> > > Anyway I installed it to play around with and noticed that rhythmbox > > > was appearing fairly frequently even though it was idle and not > > > playing (I forgot I even had it running). Something like 6.2% of the > > > nearly 2500 wakeups in a second (output below). > > <snip> > > > 3.6% rhythmbox : do_nanosleep (hrtimer_wakeup) > > <snip> > > > 2.6% rhythmbox : schedule_timeout (process_timeout) > > > > It would have been more useful getting a proper trace of where this > > wakeup comes from. Was Rhythmbox idle or not when you did this? > > Not sure how to do the proper trace, sorry. Can try if you can send me > a link to the basics. RB was idle when this was running (ie it was in > the background, in the library, no DAPs connected and no music > playing), in fact it doesn't seem to be any worse when it is playing, > the same threads are creating similar amount of wakeups. Federico and Ryan have examples in their blogs: http://primates.ximian.com/~federico/news-2006-09.html#polling http://blogs.gnome.org/view/ryanl/2006/07/27/0 It should be pretty straight forward to identify the culprits, a bit harder to actually fix them, depending on how brain-dead the design was (ie. it was really easy in Totem).
2nd go as got hit by the list Thanks Bastien, AFAICT from binding a strace to RB when its doing nothing there's lots of gettimeofday, poll and ioctl running every second. Sample attached. Not sure what else needs to be done from here. Pete
Attachment:
rb-strace.txt.gz
Description: GNU Zip compressed data