On Mon, 2007-10-01 at 23:41 +0200, Andi Kleen wrote: > > IRQ_NOBALANCING is not preventing cpu unplug. It moves the affinity to the > > next CPU, but the check in NMI watchdog for CPU == 0 would not longer > > work. > > That cannot happen right now because cpu_disable() on both i386/x86-64 > reject CPU #0. So just setting IRQ_NOBALANCING is sufficient and both > do that already. I was wrong earlier in being concerned about this. > > > int tick_do_broadcast(cpumask_t mask) > > @@ -137,6 +147,7 @@ int tick_do_broadcast(cpumask_t mask) > > cpu_clear(cpu, mask); > > td = &per_cpu(tick_cpu_device, cpu); > > td->evtdev->event_handler(td->evtdev); > > + tick_broadcast_account(cpu); > > That would not handle the case with a single CPU running only > irq 0 but not broadcasting I think. > > I believe ftp://ftp.firstfloor.org/pub/ak/x86_64/quilt/patches/fix-watchdog > is the correct fix > > -Andi Andi, If it's agreed that this is the fix - can you submit a proper [PATCH] so all users of watchdog_use_timer_and_hpet_on_x86_64.patch can be removed, and replaced with yours. Thank you very much
Attachment:
signature.asc
Description: PGP signature
- Follow-Ups:
- Re: nmi_watchdog fix for x86_64 to be more like i386
- From: Andi Kleen <[email protected]>
- Re: nmi_watchdog fix for x86_64 to be more like i386
- Prev by Date: Re: [PATCH for testing] Re: Decreasing stime running confuses top
- Next by Date: Re: 2.6.23-rc7-mm1 -- powerpc rtas panic
- Previous by thread: RE: nmi_watchdog fix for x86_64 to be more like i386
- Next by thread: Re: nmi_watchdog fix for x86_64 to be more like i386
- Index(es):
 |