计算机科学 ›› 2017, Vol. 44 ›› Issue (6): 17-22.doi: 10.11896/j.issn.1002-137X.2017.06.003

• 2016 年全国信息存储技术学术年会 • 上一篇    下一篇

异构存储感知的Ceph存储系统数据放置方法

刘飞,蒋德钧,张欢,陈静,王筠,熊劲   

  1. 中国科学院计算技术研究所 北京100190,中国科学院计算技术研究所 北京100190,中国科学院计算技术研究所 北京100190,山东省计算中心国家超级计算济南中心山东省计算机网络重点实验室 济南250101;山东科技大学计算机科学与工程学院 青岛266590,山东省计算中心国家超级计算济南中心山东省计算机网络重点实验室 济南250101,中国科学院计算技术研究所 北京100190
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受山东省计算机网络重点实验室开放课题基金(SDKLCN-2013-01),山东省自然科学基金项目(ZR2016FM41),国家青年自然科学基金项目(61502448)资助

Heterogeneous Storage Aware Data Placement of Ceph Storage System

LIU Fei, JIANG De-jun, ZHANG Huan, CHEN Jing, WANG Jun and XIONG Jin   

  • Online:2018-11-13 Published:2018-11-13

摘要: Ceph分布式存储系统正成为广泛使用的开源云环境存储解决方案。异构存储如果应用有效的数据管理策略,则能够在保持低成本的同时提供大容量和高性能存储。在Ceph中使用异构存储设备不能有效发挥异构存储设备的性能,由于数据的多个副本可以存放到不同的存储介质中,因此不同的副本组合的性能和成本都不一样。针对Ceph提出一种面向异构存储的数据放置方法,通过划分多种不同的副本组合,根据数据热度和读写比例将不同的数据放到不同的副本组合上,在提升系统性能的同时有效地控制了系统容量成本。

关键词: 异构存储,数据放置,副本,Ceph

Abstract: Ceph distributed storage system is becoming a widely used open source cloud storage solution.Heterogeneous storage can provide large capacity and high performance storage while maintaining low cost if it uses an effective data management strategy.Using heterogeneous storage devices in Ceph currently cannot effectively exploit the performance of heterogeneous storage devices.Since multiple replicas of the data can be stored in different storage media,the performance and cost of different device combinations for multiple replicas are not the same.In this paper,a data placement method was proposed for heterogeneous storage based on Ceph.The method puts different data on different replica combination based on the access intensity and read/write ratio,which can effectively improve the system performance while controlling the cost of the system.

Key words: Heterogeneous storage,Data placement,Replicas,Ceph

[1] WEIL S A,BRANDT S A,MILLER E L,et al.Ceph:A scalable,high-performance distributed file system[C]∥Proceedings of the 7th Symposium on Operating Systems Design and Implementation.USENIX Association,2006:307-320.
[2] WEIL S A,BRANDT S A,MILLER E L,et al.CRUSH:Controlled,scalable,decentralized placement of replicated data[C]∥Proceedings of the 2006 ACM/IEEE Conference on Supercomputing.ACM,2006:122.
[3] WEIL S A,LEUNG A W,BRANDT S A,et al.Rados:a scalable,reliable storage service for petabyte-scale storage clusters[C]∥Proceedings of the 2nd International Workshop on Petascale Data Storage:Held in conjunction with Supercomputing’07.ACM,2007:35-44.
[4] PARK D,DU D H C.Hot data identification for flash-basedstorage systems using multiple bloom filters[C]∥2011 IEEE 27th Symposium on Mass Storage Systems and Technologies (MSST).IEEE,2011:1-11.
[5] CAI Y J,KANG C K,WU C H.A virtual storage environment for SSDs and HDDs in Xen hypervisor[C]∥ACM SIGBED.2014:39-44.
[6] fio.http://freecode.com/projects/fio/.
[7] TPC-WHomepage.http://www.tpc.org/tpcw/.
[8] Block I/O Traces.http://iotta.snia.org/traces/.
[9] FlashCache.https://github.com/facebook/flashcache.
[10] KLONATOS Y,MAKATOS T,MARAZAKIS M,et al.Azor:using two-level block selection to improve SSD-based I/O caches[C]∥2011 6th IEEE International Conference on En Networking,Architecture and Storage (NAS).IEEE,2011:309-318.
[11] CHEN F,JIANG S,ZHANG X.SmartSaver:turning flash drive into a disk energy saver for mobile computers[C]∥International Symposium on Low Power Electronics and Design,2006(ISLPED’06).IEEE,2006:412-417.
[12] KHATIB M G,VAN DER ZWAAG B J,Hartel P H,et al.Interposing flash between disk and DRAM to save energy for streaming workloads[C]∥IEEE/ACM/IFIP Workshop on Embedded Systems for Real-Time Multimedia,2007(ESTIMedia 2007).IEEE,2007:7-12.
[13] KIM Y,GUPTA A,URGAONKAR B,et al.HybridStore:acost-efficient,high-performance storage system combining SSDs and HDDs[C]∥2011 IEEE 19th International Symposium on Modeling,Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS).IEEE,2011:227-236.
[14] STRUNK,JON D.Hybrid Aggregates:Combining SSDs andHDDs in a single storage pool[J].ACM SIGOPS Operating Systems Review,2012,46(3):50-56.
[15] CHEN F,KOUFATY D A,ZHANG X D.Hystor:making the best use of solid state drives in high performance storage systems[C]∥Proceedings of the International Conference on Supercomputing.ACM,2011:22-32.
[16] LUO T,LEE R,MESNIER M,et al.hStorage-DB:heterogeneity-aware data management to exploit the full capability of hybrid storage systems[J].Proceedings of the VLDB Endowment,2012,5(10):1076-1087.
[17] JO H,KWON Y,KIM H,et al.SSD-HDD-hybrid virtual disk in consolidated environments[M]∥En Euro-Par 2009-Parallel Processing Workshops.Springer Berlin Heidelberg,2010:375-384.
[18] LIN L,et al.Hot random off-loading:a hybrid storage system with dynamic data migration[C]∥2011 IEEE 19th International Symposium on En Modeling,Analysis & Simulation of Compu-ter and Telecommunication Systems (MASCOTS).IEEE,2011:318-325.
[19] AWASTHI A,NANDINI A,Bhattacharya A,et al.HybridHBase:Leveraging flash SSDs to improve cost per throughput of HBase[C]∥Proceedings of the 18th International Conference on Management of Data.Computer Society of India,2012:68-79.
[20] KRISH K R,ANWAR A,BUTT A R.hatS:A heterogeneity-aware tiered storage for Hadoop[C]∥2014 14th IEEE/ACM International Symposium on Cluster,Cloud and Grid Computing (CCGrid).IEEE,2014:502-511.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .