On Mon, 26 Jun 2000, Andrea Arcangeli wrote:
> On Mon, 26 Jun 2000, Marcelo Tosatti wrote:
>
> >Then fix the mmap002 on a 8Mb box issue in other way 2.2.17pre7 does, so
> >we can remove sync_page_buffers().
>
> Could you tell me why the fact mmap002 fails on a 8mbyte box is
> a showstopper for you?
A process gets killed while there is still backing store
available. It doesn't matter if this is mmap002 or a
business critical database, it is something that should
never ever happen.
> I am very concerned on mmap002 failing on 2.4.x but the 2.2.x VM
> is ugly anyway in handling the writeable mappings and accounting
> for the amount of dirty pages not mapped on the fs side is not
> trivial there.
2.4 doesn't do it either. I suppose we may want to spend some
effort to do proper write throttling for VMAs in 2.4 ...
regards,
Rik
-- The Internet is not a network of computers. It is a network of people. That is its real strength.Wanna talk about the kernel? irc.openprojects.net / #kernelnewbies http://www.conectiva.com/ http://www.surriel.com/
- 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 : Mon Jun 26 2000 - 21:00:09 EST