It sounds like an IRIX bug to me.
> is to be substituted by the linux server... Nevertheless I have tested the
> lockd stuff:
>
> Catia reads and writes files (tested up to 30MB of filesize) without
> causing any errors. This looks good, compared to earlier tests. Catia
> heavily depends on lockd. The problem now is a veerrry poor write
> performance, I did some speed-tests:
>
> Read a 30MB file from server to AIX 4.3 workstation:
>
> >From linux-2.1.122: about 45 sec
> >From IRIX 5.3: about 45-50 sec
>
> Both with a stopwatch, good enough if you look at the next results:
>
> Write a 30MB file from AIX to server, includes 30sec of data preparation
> (no network traffic) by Catia:
>
> To linux-2.1.122: about 585 sec
> To IRIX 5.3: about 90 sec
>
> 2. Test: copy 30MB from IRIX client to linux server and back:
>
> cp cptest.txt /achilles/catv4 : Write to linux = 385 sec
> cp /achilles/catv4/cptest.txt . : Read from linux = 42 sec
>
> Network is 10MBit Ethernet TP, low traffic.
> Linux is a P100 64MB, 3C509 PnP, AHA 1542C, 2GB IBM SCSI
> IRIX is a R3000 33MHz, 48MB, 2GB IBM SCSI
> AIX is a 42P (140MHz) 192MB RAM
>
> The machines were all restricted to nfsv2 and udp and 8192 buffersizes.
I saw that one also. I don't have the time to track it down. It
must be a bug somewhere in the kernel nfsd. If noone is working on
it, I will take a look when I have time. But that will be a whole.
However, I was told you could turn on async write on the NFS server.
H.J.
-
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/