Efficient cooperative backup with decentralized trust management

Existing backup systems are unsatisfactory: commercial backup services are reliable but expensive while peer-to-peer systems are cheap but offer limited assurance of data reliability. This article introduces Friendstore, a system that provides inexpensive and reliable backup by giving users the choice to store backup data only on nodes they trust (typically those owned by friends and colleagues). Because it is built on trusted nodes, Friendstore is not burdened by the complexity required to cope with potentially malicious participants. Friendstore only needs to detect and repair accidental data loss and to ensure balanced storage exchange. The disadvantage of using only trusted nodes is that Friendstore cannot achieve perfect storage utilization. Friendstore is designed for a heterogeneous environment where nodes have very different access link speeds and available disk spaces. To ensure long-term data reliability, a node with limited upload bandwidth refrains from storing more data than its calculated maintainable capacity. A high bandwidth node might be limited by its available disk space. We introduce a simple coding scheme, called XOR(1,2), which doubles a node's ability to store backup information in the same amount of disk space at the cost of doubling the amount of data transferred during restore. Analysis and simulations using long-term node activity traces show that a node can reliably back up tens of gigabytes of data even with low upload bandwidth.

[1]  Brian D. Noble,et al.  Proceedings of the 5th Symposium on Operating Systems Design and Implementation Pastiche: Making Backup Cheap and Easy , 2022 .

[2]  Eduardo Pinheiro,et al.  Failure Trends in a Large Disk Drive Population , 2007, FAST.

[3]  Krishna P. Gummadi,et al.  Exploiting Social Networks for Internet Search , 2006, HotNets.

[4]  Ben Y. Zhao,et al.  Deployment of a Large-scale Peer-to-Peer Social Network , 2004, WORLDS.

[5]  Ben Y. Zhao,et al.  Pond: The OceanStore Prototype , 2003, FAST.

[6]  Mary Baker,et al.  A fresh look at the reliability of long-term digital storage , 2005, EuroSys.

[7]  David Mazières,et al.  On-the-fly verification of rateless erasure codes for efficient content distribution , 2004, IEEE Symposium on Security and Privacy, 2004. Proceedings. 2004.

[8]  Ramakrishna Kotla,et al.  SafeStore: A Durable and Practical Storage System , 2007, USENIX Annual Technical Conference.

[9]  Randy H. Katz,et al.  A case for redundant arrays of inexpensive disks (RAID) , 1988, SIGMOD '88.

[10]  Michael Dahlin,et al.  BAR fault tolerance for cooperative services , 2005, SOSP '05.

[11]  Robert Tappan Morris,et al.  Persistent personal names for globally connected mobile devices , 2006, OSDI '06.

[12]  Hector Garcia-Molina,et al.  DHT Routing Using Social Links , 2004, IPTPS.

[13]  B. Cohen,et al.  Incentives Build Robustness in Bit-Torrent , 2003 .

[14]  Ari Juels,et al.  Proofs of retrievability: theory and implementation , 2009, CCSW '09.

[15]  Dan S. Wallach,et al.  Enforcing Fair Sharing of Peer-to-Peer Resources , 2003, IPTPS.

[16]  Butler W. Lampson,et al.  SPKI Certificate Theory , 1999, RFC.

[17]  Ethan L. Miller,et al.  POTSHARDS: Secure Long-Term Storage Without Encryption , 2007, USENIX Annual Technical Conference.

[18]  Miguel Castro,et al.  Farsite: federated, available, and reliable storage for an incompletely trusted environment , 2002, OPSR.

[19]  Marvin Theimer,et al.  Feasibility of a serverless distributed file system deployed on an existing set of desktop PCs , 2000, SIGMETRICS '00.

[20]  Mary Baker,et al.  The LOCKSS peer-to-peer digital preservation system , 2005, TOCS.

[21]  Michael Burrows,et al.  A Cooperative Internet Backup Scheme , 2003, USENIX Annual Technical Conference, General Track.

[22]  Emin Gün Sirer,et al.  Latency and bandwidth-minimizing failure detectors , 2007, EuroSys '07.

[23]  Antony I. T. Rowstron,et al.  Storage management and caching in PAST, a large-scale, persistent peer-to-peer storage utility , 2001, SOSP.

[24]  TranNguyen,et al.  Efficient cooperative backup with decentralized trust management , 2012 .

[25]  K. Kaski,et al.  A Model For Social Networks , 2006, physics/0601114.

[26]  David Mazières,et al.  RE: Reliable Email , 2006, NSDI.

[27]  David A. Patterson,et al.  Designing Disk Arrays for High Data Reliability , 1993, J. Parallel Distributed Comput..

[28]  Jinyang Li,et al.  Friendstore: cooperative online backup using trusted nodes , 2008, SocialNets '08.

[29]  Jordi Sabater-Mir,et al.  Social ReGreT, a reputation model based on social relations , 2001, SECO.

[30]  Geoffrey M. Voelker,et al.  On Object Maintenance in Peer-to-Peer Systems , 2006, IPTPS.

[31]  Andrew S. Tanenbaum,et al.  Safe and Private Data Sharing with Turtle: Friends Team-Up and Beat the System , 2004, Security Protocols Workshop.

[32]  Ari Juels,et al.  HAIL: a high-availability and integrity layer for cloud storage , 2009, CCS.

[33]  Brighten Godfrey,et al.  OpenDHT: a public DHT service and its uses , 2005, SIGCOMM '05.

[34]  Jinyang Li,et al.  F2F: Reliable Storage in Open Networks , 2006, IPTPS.

[35]  Tad Hogg,et al.  Enhancing reputation mechanisms via online social networks , 2004, EC '04.

[36]  Sharon E. Perl,et al.  Myriad: Cost-Effective Disaster Tolerance , 2002, FAST.

[37]  Christopher Batten,et al.  pStore: A Secure Peer-to-Peer Backup System∗ , 2007 .

[38]  Andreas Haeberlen,et al.  Efficient Replica Maintenance for Distributed Storage Systems , 2006, NSDI.

[39]  Rodrigo Rodrigues,et al.  Proceedings of Hotos Ix: the 9th Workshop on Hot Topics in Operating Systems Hotos Ix: the 9th Workshop on Hot Topics in Operating Systems High Availability, Scalable Storage, Dynamic Peer Networks: Pick Two , 2022 .

[40]  James S. Plank,et al.  Small parity-check erasure codes - exploration and observations , 2005, 2005 International Conference on Dependable Systems and Networks (DSN'05).

[41]  Stefan Savage,et al.  Total Recall: System Support for Automated Availability Management , 2004, NSDI.

[42]  Robert Tappan Morris,et al.  Designing a DHT for Low Latency and High Throughput , 2004, NSDI.

[43]  Michael Dahlin,et al.  BAR gossip , 2006, OSDI '06.

[44]  Cheng Huang,et al.  Can internet video-on-demand be profitable? , 2007, SIGCOMM '07.

[45]  Joseph Pasquale,et al.  Analysis of Long-Running Replicated Systems , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[46]  Antony I. T. Rowstron,et al.  Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer Systems , 2001, Middleware.

[47]  Andreas Haeberlen,et al.  Glacier: highly durable, decentralized storage despite massive correlated failures , 2005, NSDI.

[48]  David Mazières,et al.  A low-bandwidth network file system , 2001, SOSP.

[49]  Hector Garcia-Molina,et al.  The Eigentrust algorithm for reputation management in P2P networks , 2003, WWW '03.

[50]  Bianca Schroeder,et al.  Disk Failures in the Real World: What Does an MTTF of 1, 000, 000 Hours Mean to You? , 2007, FAST.

[51]  Krishna P. Gummadi,et al.  Measurement and analysis of online social networks , 2007, IMC '07.

[52]  Brian D. Noble,et al.  Samsara: honor among thieves in peer-to-peer storage , 2003, SOSP '03.