Optimization for Speculative Execution in Big Data Processing Clusters

Xu, Huanle; Lau, Wing Cheong

doi:10.1109/tpds.2016.2564962

Cited by 26 publications

(23 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We observe that the task execution time measured on our testbed follows a Pareto distribution with an exponent β < 2. This is consistent with observations made in [6,7,14,59]. As shown in Morpheus [62] and Jockey [63], job deadlines can be introduced by third parties and/or specified in Service Level Agreements (SLAs).…”

Section: ) Setupsupporting

confidence: 89%

“…Thus, many researchers have shown interest in mitigating stragglers and improving the default Hadoop speculation mechanism. They proposed new mechanisms to detect stragglers reactively and proactively and launch speculative tasks accordingly [2][3][4][6][7][8][9][10]. This is important to ensure providing high reliability to satisfy a given QoS, as it can be at risk when stragglers exist or when failures occur.…”

Section: Related Workmentioning

confidence: 99%

“…The Pareto distribution is proposed to model the execution times of tasks in [59], and is used in [6,7,14] to analyze the straggler problem. Following these papers, we assume the execution time T i,j,k of each attempt follows a Pareto distribution with parameters t min and β.…”

Section: Related Workmentioning

confidence: 99%

“…Several better approaches, both proactive and reactive, have been proposed recently to deal with the straggler problem [2][3][4][6][7][8][9][10]. In particular, reactive approaches typically detect stragglers by monitoring the progress of tasks and then launch speculative copies of slow-running tasks.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, we define a new metric, Probability of Completion before Deadlines (PoCD), to measure the probability that MapReduce jobs meet their desired deadlines. Assuming that a single task execution time follows a Pareto distribution [6,7,14,15], we analyze three popular classes of (proactive and reactive) strategies, including Clone, Speculative-Restart, and Speculative-Resume, and quantify their PoCD in closedform under the same framework. We note that our analysis also applies to MapReduce jobs, whose PoCD for map and reduce stages can be optimized separately.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Chronos: A Unifying Optimization Framework for Speculative Execution of Deadline-Critical MapReduce Jobs

Alamro

Lan

et al. 2018

2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

Meeting desired application deadlines in cloud processing systems such as MapReduce is crucial as the nature of cloud applications is becoming increasingly mission-critical and deadline-sensitive. It has been shown that the execution times of MapReduce jobs are often adversely impacted by a few slow tasks, known as stragglers, which result in high latency and deadline violations. While a number of strategies have been developed in existing work to mitigate stragglers by launching speculative or clone task attempts, none of them provides a quantitative framework that optimizes the speculative execution for offering guaranteed Service Level Agreements (SLAs) to meet application deadlines. In this paper, we bring several speculative scheduling strategies together under a unifying optimization framework, called Chronos, which defines a new metric, Probability of Completion before Deadlines (PoCD), to measure the probability that MapReduce jobs meet their desired deadlines. We systematically analyze PoCD for popular strategies including Clone, Speculative-Restart, and Speculative-Resume, and quantify their PoCD in closed-form. The result illuminates an important tradeoff between PoCD and the cost of speculative execution, measured by the total (virtual) machine time required under different strategies. We propose an optimization problem to jointly optimize PoCD and execution cost in different strategies, and develop an algorithmic solution that is guaranteed to be optimal. Chronos is prototyped on Hadoop MapReduce and evaluated against three baseline strategies using both experiments and trace-driven simulations, achieving 50% net utility increase with up to 80% PoCD and 88% cost improvements.

show abstract

Section: ) Setupsupporting

confidence: 89%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Chronos: A Unifying Optimization Framework for Speculative Execution of Deadline-Critical MapReduce Jobs

Alamro

Lan

et al. 2018

2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)

View full text Add to dashboard Cite

show abstract

Near-Data Prediction Based Speculative Optimization in a Distribution Environment

Sun

Jin

et al. 2020

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

ApacheHadoop is an open source software framework that supports data-intensive distributed applications and is distributed under the Apache 2.0 licensing agreement, where consumers will no longer deal with complex configuration of software and hardware but only pay for cloud services on demand. So how to make the performance of the cloud platform become more important in a consumer-centric environment. There exists imbalance between in some distribution of slow tasks, which results in straggling tasks will have a great influence on the Hadoop framework. By monitoring those tasks in real-time progress and copying the potential Stragglers to a different node, the speculative execution (SE) realizes to improve the probability of finishing those backup tasks before the original ones. The Speculative execution (SE) applies this principle and thus proposed a solution to handle the Straggling tasks. At present, the performance of the Hadoop system is unsatisfying because of the erroneous judgement and inappropriate selection for the backup nodes in the current SE policy. This paper proposes an SE optimized strategy which can be used in prediction of near data. In this strategy, the first step is gathering the real-time task execution information and the remaining runtime required for the task is predicted by a local prediction method. Then it chooses a proper backup node according to the near data and actual demand in the second step. On the other side, this model also includes a cost-effective model in order to make the performance of SE to the peak. The results show that using this strategy in Hadoop effectively improves the accuracy of alternative tasks and effects better in heterogeneous Hadoop environments in various situations, which is beneficial to consumers and cloud platform.

show abstract

Cluster Performance by Dynamic Load and Resource-Aware Speculative Execution

Mathew¹

2021

Inventive Systems and Control

View full text Add to dashboard Cite

Optimization for Speculative Execution in Big Data Processing Clusters

Cited by 26 publications

References 25 publications

Chronos: A Unifying Optimization Framework for Speculative Execution of Deadline-Critical MapReduce Jobs

Chronos: A Unifying Optimization Framework for Speculative Execution of Deadline-Critical MapReduce Jobs

Near-Data Prediction Based Speculative Optimization in a Distribution Environment

Cluster Performance by Dynamic Load and Resource-Aware Speculative Execution

Contact Info

Product

Resources

About