On Sat, 22 Jan 2000, Andrea Arcangeli wrote:
> On Sat, 22 Jan 2000, Rik van Riel wrote:
>
> >2.2.15pre4 includes my second chance page replacement trick,
>
> kswapd still 1-sec poll and that make no sense.
It makes perfect sense. Under light VM load you want
processes to be able to take the fast-path and grab
the memory they need.
> You are also forbidding GFP_KERNEL allocations to succeed during
> oom and that make no sense as well. In 2.2.15pre4 GFP_KERNEL and
> GFP_USER become the same thing.
Please answer this question:
Why are there both a __GFP_MED *and* a __GFP_HIGH?
If you cannot answer this question, then please stop
repeating your groundless claim over and over again.
> >this should reduce the number of page faults a bit and make
>
> Your changes have _nothing_ to do with page faults.
Yes they have. As I and a lot of other people have observed
the system runs a lot smoother with the changes integrated.
Please try it before you dismiss it.
regards,
Rik
-- The Internet is not a network of computers. It is a network of people. That is its real strength.- 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/
This archive was generated by hypermail 2b29 : Sun Jan 23 2000 - 21:00:28 EST