Re: Followup on NFS writing

Miguel de Icaza (
Mon, 1 Jul 1996 16:02:12 -0500

> I logged on to one of our Linux systems from home, tweaked the rsize and
> wsize settings, and saw the writing throughput go from 42K per second to
> 200K per second. As Linus pointed out, as and ld will continue to hurt
> performance, but that's normal.

I have always wondered why the default for the rsize and wsize has not
been set to 8192 now? I remember the limits for the 1k block sizes
were there when Linux couldn't allocate buffers bigger than some limit
I don't remember right now (4096 bytes - headers?). This restriction
went away with the new kmalloc code (written by Alex Bligh?).