Re: [2.1.130-3] Page cache DEFINATELY too persistant... feature?

[Zlatko Calusic <Zlatko.Calusic@CARNet.hr>]

Rik van Riel <H.H.vanRiel@phys.uu.nl> writes:

> I am now trying:
> 	if (buffer_over_borrow() || pgcache_over_borrow() ||
> 			atomic_read(&nr_async_pages)
> 		shrink_mmap(i, gfp_mask);
> 
> Note that this doesn't stop kswapd from swapping out so
> swapout performance shouldn't suffer. It does however
> free up memory so kswapd should _terminate_ and keep the
> amount of I/O done to a sane level.

This still slows down swapping somewhat (20-30%) in my tests.

> 
> Note that I'm running with my experimentas swapin readahead
> patch enabled so the system should be stressed even more
> than normally :)
> 

I tried your swapin_readahead patch but it didn't work right:

swap_duplicate at c012054b: entry 00011904, unused page 
swap_duplicate at c012054b: entry 002c8c00, unused page 
swap_duplicate at c012054b: entry 00356700, unused page 
swap_duplicate at c012054b: entry 00370f00, unused page 
swap_duplicate at c012054b: entry 0038d000, unused page 
swap_duplicate at c012054b: entry 0039d100, unused page 
swap_duplicate at c012054b: entry 0000b500, unused page 

c012054b is read_swap_cache_async()

Memory gets eaten when I bang MM, and after sometime system blocks. I
also had one FS corruption, thanks to that. Didn't investigate
further.

Do you have a newer version of the patch?

Regards,
-- 
Posted by Zlatko Calusic           E-mail: <Zlatko.Calusic@CARNet.hr>
---------------------------------------------------------------------
	       Multitasking attempted. System confused.
--
This is a majordomo managed list.  To unsubscribe, send a message with
the body 'unsubscribe linux-mm me@address' to: majordomo@kvack.org