EPICS Controls Argonne National Laboratory

Experimental Physics and
Industrial Control System

1994  1995  1996  1997  1998  1999  2000  2001  2002  2003  2004  2005  2006  2007  2008  2009  <20102011  2012  2013  2014  2015  2016  2017  2018  2019  2020  2021  2022  2023  2024  Index 1994  1995  1996  1997  1998  1999  2000  2001  2002  2003  2004  2005  2006  2007  2008  2009  <20102011  2012  2013  2014  2015  2016  2017  2018  2019  2020  2021  2022  2023  2024 
<== Date ==> <== Thread ==>

Subject: RE: areaDetector video (Was: network video)
From: "Mark Rivers" <[email protected]>
To: "J. Lewis Muir" <[email protected]>, "EPICS Tech-Talk" <[email protected]>
Date: Wed, 1 Sep 2010 13:47:53 -0500
If multiple cameras are being used each areaDetector Prosilica driver
runs in its own thread.  But their driver library actually creates a
thread that calls back the areaDetector drivers.  It's possible that
they only create one thread even for multiple cameras, I'm not sure.

Mark


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of J. Lewis Muir
Sent: Wednesday, September 01, 2010 11:06 AM
To: EPICS Tech-Talk
Subject: Re: areaDetector video (Was: network video)

On 9/1/10 10:37 AM, [email protected] wrote:
> Lewis,
> 
> No, the software is multithreaded. The images I mentioned were black
and
> white and if you switch to colour compression (which is more
expensive)
> the CPU load goes up to around 220% at times.
> 
> This is all implemented as an areaDetector plugin in a single IOC. I
> don't know what would happen if you tried to use two IOC's on one
host,
> but I suspect the gains would be minimal. Clearly, if you used a
second
> host system you would get a doubling of everything.
> 
> As I understand it the frames are lost before they leave the Prosilica
> driver. The GigE standard is real-time UDP and since we have multiple
> independent data sources with no bandwidth allocation I think if you
> looked carefully you would see data bits all over the floor. I feel
> having the system die reasonably gracefully when the incoming Ethernet
> pipe chokes is the best we can do - even if the choke point is
> significantly less than the full theoretical bandwidth.

Hi, Nick.

If you think frames are lost before they leave the Prosilica driver,
then perhaps the Prosilica driver is not multithreaded?  It seems like
something must not be multithreaded since you have one core completely
idle.  Of course, not all tasks are easily split into smaller tasks that
could be run on different cores, but in this case, I would think it
could.

Lewis


Replies:
RE: areaDetector video (Was: network video) tom.cobb
References:
network video John Dobbins
Re: network video emmanuel_mayssat
RE: network video Mark Rivers
areaDetector video (Was: network video) emmanuel_mayssat
RE: areaDetector video (Was: network video) Mark Rivers
RE: areaDetector video (Was: network video) nick.rees
Re: areaDetector video (Was: network video) J. Lewis Muir
RE: areaDetector video (Was: network video) nick.rees
Re: areaDetector video (Was: network video) J. Lewis Muir

Navigate by Date:
Prev: Sr. High Level Controls Engineer Posting Lashbrook, Megan
Next: Re: record support not found Eric Bjorklund
Index: 1994  1995  1996  1997  1998  1999  2000  2001  2002  2003  2004  2005  2006  2007  2008  2009  <20102011  2012  2013  2014  2015  2016  2017  2018  2019  2020  2021  2022  2023  2024 
Navigate by Thread:
Prev: Re: areaDetector video (Was: network video) J. Lewis Muir
Next: RE: areaDetector video (Was: network video) tom.cobb
Index: 1994  1995  1996  1997  1998  1999  2000  2001  2002  2003  2004  2005  2006  2007  2008  2009  <20102011  2012  2013  2014  2015  2016  2017  2018  2019  2020  2021  2022  2023  2024 
ANJ, 09 Sep 2010 Valid HTML 4.01! · Home · News · About · Base · Modules · Extensions · Distributions · Download ·
· Search · EPICS V4 · IRMIS · Talk · Bugs · Documents · Links · Licensing ·