Empirical delay comparisons of push and pull implementation models for local audio video streams

We focus on the local delay concerned with the schemes which handle continuous inflow of encoded data from constant or variable bit-rate audio and video encoders. We introduce two implementation approaches, the pull model and the push model. While the pull model periodically pumps out the incoming data from the system buffer, the push model receives events from the device drivers. From our experiments, it was shown that the push model outperforms the other for both constant and variable bit-rate streams in terms of the local delay, when the system suffers reasonable loads. We interpret this experimental data with M/G/1 multiple vacation queueing theories, and show that it is consistent with the queueing theoretic interpretations. We also suggest that the push model potentially obtains a shorter delay in the usage of public network transport services such as the Internet.