Messages in this thread | | | Date | Mon, 14 Dec 1998 10:00:32 -0800 | From | "David S. Miller" <> | Subject | Re: PATCH: Raw device IO for 2.1.131 |
| |
Date: Mon, 14 Dec 1998 18:56:07 +0100 From: Pavel Machek <pavel@atrey.karlin.mff.cuni.cz>
> For receive and writes to a disk, sendfile() is not the answer.
Why not? I see current sendfile implementation can not do it, but what is wrong with this? I think that we should extent sendfile to do such things in future... (Is there any problem with it?)
You are right. I meant "now, with the current architecture" it makes no sense to use sendfile for when the disk file is the destination.
It makes sense when full blown writes directly into the page cache are supported across the whole kernel (they sort of are right now minimally for the sake of nfs).
Later, David S. Miller davem@dm.cobaltmicro.com
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |