This just makes x86_64 behave like i386 which sets the flag today.
With tick-broadcast, even though we handle timer tick happening anywhere, it will be nice if timer always goes to CPU 0 and we then broadcast to any other CPUs. This is not a must have patch from my perspective. But, we should make i386 and x86_64 same. So, we need to change either one. Thanks, Venki >-----Original Message----- >From: Arjan van de Ven [mailto:[EMAIL PROTECTED] >Sent: Sunday, June 10, 2007 9:29 AM >To: Thomas Gleixner >Cc: LKML; Andrew Morton; Ingo Molnar; Andi Kleen; Pallipadi, >Venkatesh; Chris Wright >Subject: Re: [patch-mm 21/23] x86-64 block irq balancing for timer > >this isn't needed actually.. the userspace irq balancer won't balance >irq 0 anyway, and if the sysadmin has a REAL good reason to move this >himself... then why shouldn't we let him? > > > >On Sun, 2007-06-10 at 09:44 +0000, Thomas Gleixner wrote: >> plain text document attachment >> (x86-64-clockevents-irq-balancing.patch) >> From: Venki Pallipadi <[EMAIL PROTECTED]> >> >> Disable irq balancing on IRQ0. >> >> Signed-off-by: Venkatesh Pallipadi <[EMAIL PROTECTED]> >> Signed-off-by: Thomas Gleixner <[EMAIL PROTECTED]> >> Cc: Andi Kleen <[EMAIL PROTECTED]> >> >> --- >> arch/x86_64/kernel/time.c | 2 +- >> 1 file changed, 1 insertion(+), 1 deletion(-) >> >> Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/time.c >> =================================================================== >> --- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/time.c >2007-06-10 10:44:39.000000000 +0200 >> +++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/time.c >2007-06-10 10:44:40.000000000 +0200 >> @@ -255,7 +255,7 @@ static unsigned int __init tsc_calibrate >> >> static struct irqaction irq0 = { >> .handler = timer_interrupt, >> - .flags = IRQF_DISABLED | IRQF_IRQPOLL, >> + .flags = IRQF_DISABLED | IRQF_IRQPOLL | >IRQF_NOBALANCING, >> .mask = CPU_MASK_NONE, >> .name = "timer" >> }; > >-- >if you want to mail me at work (you don't), use arjan (at) >linux.intel.com >Test the interaction between Linux and your BIOS via >http://www.linuxfirmwarekit.org > - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
