snd_emu10k1 tremendous interrupt load?

From: Rink Springer <rink_at_FreeBSD.org>
Date: Fri, 9 Feb 2007 19:20:21 +0100
Hi people,

Over the last few days, my CURRENT box has started to slow down to a
crawl. top(1) reports most CPU load is spent on interrupts, and a quick
vmstat -i to support this completely:

interrupt                          total       rate
irq1: atkbd0                        1631          0
irq15: ata1                        14197          2
irq16: pcm0                   1056243398     160109
irq17: nvidia0+                386190689      58540
irq20: ohci0                        2739          0
irq22: atapci2                     80913         12
irq26: atapci3                     58375          8
irq28: bge0                         6770          1
cpu0: timer                     13193362       1999
cpu1: timer                     13193305       1999
Total                         1468985379     222674

My soundcard is:

pcm0: <Creative EMU10K1> port 0x2040-0x205f irq 16 at device 4.0 on pci1
pcm0: <TriTech TR28602 AC97 Codec>

pciconf -lv says:

pcm0_at_pci1:4:0:  class=0x040100 card=0x80271102 chip=0x00021102 rev=0x06
hdr=0x00
    vendor   = 'Creative Labs'
    device   = 't4830020080332 Sound Blaster Live! (Also Live! 5.1) -
OEM from DELL - CT4780'
    class    = multimedia
    subclass = audio

Whenever I kldunload the snd_emu10k1 driver, all problems disappear.
This is CURRENT from 02-Feb-2007.  The box is a Dual Opteron 2x 846 on a
Tyan K8SE motherboard. The sound card works fine in Windows XP however.

Does anyone have any ideas why this is happening? Quick inspection of
/sys/dev/sound/pci/emu10k1.c:emu_intr() seems to hint that the
emu_rd(sc, IPR, 4) value takes a long time to clear, anyone have more
hints on this annoying behaviour?

Regards,

-- 
Rink P.W. Springer                                - http://rink.nu
"It is such a quiet thing, to fall. But yet a far more terrible thing,
 to admit it."                                    - Darth Traya

Received on Fri Feb 09 2007 - 17:52:38 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:05 UTC