Re: [PATCH 0 of 8] x86/smp function calls: convert x86 tlb flushes to use function calls

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Jeremy Fitzhardinge
Date: Monday, August 11, 2008 - 4:57 pm

Andi Kleen wrote:

On a HT 3GHz Xeon, I see a ~35% increase in time (1830ns -> 2500ns), 
averaged over 1000,000 interrupts.  Because it's only 2 cpu, it ends up 
always using the smp_call_function_single path (but via the 
smp_call_function_mask path).

I need to try getting a more-cpu machine running native to do a proper 
test, esp to see if putting kmalloc on that path is very expensive or 
not.  (Is it worth using a kmem_cache?)

    J
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[PATCH 0 of 8] x86/smp function calls: convert x86 tlb flu ..., Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 1 of 8] x86-32: use smp_call_function_mask for SMP ..., Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 2 of 8] x86-64: use smp_call_function_mask for SMP ..., Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 3 of 8] x86: make tlb_32|64 closer, Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 4 of 8] x86: unify tlb.c, Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 5 of 8] smp_function_call: add multiple queues for ..., Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 6 of 8] x86: add multiple smp_call_function queues, Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 7 of 8] x86: make number of smp_call_function queue ..., Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
[PATCH 8 of 8] smp function calls: add kernel parameter to ..., Jeremy Fitzhardinge, (Fri Aug 1, 5:14 pm)
Re: [PATCH 0 of 8] x86/smp function calls: convert x86 tlb ..., Jeremy Fitzhardinge, (Tue Aug 5, 8:33 pm)
Re: [PATCH 0 of 8] x86/smp function calls: convert x86 tlb ..., Jeremy Fitzhardinge, (Mon Aug 11, 4:57 pm)