Re: Measuring USB "packet loss"

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, 7 Nov 2012, Chris Stankevitz wrote:

> Hello,
> 
> Background:  I'm running an experiment that is sensitive to USB
> latency of a few milliseconds.  During a typical overnight run I
> encounter a handful such "high latency events" and I am trying to
> understand why they happen.  If you can recommend kernel
> settings/hacks that will decrease USB latency, please share!

Run with non-USB interrupts disabled on a single-processor system.

Seriously, any other interrupt can increase latency for what you're
interested in.  If you need latencies under a couple of ms, USB
probably isn't a good choice.

> ===
> 
> Question:  How can I retrieve a count of USB transmissions that failed
> or were retransmitted (similar to ifconfig on ethernet)?  I am using
> bulk transfers.

The host controller drivers do not keep track of retransmission 
information.  You would have to change the driver you are using.

> If you do not answer this question, can you instead recommend
> documentation that will shed light on the subject?  Can you recommend
> somewhere else for me to ask this question?

The USB specifications are freely avaible at www.usb.org.  The USB-2.0 
spec has many sections that are quite readable.

Alan Stern

--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [Linux Media]     [Linux Input]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [Old Linux USB Devel Archive]

  Powered by Linux