Richard Reich wrote:
I'm currently using test-8, with no patches.  When I mount a usb storage
device using the EHCI driver I get about 128MB copied and then one of
the HT CPUs gets locked into a 100% IO wait.  At least this is what I
assume due to top reporting 50% idle and 50% I/O Wait.  Is this a known
bug?  Is there a work around?  The file system on the device does not
matter, I've tried ext3fs, JFS, and Reiserfs.

You didn't say what sort of usb storage device you're using.


There do seem to be some high speed storage devices, notably
ones with GeneSys usb-to-ide adapters, which don't behave
right.  They basically lock up mid-request.  There's not much
that host side software can do with defective devices, though
one theory is that the defect can be avoided by limiting the
host to about 6 MByte/sec data rate.

You might send the /sys/class/usb_host/*/{registers,async}
files (might need to compile with usb debug messages enabled).
Those can be informative.

- Dave





-------------------------------------------------------
This SF.net email is sponsored by OSDN developer relations
Here's your chance to show off your extensive product knowledge
We want to know what you know. Tell us and you have a chance to win $100
http://www.zoomerang.com/survey.zgi?HRPT1X3RYQNC5V4MLNSV3E54
_______________________________________________
[EMAIL PROTECTED]
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-devel

Reply via email to