Re: uhci vs ehci: 5 wakeups/s saved

[Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>]

On Wed, 3 Oct 2007, Alan Jenkins wrote:

> >>> Using UHCI instead of EHCI saves ~5 wakeup/s:
> >>>
> >>> With ehci_hcd loaded (and not uhci_hcd):
> >>>   31.1% ( 10.0)     <kernel core> : ehci_work (ehci_watchdog)
> >>>   30.4% (  9.8)       <interrupt> : ehci_hcd:usb5
> >>>       
> >
> > Pardon me, but can somebody explain what those numbers mean?  Are they 
> > an average number of interrupts per second?
> >   
> That's exactly right.  Side note: The percentages are for all 
> interrupts, including timer interrupts.  The ehci_hcd:usb5 interrupt is 
> firing, on average, 10 times a second.

At least as important is to know what was happening during the time
interval when the interrupts were measured.  If you're interested in
saving power by avoiding unnecessary interrupts, then there's little
point in observing what happens while the USB bus is in use -- the CPU
is going to have to be awake then anyway.  Much more interesting is
what happens when the bus is supposed to be idle.  If you measure
idle-time interrupt usage, you should find that both uhci-hcd and
ehci-hcd have long-run averages very close to 0.

Another aspect that's impossible to determine just from the interrupt 
averages is how much time the CPU spends servicing each interrupt.

Alan Stern


-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
Linux-usb-users@xxxxxxxxxxxxxxxxxxxxx
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-users