{"title":"Garbage Collections Delays on Java GUIs","authors":"Panagiotis Patros, Michael H. Dawson, K. Kent","doi":"10.23919/ICMU.2018.8653592","DOIUrl":null,"url":null,"abstract":"Tablets, smartphones, wearables, etc. project a (usually graphical) interface to their human users that offloads the majority of the computation to a cloud/fog system. Graphical User Interface (GUI) applications are frequently written in high-level programming languages, which provide automatic memory management: placement and deletion of memory objects is not performed manually; instead, an underlying software component called a Garbage Collector (GC) handles this. Nevertheless, the GC policies and algorithms that are best suited for large datacenters are not necessarily ideal for a small, embedded device. Therefore, in this paper, we present GUI GC, a JavaFX GUI benchmark, which we use to compare the performance of the four GC policies of the IBM J9 Java runtime on a resource-constrained environment. Overall, our experiments suggest that the default policy Gencon, outperformed its counterparts. Additionally, the region-based policy, Balanced, did not fully utilize blocking times; thus, using GUI GC, we conducted experiments with explicit GC invocations that measured significant improvements of up to 13.22% when multiple CPUs were available.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/ICMU.2018.8653592","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Tablets, smartphones, wearables, etc. project a (usually graphical) interface to their human users that offloads the majority of the computation to a cloud/fog system. Graphical User Interface (GUI) applications are frequently written in high-level programming languages, which provide automatic memory management: placement and deletion of memory objects is not performed manually; instead, an underlying software component called a Garbage Collector (GC) handles this. Nevertheless, the GC policies and algorithms that are best suited for large datacenters are not necessarily ideal for a small, embedded device. Therefore, in this paper, we present GUI GC, a JavaFX GUI benchmark, which we use to compare the performance of the four GC policies of the IBM J9 Java runtime on a resource-constrained environment. Overall, our experiments suggest that the default policy Gencon, outperformed its counterparts. Additionally, the region-based policy, Balanced, did not fully utilize blocking times; thus, using GUI GC, we conducted experiments with explicit GC invocations that measured significant improvements of up to 13.22% when multiple CPUs were available.