Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Leveraging Glocality for Fast Failure Recovery in Distributed RAM Storage

Leveraging Glocality for Fast Failure Recovery in Distributed RAM Storage Distributed RAM storage aggregates the RAM of servers in data center networks (DCN) to provide extremely high I/O performance for large-scale cloud systems. For quick recovery of storage server failures, MemCube [53] exploits the proximity of the BCube network to limit the recovery traffic to the recovery servers’ 1-hop neighborhood. However, the previous design is applicable only to the symmetric BCube(n,k) network with nk+1 nodes and has suboptimal recovery performance due to congestion and contention. To address these problems, in this article, we propose CubeX, which (i) generalizes the “1-hop” principle of MemCube for arbitrary cube-based networks and (ii) improves the throughput and recovery performance of RAM-based key-value (KV) store via cross-layer optimizations. At the core of CubeX is to leverage the glocality (= globality + locality) of cube-based networks: It scatters backup data across a large number of disks globally distributed throughout the cube and restricts all recovery traffic within the small local range of each server node. Our evaluation shows that CubeX not only efficiently supports RAM-based KV store for cube-based networks but also significantly outperforms MemCube and RAMCloud in both throughput and recovery time. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Storage (TOS) Association for Computing Machinery

Leveraging Glocality for Fast Failure Recovery in Distributed RAM Storage

Download PDF
24 pages

Loading next page...
 
/lp/association-for-computing-machinery/leveraging-glocality-for-fast-failure-recovery-in-distributed-ram-5A0T6HDqw8
Publisher
Association for Computing Machinery
Copyright
Copyright © 2019 ACM
ISSN
1553-3077
eISSN
1553-3093
DOI
10.1145/3289604
Publisher site
See Article on Publisher Site

Abstract

Distributed RAM storage aggregates the RAM of servers in data center networks (DCN) to provide extremely high I/O performance for large-scale cloud systems. For quick recovery of storage server failures, MemCube [53] exploits the proximity of the BCube network to limit the recovery traffic to the recovery servers’ 1-hop neighborhood. However, the previous design is applicable only to the symmetric BCube(n,k) network with nk+1 nodes and has suboptimal recovery performance due to congestion and contention. To address these problems, in this article, we propose CubeX, which (i) generalizes the “1-hop” principle of MemCube for arbitrary cube-based networks and (ii) improves the throughput and recovery performance of RAM-based key-value (KV) store via cross-layer optimizations. At the core of CubeX is to leverage the glocality (= globality + locality) of cube-based networks: It scatters backup data across a large number of disks globally distributed throughout the cube and restricts all recovery traffic within the small local range of each server node. Our evaluation shows that CubeX not only efficiently supports RAM-based KV store for cube-based networks but also significantly outperforms MemCube and RAMCloud in both throughput and recovery time.

Journal

ACM Transactions on Storage (TOS) – Association for Computing Machinery

Published: Feb 18, 2019

Keywords: Globality

References

  • Summary of the Amazon EC2 and Amazon RDS Service Disruption in the US East Region
    Team, AWS
  • Ursa Block Store
    Lab, NiceX
  • Redis Official Website
    RedisLabs,
  • HDFS Architecture Guide
    Borthakur, Dhruba
  • SOSP 2011 Reviews and Comments on RAMCloud
    SOSP,
  • Samsung SSD 960 EVO (500GB)
    Norem, Josh
  • Failure Rates in Google Data Centers
    Miller, Rich
  • Memcached Official Website
    Dormando,
  • A performance analysis of the iSCSI protocol
    Aiken, Stephen; Grunwald, Dirk; Pleszkun, Andrew R.; Willeke, Jesse
  • Cheap and large CAMs for high performance data-intensive networked systems
    Anand, Ashok; Muthukrishnan, Chitra; Kappes, Steven; Akella, Aditya; Nath, Suman
  • FAWN: A fast array of wimpy nodes
    Andersen, David G.; Franklin, Jason; Kaminsky, Michael; Phanishayee, Amar; Tan, Lawrence; Vasudevan, Vijay
  • {n
    Antirez,
  • Kernel korner: Ata over ethernet: Putting hard drives on the lan
    Cashin, Ed L.
  • Bigtable: A distributed storage system for structured data
    Chang, Fay; Dean, Jeffrey; Ghemawat, Sanjay; Hsieh, Wilson C.; Wallach, Deborah A.; Burrows, Michael; Chandra, Tushar; Fikes, Andrew; Gruber, Robert
  • Optimistic crash consistency
    Chidambaram, Vijay; Pillai, Thanumalayan Sankaranarayana; Arpaci-Dusseau, Andrea C.; Arpaci-Dusseau, Remzi H.
  • Leveraging endpoint flexibility in data-intensive clusters
    Chowdhury, Mosharaf; Kandula, Srikanth; Stoica, Ion
  • Managing data transfers in computer clusters with orchestra
    Chowdhury, Mosharaf; Zaharia, Matei; Ma, Justin; Jordan, Michael I.; Stoica, Ion
  • FlashStore: High throughput persistent key-value store
    Debnath, Biplob K.; Sengupta, Sudipta; Li, Jin
  • SkimpyStash: RAM space skimpy key-value store on flash-based storage
    Debnath, Biplob K.; Sengupta, Sudipta; Li, Jin
  • FaRM: Fast remote memory
    Dragojević, Aleksandar; Narayanan, Dushyanth; Castro, Miguel; Hodson, Orion
  • MemC3: Compact and concurrent memcache with dumber caching and smarter hashing
    Fan, Bin; Andersen, David G.; Kaminsky, Michael
  • Hyperbanyan networks: A new class of networks for distributed memory multiprocessors
    Ferner, Clayto S.; Lee, Kyungsook Y.
  • Toward recovery-oriented computing
    Fox, Armando
  • The Google file system
    Ghemawat, Sanjay; Gobioff, Howard; Leung, Shun-Tak
  • Understanding network failures in data centers: Measurement, analysis, and implications
    Gill, Phillipa; Jain, Navendu; Nagappan, Nachiappan
  • The 5 minute rule for trading memory for disk accesses and the 10 byte rule for trading memory for CPU time
    Gray, Jim; Putzolu, Gianfranco R.
  • VL2: A scalable and flexible data center network
    Greenberg, Albert G.; Hamilton, James R.; Jain, Navendu; Kandula, Srikanth; Kim, Changhoon; Lahiri, Parantap; Maltz, David A.; Patel, Parveen; Sengupta, Sudipta
  • BCube: A high performance, server-centric network architecture for modular data centers
    Guo, Chuanxiong; Lu, Guohan; Li, Dan; Wu, Haitao; Zhang, Xuan; Shi, Yunfeng; Tian, Chen; Zhang, Yongguang; Lu, Songwu
  • Pingmesh: A large-scale system for data center network latency measurement and analysis
    Guo, Chuanxiong; Yuan, Lihua; Xiang, Dong; Dang, Yingnong; Huang, Ray; Maltz, Dave; Liu, Zhaoyi; Wang, Vin; Pang, Bin; Chen, Hua
  • Analysis of hdfs under hbase: A facebook messages case study
    Harter, Tyler; Borthakur, Dhruba; Dong, Siying; Aiyer, Amitanand; Tang, Liyin; Arpaci-Dusseau, Andrea C.; Arpaci-Dusseau, Remzi H.
  • The Zebra striped network file system
    Hartman, John H.; Ousterhout, John K.
  • Exporting storage systems in a scalable manner with pNFS
    Hildebrand, Dean; Honeyman, Peter
  • ZooKeeper: Wait-free coordination for Internet-scale systems
    Hunt, Patrick; Konar, Mahadev; Junqueira, Flavio P.; Reed, Benjamin
  • Petal: Distributed virtual disks
    Lee, Edward K.; Thekkath, Chandramohan A.
  • Superscalar communication: A runtime optimization for distributed applications
    Li, HuiBa; Liu, ShengYun; Peng, YuXing; Li, DongSheng; Zhou, HangJun; Lu, XiCheng
  • MICA: A holistic approach to fast in-memory key-value storage
    Lim, Hyeontaek; Han, Donsu; Andersen, David G.; Kaminsky, Michael
  • ServerSwitch: A programmable and high performance platform for data center networks
    Lu, Guohan; Guo, Chuanxiong; Li, Yulong; Zhou, Zhiqiang; Yuan, Tong; Wu, Haitao; Xiong, Yongqiang; Gao, Rui; Zhang, Yongguang
  • Internet-based virtual computing environment (iVCE): Concepts and architecture
    Lu, Xicheng; Wang, Huaimin; Wang, Ji
  • Internet-based virtual computing environment: Beyond the data center as a computer
    Lu, Xicheng; Wang, Huaimin; Wang, Ji; Xu, Jie
  • Improving the performance of log-structured file systems with adaptive methods
    Matthews, Jeanna Neefe; Roselli, Drew; Costello, Adam M.; Wang, Randolph Y.; Anderson, Thomas E.
  • Blizzard: Fast, cloud-scale block storage for cloud-oblivious applications
    Mickens, James; Nightingale, Edmund B.; Elson, Jeremy; Gehring, Darren; Fan, Bin; Kadav, Asim; Chidambaram, Vijay; Khan, Osama; Nareddy, Krishna
  • f4: Facebook’s warm BLOB storage system
    Muralidhar, Subramanian; Lloyd, Wyatt; Roy, Sabyasachi; Hill, Cory; Lin, Ernest; Liu, Weiwen; Pan, Satadru; Shankar, Shiva; Sivakumar, Viswanath; Tang, Linpeng
  • Flat datacenter storage
    Nightingale, Edmund B.; Elson, Jeremy; Fan, Jinliang; Hofmann, Owen; Howell, Jon; Suzue, Yutaka
  • Fast crash recovery in RAMCloud
    Ongaro, Diego; Rumble, Stephen M.; Stutsman, Ryan; Ousterhout, John K.; Rosenblum, Mendel
  • The case for RAMClouds: Scalable high-performance storage entirely in DRAM
    Ousterhout, John K.; Agrawal, Parag; Erickson, David; Kozyrakis, Christos; Leverich, Jacob; Mazières, David; Mitra, Subhasish; Narayanan, Aravind; Parulkar, Guru M.; Rosenblum, Mendel; Rumble, Stephen M.; Stratmann, Eric; Stutsman, Ryan
  • The design and implementation of a log-structured file system
    Rosenblum, Mendel; Ousterhout, John K.
  • It’s time for low latency
    Rumble, Stephen M.; Ongaro, Diego; Stutsman, Ryan; Rosenblum, Mendel; Ousterhout, John K.
  • Trinity: A distributed graph engine on a memory cloud
    Shao, Bin; Wang, Haixun; Li, Yatao
  • Gecko: Contention-oblivious disk arrays for cloud storage
    Shin, Ji-Yong; Balakrishnan, Mahesh; Marian, Tudor; Weatherspoon, Hakim
  • BlueSky: A cloud-backed file system for the enterprise
    Vrable, Michael; Savage, Stefan; Voelker, Geoffrey M.
  • Robustness in the salus scalable block store
    Wang, Yang; Kapritsos, Manos; Ren, Zuocheng; Mahajan, Prince; Kirubanandam, Jeevitha; Alvisi, Lorenzo; Dahlin, Mike
  • MDCube: A high performance network structure for modular data center interconnection
    Wu, Haitao; Lu, Guohan; Li, Dan; Guo, Chuanxiong; Zhang, Yongguang
  • CubicRing: Enabling one-hop failure detection and recovery for distributed in-memory storage systems
    Zhang, Yiming; Guo, Chuanxiong; Li, Dongsheng; Chu, Rui; Wu, Haitao; Xiong, Yongqiang
  • Packet-level telemetry in large datacenter networks
    Zhu, Yibo; Kang, Nanxi; Cao, Jiaxin; Greenberg, Albert; Lu, Guohan; Mahajan, Ratul; Maltz, Dave; Yuan, Lihua; Zhang, Ming; Zhao, Ben Y.