The Impact of Soft Resource Allocation on n-Tier Application Scalability

Abstract-The flexibility and scalability of computing clouds make them an attractive application migration target; yet, the cloud remains a black-box for the most part. In particular, their opacity impedes the efficient but necessary testing and tuning prior to moving new applications into the cloud. A natural and presumably unbiased approach to reveal the cloud's complexity is to collect significant performance data by conducting more experimental studies. However, conducting large-scale system experiments is particularly challenging because of the practical difficulties that arise during experimental deployment, configuration, execution and data processing. In this paper we address some of these challenges through Expertus -a flexible automation framework we have developed to create, store and analyze large-scale experimental measurement data. We create performance data by automating the measurement processes for large-scale experimentation, including: the application deployment, configuration, workload execution and data collection processes. We have automated the processing of heterogeneous data as well as the storage of it in a data warehouse, which we have specifically designed for housing measurement data. Finally, we have developed a rich web portal to navigate, statistically analyze and visualize the collected data. Expertus combines template-driven code generation techniques with aspect-oriented programming concepts to generate the necessary resources to fully automate the experiment measurement process. In Expertus, a researcher provides only the high-level description about the experiment, and the framework does everything else. At the end, the researcher can graphically navigate and process the data in the web portal.

show abstract

“…We have used most of those findings for our publications [18]- [20], [24], [25], and we continue to use the collected data for more publications.…”

Section: Data Analysis and Performance Phenomenamentioning

confidence: 99%

An automated approach to create, store, and analyze large-scale experimental data in clouds

Jayasinghe

Kimball

Choudhary

et al. 2013

2013 IEEE 14th International Conference on Information Reuse &Amp; Integration (IRI)

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, analogously to hardware resources, allocating the appropriate amount of software resources is a non-trivial challenge. In fact, previous research shows that an intricate balance between concurrency overhead and bottlenecks may necessitate the use of sophisticated configuration algorithms in dedicated deployment scenarios [8].…”

Section: Experimental Consolidation Studymentioning

confidence: 99%

“…Sys_A is configured with a database connection pool size of 96 (12 DB connections per each of the 8 servlet programs in Tomcat). For the other software resources, we follow our previously published allocation algorithm and configure the system according to the RUBBoS-specific transaction-flow models to minimize concurrency overhead (e.g., Apache worker connection pool of 200 and 240 Tomcat threads) [8]. Sys_B is configured with a tuned DB connection pool size of 16 (2 DB connections per each of the 8 servlets in Tomcat), which is the best-performing software resource allocation in many dedicated deployment scenarios (e.g., Figure 8c).…”

Section: Experimental Consolidation Studymentioning

confidence: 99%

Challenges and Opportunities in Consolidation at High Resource Utilization: Non-monotonic Response Time Variations in n-Tier Applications

Malkowski

Kanemasa

Chen

et al. 2012

2012 IEEE Fifth International Conference on Cloud Computing

Self Cite

View full text Add to dashboard Cite

Abstract-A central goal of cloud computing is high resource utilization through hardware sharing; however, utilization often remains modest in practice due to the challenges in predicting consolidated application performance accurately. We present a thorough experimental study of consolidated n-tier application performance at high utilization to address this issue through reproducible measurements. Our experimental method illustrates opportunities for increasing operational efficiency by making consolidated application performance more predictable in high utilization scenarios. The main focus of this paper are non-trivial dependencies between SLA-critical response time degradation effects and software configurations (i.e., readily available tuning knobs). Methodologically, we directly measure and analyze the resource utilizations, request rates, and performance of two consolidated n-tier application benchmark systems (RUBBoS) in an enterprise-level computer virtualization environment. We find that monotonically increasing the workload of an n-tier application system may unexpectedly spike the overall response time of another co-located system by 300 percent despite stable throughput. Based on these findings, we derive a software configuration best-practice to mitigate such non-monotonic response time variations by enabling higher request-processing concurrency (e.g., more threads) in all tiers. More generally, this experimental study increases our quantitative understanding of the challenges and opportunities in the widely used (but seldom supported, quantified, or even mentioned) hypothesis that applications consolidate with linear performance in cloud environments.

show abstract

“…Recently, autonomic computing in modern data centers has become a very active and important research area [2], [6], [8], [15], [18], [20], [21], [23], [24], [27], [29]. Those studies focused on capacity planning for virtual machines (VMs) co-location and distribution across a data center [8], [15], [26], VM provisioning for applications [3], [9], [10], [12], [24], [25], resource allocation in a VM [20], [21], [7], and server parameter tuning [2], [29].…”

Section: Related Workmentioning

confidence: 99%

Automated and Agile Server Parameter Tuning with Learning and Control

Guo

Lama

Zhou

2012

2012 IEEE 26th International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

Abstract-Server parameter tuning in virtualized data centers is crucial to performance and availability of hosted Internet applications. It is challenging due to high dynamics and burstiness of workloads, multi-tier service architecture, and virtualized server infrastructure. In this paper, we investigate automated and agile server parameter tuning for maximizing effective throughput of multi-tier Internet applications. A recent study proposed a reinforcement learning based server parameter tuning approach for minimizing average response time of multi-tier applications. Reinforcement learning is a decision making process determining the parameter tuning direction based on trial-and-error, instead of quantitative values for agile parameter tuning. It relies on a predefined adjustment value for each tuning action. However it is nontrivial or even infeasible to find an optimal value under highly dynamic and bursty workloads. We design a neural fuzzy control based approach that combines the strengths of fast online learning and self-adaptiveness of neural networks and fuzzy control. Due to the model independence, it is robust to highly dynamic and bursty workloads. It is agile in server parameter tuning due to its quantitative control outputs. We implement the new approach on a testbed of virtualized HP ProLiant blade servers hosting RUBiS benchmark applications. Experimental results demonstrate that the new approach significantly outperforms the reinforcement learning based approach for both improving effective system throughput and minimizing average response time.

show abstract

The Impact of Soft Resource Allocation on n-Tier Application Scalability

Cited by 40 publications

References 18 publications

An automated approach to create, store, and analyze large-scale experimental data in clouds

An automated approach to create, store, and analyze large-scale experimental data in clouds

Challenges and Opportunities in Consolidation at High Resource Utilization: Non-monotonic Response Time Variations in n-Tier Applications

Automated and Agile Server Parameter Tuning with Learning and Control

Contact Info

Product

Resources

About