Assessing the Limits of Program-Specific Garbage Collection Performance

作者：Jacek Nicholas^*; Chiu Meng Chieh; Marlin Benjamin; Moss Eliot

来源：ACM Sigplan Notices, 2016, 51(6): 584-598.

DOI：10.1145/2908080.2908120

• Optimal garbage collection
• Markov decision processes
• least squares policy iteration

We consider the ultimate limits of program-specific garbage collector performance for real programs. We first characterize the GC schedule optimization problem using Markov Decision Processes (MDPs). Based on this characterization, we develop a method of determining, for a given program run and heap size, an optimal schedule of collections for a non-generational collector. We further explore the limits of performance of a generational collector, where it is not feasible to search the space of schedules to prove optimality. Still, we show significant improvements with Least Squares Policy Iteration, a reinforcement learning technique for solving MDPs. We demonstrate that there is considerable promise to reduce garbage collection costs by developing programspecific collection policies.

• 出版日期2016-6