Re: Implementation of POSIX shared memory objects

[Mindaugas Rasiukevicius <rmind%netbsd.org@localhost>]

Hello,

yamt%mwd.biglobe.ne.jp@localhost (YAMAMOTO Takashi) wrote:
> > Here is the implementation of POSIX shared memory objects:
> > 
> > http://www.netbsd.org/~rmind/shm_memobj.diff
> > 
> > Please review.
> 
> why did you choose to implement it in kernel?
> 

After some thinking about this, I have few things to mention.

For many cases, it makes sense to dump this complexity out from the kernel,
and use file-system layer (with eg. tmpfs). However:

- It could not provide determinism for real-time systems.

- It would have significant overhead for embedded systems. High bandwidth and
  performance is a requirement for POSIX shared memory.

- Similar bits of kernel functionality (and therefore some complexity) might
  be needed if we plan to support POSIX typed memory objects.

Your thoughts?

-- 
Mindaugas