Jens Axboe wrote:
On Mon, Jan 30 2006, Jens Axboe wrote:
On Mon, Jan 30 2006, Jens Axboe wrote:
If this is a hardware bug, why am I only seeing it now all of a sudden?
I'll try with e1000 drivers from an older kernel on this box now, just
to be sure. Starting with 2.6.14, although I'm pretty certain that
2.6.15 worked flawlessly as well.
Just copying over e1000/* from 2.6.14 works great, no timeouts
experienced. It's scp'ed ~150MiB now, before it threw timeouts before it
hit 16MiB even. Rate is about ~800KiB/sec, this is over the internet
through my router. This must be a driver bug introduced recently. I'll
try 2.6.15 e1000 as well, but as written above, I'm pretty sure the bug
only started to show its ugly face after the e1000 updates in
2.6.16-rc1.
2.6.15 hangs as well. So: 2.6.14 good, 2.6.15 bad :-)
Interesting..I have seen problems with 2.6.15 too. But, it very
well could be my own hackings that are causing the problem...
I don't remember seeing any timeouts in the logs, but I do get
NFS hangs. In my case, ping continues to work while NFS is sucking,
which doesn't really make much sense to me. I hope to get some
better data on the problem this week...
Ben
I'll stop testing now and live with 2.6.14 until you have something for
me to try out.
--
Ben Greear <[EMAIL PROTECTED]>
Candela Technologies Inc http://www.candelatech.com
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
