Fwd: [Xen-users] [XEN 3.3 - PCI passthrough] - interaction latencies with /dev/ttyUSB0

["jer jer" <jeremie.garcia.trash@xxxxxxxxx>]

Thanks all for your help!
In fact, I've tried the soft outside XEN from console and it works fine.
If I resume :
  - no XEN ==> works fine from console or GUI
  - with XEN on dom0 ==> works fine from console or GUI
  - with XEN on domU with GUI (VNC) ==> works ok but is slower than previous environments
  - with XEN on domU with console ==> huge latencies
  - with XEN on domU SSH connected ==> huge latencies
     

2009/1/12 Dylan Martin <dmartin@xxxxxxxxxxxx>

The fact that you say it works fine with X-Windows running and badly
from the console makes me think you've got a software problem
unrelated to Xen.  If Xen+X-Windows  works well, then it's hard to
imagine it being a problem with the USB/PCI.  Does it work well at the
command line outside of Xen?  If so, I'd spend time looking at the
difference between console+xen, gui+xen, console-xen etc, rather than
the USB & PCI passthrough.   If it doesn't work well at the console
outside of Xen, then you know it's not a Xen problem.

-Dylan

On Fri, Jan 9, 2009 at 6:29 AM, jer jer <jeremie.garcia.trash@xxxxxxxxx> wrote:
> Hi everybody!
> I'm a pretty new XEN user (3.3) and I need your help on a weird situation.
> In fact I cannot conclude if it could be a XEN problem or not. So I hope you
> will be able to guide me.
> You will find below what my project is and as you guess ...the problem!
>
>
> OBJECTIVE :
> ===========
>    - validate XEN solution for potential projects
>    - setup a paravirtualized environment
>    - embedd on a domU, software interacting with a USB connected desktop
> RFID reader
>
>
> ENVIRONMENT :
> =============
>    - XEN 3.3
>    - paravirtualized environment
>    - dom0 : linux 2.6.24-19-xen (ubuntu) installed with no graphical
> interface
>    - domU : linux 2.6.24-19-xen (ubuntu) installed with gnome and vncserver
>    - PCI passthrough to dedicate all USB controllers to the single domU
>    - domU is installed in a file-backed VBDs
>
> BASIC RESULT:
> =============
>    - dom0 and domU boots well
>    - PCI passthrough works
>    - system is stable
>    - on domU, lsusb shows the device connected
>
> USB DEVICE :
> ============
>    - RFID desktop reader (STID)
>    - serial communication ("/dev/ttyUSB0) 9600 8 n 2
>    - very short instructions sent and received asynchronously (5 bytes) ;
> minimum system stress...
>
> EMBEDDED SOFTWARE :
> ===================
>    - very basic test software that polls the device for an event
>    - if event detected, send a sound instruction to the device
>    - communication with the device is done via the serial dev file
> "/dev/ttyUSB0"
>    - tested on non virtualized environment : no latency on execution and
> test succeeds
>
>
> PROBLEM :
> =========
>    - running the soft from the console (xm console) without GUI introduces
> hudge execution latencies
>    - if we connect our appliance from a remote PC via vncviewer, gnome is
> displayed and run the same soft from an Xterm makes the execution much more
> faster
>      and coud almost be compared to non-virtualized environment perfs.
>    - Note that I've tried to connect via SSH without and then with X
> exporting, and latencies are still noticed
>    - it seems that latencies are only seen when interacting with the device
>    - Finally, we do not want to embedd any window manager such as gnome/KDE
> for footprints concerns
>    - soft have been written in C and JAVA but results are the same
>
> HELPPPPP:
> =========
> As you see, it is a very strange problem and I can't find out who's
> responsible for that :
>    - is it a XEN problem?
>    - is it a console problem?
>    - is it a PCI passthrough problem?
>    - does gnome/vnc introduces implicits optimizations?
>
>
> Furthermore, in order to find some clues:
>    - can you confirm me that XEN 3.3 does not support USB2.0 (not really
> needed here ...)
>    - I often have a system crash connecting USB mass storage devices (even
> dom0 get frozen) ; is it a known bug? I haven't found anything on forums.
>    - based on what I've read (and test) I cannot use newer XEN kernels if I
> want to keep PCI passthrough working
>    - are there some "best practices" to optimize USB passthrough
>
> I've process a lot of diff, compare, readings and I have to tell you I've no
> more idea to solve this silly problem. Any help is thus welcomed!!
>
> Thanks a lot for your help!
>
> Cordially,
> Jérémie
>

> _______________________________________________
> Xen-users mailing list
> Xen-users@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-users
>

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users