Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 14 Feb 1996 09:58:16 -0500 (EST)
From:      "Ron G. Minnich" <rminnich@Sarnoff.COM>
To:        hackers@FreeBSD.org
Subject:   Re: VM question
Message-ID:  <Pine.SUN.3.91.960214095357.10107B-100000@terra>
In-Reply-To: <3121D613.C680.001@pmail.tepco.co.jp>

next in thread | previous in thread | raw e-mail | index | archive | help
> Actually, I'd like to implement a sort of DSM that provides
> page-in/out over the network transparently to the user process.

well, having done some of these myself I can tell you: the freebsd signal 
handling code is not quite there and so won't tell you what you need to 
know when a sigsegv/sigbus happens, to wit: you can't tell what type of 
fault occurred (read or write). It is now giving you the faulting virtual 
address, which is an improvement.

also, the vm does not quite work right in terms of communicating needed 
information to the lower-level layers so that information is not 
available there also. For a view of how to do this right, check out the 
sunos vm (just look in the include files for protos of getpage/putpage 
etc.). No bsd unix has done this right for DSM, and neither has linux, 
which is a shame. 

IF you want to write a DSM to learn how to do it, go for it. If you just 
want one you have a couple choices:
1) basic DSM with no coherency support: use NFS shared mapped files over 
   the net
2) Add simple coherency support: many options: 
   1) use my MNFS, except due to aforementioned VM/VFS problems it does
      not work completely
   2) add a tcp connection to support coherency traffic


ron


ron



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SUN.3.91.960214095357.10107B-100000>