高效支持负载聚合的程序资源敏感度获取及分析方法

王琳 1; 钱德沛 1; 2; 王锐 1; 栾钟治 1; 魏光 1

doi:10.7652/xjtuxb201704012

您当前的位置：

首页 >

文章列表页 >

高效支持负载聚合的程序资源敏感度获取及分析方法

更新时间：2025-07-09

- 高效支持负载聚合的程序资源敏感度获取及分析方法
- A Method for Acquiring and Analyzing Program Resource Sensitivity for Workload Consolidation
- 西安交通大学学报 2017年51卷第4期页码：79-84
- 作者机构：
  
  北京航空航天大学计算机学院,北京,100191
- 作者简介：
- 基金信息：
  
  : 2016-11-06。作者简介: 王琳(1982—),女,博士生;王锐(通信作者),男,讲师。基金项目: 国家重点基础研究发展计划资助项目(2016YFB1000503);国家自然科学基金资助项目(61133004,61361126011,61502019)
- DOI：10.7652/xjtuxb201704012
  中图分类号： TP303
- 网络首发：2017-04-10，
  
  纸质出版：2017
- 稿件说明：
移动端阅览
王琳 1, 钱德沛 1, 2, 等. 高效支持负载聚合的程序资源敏感度获取及分析方法[J]. 西安交通大学学报, 2017,51(4):79-84.

A Method for Acquiring and Analyzing Program Resource Sensitivity for Workload Consolidation[J]. 2017, 51(4): 79-84.
王琳 1, 钱德沛 1, 2, 等. 高效支持负载聚合的程序资源敏感度获取及分析方法[J]. 西安交通大学学报, 2017,51(4):79-84. DOI： 10.7652/xjtuxb201704012.

A Method for Acquiring and Analyzing Program Resource Sensitivity for Workload Consolidation[J]. 2017, 51(4): 79-84. DOI： 10.7652/xjtuxb201704012.

摘要

针对集群或数据中心中负载聚合导致的程序和系统性能不稳定的问题

提出一种程序资源敏感度获取及分析方法。该方法利用Linux中的Cgroups机制设置可调整资源大小的控制组

并让程序在控制组内执行

获得程序在资源受限时的性能; 将程序在多个资源限制下的敏感度表示成敏感度超平面

从而预测程序协同执行时的性能; 将程序所需的资源按照重要程度排序以帮助集群调度。实验结果表明

该方法预测出的敏感度与真实值的平均绝对误差为0.093。与最小负载的簇级调度策略相比

利用程序资源敏感度信息的调度策略可以提升程序性能22.2%

还可以提升磁盘读写带宽利用率和网络带宽的利用率

程序资源敏感度能够高效地支持负载聚合。

Abstract

A method for acquiring and analyzing program resource sensitivity is proposed to deal with the problem that the performances of programs and systems are unstable due to workload consolidation in clusters or data centers. A control group with tunable resources is set up by using Cgroups in Linux

and programs are executed in the control group under various resource conditions. The performance of programs within limited resources is obtained and used for calculating the resource sensitivity. The sensitivity values of programs under restriction of multiple resources form a sensitivity hyperplane to predict the performance of co-running programs. The resources required by a program are reordered according to their importance for cluster scheduling. Experimental results show that the average absolute error between the real sensitivity value and the sensitivity value predicted by the method is 0.093. A comparison with the common least load scheduling strategy shows that the scheduling strategy using resource sensitivity aware improves program performance by 22.2% and enhances both disk I/O and network I/O utilization. It also shows the contribution of program resource sensitivity to workload consolidation.

关键词

Keywords

references

张伟, 宋莹, 阮利, 等. 面向Internet数据中心的资源管理 [J]. 软件学报, 2012, 23(2): 179-199.

ZHANG Wei, SONG Ying, RUAN Li, et al. Resource management in Internet-oriented data centers [J]. Journal of Software, 2012, 23(2): 179-199.

STANSBERRY M, KUDRITZKI J. Uptime institute 2012 data center industry survey [EB/OL].(2012-07-11)[2016-07-01]. http: ∥www.etherworks.com.au/index.php?option=com_k2Itemid=230id=91_2276d1f6c67a40bd451926a7ab5ccc49lang=entask=downloadview=item.

ZHURAVLEV S, BLAGODUROV S, FEDOROVA A. Addressing shared resource contention in multicore processors via scheduling [J]. ACM SIGARCH Computer Architecture News, 2010, 45(3): 129-142.

MORETO M, CAZORLA F J, RAMIREZ A, et al. FlexDCP: a QoS framework for CMP architectures [J]. ACM SIGOPS Operating Systems Review, 2009, 43(2): 86-96.

NATHUJI R, KANSAL A, GHAFFARKHAH A. Q-clouds: managing performance interference effects for QoS-aware clouds [C]∥Proceedings of the 5th European Conference on Computer Systems. New York, USA: ACM, 2010: 237-250.

DWYER T, FEDOROVA A, BLAGODUROV S, et al. A practical method for estimating performance degradation on multicore processors, and its application to HPC workloads [C]∥Proceedings of the 12th International Conference on High Performance Computing, Networking, Storage and Analysis. Piscataway, NJ, USA: IEEE, 2012: 1-11.

PACHECO-SANCHEZ S, CASALE G, SCOTNEY B, et al. Markovian workload characterization for QoS prediction in the cloud [C]∥Proceedings of the 2011 IEEE International Conference on Cloud Computing. Piscataway, NJ, USA: IEEE, 2011: 147-154.

薛正华, 刘伟哲, 董小社, 等. 基于思维进化的集群作业调度方法研究 [J]. 西安交通大学学报, 2008, 42(6): 651-655.

XUE Zhenghua, LIU Weizhe, DONG Xiaoshe, et al. Research on mind evolutionary computation based job scheduling for server clusters [J]. Journal of Xi'an Jiaotong University, 2008, 42(6): 651-655.

MARS J, TANG L, HUNDT R, et al. Bubble-up: increasing utilization in modern warehouse scale computers via sensible co-locations [C]∥Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture. New York, USA: ACM, 2011: 248-259.

YANG Hailong, BRESLOW A, MARS J, et al. Bubble-flux: precise online QoS management for increased utilization in warehouse scale computers [J]. ACM SIGARCH Computer Architecture News, 2013, 41(3): 607-618.

DELIMITROU C, KOZYRAKIS C. Paragon: Qos-aware scheduling for heterogeneous datacenters [C]∥Proceedings of the 18th International Conference on Architectural Support for Programming Languages and Operating Systems. New York, USA: ACM, 2013: 77-88.

DELIMITROU C, KOZYRAKIS C. Quasar: resource-efficient and QoS-aware cluster management [C]∥Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems. New York, USA: ACM, 2014: 127-144.

TANG Lingjia, MARS J, SOFFA M. Contentiousness vs. sensitivity: improving contention aware runtime systems on multicore architectures [C]∥Proceedings of the First International Workshop on Adaptive Self-Tuning Computing Systems for the Exaflop Era. New York, USA: ACM, 2011: 12-21.

HAN J, CHOI Y, HUN J, et al. Interference management for distributed parallel applications in consolidated clusters [C]∥Proceedings of the 21th International Conference on Architectural Support for Programming Languages and Operating Systems. New York, USA: ACM, 2016: 443-456.

LO D, CHENG Liqun, GOVINDARAJU R, et al. Heracles: improving resource efficiency at scale [J]. ACM SIGARCH Computer Architecture News, 2015, 43(3): 450-462.

MENAGE P. CGROUPS [EB/OL].(2016-08-08)[2016-09-08]. https: ∥www.kernel.org/doc/Documentation/cgroup-v1/cgroups.txt.

KUZNETSOV A N. TC(8)[EB/OL].(2012-05-19)[2015-01-21]. http: ∥lartc.org/manpages/tc.txt.

NAS Organization. The NASA advanced supercomputing division [EB/OL].(2016-03-21)[2016-03-25]. http: ∥www.nas.nasa.gov/publications/npb.html.

System Performance Evaluation Cooperative. SPEC CPU 2006 [EB/OL].(2007-04-03)[2012-01-11]. http: ∥www.spec.org/cpu2006/.

CloudSuite. A benchmark suite for cloud services [EB/OL].(2016-09-27)[2016-09-30]. http: ∥parsa. epfl.ch/cloudsuite/cloudsuite.html.

AKOPYTOV. SysBench [EB/OL].(2016-02-01)[2016-02-21]. https: ∥github.com/akopytov/sysbench.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

混合电解槽阵列协同的风光耦合制氢系统双层多目标优化

超临界水异常区域热力学特性研究

隧道内燃料电池汽车氢气泄漏扩散特性及影响因素

张角凹坑气膜孔对双层壁气膜冷却特性的影响

电动车辆间接热系统快速除湿响应迟滞机理及优化控制策略