[lkml]   [2011]   [Dec]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH] mm: do not drain pagevecs for mlock
One more thing.

>> Because your test program is too artificial. 20sec/100000times =
>> 200usec. And your
>> program repeat mlock and munlock the exact same address. so, yes, if
>> lru_add_drain_all() is removed, it become near no-op. but it's
>> worthless comparision.
>> none of any practical program does such strange mlock usage.
> yes, I should say it is artificial. But mlock did cause the problem in
> our product system and perf shows that the mlock uses the system time
> much more than others. That's the reason we created this program to test
> whether mlock really sucks. And we compared the result with
> rhel5(2.6.18) which runs much much faster.

rhel5 is faster because it doesn't have proper mlock implementation.
then it has a lot
of mlock related performance issue. We optimized PAGE_MLOCK thing for
typical workload.
number of mlock call are rare and number of memory reclaim are a lot.
That's the reason why we haven't got any complication of mlock thing.

 \ /
  Last update: 2011-12-30 11:17    [from the cache]
©2003-2011 Jasper Spaans