Re: NFS client performance 1.5 orders of magnitude too slow? (fwd)

Godmar Back (gback@cs.utah.edu)
Thu, 11 Mar 1999 11:22:44 -0700 (MST)


Hi Alan,

>
> 2.2.3 is "broken" if you like for the 8K case yes. 2.2.2ac7 isnt, but we are
> still combining the two to get the bugs out of both so we have a final good
> NFS client
>

I finally had a chance to try out the 2.2.3ac1 release.
(I assume that this release subsumes the 2.2.2ac7 release?)

I assume you're interested in feedback: it appears that it's still broken,
and in fact has gotten somewhat slower compared to 2.2.3.

It still takes 6 times as long to transfer a 12 MB file onto a Solaris 2.6
server than it takes with a mature nfs client like the one used in
FreeBSD 2.2.8, under identical hardware setup and network topology.
(15 seconds for 2.2.3-ac1 vs. 14 seconds for 2.2.3). This is with a
default wsize of 4k.
/proc/mounts:
envy:/server/home/gback /.a/envy/server/home/gback nfs rw,addr=envy 0 0

My other test set, where I write to a synchronously writing BSD ffs server
did get slightly faster (from 30 seconds down to 26 seconds; the BSD nfs
client took 18 seconds under identical conditions.)

Thanks,

- Godmar

-
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/