Subject: AlphaPC164 net performance closure (Re: 1.5.1 SPL0 fix??)
To: None <email@example.com>
From: Eric Schnoebelen <firstname.lastname@example.org>
Date: 04/19/2001 22:38:04
Eric Schnoebelen writes:
- Well, having applied the patch, I can say that it
- doesn't help the network/disk-io problem I've seen and others
- have reported.
- Problem summary:
- With simultaneous disk and network IO, the
- network IO is about 6kbp/sec.
- System Description:
- AlphaPC164/500Mhz, 64Mb RAM, IDE disk
- Intel EtherExpress Pro/100+ (fxp)
- NetBSD 1.5.1_BETA kernel
I thought I'd report closure on the above problem. I
was heading down the hardware problem route, and in the process
of reducing the CPU clock speed, I noticed that the system
clock divisor (IRQ3-IRQ0) were set 366Mhz instead of the 500Mhz
the CPU (and oscillator) were doing.
In some respects, its a wonder the bleeding thing ran at
all. (and I wonder how I managed to miss that in building the
Thank you for everyone's help and assistance..
(oh, I'm now seeing ~400kbp/sec from dump over a 10baseT-fdx
Eric Schnoebelen email@example.com http://www.cirr.com
"I'm going to a commune in Vermont and will deal with no unit of time
shorter than a season" -- Josh Rosen in _The Soul of a New Machine_