A Comparative Study of Stampede Garbage Collection Algorithms

Abstract

Stampede is a parallel programming system to support interactive multimedia applications. The system maintains temporal causality in such streaming real-time applications via channels that buffer timestamped items. A Stampede application is a coarse-grain dataflow pipeline of these timestamped items. Not all timestamps are relevant for an application output due to the differential processing rates of pipeline stages. Therefore, garbage collection (GC) is crucial for Stampede runtime performance. Three GC algorithms are currently available in Stampede. In this paper, we ask the question how far off these algorithms are from an ideal garbage collector, one in which the memory usage is exactly equal to that which is required for buffering only the relevant timestamped items in channels. This oracle, while unimplementable, serves as an empirical lower-bound for memory usage. We then propose optimizations that will help us get closer to this lower-bound. Using an elaborate measurement and post-mortem analysis infrastructure in Stampede, we evaluate the performance potential for these optimizations. A color-based people tracking application is used for the performance evaluation. Our results show that these optimizations reduce the memory usage by over 60% for this application over the best GC algorithm available in Stampede.

Distributed Garbage Collection Algorithms for Timestamped Data

“…An execution trace of an actual application run using DGC records the exact set of relevant timestamps that make it all the way through the pipeline. This trace is used by the IGC oracle [19] to determine a lower bound for the application average memory usage and to provide a base to compare different GC algorithms.…”

“…To compute a lower bound for memory usage, we developed an oracle called the Ideal Garbage Collector (IGC) [19]. An execution trace of an actual application run using DGC records the exact set of relevant timestamps that make it all the way through the pipeline.…”

“…The Linux kernel used is Redhat 2.4.20, along with a reliable UDP messaging library called CLF. 4 We have reported on a limited comparative study of the garbage collection algorithms in an earlier paper [19]. In this section, we expand on that study and consider the scalability of these algorithms as well.…”

Adaptive Resource Utilization via Feedback Control for Streaming Applications

“…In an earlier work [14], we introduced an Ideal Garbage Collector (IGC) [14]. IGC gives a theoretical lower limit for the memory footprint by performing a postmortem analysis of the execution trace of an application.…”

“…Efficient implementation of the application will attempt to minimize resource utilization wasted in maintaining such data. Stampede run-time system contains garbage collection (GC) algorithms [18,6,14] based on timestamp visibility that free data elements as soon as the run-time system can be certain that they are not going to be used by the application. These Stampede GC algorithms differ from traditional GC in their logic governing garbage collection in that they assert data will not be used in the future.…”