Alan Stern wrote:
>>   I'll try it again though (with 
>> irqbalance turned on for consistency's sake) and report back tomorrow 
>> (probably, it can take a while for the problem to show up).
>>     
> I asked because the log doesn't mention anything to do with the mouse.  It 
> could simply be that the repeated retries for the dying card reader are 
> using up too much CPU time, not leaving enough for the mouse handler to 
> run with sufficiently low latency.
>   
Good point.   I had an accident with the dmesg output (it's been a long 
day) but it was interesting when the mouse went strange.

Both cores were pretty well idle, not much going on at all.  I checked 
/proc/interrupts and to my considerable surprise there were no 
interrupts being delivered for uhci_hcd at all.   That is, in this line:

 66:      69272      68272   IO-APIC-level  uhci_hcd:usb1, 
uhci_hcd:usb2, uhci_hcd:usb3, uhci_hcd:usb4

the interrupt counts were going up at all.  I'm surprised that the mouse 
runs at all.   I didn't see anything in the dmesg output before I lost 
it that indicated that there was a problem here, but next time I'll be a 
little more careful with it.

jch

-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys -- and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
Linux-usb-users@lists.sourceforge.net
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-users

Reply via email to