DragonFly kernel List (threaded) for 2004-02
Re: lkwt in DragonFly
Content-Type: text/plain; charset=us-ascii; format=flowed
X-Trace: 1076552276 crater_reader.dragonflybsd.org 184 126.96.36.199
Xref: crater_reader.dragonflybsd.org dragonfly.kernel:3754
Matthew Dillon wrote:
> :idem for linux, see: http://people.redhat.com/drepper/nptl-design.pdf
> :the short summary is that fixing your kernel to work nicely with 1:1
> :is easier then getting the hairy details of n:m properly working.
I would like to point out that FreeBSD 5 has its M:N implementation pretty
worked out by now and it was:
1 persom part time for 2 year
2 people part time for 2 years
Considerrring that it was very "part time" at times,
that's not a lot, and given what we learned,
it would take DF a lot less time to implement something similar.
(especially with people working Full time (TM) on it :-)
> :I'd like to know why for dragonfly n:m would be better.
> :Sten Spans
> n:m is always better then 1:1 because thread switches within each
> virtual cpu (where the virtual cpu is represented by a single user
> process) require no context switch into the kernel at all.
> n:m is definitely harder to do, but that doesn't mean it shouldn't be
> done. It's a great goal for DFly, IMHO. The paper you are quoting is
> simply an opinion, like any paper. It is not necessarily correct.
> Matthew Dillon