housing the benefit should not differ from two CPUs sitting in two different housings. I'd expect a different story from "Hyperthreading" processors where the second CPU is a virtual one. I'd be glad if you'd kindly shed some light on what I've got wrong here (just in case), take care Dieter Jurzitza -- Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are on the CC list for the bug, or are watching someone who is.