On 12/12/2013 09:13 PM, Ingo Molnar wrote: > > * Mel Gorman <mgorman@xxxxxxx> wrote: > >> There was a large performance regression that was bisected to commit 611ae8e3 >> (x86/tlb: enable tlb flush range support for x86). This patch simply changes >> the default balance point between a local and global flush for IvyBridge. >> >> Signed-off-by: Mel Gorman <mgorman@xxxxxxx> >> --- >> arch/x86/kernel/cpu/intel.c | 2 +- >> 1 file changed, 1 insertion(+), 1 deletion(-) >> >> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c >> index dc1ec0d..2d93753 100644 >> --- a/arch/x86/kernel/cpu/intel.c >> +++ b/arch/x86/kernel/cpu/intel.c >> @@ -627,7 +627,7 @@ static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) >> tlb_flushall_shift = 5; >> break; >> case 0x63a: /* Ivybridge */ >> - tlb_flushall_shift = 1; >> + tlb_flushall_shift = 2; >> break; > > I'd not be surprised if other CPU models showed similar weaknesses > under ebizzy as well. > > I don't particularly like the tuning aspect of the whole feature: the > tunings are model specific and they seem to come out of thin air, > without explicit measurements visible. > > In particular the first commit that added this optimization: > > commit c4211f42d3e66875298a5e26a75109878c80f15b > Date: Thu Jun 28 09:02:19 2012 +0800 > > x86/tlb: add tlb_flushall_shift for specific CPU > > already had these magic tunings, with no explanation about what kind > of measurement was done to back up those tunings. > > I don't think this is acceptable and until this is cleared up I think > we might be better off turning off this feature altogether, or making > a constant, very low tuning point. > > The original code came via: > > 611ae8e3f520 x86/tlb: enable tlb flush range support for x86 > > which references a couple of benchmarks, in particular a > micro-benchmark: > > My micro benchmark 'mummap' http://lkml.org/lkml/2012/5/17/59 > show that the random memory access on other CPU has 0~50% speed up > on a 2P * 4cores * HT NHM EP while do 'munmap'. > > if the tunings were done with the micro-benchmark then I think they > are bogus, because AFAICS it does not measure the adversarial case of > the optimization. > > So I'd say at minimum we need to remove the per model tunings, and > need to use very conservative defaults, to make sure we don't slow > down reasonable workloads. I also hate to depends on mysterious hardware differentiation. But there do have some changes in tlb/cache part on different Intel CPU.(Guess HPA know this more). And the different shift value get from testing not from air. :) > > ( In theory madvise() could give us information about the usage > pattern of the vma - but in practice madvise() is rarely used and I > doubt ebizzy or other real-world apps are using it, so it's > meaningless. ) > > Thanks, > > Ingo > -- Thanks Alex -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>