Re: [RFC] change non-atomic bitops method

[Andrew Morton <akpm@linux-foundation.org>]

On Tue, 3 Feb 2015 16:42:14 +0800 "Wang, Yalin" <Yalin.Wang@sonymobile.com> wrote:

> I make a change in kernel to test hit/miss ratio:

Neat, thanks.

>
> ...
>
> After use the phone some time:
> root@D5303:/ # cat /proc/meminfo
> VmallocUsed:       10348 kB
> VmallocChunk:      75632 kB
> __set_bit_miss_count:10002 __set_bit_success_count:1096661
> __clear_bit_miss_count:359484 __clear_bit_success_count:3674617
> __test_and_set_bit_miss_count:7 __test_and_set_bit_success_count:221
> __test_and_clear_bit_miss_count:924611 __test_and_clear_bit_success_count:193
> 
> __test_and_clear_bit_miss_count has a very high miss rate.
> In fact, I think set/clear/test_and_set(clear)_bit atomic version can also
> Be investigated to see its miss ratio,
> I have not tested the atomic version,
> Because it reside in different architectures.

Hopefully misses in test_and_X_bit are not a problem.  The CPU
implementation would be pretty stupid to go and dirty the cacheline
when it knows it didn't change anything.  But maybe I'm wrong about
that.  

That we're running clear_bit against a cleared bit 10% of the time is a
bit alarming.  I wonder where that's coming from.

The enormous miss count in test_and_clear_bit() might indicate an
inefficiency somewhere.