Re: [PATCH] 2.4.1-ac UP-APIC updates

2001-02-20 Thread Mikael Pettersson
On Tue, 20 Feb 2001 16:00:53 -0500 (EST), Ingo Molnar wrote: >my major gripe right now is that we still have bug reports that say that >systems hang when using nmi_watchdog=1 and work if nmi_watchdog=0. >Changing the NMI watchdog to be 1 Hz will make these bugreports "Linux >hangs once a week" in

Re: [PATCH] 2.4.1-ac UP-APIC updates

2001-02-20 Thread Ingo Molnar
On Tue, 20 Feb 2001, Alan Cox wrote: > > i dont like this one. 100 times a second makes absolutely no performance > > difference whatsoever - but eg. i'm driving kernel profiling from the NMI > > handler to get profiles of eg. IRQ handlers and other cli()-ed code areas. > > So set it to 100Hz as

Re: [PATCH] 2.4.1-ac UP-APIC updates

2001-02-20 Thread Alan Cox
> i dont like this one. 100 times a second makes absolutely no performance > difference whatsoever - but eg. i'm driving kernel profiling from the NMI > handler to get profiles of eg. IRQ handlers and other cli()-ed code areas. So set it to 100Hz as a debugging option like slab debugging - To uns

Re: [PATCH] 2.4.1-ac UP-APIC updates

2001-02-20 Thread Ingo Molnar
On Tue, 20 Feb 2001, Mikael Pettersson wrote: > * NMI rate reduction for UP-APIC: the 100Hz default rate is excessive for > normal systems, 1Hz suffices. It turns out we cannot start at 1Hz due to > this interacting badly with check_nmi_watchdog() and the watchdog itself, > so the rate is

[PATCH] 2.4.1-ac UP-APIC updates

2001-02-20 Thread Mikael Pettersson
Alan, This patch (against 2.4.1-ac19) includes the following UP-APIC updates: * Power Management: If the kernel's UP-APIC code enabled the local APIC because the BIOS chose not to, it is imperative that the kernel also disables the local APIC before entering apm/acpi suspend mode. Failure