> telomere:/proc/sys/vm> cat pagecache
> 1 30 75
> telomere:/proc/sys/vm> cat buffermem
> 1 20 60
I should have told that to you before. The pgcache_min limit to 5% is
something that will improve performance (at least with hight memory)
because it will avoid your latest caching part of the page cache and
buffers to be shrinked.
My latestlatest patch I posted here is reported to be a little slower than
the previous . This should be due to the swapout weight change. We was
used to be very more aggressive in swap_out(). So I am now changing >>
priority to >>(priority>>1). This will cause the swapout code to be more
aggressive. This make sense since when shrink_mmap() fail we like more to
swapout at the first try than shrink_mmap() with higher priority at the
next try...
The shrink_mmap() change instead seems to improve performances.
Andrea Arcangeli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/