Re: em interrupt storm

From: Frank Mayhar <frank_at_exit.com>
Date: Wed, 23 Nov 2005 23:42:32 -0800
On Thu, 2005-11-24 at 02:14 -0500, Barney Wolff wrote:
> I've observed the interrupt aliasing problem on an Asus A7M266-D
> with 2 Athlon 2200-MPs, so it's not confined to the Intel chipset.
> Here's the evidence (there is nothing connected to ehci0):

This prompted me to take a look at my setup.  Sure enough, same thing:

realtime ~>vmstat -i
interrupt                          total       rate
irq1: atkbd0                        6218          0
irq3: sio1                             2          0
irq4: sio0                        245363          1
irq6: fdc0                             3          0
irq12: psm0                       379932          2
irq13: npx0                            1          0
irq16: ohci2                     1651974          9
irq17: pcm0 ehci0               35766600        198
irq18: nvidia0++                15223737         84
irq19: xl0 ohci0+                2407671         13
irq20: ahc0                      1610309          8
irq21: em0                      35275352        196
cpu0: timer                    359360608       1998
cpu1: timer                    359337445       1998
Total                          811265215       4512

I haven't been using pcm0 and there's nothing on ohci2.  This is a dual
Athlon MP 1900+, AMD chipset (Tyan Tiger MPX board)...

realtime ~>uname -a
FreeBSD realtime.exit.com 6.0-STABLE FreeBSD 6.0-STABLE #0: Wed Nov 16
19:57:03 PST 2005     frank_at_jill.exit.com:/usr/obj/usr/src/sys/REALTIME
i386
-- 
Frank Mayhar frank_at_exit.com     http://www.exit.com/
Exit Consulting                 http://www.gpsclock.com/
                                http://www.exit.com/blog/frank/
Received on Thu Nov 24 2005 - 06:42:59 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:48 UTC