Thoughts about malloc(3) and threading.
Poul-Henning Kamp
phk at phk.freebsd.dk
Tue Sep 7 10:42:43 PDT 2004
In message <20040907101447.U67477 at carver.gumbysoft.com>, Doug White writes:
>On Mon, 6 Sep 2004, Poul-Henning Kamp wrote:
>
>> In message <xzpllfnve4l.fsf at dwp.des.no>, =?iso-8859-1?q?Dag-Erling_Sm=F8rgrav?=
>> writes:
>> >Poul-Henning Kamp <phk at phk.freebsd.dk> writes:
>> >> So, short version of my position is:
>> >> [...]
>> >
>> >you forgot the most important part:
>> >
>> >"no matter how hard you think it will be to write a good paralell
>> >allocator, it will be harder than you think"
>>
>> Shhhh! you shouldn't have told them that yet.
>
>*snicker*
>
>Sounds like a project for a bored college student looking for a thesis.
>Do you know of any references to research papers on the topic? Would some
>of UMA's fundamentals apply?
Sun has done some work and I belive it is basically a userland version
of UMA.
--
Poul-Henning Kamp | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG | TCP/IP since RFC 956
FreeBSD committer | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.
More information about the freebsd-arch
mailing list