Predicting the Cache Performance Benefits for In-memory Data Analytics Frameworks

목차 (Table of Contents)

• 요약
• Abstract
• 1. 서론
• 2. 관련 연구
• 3. 기존 프레임워크 시간 측정의 한계점
• 4. 연산비용모델 기반 캐시 성능 예측
• 5. 정확도 평가
• 6. 결론 및 향후 계획
• References

참고문헌 (Reference)

1 A. Nasu, "Transparent In-memory Cache Management in Apache Spark based on Post-Mortem Analysis" 3388-3396, 2019

2 J. D. T. X. Shengsheng Huang, "The hibench benchmark suite: Characterization of the mapreduce-based data analysis" 41-51, 2010

3 Adrian Daniel Popescu, "PREDIcT: Towards Predicting the Runtime of Large Scale Iterative Analytics" 6 (6): 2013

4 S. Sidhanta, "OptEx: A Deadline-Aware Cost Optimization Model for Spark" 193-202, 2016

5 A. Shinnar, "M3r: Increased performance for in-memory hadoop jobs" 5 (5): 1736-1747, 2012

6 A. D. Ferguson, "Jockey: Guaranteed job latency in data parallel clusters" 99-112, 2012

7 S. Venkataraman, "Ernest:Efficient performance prediction for large-scale advanced analytics" 363-378, 2016

8 Michael Isard, "Dryad: Distributed Data-Parallel Programs from Sequential Building Blocks" 41 (41): 59-72, 2007

9 M. Jeong, "Caching Benefit Prediction Model for In-memory Analytics Framework" 1198-1200, 2020

10 Vinicius M. Gottin, "Automatic Caching Decision for Scientific Dataflow Execution in Apache Spark" 1-10, 2018

11 "Apache Tez"

12 "Apache Spark"

13 "Apache Hadoop"