Load Balancing of Java Applications by Forecasting Garbage Collections

Portillo-Dominguez, A. Omar; Wang, Miao; Magoni, Damien; Perry, Philip; Murphy, John

doi:10.1109/ispdc.2014.20

Cited by 13 publications

(27 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work [15], we presented an algorithm to predict MaGC events in generational heaps. The algorithm works by periodically retrieving MiGC and memory samples from a monitored JVM (as per a configurable Sample Interval) to build the history of memory allocations that occur in the Young and Old Generations through time.…”

Section: Background and Related Workmentioning

confidence: 99%

“…To assess the performance benefits of adapting the load balancing based on the MaGC forecasts, in [15] we also presented a modified version of the round-robin 3 load balancing algorithm. The main difference of our algorithm (compared against the normal round-robin) is that it performs an additional check in the selection of the next node.…”

Section: Background and Related Workmentioning

confidence: 99%

“…To achieve this, we evaluated the effectiveness of our MaGC forecast algorithm (proposed on [15]) against a broad set of Java programs and experimental configurations with the aim of analysing the conditions in which the algorithm performed better. The following sections describe this experiment and its results.…”

Section: Experiments #1: Assessment Of Forecast Accuracymentioning

confidence: 99%

“…Three main metrics were calculated: Firstly, the Forecast Error (FE) [15], which is the ratio of the absolute forecasting error (difference between the forecast time and the time of the real MaGC event) as a proportion of the time elapsed since the previous MaGC. It is usually expressed as a percentage to be comparable among different programs.…”

Section: Magc Forecastmentioning

confidence: 99%

“…This strategy (shown in Figure 1) can keep the system performance safe from MaGC pauses. In [15] we proposed a novel MaGC forecast algorithm and demonstrated how a load balancing strategy can exploit the MaGC forecast to improve the performance of a distributed system. However, as that strategy uses a static configuration, it mostly relies on human expert knowledge to optimise its settings to achieve the best system performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Adaptive GC-Aware Load Balancing Strategy for High-Assurance Java Distributed Systems

Portillo-Dominguez

Wang

Murphy

et al. 2015

2015 IEEE 16th International Symposium on High Assurance Systems Engineering

Self Cite

View full text Add to dashboard Cite

Section: Background and Related Workmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

Section: Experiments #1: Assessment Of Forecast Accuracymentioning

confidence: 99%

Section: Magc Forecastmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Adaptive GC-Aware Load Balancing Strategy for High-Assurance Java Distributed Systems

Portillo-Dominguez

Wang

Murphy

et al. 2015

2015 IEEE 16th International Symposium on High Assurance Systems Engineering

Self Cite

View full text Add to dashboard Cite

TRINI: an adaptive load balancing strategy based on garbage collection for clustered Java systems

et al. 2016

Self Cite

View full text Add to dashboard Cite

Summary Nowadays, clustered environments are commonly used in high‐performance computing and enterprise‐level applications to achieve faster response time and higher throughput than single machine environments. Nevertheless, how to effectively manage the workloads in these clusters has become a new challenge. As a load balancer is typically used to distribute the workload among the cluster's nodes, multiple research efforts have concentrated on enhancing the capabilities of load balancers. Our previous work presented a novel adaptive load balancing strategy (TRINI) that improves the performance of a clustered Java system by avoiding the performance impacts of major garbage collection, which is an important cause of performance degradation in Java. The aim of this paper is to strengthen the validation of TRINI by extending its experimental evaluation in terms of generality, scalability and reliability. Our results have shown that TRINI can achieve significant performance improvements, as well as a consistent behaviour, when it is applied to a set of commonly used load balancing algorithms, demonstrating its generality. TRINI also proved to be scalable across different cluster sizes, as its performance improvements did not noticeably degrade when increasing the cluster size. Finally, TRINI exhibited reliable behaviour over extended time periods, introducing only a small overhead to the cluster in such conditions. These results offer practitioners a valuable reference regarding the benefits that a load balancing strategy, based on garbage collection, can bring to a clustered Java system. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

PHOEBE: an automation framework for the effective usage of diagnosis tools in the performance testing of clustered systems

et al. 2017

Self Cite

View full text Add to dashboard Cite

The identification of performance issues and the diagnosis of their root causes are time-consuming and complex tasks, especially in clustered environments. To simplify these tasks, researchers have been developing tools with built-in expertise for practitioners. However, various limitations exist in these tools that prevent their efficient usage in the performance testing of clusters (e.g. the need of manually analysing huge volumes of distributed results). In a previous work, we introduced a policy-based adaptive framework (PHOEBE) that automates the usage of diagnosis tools in the performance testing of clustered systems, in order to improve a tester's productivity, by decreasing the effort and expertise needed to effectively use such tools. This paper extends that work by broadening the set of policies available in PHOEBE, as well as by performing a comprehensive assessment of PHOEBE in terms of its benefits, costs and generality (with respect to the used diagnosis tool). The performed evaluation involved a set of experiments in assessing the different trade-offs commonly experienced by a tester when using a performance diagnosis tool, as well as the time savings that PHOEBE can bring to the performance testing and analysis processes. Our results have shown that PHOEBE can drastically reduce the effort required by a tester to do performance testing and analysis in a cluster. PHOEBE also exhibited consistent behaviour (i.e. similar time-savings and resource utilisations), when applied to a set of commonly used diagnosis tools, demonstrating its generality. Finally, PHOEBE proved to be capable of simplifying the configuration of a diagnosis tool. This was achieved by addressing the identified trade-offs without the need for manual intervention from the tester. PHOEBE is implemented with the multi-agent architecture depicted in Figure 1. There, it can be seen how PHOEBE is composed of three types of agents: the control agent is responsible for interacting with the load testing tool to know when the test starts and ends. It is also responsible for evaluating the policies and propagating the decisions to the other nodes. Meanwhile, the application node agent is responsible for performing the required tasks in each application node (e.g. sampling collection or sending the collected samples to the diagnosis tool). Finally, the diagnosis tool Here, the objective was to evaluate the potential trade-off between the number of samples concurrently processed by a diagnosis tool and the number of resources it requires to process the samples. The following sections describe this experiment and its results. PHOEBE 1863 7.1. Experiment #4: proposed policies assessmentThe objective of this experiment was to evaluate the behaviour of PHOEBE, as well as the set of proposed policies, in order to assess how well they have fulfilled their purpose of addressing the identified trade-offs without the need for manual intervention from the tester. The following sections describe this experiment and its results.7.1.1. Experimental set-up....

show abstract

Load Balancing of Java Applications by Forecasting Garbage Collections

Cited by 13 publications

References 15 publications

Adaptive GC-Aware Load Balancing Strategy for High-Assurance Java Distributed Systems

Adaptive GC-Aware Load Balancing Strategy for High-Assurance Java Distributed Systems

TRINI: an adaptive load balancing strategy based on garbage collection for clustered Java systems

PHOEBE: an automation framework for the effective usage of diagnosis tools in the performance testing of clustered systems

Contact Info

Product

Resources

About