Normally This occurs when there as a result of latency by your hardware. In
your case it is your NIC. This is very common in old NIC cards with a small
amount of cache(i.e. 3c509 rev. A). To make things short, Your MB allows
your NIC to use its bus for a certain amount of time and the NIC was latent.
Now there are these i/o's on your MB's bus and because they are masked it
does not know what device they belong to... So the MB interrupts and you get
your message. There is a command to unmask i/o's so that the MB knows which
device they belong and it will wait for those.
There is an option in the hdparm command to turn off the mask feature:
hdparm -u 1
Get/set interrupt-unmask flag for the drive. A
setting of 1 permits the driver to unmask other
interrupts during processing of a disk interrupt,
which greatly improves Linux's responsiveness and
eliminates "serial port overrun" errors.
You might want to try this. The excerpt above is from the hdparm man page...
I suggest reading it. *Note this has worked for some and not for others.
Your other option is to get a newer NIC.
Earle Nietzel
-----Original Message-----
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]]On Behalf Of Dale E. Martin
Sent: Monday, September 28, 1998 2:10 PM
To: [EMAIL PROTECTED]
Subject: eth0: Interrupted while interrupts are masked! isr=0x0 imr=0x0.
I get hundreds of those messages running 2.1.122 on a Tyan S1668 Dual PPro
machine, with two PPro 150s and a Boca NE2000 (ISA) clone card. It doesn't
seem to actually bother anything, the machine has been up for 6 days with a
heavy load at times - just thought I'd ask if anyone knows what's up with
it?
Thanks,
Dale
--
+-------------------- finger for pgp public key ---------------------+
| Dale E. Martin | Clifton Labs, Inc. | Senior Computer Engineer |
| [EMAIL PROTECTED] | http://www.clifton-labs.com |
+----------------------------------------------------------------------+
