Messages in this thread | | | From | (Alan Cox) | Subject | Re: 2.1.131 isn't quite it for me | Date | Mon, 7 Dec 1998 14:39:31 +0000 (GMT) |
| |
> > It will be for servers with 8K page size (ie DEC Unix, Solaris Sparc) > > Ok. Is this a matter of design problem or closer to 'just a matter > of programming'? If NFS is going to be that slow I'll either have > to undertake to fix it or switch to a BSD :-I
Its a design flaw in the current code
> The mounted rsize/wsize was 8k as under 2.0, that might not be optimal > anymore.
8K is the optimal value. The current NFS code is driven off the page cache which means it gets 4K requests, and doesn't yet merge adjacent requests into a single 8K write. Most of the needed code is there
- 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/
| |