Hi,
I am working on video conference application using gstreamer & farsight2
framework.
In video conference pipeline, the element "fs-funnel" is used after remote
video stream is decoded, finally the stream is sent to xvimagesink for
rendering. But the sink pad of "fs-funnel"
is created by request dynamically and there is no associate buffer allocation
handler.
So during runtime, the output buffer allocation request chain will be chopped
in "fs-funnel" and only traditional buffer will be allocated to upstream
elements as output buffer.
In that case, the downstream buffer allocation (device specific buffer:
XvImage) will not be enabled and lots of buffer allocation/de-allocation and
memory copy operations incurred.
That will cause resource (CPU & power) waste finally, especially at mobile and
thin client side.
Does above analysis make sense? If so, I plan to create a bug entry for that
issue. Do you have any feedback or instructions on next steps? Thanks a lot for
your suggestions!
Best Regards
Yongnian
------------------------------------------------------------------------------
Increase Visibility of Your 3D Game App & Earn a Chance To Win $500!
Tap into the largest installed PC base & get more eyes on your game by
optimizing for Intel(R) Graphics Technology. Get started today with the
Intel(R) Software Partner Program. Five $500 cash prizes are up for grabs.
http://p.sf.net/sfu/intelisp-dev2dev
_______________________________________________
Farsight-devel mailing list
Farsight-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/farsight-devel
