Re: NFSv3 client for Linux-2.2.5 ready for alpha testing...

Andrew Schretter (schrett@math.duke.edu)
Thu, 15 Apr 1999 15:01:29 -0400 (EDT)


> Assuming that "testfile" changed into "test1" by magic and given that I have
> yet to look Linux kerenel code, I have a dumb question. The NFS read you do
> - is that going across the wire or is it reading from local cache? That you
> have only 20.9% of the CPU, that suggests that at least some requests went
> over the wire (or waiting on disk). Certainly close-to-open consistancy will
> send one GETATTR. There's also the converse dumb question - if the reads are
> going over the wire, why wasn't the data cached?

I realized after I sent this that I was not clear again. I went to the
server and created a new file in the same fashion called test1. So the
files should not have been cached in any form.

> Connectathon's test5 has this incantation that flushes the local cache on
> Solaris, Tru64, but may not be a Posix requirement:

I'll take a look but as I said, the files were created from scratch
locally then used. If you do something again with the file it is
blazingly fast (0.01 seconds) so this is cached.

> Maybe V2 caches data locally and V3 doesn't?

I've been talking with Trond lately. With the latest version,
he asked me to try using an nfs mount of a ramdisk on the Solaris
machine. When I did this, speed was consistent for reads and writes.
That is, the same 4MB file was written in 0.44 seconds and read in
0.52 seconds (I assume the difference here is the speed difference
in local disks between the one on the Solaris machine and my local
machine).

This leads me to believe that the Solaris local UFS read ahead is somehow
mistimed with the NFS read ahead and thus causing a large delay
on the reads. This is just a guess and I'm still working on it.

Andrew Schretter
Systems Programmer, Duke University
Dept. of Mathematics (919) 660-2866

-
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/