Messages in this thread | | | Date | Thu, 18 Apr 1996 23:28:42 -0400 | From | "David S. Miller" <> | Subject | Re: Ideas for reducing memory copying and zeroing times |
| |
Date: Wed, 17 Apr 96 19:41 BST From: Jamie Lokier <jamie@rebellion.co.uk>
No, they read different things into the same I/O areas. This applies to any program that is copying data, optionally reading it as it goes. This kind of thing is also done by the network subsystem, and although it could be done as a special case for networking, I'd prefer to see a more general page sharing mechanism. Perhaps we can assume that all such programs are optimised to use mmap() already, or perhaps we can't.
Now that you are mentioning I/O, keep in mind architectures where virtual caches can cause problems and virtual dvma is available. (MIPS and Sparc come to mind of course)
Later, David S. Miller davem@caip.rutgers.edu
| |