一种采用纠删码缓存的高能效且可靠的存储系统（英文）
|
摘要
在现代的多副本节能存储系统中,主副本的磁盘总是保持着开启以对外提供服务,而其他副本的磁盘则可以在负载低时保持关闭状态以节能。然而,因为新的写请求不能够被立即同步到所有的磁盘上,所以系统的可靠性被降低了。本文中,我们设计了一个基于RAID10的具有高可靠性和高能效的副本存储系统——RERAID。RERAID使用主副本磁盘上的一部分空闲空间结合纠删码构造了一个编码缓存来接收新的写请求。因为通过使用纠删码,编码缓存能够支持2个甚至更多磁盘的故障恢复,所以RERAID能够保证与RAID10存储系统想当的可靠性。另外,我们还设计了一个纠删码写(erasure coding write,ECW)算法来缓存那些小的随机写,并把它们合并成大的写数据块,然后并行写入编码缓存中以提高写性能。实验结果显示RERAID相比现有的方案能够提高写性能并且节省更多的能源。
In modern energy-saving replication storage systems, a primary group of disks is always powered up to serve incoming requests while other disks are often spun down to save energy during slack periods. However,since new writes cannot be immediately synchronized into all disks, system reliability is degraded. In this paper,we develop a high-reliability and energy-efficient replication storage system, named RERAID, based on RAID10.RERAID employs part of the free space in the primary disk group and uses erasure coding to construct a code cache at the front end to absorb new writes. Since code cache supports failure recovery of two or more disks by using erasure coding, RERAID guarantees a reliability comparable with that of the RAID10 storage system. In addition, we develop an algorithm, called erasure coding write(ECW), to buffer many small random writes into a few large writes, which are then written to the code cache in a parallel fashion sequentially to improve the write performance. Experimental results show that RERAID significantly improves write performance and saves more energy than existing solutions.
In modern energy-saving replication storage systems, a primary group of disks is always powered up to serve incoming requests while other disks are often spun down to save energy during slack periods. However,since new writes cannot be immediately synchronized into all disks, system reliability is degraded. In this paper,we develop a high-reliability and energy-efficient replication storage system, named RERAID, based on RAID10.RERAID employs part of the free space in the primary disk group and uses erasure coding to construct a code cache at the front end to absorb new writes. Since code cache supports failure recovery of two or more disks by using erasure coding, RERAID guarantees a reliability comparable with that of the RAID10 storage system. In addition, we develop an algorithm, called erasure coding write(ECW), to buffer many small random writes into a few large writes, which are then written to the code cache in a parallel fashion sequentially to improve the write performance. Experimental results show that RERAID significantly improves write performance and saves more energy than existing solutions.
引文
Amazon,2007.Amazon S3:Object Storage Built to Store and Retrieve Any Amount of Data from Anywhere.http://aws.amazon.com/s3/
Amur,H.,Cipar,J.,Gupta,V.,et al.,2010.Robust and flexible power-proportional storage.Proc.1st ACMSymp.on Cloud Computing,p.217-228.https://doi.org/10.1145/1807128.1807164
Bhadkamkar,M.,Guerra,J.,Useche,L.,et al.,2009.BORG:Block-re ORGanization for self-optimizing storage systems.Proc.Usenix Conf.on File and Storage Technologies,p.183-196.
Blaum,M.,Brady,J.,Bruck,J.,et al.,1994.EVENODD:an optimal scheme for tolerating double disk failures in RAID architectures.Proc.21st Int.Symp.on Computer Architecture,p.245-254.https://doi.org/10.1109/isca.1994.288145
Borthaku,D.,2010.What is Apache Hadoop?http://hadoop.apache.org/
Chen,Y.,Hsu,W.,Young,H.,2000.Logging RAID-an approach to fast,reliable,and low-cost disk arrays.Euro-Par,p.1302-1312.https://doi.org/10.1007/3-540-44520-x_182
Colarelli,D.,Grunwald,D.,2002.Massive arrays of idle disks for storage archives.Proc.ACM/IEEE Conf.on Supercomputing,p.1-11.https://doi.org/10.1109/sc.2002.10058
Corbett,P.,English,B.,Goel,A.,et al.,2004.Row-diagonal parity for double disk failure correction.Proc.3rd USENIX Conf.on File and Storage Technologies,p.1-14.
Department of Energy,2012.NETL shares computing speed,efficiency to tackle barriers.Fossil Energy Today,1(6):1-3.
EMC,2008.ATMOS:Big.Smart.Elastic.http://www.emc.com/storage/atmos/atmos.htm
Eom,H.,Hollingsworth,J.K.,2000.Speed vs.accuracy in simulation for I/O-intensive applications.Proc.14th Int.Parallel and Distributed Processing Symp.,p.315-322 .https://doi.org/10.1109/ipdps.2000.846001
Ghemawat,S.,Gobioff,H.,Leung,S.,2003.The Google File System.Proc.19th ACM Symp.on Operating Systems Principles,p.29-43.https://doi.org/10.1145/945445.945450
Hu,Y.,Yang,Q.,1996.DCD—disk caching disk:a new approach for boosting I/O performance.ACM SIGARCH Comput.Archit.News,24(2):169-178.https://doi.org/10.1145/232974.232991
Li,D.,Wang,J.,2004.EERAID:energy-efficient redundant and inexpensive disk array.Proc.11th ACM SIGOPS European Workshop,p.29.https://doi.org/10.1145/1133572.1133577
Li,D.,Wang,J.,2006.eR AID:a queuing model based energy saving policy.Proc.IEEE Int.Symp.on Modeling,Analysis,and Simulation of Computer and Telecommunication Systems,p.77-86.https://doi.org/10.1109/mascots.2006.23
Lu,L.,Varman,P.J.,Wang,J.,2007.DiskG roup:energy efficient disk layout for RAID1 systems.Proc.Int.Conf.on Networking,Architecture,and Storage,p.233-242 .https://doi.org/10.1109/nas.2007.21
Mao,B.,Feng,D.,Jiang,H.,et al.,2008.GRAID:a green RAID storage architecture with improved energy efficiency and reliability.Proc.IEEE Int.Symp.on Modeling,Analysis,and Simulation of Computer and Telecommunication Systems,p.113-120.https://doi.org/10.1109/mascot.2008.4770574
Menon,J.,1995.A performanee comparison of RAID-5 and log-struetured arrays.Proc.4th IEEE In.Symp.on High Performance Distributed Computing,p.167-178.https://doi.org/10.1109/hpdc.1995.518707
Patterson,D.A.,Gibson,G.,Katz,R.H.,1988.A case for redundant arrays of inexpensive disks(RAID).Proc.ACM SIGMOD Int.Conf.on Management of Data,p.109-116.https://doi.org/10.1145/971701.50214
Plank,J.S.,Xu,L.H.,2006.Optimizing Cauchy ReedSolomon codes for fault-tolerant storage applications.Proc.5th Int.Symp.on Network Computing and Applications,p.173-180.https://doi.org/10.1109/nca.2006.43
Pinheiro,E.,Bianchini,R.,2004.Energy conservation techniques for disk array-based servers.Proc.18th Annual Int.Conf.on Supercomputing,p.68-78.https://doi.org/10.1145/1006209.1006220
Pinheiro,E.,Weber,W.D.,Barroso,L.A.,2007.Failure trends in a large disk drive population.Proc.5th USENIX Conf.on File and Storage Technologies,p.17-28.
Soundararajan,G.,Prabhakaran,V.,Balakrishnan,M.,et al.,2010.Extending SSD lifetimes with disk-based write caches.Proc.8th USENIX Conf.on File and Storage Technologies,p.101-114.
Stodolsky,D.,Gibson,G.,Holland,M.,1993.Parity logging overcoming the small write problem in redundant disk arrays.ACM SIGARCH Comput.Architect.News,21(2):64-75.https://doi.org/10.1145/173682.165143
Thereska,E.,Donnelly,A.,Narayanan,D.,2011.Sierra:practical power-proportionality for data center storage.Proc.6th Conf.on Computer Systems,p.169-182.https://doi.org/10.1145/1966445.1966461
Wang,J.,Zhu,H.J.,Li,D.,2008.eR AID:conserving energy in conventional disk-based RAID system.IEEE Trans.Comput.,57(3):359-374.https://doi.org/10.1109/tc.2007.70821
Weil,S.,Brandt,S.A.,Miller,E.L.,et al.,2006.Ceph:a scalable,high-performance distributed file system.Proc.7 th Conf.on Operating Systems Design and Implementation,p.307-320.
Wilkes,J.,Golding,R.,Staelin,R.,et al.,1996.The HP AutoR AID hierarchical storage system.ACM Trans.Comput.Syst.,14(1):108-136.https://doi.org/10.1145/225535.225539
Xin,Q.,Miller,E.L.,Schwarz,T.,et al.,2003.Reliability mechanisms for very large storage systems.Proc.20th IEEE/11th NASA Goddard Conf.on Mass Storage Systems and Technologie,p.146-156.https://doi.org/10.1109/mass.2003.1194851
Xu,L.H.,Bruck,J.,1999.X-code:MDS array codes with optimal encoding.IEEE Trans.Inform.Theory,45 (1):272-276.https://doi.org/10.1109/18.746809
Yue,Y.,Tian,L.,Jiang,H.,et al.,2010.RoL o:a rotated logging storage architecture for enterprise data centers.Proc.IEEE 30th Int.Conf.on Distributed Computing Systems,p.293-304.https://doi.org/10.1109/ICDCS.2010.22
Yue,Y.,He,B.,Tian,L.,et al.,2016.Rotated logging storage architectures for data centers:models and optimizations.IEEE Trans.Comput.,65(1):203-215.https://doi.org/10.1109/tc.2015.2417539
Zhu,Q.,Chen,Z.,Tan,L.,et al.,2005.Hibernator:helping disk arrays sleep through the winter.Proc.20th ACM Symp.on Operating Systems Principles,p.177-190.https://doi.org/10.1145/1095809.1095828
Amur,H.,Cipar,J.,Gupta,V.,et al.,2010.Robust and flexible power-proportional storage.Proc.1st ACMSymp.on Cloud Computing,p.217-228.https://doi.org/10.1145/1807128.1807164
Bhadkamkar,M.,Guerra,J.,Useche,L.,et al.,2009.BORG:Block-re ORGanization for self-optimizing storage systems.Proc.Usenix Conf.on File and Storage Technologies,p.183-196.
Blaum,M.,Brady,J.,Bruck,J.,et al.,1994.EVENODD:an optimal scheme for tolerating double disk failures in RAID architectures.Proc.21st Int.Symp.on Computer Architecture,p.245-254.https://doi.org/10.1109/isca.1994.288145
Borthaku,D.,2010.What is Apache Hadoop?http://hadoop.apache.org/
Chen,Y.,Hsu,W.,Young,H.,2000.Logging RAID-an approach to fast,reliable,and low-cost disk arrays.Euro-Par,p.1302-1312.https://doi.org/10.1007/3-540-44520-x_182
Colarelli,D.,Grunwald,D.,2002.Massive arrays of idle disks for storage archives.Proc.ACM/IEEE Conf.on Supercomputing,p.1-11.https://doi.org/10.1109/sc.2002.10058
Corbett,P.,English,B.,Goel,A.,et al.,2004.Row-diagonal parity for double disk failure correction.Proc.3rd USENIX Conf.on File and Storage Technologies,p.1-14.
Department of Energy,2012.NETL shares computing speed,efficiency to tackle barriers.Fossil Energy Today,1(6):1-3.
EMC,2008.ATMOS:Big.Smart.Elastic.http://www.emc.com/storage/atmos/atmos.htm
Eom,H.,Hollingsworth,J.K.,2000.Speed vs.accuracy in simulation for I/O-intensive applications.Proc.14th Int.Parallel and Distributed Processing Symp.,p.315-322 .https://doi.org/10.1109/ipdps.2000.846001
Ghemawat,S.,Gobioff,H.,Leung,S.,2003.The Google File System.Proc.19th ACM Symp.on Operating Systems Principles,p.29-43.https://doi.org/10.1145/945445.945450
Hu,Y.,Yang,Q.,1996.DCD—disk caching disk:a new approach for boosting I/O performance.ACM SIGARCH Comput.Archit.News,24(2):169-178.https://doi.org/10.1145/232974.232991
Li,D.,Wang,J.,2004.EERAID:energy-efficient redundant and inexpensive disk array.Proc.11th ACM SIGOPS European Workshop,p.29.https://doi.org/10.1145/1133572.1133577
Li,D.,Wang,J.,2006.eR AID:a queuing model based energy saving policy.Proc.IEEE Int.Symp.on Modeling,Analysis,and Simulation of Computer and Telecommunication Systems,p.77-86.https://doi.org/10.1109/mascots.2006.23
Lu,L.,Varman,P.J.,Wang,J.,2007.DiskG roup:energy efficient disk layout for RAID1 systems.Proc.Int.Conf.on Networking,Architecture,and Storage,p.233-242 .https://doi.org/10.1109/nas.2007.21
Mao,B.,Feng,D.,Jiang,H.,et al.,2008.GRAID:a green RAID storage architecture with improved energy efficiency and reliability.Proc.IEEE Int.Symp.on Modeling,Analysis,and Simulation of Computer and Telecommunication Systems,p.113-120.https://doi.org/10.1109/mascot.2008.4770574
Menon,J.,1995.A performanee comparison of RAID-5 and log-struetured arrays.Proc.4th IEEE In.Symp.on High Performance Distributed Computing,p.167-178.https://doi.org/10.1109/hpdc.1995.518707
Patterson,D.A.,Gibson,G.,Katz,R.H.,1988.A case for redundant arrays of inexpensive disks(RAID).Proc.ACM SIGMOD Int.Conf.on Management of Data,p.109-116.https://doi.org/10.1145/971701.50214
Plank,J.S.,Xu,L.H.,2006.Optimizing Cauchy ReedSolomon codes for fault-tolerant storage applications.Proc.5th Int.Symp.on Network Computing and Applications,p.173-180.https://doi.org/10.1109/nca.2006.43
Pinheiro,E.,Bianchini,R.,2004.Energy conservation techniques for disk array-based servers.Proc.18th Annual Int.Conf.on Supercomputing,p.68-78.https://doi.org/10.1145/1006209.1006220
Pinheiro,E.,Weber,W.D.,Barroso,L.A.,2007.Failure trends in a large disk drive population.Proc.5th USENIX Conf.on File and Storage Technologies,p.17-28.
Soundararajan,G.,Prabhakaran,V.,Balakrishnan,M.,et al.,2010.Extending SSD lifetimes with disk-based write caches.Proc.8th USENIX Conf.on File and Storage Technologies,p.101-114.
Stodolsky,D.,Gibson,G.,Holland,M.,1993.Parity logging overcoming the small write problem in redundant disk arrays.ACM SIGARCH Comput.Architect.News,21(2):64-75.https://doi.org/10.1145/173682.165143
Thereska,E.,Donnelly,A.,Narayanan,D.,2011.Sierra:practical power-proportionality for data center storage.Proc.6th Conf.on Computer Systems,p.169-182.https://doi.org/10.1145/1966445.1966461
Wang,J.,Zhu,H.J.,Li,D.,2008.eR AID:conserving energy in conventional disk-based RAID system.IEEE Trans.Comput.,57(3):359-374.https://doi.org/10.1109/tc.2007.70821
Weil,S.,Brandt,S.A.,Miller,E.L.,et al.,2006.Ceph:a scalable,high-performance distributed file system.Proc.7 th Conf.on Operating Systems Design and Implementation,p.307-320.
Wilkes,J.,Golding,R.,Staelin,R.,et al.,1996.The HP AutoR AID hierarchical storage system.ACM Trans.Comput.Syst.,14(1):108-136.https://doi.org/10.1145/225535.225539
Xin,Q.,Miller,E.L.,Schwarz,T.,et al.,2003.Reliability mechanisms for very large storage systems.Proc.20th IEEE/11th NASA Goddard Conf.on Mass Storage Systems and Technologie,p.146-156.https://doi.org/10.1109/mass.2003.1194851
Xu,L.H.,Bruck,J.,1999.X-code:MDS array codes with optimal encoding.IEEE Trans.Inform.Theory,45 (1):272-276.https://doi.org/10.1109/18.746809
Yue,Y.,Tian,L.,Jiang,H.,et al.,2010.RoL o:a rotated logging storage architecture for enterprise data centers.Proc.IEEE 30th Int.Conf.on Distributed Computing Systems,p.293-304.https://doi.org/10.1109/ICDCS.2010.22
Yue,Y.,He,B.,Tian,L.,et al.,2016.Rotated logging storage architectures for data centers:models and optimizations.IEEE Trans.Comput.,65(1):203-215.https://doi.org/10.1109/tc.2015.2417539
Zhu,Q.,Chen,Z.,Tan,L.,et al.,2005.Hibernator:helping disk arrays sleep through the winter.Proc.20th ACM Symp.on Operating Systems Principles,p.177-190.https://doi.org/10.1145/1095809.1095828