Performance Analysis and Optimization of Full Garbage Collection in Memory-hungry Environments

Yu, Yang; Lei, Tianyang; Zhang, Weihua; Chen, Haibo; Zang, Binyu

doi:10.1145/2892242.2892251

Cited by 16 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Garbage collection is an active area of research [2,3,23,34]. [26] proposes new user-facing APIs to more easily (manually) customize garbage collectors.…”

Section: Related Workmentioning

confidence: 99%

Learned garbage collection

Cen

Marcus

Mao

et al. 2020

Proceedings of the 4th ACM SIGPLAN International Workshop on Machine Learning and Programming Languages

View full text Add to dashboard Cite

Several programming languages use garbage collectors (GCs) to automatically manage memory for the programmer. Such collectors must decide when to look for unreachable objects to free, which can have a large performance impact on some applications. In this preliminary work, we propose a design for a learned garbage collector that autonomously learns over time when to perform collections. By using reinforcement learning, our design can incorporate user-defined reward functions, allowing an autonomous garbage collector to learn to optimize the exact metric the user desires (e.g., request latency or queries per second). We conduct an initial experimental study on a prototype, demonstrating that an approach based on tabular Q learning may be promising.

show abstract

“…Garbage collection is an active area of research [2,3,23,34]. [26] proposes new user-facing APIs to more easily (manually) customize garbage collectors.…”

Section: Related Workmentioning

confidence: 99%

Learned garbage collection

Cen

Marcus

Mao

et al. 2020

Proceedings of the 4th ACM SIGPLAN International Workshop on Machine Learning and Programming Languages

View full text Add to dashboard Cite

show abstract

“…Garbage collection optimization for big data applications. As mentioned in the survey [31], researchers begin to optimize existing garbage collectors [53,41,50,30,36] or design new garbage collectors [44,32] for big data applications. For example, Suo et al [50] proposed dynamic GC load balancing strategy to optimize the concurrency of Parallel GC in multicore environment.…”

Section: Related Workmentioning

confidence: 99%

An experimental evaluation of garbage collectors on big data applications

Guo

Dou

et al. 2019

Proc. VLDB Endow.

View full text Add to dashboard Cite

Popular big data frameworks, ranging from Hadoop MapReduce to Spark, rely on garbage-collected languages, such as Java and Scala. Big data applications are especially sensitive to the effectiveness of garbage collection (i.e., GC), because they usually process a large volume of data objects that lead to heavy GC overhead. Lacking indepth understanding of GC performance has impeded performance improvement in big data applications. In this paper, we conduct the first comprehensive evaluation on three popular garbage collectors, i.e., Parallel, CMS, and G1, using four representative Spark applications. By thoroughly investigating the correlation between these big data applications' memory usage patterns and the collectors' GC patterns, we obtain many findings about GC inefficiencies. We further propose empirical guidelines for application developers, and insightful optimization strategies for designing big-datafriendly garbage collectors.

show abstract

“…Przyjrzano się także pracom autorów implementacji odzyskiwaczy pamięci, w których porównywano ich osiągnięcia względem istniejących już algorytmów [3,11]. W kilku pracach badano zgodność algorytmów z teorią generacyjną [1], skalowalność poszczególnych algorytmów [4] a także badania skupiające się na wydajności odzyskiwania w procesach całkowitego odzyskiwania pamięci [6,7,10]. Żadna z prac nie uwzględniała wydajności algorytmów względem rozkładu czasu życia obiektów.…”

Section: Przegląd Literaturyunclassified

A performance comparison of garbage collector algorithms in Java Virtual Machine

Kopeć

Smółka

2019

jcsi

View full text Add to dashboard Cite

In programming languages with automatic memory management garbage collection plays an important role of cleaning unused memory. Garbage collection algorithms have been developed for many years and aim to maximize the application’s performance. This paper presents and compares a performance of five garbage collection algorithms present in current version of Java 12 in three applications with different object lifetime span. The analysis covered the system responsiveness, garbage collector workload and application throughput at high application load.

show abstract

Performance Analysis and Optimization of Full Garbage Collection in Memory-hungry Environments

Cited by 16 publications

References 24 publications

Learned garbage collection

Learned garbage collection

An experimental evaluation of garbage collectors on big data applications

A performance comparison of garbage collector algorithms in Java Virtual Machine

Contact Info

Product

Resources

About