It has been a few weeks, but in my defense, I have been pretty busy testing and debugging in this new environment. As an assignee to the Linaro project, my first task was to figure out if increasing the buffer size would enable the ARM cpu to drop into a lower power state. Code investigation, community feedback and prototyping said probably not, but I followed through. Below is a chart showing all the testing done, including the recent work to go back through the tests with ALSA 1.0.24 in the stack to enable checking for period disable. Enjoy!
Pingback: about pulseaudio buffer size : printf("
In reply to the question about methods not completely disclosed in the post: Yes it was done with the methods listed in the later blog post, but also by changing compiled-in values, with the same effect. The playback was kept as simple as possible, using only paplay on a long 2ch 44100 .wav file, with >10 samples taken and averaged. As I continue to learn more about ALSA and PulseAudio, I now realize I could have done a few things differently or better or more accurately. I may return to this study in the future. But, there is simply much higher priority work for Linux on ARM at this point. I welcome further study and comparisons! Thanks!