Re: [PATCH] mm: add counters for different page fault types

[Minchan Kim <minchan@kernel.org>]

On Thu, May 25, 2017 at 08:54:09AM -0700, Luigi Semenzato wrote:
> Thank you Minchan, that's certainly simpler and I am annoyed that I
> didn't consider that :/
> 
> By a quick look, there are a few differences but maybe they don't matter?
> 
> 1. can a major (anon) fault result in a hit in the swap cache?  So
> pswpin will not get incremented and the fault will be counted as a
> file fault.

If it is swap cache hit, it's not a major fault which causes IO
so VM count it as minor fault, not major.

> 
> 2. pswpin also counts swapins from readahead --- which however I think
> we have turned off (at least I hope so, since readahead isn't useful
> with zram, in fact maybe zram should log a warning when readahead is
> greater than 0 because I think that's the default).

Yub, I expected you guys used zram with readahead off so it shouldn't
be a big problem.
About auto resetting readahead with zram, I agree with you.
But there are some reasons I postpone the work. No want to discuss
it in this thread/moment. ;)

> 
> Incidentally, I understand anon and file faults, but what's a shmem fault?

For me, it was out of my interest but if you want to count shmem fault,
maybe, we need to introdue new stat(e.g., PSWPIN_SHM) in shmem_swapin
but there are concrete reasons to justify in changelog. :)

Thanks!

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>