[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: mmap investigations



Daniel Burrows wrote:
> On Sun, Nov 02, 2008 at 06:10:19PM +0200, "Eugene V. Lyubimkin" <jackyf.devel@gmail.com> was heard to say:
>> These investigations incited me to wonder if we... can simply do mmap(2GiB -1) amount of
>> memory, without any troubles?!
> 
>   Not on a 32-bit system you can't -- there's nowhere to put all the mappings.
Well, agreed, that's was very large value. What about 64-128 MiB by default?

BTW to whose who also are reading this thread: I've recently asked in lkml
about such a usage of mmap(). Linux kernel developers answered that this is
normal approach (unless we are using vfat filesystem for /var, but I claim we
shouldn't), though not strictly guaranteed to be in the future in that sense
that kernel may also populate adjacent pages. For us, several adjacent pages
are not a problem.

-- 
Eugene V. Lyubimkin aka JackYF, JID: jackyf.devel(maildog)gmail.com
Ukrainian C++ Developer, Debian APT contributor

Attachment: signature.asc
Description: OpenPGP digital signature


Reply to: