@INPROCEEDINGS{Stoica01Chord_scalablepeer-to-peer,
  author = {Ion Stoica and Robert Morris and David Karger and M. Frans Kaashoek
	and Hari Balakrishnan},
  title = {Chord: a scalable peer-to-peer lookup service for internet applications},
  booktitle = {SIGCOMM '01: Proc. 2001 conference on Applications, Technologies,
	Architectures, and Protocols for Computer Communications},
  year = {2001},
  pages = {149--160},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {A fundamental problem that confronts peer-to-peer applications is
	to efficiently locate the node that stores a particular data item.
	This paper presents Chord, a distributed lookup protocol that addresses
	this problem. Chord provides support for just one operation: given
	a key, it maps the key onto a node. Data location can be easily implemented
	on top of Chord by associating a key with each data item, and storing
	the key/data item pair at the node to which the key maps. Chord adapts
	efficiently as nodes join and leave the system, and can answer queries
	even if the system is continuously changing. Results from theoretical
	analysis, simulations, and experiments show that Chord is scalable,
	with communication cost and the state maintained by each node scaling
	logarithmically with the number of Chord nodes.},
  crossref = {`},
  doi = {10.1145/383059.383071},
  isbn = {1-58113-411-8},
  location = {San Diego, California, United States},
  url = {http://portal.acm.org/citation.cfm?id=383059.383071}
}

@ARTICLE{Tang03pSearch_informationretrieval,
  author = {Chunqiang Tang and Zhichen Xu and Mallik Mahalingam},
  title = {{pSearch:} Information retrieval in structured overlays},
  journal = {ACM SIGCOMM Computer Communication Review},
  year = {2003},
  volume = {33},
  pages = {89--94},
  number = {1},
  abstract = {We describe an efficient peer-to-peer information retrieval system,
	pSearch; that supports state-of-the-art content- and semantic-based
	full-text searches. pSearch avoids the scalability problem of existing
	systems that employ centralized indexing, or index/query flooding.
	It also avoids the nondeterminism that is exhibited by heuristic-based
	approaches. In pSearch; documents in the network are organized around
	their vector representations (based on modern document ranking algorithms)
	such that the search space for a given query is organized around
	related documents, achieving both efficiency and accuracy.},
  address = {New York, NY, USA},
  doi = {10.1145/774763.774777},
  issn = {0146-4833},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?id=774763.774777}
}

@ARTICLE{Ratnasamy01scalablecontent-addressablenetwork,
  author = {Sylvia Ratnasamy and Paul Francis and Mark Handley and Richard Karp
	and Scott Schenker},
  title = {A scalable content-addressable network},
  journal = {ACM SIGCOMM Computer Communication Review},
  year = {2001},
  volume = {31},
  pages = {161--172},
  number = {4},
  abstract = {Hash tables - which map "keys" onto "values" - are an essential building
	block in modern software systems. We believe a similar functionality
	would be equally valuable to large distributed systems. In this paper,
	we introduce the concept of a Content-Addressable Network (CAN) as
	a distributed infrastructure that provides hash table-like functionality
	on Internet-like scales. The CAN is scalable, fault-tolerant and
	completely self-organizing, and we demonstrate its scalability, robustness
	and low-latency properties through simulation.},
  address = {New York, NY, USA},
  doi = {10.1145/964723.383072},
  issn = {0146-4833},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?id=964723.383072}
}

@ARTICLE{Dabek01Wide-areacooperativestorage,
  author = {Frank Dabek and M. Frans Kaashoek and David Karger and Robert Morris
	and Ion Stoica},
  title = {Wide-area cooperative storage with {CFS}},
  journal = {SIGOPS Operating Systems Review},
  year = {2001},
  volume = {35},
  pages = {202--215},
  number = {5},
  abstract = {The Cooperative File System (CFS) is a new peer-to-peer read-only
	storage system that provides provable guarantees for the efficiency,
	robustness, and load-balance of file storage and retrieval. CFS does
	this with a completely decentralized architecture that can scale
	to large systems. CFS servers provide a distributed hash table (DHash)
	for block storage. CFS clients interpret DHash blocks as a file system.
	DHash distributes and caches blocks at a fine granularity to achieve
	load balance, uses replication for robustness, and decreases latency
	with server selection. DHash finds blocks using the Chord location
	protocol, which operates in time logarithmic in the number of servers.CFS
	is implemented using the SFS file system toolkit and runs on Linux,
	OpenBSD, and FreeBSD. Experience on a globally deployed prototype
	shows that CFS delivers data to clients as fast as FTP. Controlled
	tests show that CFS is scalable: with 4,096 servers, looking up a
	block of data involves contacting only seven servers. The tests also
	demonstrate nearly perfect robustness and unimpaired performance
	even when as many as half the servers fail.},
  address = {New York, NY, USA},
  doi = {10.1145/502059.502054},
  issn = {0163-5980},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?id=502059.502054}
}

@ARTICLE{Ghemawat03Googlefilesystem,
  author = {Sanjay Ghemawat and Howard Gobioff and Shun-Tak Leung},
  title = {The {Google} file system},
  journal = {SIGOPS Operating System Review},
  year = {2003},
  volume = {37},
  pages = {29--43},
  number = {5},
  abstract = {We have designed and implemented the Google File System, a scalable
	distributed file system for large distributed data-intensive applications.
	It provides fault tolerance while running on inexpensive commodity
	hardware, and it delivers high aggregate performance to a large number
	of clients.
	
	
	While sharing many of the same goals as previous distributed file
	systems, our design has been driven by observations of our application
	workloads and technological environment, both current and anticipated,
	that reflect a marked departure from some earlier file system assumptions.
	This has led us to reexamine traditional choices and explore radically
	different design points.
	
	
	The file system has successfully met our storage needs. It is widely
	deployed within Google as the storage platform for the generation
	and processing of data used by our service as well as research and
	development efforts that require large data sets. The largest cluster
	to date provides hundreds of terabytes of storage across thousands
	of disks on over a thousand machines, and it is concurrently accessed
	by hundreds of clients.
	
	
	In this paper, we present file system interface extensions designed
	to support distributed applications, discuss many aspects of our
	design, and report measurements from both micro-benchmarks and real
	world use.},
  address = {New York, NY, USA},
  doi = {10.1145/1165389.945450},
  issn = {0163-5980},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?doid=1165389.945450}
}

@ARTICLE{Kubiatowicz00OceanStore_architectureglobal-scale,
  author = {John Kubiatowicz and David Bindel and Yan Chen and Steven Czerwinski
	and Patrick Eaton and Dennis Geels and Ramakrishna Gummadi and Sean
	Rhea and Hakim Weatherspoon and Chris Wells and Ben Zhao},
  title = {{OceanStore:} an architecture for global-scale persistent storage},
  journal = {SIGARCH Computer Architecture News},
  year = {2000},
  volume = {28},
  pages = {190--201},
  number = {5},
  abstract = {OceanStore is a utility infrastructure designed to span the globe
	and provide continuous access to persistent information. Since this
	infrastructure is comprised of untrusted servers, data is protected
	through redundancy and cryptographic techniques. To improve performance,
	data is allowed to be cached anywhere, anytime. Additionally, monitoring
	of usage patterns allows adaptation to regional outages and denial
	of service attacks; monitoring also enhances performance through
	pro-active movement of data. A prototype implementation is currently
	under development.},
  address = {New York, NY, USA},
  doi = {10.1145/378995.379239},
  issn = {0163-5964},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?id=379239}
}

@INPROCEEDINGS{Mazi`eres99Separatingkeymanagement,
  author = {David Mazi\`{e}res and Michael Kaminsky and M. Frans Kaashoek and
	Emmett Witchel},
  title = {Separating key management from file system security},
  booktitle = {SOSP '99: Proc. 17th ACM symposium on Operating Systems Principles},
  year = {1999},
  volume = {33},
  number = {5},
  pages = {124--139},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {No secure network file system has ever grown to span the Internet.
	Existing systems all lack adequate key management for security at
	a global scale. Given the diversity of the Internet, any particular
	mechanism a file system employs to manage keys will fail to support
	many types of use.We propose separating key management from file
	system security, letting the world share a single global file system
	no matter how individuals manage keys. We present SFS, a secure file
	system that avoids internal key management. While other file systems
	need key management to map file names to encryption keys, SFS file
	names effectively contain public keys, making them self-certifying
	pathnames. Key management in SFS occurs outside of the file system,
	in whatever procedure users choose to generate file names.Self-certifying
	pathnames free SFS clients from any notion of administrative realm,
	making inter-realm file sharing trivial. They let users authenticate
	servers through a number of different techniques. The file namespace
	doubles as a key certification namespace, so that people can realize
	many key management schemes using only standard file utilities. Finally,
	with self-certifying pathnames, people can bootstrap one key management
	mechanism using another. These properties make SFS more versatile
	than any file system with built-in key management.},
  doi = {10.1145/319344.319160},
  isbn = {1-58113-140-2},
  location = {Charleston, South Carolina, United States},
  url = {http://portal.acm.org/citation.cfm?id=319344.319160}
}

@ARTICLE{Petersen97Flexibleupdatepropagation,
  author = {Karin Petersen and Mike J. Spreitzer and Douglas B. Terry and Marvin
	M. Theimer and Alan J. Demers},
  title = {Flexible update propagation for weakly consistent replication},
  journal = {ACM SIGOPS Operating Systems Review},
  year = {1997},
  volume = {31},
  pages = {288--301},
  number = {5},
  abstract = {Bayou’s anti-entropy protocol for update propagation between weakly
	consistent storage replicas is based on pair-wise communication,
	the propagation of write operations, and a set of ordering and closure
	constraints on the propagation of the writes. The simplicity of the
	design makes the protocol very flexible, thereby providing support
	for diverse networking environments and usage scenarios. It accommodates
	a variety of policies for when and where to propagate updates. It
	operates over diverse network topologies, including low-bandwidth
	links. It is incremental. It enables replica convergence, and updates
	can be propagated using floppy disks and similar transportable media.
	Moreover, the protocol handles replica creation and retirement in
	a light-weight manner. Each of these features is enabled by only
	one or two of the protocol’s design choices, and can be independently
	incorporated in other systems. This paper presents the antientropy
	protocol in detail, describing the design decisions and resulting
	features.},
  address = {New York, NY, USA},
  doi = {10.1145/269005.266711},
  issn = {0163-5980},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?doid=269005.266711}
}

@ARTICLE{Rowstron01Storagemanagementand,
  author = {Antony Rowstron and Peter Druschel},
  title = {Storage management and caching in {PAST}, a large-scale, persistent
	peer-to-peer storage utility},
  journal = {ACM SIGOPS Operating Systems Review},
  year = {2001},
  volume = {35},
  pages = {188--201},
  number = {5},
  abstract = {This paper presents and evaluates the storage management and caching
	in PAST, a large-scale peer-to-peer persistent storage utility. PAST
	is based on a self-organizing, Internet-based overlay network of
	storage nodes that cooperatively route file queries, store multiple
	replicas of files, and cache additional copies of popular files.In
	the PAST system, storage nodes and files are each assigned uniformly
	distributed identifiers, and replicas of a file are stored at nodes
	whose identifier matches most closely the file's identifier. This
	statistical assignment of files to storage nodes approximately balances
	the number of files stored on each node. However, non-uniform storage
	node capacities and file sizes require more explicit storage load
	balancing to permit graceful behavior under high global storage utilization;
	likewise, non-uniform popularity of files requires caching to minimize
	fetch distance and to balance the query load.We present and evaluate
	PAST, with an emphasis on its storage management and caching system.
	Extensive trace-driven experiments show that the system minimizes
	fetch distance, that it balances the query load for popular files,
	and that it displays graceful degradation of performance as the global
	storage utilization increases beyond 95%.},
  address = {New York, NY, USA},
  doi = {10.1145/502059.502053},
  issn = {0163-5980},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?id=502053}
}

@ARTICLE{Terry95Managingupdateconflicts,
  author = {Douglas B. Terry and Marvin M. Theimer and Karin Petersen and Alan
	J. Demers and Mike J. Spreitzer and Carl H. Hauser},
  title = {Managing update conflicts in Bayou, a weakly connected replicated
	storage system},
  journal = {ACM SIGOPS Operating Systems Review},
  year = {1995},
  volume = {29},
  pages = {172--182},
  number = {5},
  abstract = {Bayou is a replicated, weakly consmtent storage system designed for
	a mobile computing environment that includes portable machines with
	less than ideal network connectivity. To maximize availabdity, users
	can read and write any accessible replica. Bayou’s design has focused
	on supporting apphcation-specific mechanisms to detect and resolve
	the update conflicts that naturally arise in such a system, ensuring
	that replicas move towards eventual consistency, and defining a protocol
	by which the resolution of update conflicts stabilizes, It includes
	novel methods for confhct detection, called dependency checks, and
	per-write conflict resolution based on client-provided merge procedures.
	To guarantee eventual consistency, Bayou servers must be able to
	rollback the effects of previously executed writes and redo them
	according to a global serialization order. Furthermore, Bayou per-mits
	clients to observe the results of all writes received by a server,
	mchrding tentative writes whose conflicts have not been ultimately
	resolved. This paper presents the motivation for and design of these
	mechanisms and describes the experiences gained with an initial implementation
	of the system.},
  address = {New York, NY, USA},
  doi = {10.1145/224057.224070},
  issn = {0163-5980},
  publisher = {ACM},
  url = {http://portal.acm.org/citation.cfm?doid=224057.224070}
}

@ARTICLE{cCetintemel03Deno_DecentralizedPeer-to-Peer,
  author = {Ugur \c{C}etintemel and Peter J. Keleher and Bobby Bhattacharjee
	and Michael J. Franklin},
  title = {Deno: A decentralized, peer-to-peer object-replication system for
	weakly connected environments},
  journal = {IEEE Transactions on Computers},
  year = {2003},
  volume = {52},
  pages = {943--959},
  number = {7},
  abstract = {This paper presents the design, implementation, and evaluation of
	the replication framework of Deno, a decentralized, peer-to-peer
	object-replication system targeted for weakly connected environments.
	Deno uses weighted voting for availability and pair-wise, epidemic
	information flow for flexibility. This combination allows the protocols
	to operate with less than full connectivity, to easily adapt to changes
	in group membership, and to make few assumptions about the underlying
	network topology. We present two versions of Deno's protocol that
	differ in the consistency levels they support. We also propose security
	extensions to handle a class of malicious actions that involve misrepresentation
	of protocol information. Deno has been implemented and runs on top
	of Linux and Win32 platforms. We use the Deno prototype to characterize
	the performance of the Deno protocols and extensions. Our study reveals
	several interesting results that provide fundamental insight into
	the benefits of decentralization and the mechanics of epidemic protocols.},
  address = {Washington, DC, USA},
  doi = {10.1109/TC.2003.1214342},
  issn = {0018-9340},
  publisher = {IEEE Computer Society},
  url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1214342}
}

@INPROCEEDINGS{Adya02Farsite_federatedavailable,
  author = {Atul Adya and William J. Bolosky and Miguel Castro and Gerald Cermak
	and Ronnie Chaiken and John R. Douceur and Jon Howell and Jacob R.
	Lorch and Marvin Theimer and Roger P. Wattenhofer},
  title = {Farsite: federated, available, and reliable storage for an incompletely
	trusted environment},
  booktitle = {OSDI '02: Proc. 5th symposium on Operating systems design and implementation},
  year = {2002},
  pages = {1--14},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {Farsite is a secure, scalable file system that logically functions
	as a centralized file server but is physically distributed among
	a set of untrusted computers. Farsite provides file availability
	and reliability through randomized replicated storage; it ensures
	the secrecy of file contents with cryptographic techniques; it maintains
	the integrity of file and directory data with a Byzantine-fault-tolerant
	protocol; it is designed to be scalable by using a distributed hint
	mechanism and delegation certificates for pathname translations;
	and it achieves good performance by locally caching file data, lazily
	propagating file updates, and varying the duration and granularity
	of content leases. We report on the design of Farsite and the lessons
	we have learned by implementing much of that design.},
  doi = {10.1145/1060289.1060291},
  location = {Boston, Massachusetts},
  url = {http://portal.acm.org/citation.cfm?id=1060291}
}

@INPROCEEDINGS{Aguilera03Block-LevelSecurityNetwork-Attached,
  author = {Marcos K. Aguilera and Minwen Ji and Mark Lillibridge and John MacCormick
	and Erwin Oertli and Dave Andersen and Mike Burrows and Timothy Mann
	and Chandramohan A. Thekkath},
  title = {Block-level security for network-attached disks},
  booktitle = {FAST '03: Proc. 2nd USENIX conference on File and Storage Technologies},
  year = {2003},
  pages = {159--174},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {We propose a practical and efficient method for adding security to
	network-attached disks (NADs). In contrast to previous work, our
	design requires no changes to the data layout on disk, minimal changes
	to existing NADs, and only small changes to the standard protocol
	for accessing remote block-based devices. Thus, existing NAD file
	systems and storage-management software could incorporate our scheme
	very easily. Our design enforces security using the well-known idea
	of self-describing capabilities, with two novel features that limit
	the need for memory on secure NADs: a scheme to manage revocations
	based on capability groups, and a replay-detection method using Bloom
	filters.
	
	
	We have implemented a prototype NAD file system, called Snapdragon,
	that incorporates our ideas. We evaluated Snapdragon's performance
	and scalability. The overhead of access control is small: latency
	for reads and writes increases by less than 0.5 ms (5%), while bandwidth
	decreases by up to 16%. The aggregate throughput scales linearly
	with the number of NADs (up to 7 in our experiments).},
  location = {San Francisco, CA},
  url = {http://www.usenix.org/publications/library/proceedings/fast03/tech/aguilera.html}
}

@INPROCEEDINGS{Aguilera07Sinfonia_newparadigm,
  author = {Marcos~K. Aguilera and Arif Merchant and Mehul Shah and Alistair
	Veitch and Christos Karamanolis},
  title = {Sinfonia: A new paradigm for building scalable distributed systems},
  booktitle = {SOSP '07: Proc. 21st ACM SIGOPS symposium on Operating Systems Principles},
  year = {2007},
  pages = {159--174},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {We propose a new paradigm for building scalable distributed systems.
	Our approach does not require dealing with message-passing protocols
	-- a major complication in existing distributed systems. Instead,
	developers just design and manipulate data structures within our
	service called Sinfonia. Sinfonia keeps data for applications on
	a set of memory nodes, each exporting a linear address space. At
	the core of Sinfonia is a novel minitransaction primitive that enables
	efficient and consistent access to data, while hiding the complexities
	that arise from concurrency and failures. Using Sinfonia, we implemented
	two very different and complex applications in a few months: a cluster
	file system and a group communication service. Our implementations
	perform well and scale to hundreds of machines.},
  doi = {10.1145/1294261.1294278},
  isbn = {978-1-59593-591-5},
  location = {Stevenson, Washington, USA},
  url = {http://portal.acm.org/citation.cfm?doid=1294261.1294278}
}

@INPROCEEDINGS{Belaramani06PRACTIReplication,
  author = {Nalini Moti Belaramani and Michael Dahlin and Lei Gao and Amol Nayate
	and Arun Venkataramani and Praveen Yalagandula and Jiandan Zheng},
  title = {{PRACTI} replication},
  booktitle = {NSDI '06: Proc. 3rd USENIX symposium on Networked Systems Design
	\& Implementation},
  year = {2006},
  pages = {59--72},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {We present PRACTI, a new approach for large-scale replication. PRACTI
	systems can replicate or cache any subset of data on any node (Partial
	Replication), provide a broad range of consistency guarantees (Arbitrary
	Consistency), and permit any node to send information to any other
	node (Topology Independence). A PRACTI architecture yields two signi?cant
	advantages. First, by providing all three PRACTI properties, it enables
	better trade-offs than existing mechanisms that support at most two
	of the three desirable properties. The PRACTI approach thus exposes
	new points in the design space for replication systems. Second, the
	?exibility of PRACTI protocols simpli?es the design of replication
	systems by allowing a single architecture to subsume a broad range
	of existing systems and to reduce development costs for new ones.
	To illustrate both advantages, we use our PRACTI prototype to emulate
	existing server replication, client-server, and object replication
	systems and to implement novel policies that improve performance
	for mobile users, web edge servers, and grid computing by as much
	as an order of magnitude.},
  location = {San Jose, CA},
  url = {http://www.usenix.org/events/nsdi06/tech/belaramani.html}
}

@INPROCEEDINGS{Bhattacharjee03Efficientpeer-to-peersearches,
  author = {Bobby Bhattacharjee and Sudarshan Chawathe and Vijay Gopalakrishnan
	and Pete Keleher and Bujor Silaghi},
  title = {Efficient peer-to-peer searches using result-caching},
  booktitle = {IPTPS '03: Proc. 2nd international workshop on Peer-To-Peer Systems},
  year = {2003},
  volume = {2735},
  series = {Lecture Notes in Computer Science},
  pages = {225--236},
  publisher = {Springer Berlin / Heidelberg},
  abstract = {Existing peer-to-peer systems implement a single function well: data
	lookup. There is now a wealth of research describing how to reliably
	disseminate, and to later retrieve, data in a scalable and load-balanced
	manner.},
  doi = {10.1007/b11823},
  url = {http://www.springerlink.com/content/qd4tt3dp6fagvtxn}
}

@INPROCEEDINGS{Castro99PracticalByzantinefault,
  author = {Miguel Castro and Barbara Liskov},
  title = {Practical {Byzantine} fault tolerance},
  booktitle = {IPTPS '99: Proc. 3rd symposium on Operating Systems Design and Implementation},
  year = {1999},
  pages = {173--186},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {This paper describes a new replication algorithm that is able to tolerate
	Byzantine faults. We believe that Byzantine-fault-tolerant algorithms
	will be increasingly important in the future because malicious attacks
	and software errors are increasingly common and can cause faulty
	nodes to exhibit arbitrary behavior. Whereas previous algorithms
	assumed a synchronous system or were too slow to be used in practice,
	the algorithm described in this paper is practical: it works in asynchronous
	environments like the Internet and incorporates several important
	optimizations that improve the response time of previous algorithms
	by more than an order of magnitude. We implemented a Byzantine-fault-tolerant
	NFS service using our algorithm and measured its performance. The
	results show that our service is only 3% slower than a standard unreplicated
	NFS.},
  isbn = {1-880446-39-1},
  location = {New Orleans, Louisiana, United States},
  url = {http://www.pmg.lcs.mit.edu/~castro/osdi99_html/osdi99.html}
}

@INPROCEEDINGS{Cetintemel00Performanceofmobile,
  author = {Ugur Cetintemel and Peter Keleher},
  title = {Performance of mobile, single-object, replication protocols},
  booktitle = {SRDS '00: Proc. 19th IEEE symposium on Reliable Distributed Systems},
  year = {2000},
  pages = {218--227},
  abstract = {Discusses the implementation and performance of bounded voting, which
	is a new object replication protocol designed for use in mobile and
	weakly-connected environments. We show that the protocol eliminates
	several restrictions of previous work, such as the need for (1) strong
	or complete connectivity, (2) complete knowledge of system membership,
	and (3) low update rates. The protocol implements an asynchronous,
	weighted-voting scheme via epidemic information flow, and commits
	updates in an entirely decentralized fashion. A proxy mechanism is
	used to enable transparent handling of planned disconnections. We
	use a detailed simulation study to characterize the performance of
	bounded voting under a variety of loads and environments, and to
	compare it to another decentralized epidemic protocol. We further
	investigate the performance impact of the proxy mechanism},
  doi = {10.1109/RELDI.2000.885409},
  keywords = {mobile computing, object-oriented databases, protocols, replicated
	databases, software performance evaluation, asynchronous weighted-voting
	scheme, bounded voting, connectivity, decentralized epidemic protocol,
	decentralized update commitment, epidemic information flow, loads,
	mobile single-object replication protocols, performance, planned
	disconnections, proxy mechanism, simulation, system membership, transparent
	handling, update rates, weakly-connected environments},
  url = {http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=885409}
}

@INPROCEEDINGS{Chun06EfficientReplicaMaintenance,
  author = {Byung-Gon Chun and Frank Dabek and Andreas Haeberlen and Emil Sit
	and Hakim Weatherspoon and M. Frans Kaashoek and John Kubiatowicz
	and Robert Morris},
  title = {Efficient replica maintenance for distributed storage systems},
  booktitle = {NSDI '06: Proc. 3rd USENIX symposium on Networked Systems Design
	\& Implementation},
  year = {2006},
  abstract = {This paper considers replication strategies for storage systems that
	aggregate the disks of many nodes spread over the Internet. Maintaining
	replication in such systems can be prohibitively expensive, since
	every transient network or host failure could potentially lead to
	copying a server's worth of data over the Internet to maintain replication
	levels.
	
	
	The following insights in designing an efficient replication algorithm
	emerge from the paper's analysis. First, durability can be provided
	separately from availability; the former is less expensive to ensure
	and a more useful goal for many wide-area applications. Second, the
	focus of a durability algorithm must be to create new copies of data
	objects faster than permanent disk failures destroy the objects;
	careful choice of policies for what nodes should hold what data can
	decrease repair time. Third, increasing the number of replicas of
	each data object does not help a system tolerate a higher disk failure
	probability, but does help tolerate bursts of failures. Finally,
	ensuring that the system makes use of replicas that recover after
	temporary failure is critical to efficiency.
	
	
	Based on these insights, the paper proposes the Carbonite replication
	algorithm for keeping data durable at a low cost. A simulation of
	Carbonite storing 1 TB of data over a 365 day trace of PlanetLab
	activity shows that Carbonite is able to keep all data durable and
	uses 44% more network traffic than a hypothetical system that only
	responds to permanent failures. In comparison, Total Recall and DHash
	require almost a factor of two more network traffic than this hypothetical
	system.},
  url = {http://www.usenix.org/events/nsdi06/tech/chun.html}
}

@INPROCEEDINGS{Clarke01Freenet_distributedanonymous,
  author = {Ian Clarke and Oskar Sandberg and Brandon Wiley and Theodore Hong},
  title = {Freenet: A distributed anonymous information storage and retrieval
	system},
  booktitle = {Designing Privacy Enhancing Technologies: international workshop
	on Design Issues in Anonymity and Unobservability},
  year = {2001},
  volume = {2009/2001},
  series = {Lecture Notes in Computer Science},
  pages = {46--66},
  publisher = {Springer Berlin / Heidelberg},
  abstract = {We describe Freenet, an adaptive peer-to-peer network application
	that permits the publication, replication, and retrieval of data
	while protecting the anonymity of both authors and readers. Freenet
	operates as a network of identical nodes that collectively pool their
	storage space to store data files and cooperate to route requests
	to the most likely physical location of data. No broadcast search
	or centralized location index is employed. Files are referred to
	in a location-independent manner, and are dynamically replicated
	in locations near requestors and deleted from locations where there
	is no interest. It is infeasible to discover the true origin or destination
	of a file passing through the network, and dificult for a node operator
	to determine or be held responsible for the actual physical contents
	of her own node.},
  doi = {10.1007/3-540-44702-4_4},
  url = {http://www.springerlink.com/content/tmu95yypt1rd9pct/}
}

@INPROCEEDINGS{Cox03Samsara_honoramong,
  author = {Landon P. Cox and Brian D. Noble},
  title = {Samsara: honor among thieves in peer-to-peer storage},
  booktitle = {SOSP '03: Proc. 19th ACM symposium on Operating Systems Principles},
  year = {2003},
  pages = {120--132},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {Peer-to-peer storage systems assume that their users consume resources
	in proportion to their contribution. Unfortunately, users are unlikely
	to do this without some enforcement mechanism. Prior solutions to
	this problem require centralized infrastructure, constraints on data
	placement, or ongoing administrative costs. All of these run counter
	to the design philosophy of peer-to-peer systems.Samsara enforces
	fairness in peer-to-peer storage systems without requiring trusted
	third parties, symmetric storage relationships, monetary payment,
	or certified identities. Each peer that requests storage of another
	must agree to hold a claim in return---a placeholder that accounts
	for available space. After an exchange, each partner checks the other
	to ensure faithfulness. Samsara punishes unresponsive nodes probabilistically.
	Because objects are replicated, nodes with transient failures are
	unlikely to suffer data loss, unlike those that are dishonest or
	chronically unavailable. Claim storage overhead can be reduced when
	necessary by forwarding among chains of nodes, and eliminated when
	cycles are created. Forwarding chains increase the risk of exposure
	to failure, but such risk is modest under reasonable assumptions
	of utilization and simultaneous, persistent failure.},
  doi = {10.1145/945445.945458},
  isbn = {1-58113-757-5},
  location = {Bolton Landing, NY, USA},
  url = {http://portal.acm.org/citation.cfm?id=945458}
}

@INPROCEEDINGS{Dean04MapReduce_simplifieddata,
  author = {Jeffrey Dean and Sanjay Ghemawat},
  title = {{MapReduce:} Simplified data processing on large clusters},
  booktitle = {OSDI '04: Proc. 6th symposium on Operating Systems Design \& Implementation},
  year = {2004},
  pages = {10--10},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {MapReduce is a programming model and an associated implementation
	for processing and generating large data sets. Users specify a _map_
	function that processes a key/value pair to generate a set of intermediate
	key/value pairs, and a _reduce_ function that merges all intermediate
	values associated with the same intermediate key. Many real world
	tasks are expressible in this model, as shown in the paper.
	
	
	Programs written in this functional style are automatically parallelized
	and executed on a large cluster of commodity machines. The run-time
	system takes care of the details of partitioning the input data,
	scheduling the program's execution across a set of machines, handling
	machine failures, and managing the required inter-machine communication.
	This allows programmers without any experience with parallel and
	distributed systems to easily utilize the resources of a large distributed
	system.
	
	
	Our implementation of MapReduce runs on a large cluster of commodity
	machines and is highly scalable: a typical MapReduce computation
	processes many terabytes of data on thousands of machines. Programmers
	find the system easy to use: hundreds of MapReduce programs have
	been implemented and upwards of one thousand MapReduce jobs are executed
	on Google's clusters every day.},
  location = {San Francisco, CA},
  url = {http://www.usenix.org/events/osdi04/tech/dean.html}
}

@INPROCEEDINGS{DeCandia07Dynamo_Amazon'shighly,
  author = {Giuseppe DeCandia and Deniz Hastorun and Madan Jampani and Gunavardhan
	Kakulapati and Avinash Lakshman and Alex Pilchin and Swaminathan
	Sivasubramanian and Peter Vosshall and Werner Vogels},
  title = {Dynamo: {Amazon's} highly available key-value store},
  booktitle = {SOSP '07: Proc. 21st ACM SIGOPS symposium on Operating systems principles},
  year = {2007},
  pages = {205--220},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {Reliability at massive scale is one of the biggest challenges we face
	at Amazon.com, one of the largest e-commerce operations in the world;
	even the slightest outage has significant financial consequences
	and impacts customer trust. The Amazon.com platform, which provides
	services for many web sites worldwide, is implemented on top of an
	infrastructure of tens of thousands of servers and network components
	located in many datacenters around the world. At this scale, small
	and large components fail continuously and the way persistent state
	is managed in the face of these failures drives the reliability and
	scalability of the software systems.
	
	
	This paper presents the design and implementation of Dynamo, a highly
	available key-value storage system that some of Amazon's core services
	use to provide an "always-on" experience. To achieve this level of
	availability, Dynamo sacrifices consistency under certain failure
	scenarios. It makes extensive use of object versioning and application-assisted
	conflict resolution in a manner that provides a novel interface for
	developers to use.},
  doi = {10.1145/1294261.1294281},
  isbn = {978-1-59593-591-5},
  location = {Stevenson, Washington, USA},
  url = {http://portal.acm.org/citation.cfm?doid=1294261.1294281}
}

@INPROCEEDINGS{Ding04Peer-to-peerfile-sharingover,
  author = {G. Ding and Bharat Bhargava},
  title = {Peer-to-peer file-sharing over mobile ad hoc networks},
  booktitle = {Proc. 2nd IEEE annual conference on Pervasive Computing and Communications
	Workshops},
  year = {2004},
  pages = {104--108},
  month = {14--17 March },
  abstract = {Current peer-to-peer file-sharing systems mostly work on wired networks.
	Mobile ad hoc network is characterized as multihop wireless communications
	between mobile devices. Five routing approaches with different complexity
	are proposed to enable peer-to-peer file-sharing over mobile ad hoc
	networks. The complexity of the proposed approaches is evaluated
	and compared. It is concluded that the cross-layer protocols perform
	better than simply overlaying peer-to-peer searching protocol on
	mobile ad hoc networks.},
  doi = {10.1109/PERCOMW.2004.1276914},
  url = {http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=1276914}
}

@INPROCEEDINGS{Freedman02IntroducingTarzanPeer-to-Peer,
  author = {Michael J. Freedman and Emil Sit and Josh Cates and Robert Morris},
  title = {Introducing {Tarzan}, a peer-to-peer anonymizing network layer},
  booktitle = {IPTPS '02: Proc. 1st international workshop on Peer-to-Peer Systems},
  year = {2002},
  abstract = {We introduce Tarzan, a peer-to-peer anonymous network layer that provides
	generic IP forwarding. Unlike prior anonymizing layers, Tarzan is
	flexible, transparent, decentralized, and highly scalable. Tarzan
	achieves these properties by building anonymous IP tunnels between
	an open-ended set of peers. Tarzan can provide anonymity to existing
	applications, such as web browsing and file sharing, without change
	to those applications. Performance tests show that Tarzan imposes
	minimal overhead over a corresponding non-anonymous overlay route.},
  url = {http://www.cs.rice.edu/Conferences/IPTPS02/}
}

@INPROCEEDINGS{Garriss06RE_Reliableemail,
  author = {Scott Garriss and Michael Kaminsky and Michael~J. Freedman and Brad
	Karp and David Mazi\`{e}res and Haifeng Yu},
  title = {RE: reliable email},
  booktitle = {NSDI '06: Proc. 3rd USENIX symposium on Networked Systems Design
	\& Implementation},
  year = {2006},
  pages = {297-310},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {The explosive growth in unwanted email has prompted the development
	of techniques for the rejection of email, intended to shield recipients
	from the onerous task of identifying the legitimate email in their
	inboxes amid a sea of spam. Unfortunately, widely used content-based
	filtering systems have converted the spam problem into a false positive
	one: email has become unreliable. Email acceptance techniques complement
	rejection ones; they can help prevent false positives by filing email
	into a user's inbox before it is considered for rejection. Whitelisting,
	whereby recipients accept email from some set of authorized senders,
	is one such acceptance technique.
	
	We present Reliable Email (RE:), a new whitelisting system that incurs
	zero false positives among socially connected users. Unlike previous
	whitelisting systems, which require that whitelists be populated
	manually, RE: exploits friend-of-friend relationships among email
	correspondents to populate whitelists automatically. To do so, RE:
	permits an email's recipient to discover whether other email users
	have whitelisted the email's sender, while preserving the privacy
	of users' email contacts with cryptographic private matching techniques.
	Using real email traces from two sites, we demonstrate that RE: renders
	a significant fraction of received email reliable. Our evaluation
	also shows that RE: can prevent up to 88% of the false positives
	incurred by a widely deployed email rejection system, at modest computational
	cost.},
  location = {San Jose, CA},
  url = {http://www.usenix.org/events/nsdi06/tech/garriss.html}
}

@INPROCEEDINGS{Goldberg98TowardsarchivalIntermemory,
  author = {Andrew V. Goldberg and Peter N. Yianilos},
  title = {Towards an archival Intermemory},
  booktitle = {ADL '98: Proc. IEEE international forum on Research and Technology
	Advances in Digital Libraries},
  year = {1998},
  pages = {147--156},
  month = {22--24 April },
  abstract = {We propose a self-organizing archival Intermemory. That is, a noncommercial
	subscriber-provided distributed information storage service built
	on the existing Internet. Given an assumption of continued growth
	in the memory's total size, a subscriber's participation for only
	a finite time can nevertheless ensure archival preservation of the
	subscriber's data. Information disperses through the network over
	time and memories become more difficult to erase as they age. The
	probability of losing an old memory given random node failures is
	vanishingly small-and an adversary would have to corrupt hundreds
	of thousands of nodes to destroy a very old memory. This paper presents
	a framework for the design of an Intermemory, and considers certain
	aspects of the design in greater detail. In particular, the aspects
	of addressing, space efficiency, and redundant coding are discussed},
  doi = {10.1109/ADL.1998.670389},
  url = {http://ieeexplore.ieee.org/search/wrapper.jsp?arnumber=670389}
}

@INPROCEEDINGS{Gopalakrishnan04Adaptivereplicationin,
  author = {Vijay Gopalakrishnan and Bujor Silaghi and Bobby Bhattacharjee and
	Pete Keleher},
  title = {Adaptive replication in peer-to-peer systems},
  booktitle = {ICDCS '04: Proc. 24th international conference on Distributed Computing
	Systems},
  year = {2004},
  pages = {360--369},
  abstract = {Peer-to-peer systems can be used to form a low-latency decentralized
	data delivery system. Structured peer-to-peer systems provide both
	low latency and excellent load balance with uniform query and data
	distributions. Under the more common skewed access distributions,
	however, individual nodes are easily overloaded, resulting in poor
	global performance and lost messages. This paper describes a lightweight,
	adaptive, and system-neutral replication protocol, called LAR, that
	maintains low access latencies and good load balance even under highly
	skewed demand. We apply LAR to Chord and show that it has lower overhead
	and better performance than existing replication strategies.},
  doi = {10.1109/ICDCS.2004.1281601},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1281601}
}

@INPROCEEDINGS{Harjula04Plug-and-playapplicationplatform_,
  author = {Erkki Harjula and Mika Ylianttila and Jussi Ala-Kurikka and Jukka
	Riekki and Jaakko Sauvola},
  title = {Plug-and-play application platform: Towards mobile peer-to-peer},
  booktitle = {MUM '04: Proc. 3rd international conference on Mobile and Ubiquitous
	Multimedia},
  year = {2004},
  pages = {63--69},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {While peer-to-peer (P2P) has emerged as a new hot communication concept
	among the Internet users, mobile usage of P2P applications is still
	taking its first steps. This article first elaborates the evolutionary
	process that P2P architectures are going through. Challenges and
	requirements for mobile P2P are then identified, followed by a definition
	of a novel Plug-and-Play Application Platform (PnPAP). This platform
	enables dynamic selections between diverse P2P and session management
	protocols while preserving the best available network connectivity
	through Holistic Connectivity (HCon) management. On-the-fly reconfiguration
	and run-time parameter optimization can be done with a lightweight
	interpretable state machine. The concept enables flexible and seamless
	communications for mobile devices in P2P networks.},
  doi = {10.1145/1052380.1052390},
  isbn = {1-58113-981-0},
  location = {College Park, Maryland},
  url = {http://portal.acm.org/citation.cfm?doid=1052380.1052390}
}

@INPROCEEDINGS{Hazel02Achord_Variantof,
  author = {Steven Hazel and Brandon Wiley},
  title = {Achord: A variant of the {Chord} lookup service for use in censorship
	resistant peer-to-peer publishing systems},
  booktitle = {IPTPS '02: Proc. 1st international workshop on Peer-to-Peer Systems},
  year = {2002},
  abstract = {Any peer-to-peer publishing system must provide a mechanism for efficiently
	locating published documents. For censorship resistant systems, it
	is particularly important that the lookup mechanism be difficult
	to disable or abuse. Chord [1] is a promising distributed lookup
	mechanism, because analysis has provided certain useful guarantees
	about the speed and correctness of Chord's operation. We examine
	the suitability of Chord for building censorship resistant peer-to-peer
	publishing systems, and suggest Achord, a variant of the Chord mechanism
	which takes into account the additional requirements imposed by the
	goal of censorship resistance.},
  url = {http://www.thalassocracy.org/achord/achord-iptps.html}
}

@INPROCEEDINGS{Kaminsky03Decentralizeduserauthentication,
  author = {Michael Kaminsky and George Savvides and David Mazi\`{e}res and M.
	Frans Kaashoek},
  title = {Decentralized user authentication in a global file system},
  booktitle = {SOSP '03: Proc. 19th ACM symposium on Operating Systems Principles},
  year = {2003},
  pages = {60--73},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {The challenge for user authentication in a global file system is allowing
	people to grant access to specific users and groups in remote administrative
	domains, without assuming any kind of pre-existing administrative
	relationship. The traditional approach to user authentication across
	administrative domains is for users to prove their identities through
	a chain of certificates. Certificates allow for general forms of
	delegation, but they often require more infrastructure than is necessary
	to support a network file system.This paper introduces an approach
	without certificates. Local authentication servers pre-fetch and
	cache remote user and group definitions from remote authentication
	servers. During a file access, an authentication server can establish
	identities for users based just on local information. This approach
	is particularly well-suited to file systems, and it provides a simple
	and intuitive interface that is similar to those found in local access
	control mechanisms. An implementation of the authentication server
	and a file server supporting access control lists demonstrate the
	viability of this design in the context of the Self-certifying File
	System (SFS). Experiments demonstrate that the authentication server
	can scale to groups with tens of thousands of members.},
  doi = {10.1145/945445.945452},
  isbn = {1-58113-757-5},
  location = {Bolton Landing, NY, USA},
  url = {http://portal.acm.org/citation.cfm?id=945445.945452}
}

@INPROCEEDINGS{Keleher99Decentralizedreplicated-objectprotocols,
  author = {Peter J. Keleher},
  title = {Decentralized replicated-object protocols},
  booktitle = {PODC '99: Proc. eighteenth annual ACM symposium on Principles of
	distributed computing},
  year = {1999},
  pages = {143--151},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {We describe a new replicated-object protocol designed for use in mobile
	and weakly-connected environments. The protocol differs from previous
	protocols in combining epidemic information propagation with voting,
	and in using fixed per-object currencies for voting. The advantage
	of epidemic protocols is that data movement only requires pairwise
	communication. Hence, there is no need for a majority quorum to be
	available and simultaneously connected at any single time. The protocols
	increase availability by using voting, rather than primary copy or
	primary commit schemes. Finally, the use of per-object voting currencies
	allows votes to take place in an entirely decentralized fashion,
	without any server having complete knowledge of group membership.
	We show that currency allocation can be used to implement diverse
	policies. For example, uniform currency distributions emulate traditional
	dynamic voting schemes, while allocating all currency to a single
	server emulates a primary-copy scheme. We present simulation results
	showing both schemes, as well as the performance advantages of using
	currency proxies to temporarily reallocate currency during planned
	disconnections.},
  doi = {10.1145/301308.301345},
  isbn = {1-58113-099-6},
  location = {Atlanta, Georgia, United States},
  url = {http://portal.acm.org/citation.cfm?id=301308.301345}
}

@INPROCEEDINGS{Ledlie03Scoopedagain,
  author = {Jonathan Ledlie and Jeff Shneidman and Margo Seltzer and John Huth},
  title = {Scooped, again},
  booktitle = {IPTPS '03: Proc. 2nd international workshop on Peer-To-Peer Systems},
  year = {2003},
  volume = {2735},
  series = {Lecture Notes in Computer Science},
  pages = {129--138},
  publisher = {Springer Berlin / Heidelberg},
  abstract = {The Peer-to-Peer (p2p) and Grid infrastructure communities are tackling
	an overlapping set of problems. In addressing these problems, p2p
	solutions are usually motivated by elegance or research interest.
	Grid researchers, under pressure from thousands of scientists with
	real file sharing and computational needs, are pooling their solutions
	from a wide range of sources in an attempt to meet user demand. Driven
	by this need to solve large scientific problems quickly, the Grid
	is being constructed with the tools at hand: FTP or RPC for data
	transfer, centralization for scheduling and authentication, and an
	assumption of correct, obediant nodes. If history is any guide, the
	World Wide Web depicts viscerally that systems that address user
	needs can have enormous staying power and affect future research.
	The Grid infrastructure is a great customer waiting for future p2p
	products. By no means should we make them our only customers, but
	we should at least put them on the list. If p2p research does not
	at least address the Grid, it may eventually be sidelined by defacto
	distributed algorithms that are less elegant but were used to solve
	Grid problems. In essense, we'll have been scooped, again.},
  doi = {10.1007/b11823},
  url = {http://www.springerlink.com/content/vlja6rjgaq4vtavt}
}

@INPROCEEDINGS{Lee03Cooperativepeergroups,
  author = {Seungjoon Lee and Rob Sherwood and Bobby Bhattacharjee},
  title = {Cooperative peer groups in {NICE}},
  booktitle = {INFOCOM '03: Proc. 22nd annual joint conference of the IEEE Computer
	and Communications Societies},
  year = {2003},
  volume = {2},
  pages = {1272--1282},
  month = {30 March--3 April },
  abstract = {We present a distributed scheme for trust inference in peer-to-peer
	networks. Our work is in the context of the NICE system, which is
	a platform for implementing cooperative applications over the Internet.
	We describe a technique for efficiently storing user reputation information
	in a completely decentralized manner, and show how this information
	can be used to efficiently identify non-cooperative users in NICE.
	We present a simulation-based study of our algorithms, in which we
	show our scheme scales to thousands of users using modest amounts
	of storage, processing, and bandwidth at any individual node. Lastly
	we show that our scheme is robust and can form cooperative groups
	in systems where the vast majority of users are malicious.},
  keywords = {Internet, inference mechanisms, information retrieval Internet, NICE
	system, cooperative system, decentralized manner, distributed algorithm,
	individual node, malicious users, noncooperative users identification,
	peer-to-peer networks, platform, reputation information storage,
	trust inference},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1208963}
}

@INPROCEEDINGS{Li03FeasibilityofPeer-to-Peer,
  author = {Jinyang Li and Boon Loo and Joseph Hellerstein and M. Kaashoek and
	David Karger and Robert Morris},
  title = {On the feasibility of peer-to-peer web indexing and search},
  booktitle = {IPTPS '03: Proc. 2nd international workshop on Peer-To-Peer Systems},
  year = {2003},
  volume = {2735},
  series = {Lecture Notes in Computer Science},
  pages = {207--215},
  publisher = {Springer Berlin / Heidelberg},
  abstract = {This paper discusses the feasibility of peer-to-peer full-text keyword
	search of the Web. Two classes of keyword search techniques are in
	use or have been proposed: flooding of queries over an overlay network
	(as in Gnutella), and intersection of index lists stored in a distributed
	hash table. We present a simple feasibility analysis based on the
	resource constraints and search workload. Our study suggests that
	the peer-to-peer network does not have enough capacity to make naive
	use of either of search techniques attractive for Web search. The
	paper presents a number of existing and novel optimizations for {P2P}
	search based on distributed hash tables, estimates their effects
	on performance, and concludes that in combination these optimizations
	would bring the problem to within an order of magnitude of feasibility.
	The paper suggests a number of compromises that might achieve the
	last order of magnitude.},
  doi = {10.1007/b11823},
  url = {http://www.springerlink.com/content/drdkdgvlgnw0ljkh}
}

@MISC{Lohmann06IAAL_WhatPeer-to-Peer,
  author = {Fred von Lohmann},
  title = {{IAAL*:} What peer-to-peer developers need to know about copyright
	law},
  howpublished = {http://www.eff.org/wp/iaal-what-peer-peer-developers-need-know-about-copyright-law},
  month = {Jan},
  year = {2006},
  note = {Electronic Frontier Foundation},
  abstract = {Intro: The future of peer-to-peer file-sharing is entwined, for better
	or worse, with copyright law. Copyright owners have already targeted
	not only the makers of file-sharing clients like Napster, Scour,
	Audiogalaxy, Aimster and Kazaa, and Morpheus, but also companies
	that provide products that rely on or add value to public P2P networks,
	such as MP3Board.com, which provided a web-based search interface
	for the gnutella network. The U.S. Supreme Court in MGM v. Grokster
	addressed some, but by no means all, of the copyright law issues
	that may confront P2P developers and other technologists in the future.
	
	
	If these courtroom skirmishes yield any lesson for P2P developers,
	it is that a legal strategy needs to be in place early, preferably
	at the beginning of development, rather than bolted on at the end.},
  url = {http://www.eff.org/wp/iaal-what-peer-peer-developers-need-know-about-copyright-law}
}

@INPROCEEDINGS{Muthitacharoen01low-bandwidthnetworkfile,
  author = {Athicha Muthitacharoen and Benjie Chen and David Mazi\`{e}res},
  title = {A low-bandwidth network file system},
  booktitle = {SOSP '01: Proc. 18th ACM symposium on Operating systems principles},
  year = {2001},
  pages = {174--187},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {Users rarely consider running network file systems over slow or wide-area
	networks, as the performance would be unacceptable and the bandwidth
	consumption too high. Nonetheless, efficient remote file access would
	often be desirable over such networks---particularly when high latency
	makes remote login sessions unresponsive. Rather than run interactive
	programs such as editors remotely, users could run the programs locally
	and manipulate remote files through the file system. To do so, however,
	would require a network file system that consumes less bandwidth
	than most current file systems.This paper presents LBFS, a network
	file system designed for low-bandwidth networks. LBFS exploits similarities
	between files or versions of the same file to save bandwidth. It
	avoids sending data over the network when the same data can already
	be found in the server's file system or the client's cache. Using
	this technique in conjunction with conventional compression and caching,
	LBFS consumes over an order of magnitude less bandwidth than traditional
	network file systems on common workloads.},
  doi = {10.1145/502034.502052},
  isbn = {1-58113-389-8},
  location = {Banff, Alberta, Canada},
  url = {http://portal.acm.org/citation.cfm?id=502052}
}

@INPROCEEDINGS{Quinlan02AwardedBestPaper!,
  author = {Sean Quinlan and Sean Dorward},
  title = {Venti: a new approach to archival data storage},
  booktitle = {FAST '02: Proc. 1st USENIX conference on File and Storage Technologies},
  year = {2002},
  pages = {7},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {This paper describes a network storage system, called Venti, intended
	for archival data. In this system, a unique hash of a block's contents
	acts as the block identifier for read and write operations. This
	approach enforces a write-once policy, preventing accidental or malicious
	destruction of data. In addition, duplicate copies of a block can
	be coalesced, reducing the consumption of storage and simplifying
	the implementation of clients. Venti is a building block for constructing
	a variety of storage applications such as logical backup, physical
	backup, and snapshot file systems.
	
	
	We have built a prototype of the system and present some preliminary
	performance results. The system uses magnetic disks as the storage
	technology, resulting in an access time for archival data that is
	comparable to non-archival data. The feasibility of the write-once
	model for storage is demonstrated using data from over a decadeÕs
	use of two Plan 9 file systems.},
  location = {Monterey, CA},
  url = {http://www.usenix.org/publications/library/proceedings/fast02/quinlan.html}
}

@INPROCEEDINGS{Rhea03Pond_OceanStoreprototype,
  author = {Sean Rhea and Patrick Eaton and Dennis Geels and Hakim Weatherspoon
	and Ben Zhao and John Kubiatowicz},
  title = {Pond: the {OceanStore} prototype},
  booktitle = {FAST '03: Proc. 2nd USENIX conference on File and Storage Technologies},
  year = {2003},
  pages = {1--14},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {OceanStore is an Internet-scale, persistent data store designed for
	incremental scalability, secure sharing, and long-term durability.
	Pond is the OceanStore prototype; it contains many of the features
	of a complete system including location-independent routing, Byzantine
	update commitment, push-based update of cached copies through an
	overlay multicast network, and continuous archiving to erasure-coded
	form. In the wide area, Pond outperforms NFS by up to a factor of
	4.6 on read-intensive phases of the Andrew benchmark, but underperforms
	NFS by as much as a factor of 7.3 on write-intensive phases. Microbenchmarks
	show that write performance is limited by the speed of erasure coding
	and threshold signature generation, two important areas of future
	research. Further microbenchmarks show that Pond manages replica
	consistency in a bandwidth-efficient manner and quantify the latency
	cost imposed by this bandwidth savings.},
  location = {San Francisco, CA},
  url = {http://www.usenix.org/events/fast03/tech/rhea.html}
}

@INPROCEEDINGS{Rowstron01Pastry_ScalableDecentralized,
  author = {Antony Rowstron and Peter Druschel},
  title = {Pastry: Scalable, decentralized object location, and routing for
	{Large-Scale} {Peer-to-Peer} systems},
  booktitle = {Middleware '01: Proc. IFIP/ACM international conference on Distributed
	Systems Platforms},
  year = {2001},
  series = {Lecture Notes in Computer Science},
  pages = {329--350},
  address = {Heidelberg, Germany},
  publisher = {Springer Berlin / Heidelberg},
  abstract = {This paper presents the design and evaluation of Pastry, a scalable,
	distributed object location and routing substrate for wide-area peer-to-peer
	applications. Pastry performs application-level routing and object
	location in a potentially very large overlay network of nodes connected
	via the Internet. It can be used to support a variety of peer-to-peer
	applications, including global data storage, data sharing, group
	communication and naming.
	
	Each node in the Pastry network has a unique identifier {(nodeId).}
	When presented with a message and a key, a Pastry node efficiently
	routes the message to the node with a {nodeId} that is numerically
	closest to the key, among all currently live Pastry nodes. Each Pastry
	node keeps track of its immediate neighbors in the {nodeId} space,
	and notifies applications of new node arrivals, node failures and
	recoveries. Pastry takes into account network locality; it seeks
	to minimize the distance messages travel, according to a to scalar
	proximity metric like the number of {IP} routing hops
	
	
	Pastry is completely decentralized, scalable, and self-organizing;
	it automatically adapts to the arrival, departure and failure of
	nodes. Experimental results obtained with a prototype implementation
	on an emulated network of up to 100,000 nodes confirm Pastry's scalability
	and efficiency, its ability to self-organize and adapt to node failures,
	and its good network locality properties},
  doi = {10.1007/3-540-45518-3_18},
  keywords = {dht, p2p},
  url = {http://www.springerlink.com/content/404522p56nm85503/}
}

@INPROCEEDINGS{Thekkath97Frangipani_scalabledistributed,
  author = {Chandramohan A. Thekkath and Timothy Mann and Edward K. Lee},
  title = {Frangipani: a scalable distributed file system},
  booktitle = {SOSP '97: Proc. 16th ACM symposium on Operating Systems Principles},
  year = {1997},
  pages = {224--237},
  address = {New York, NY, USA},
  publisher = {ACM},
  abstract = {The ideal distributed file system wouldprovide all its users with
	coherent, shared access to the same set of files,yet would be arbitrarily
	scalable to provide more storage space and higher performance to
	a growing user community. It would be highly available in spite of
	component failures. It would require minimal human administration,
	and administration would not become more complex as more components
	were added. Frangipani is a new file system that approximates this
	ideal, yet was relatively easy to build because of its two-layer
	structure. The lower layer is Petal (described in an earlier paper),
	a distributed storage service that provides incrementally scalable,
	highly available, automatically managed virtual disks. In the upper
	layer, multiple machines run the same Frangipani file system code
	on top of a shared Petal virtual disk, using a distributed lock service
	to ensure coherence. Frangipani is meant to run in a cluster of machines
	that are under a common administration and can communicate securely.
	Thus the machines trust one another and the shared virtual disk approach
	is practical. Of course, a Frangipani file system can be exported
	to untrusted machines using ordinary network file access protocols.
	We have implemented Frangipani on a collection of Alphas running
	DIGITAL Unix 4.0. Initial measurements indicate that Frangipani has
	excellent single-server performance and scales well as servers are
	added.},
  doi = {10.1145/268998.266694},
  isbn = {0-89791-916-5},
  location = {Saint Malo, France},
  url = {http://portal.acm.org/citation.cfm?doid=268998.266694}
}

@INPROCEEDINGS{Waldman00Publius_robusttamper-evident,
  author = {Marc Waldman and Aviel D. Rubin and Lorrie Faith Cranor},
  title = {Publius: A robust, tamper-evident, censorship-resistant web publishing
	system},
  booktitle = {SSYM '00: Proc. 9th USENIX Security Symposium},
  year = {2000},
  pages = {59--72},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {We describe a system that we have designed and implemented for publishing
	content on the web. Our publishing scheme has the property that it
	is very difficult for any adversary to censor or modify the content.
	In addition, the identity of the publisher is protected once the
	content is posted. Our system differs from others in that we provide
	tools for updating or deleting the published content, and users can
	browse the content in the normal point and click manner using a standard
	web browser and a client-side proxy that we provide. All of our code
	is freely available.},
  location = {Denver, Colorado},
  url = {http://www.cs.nyu.edu/~waldman/publius/paper.html}
}

@INPROCEEDINGS{Walfish06Distributedquotaenforcement,
  author = {Michael Walfish and J.D. Zamfirescu and Hari Balakrishnan and David
	Karger},
  title = {Distributed quota enforcement for spam control},
  booktitle = {NSDI '06: Proc. 3rd USENIX symposium on Networked Systems Design
	\& Implementation},
  year = {2006},
  pages = {281--296},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {Spam, by overwhelming inboxes, has made email a less reliable medium
	than it was just a few years ago. Spam filters are undeniably useful
	but unfortunately can flag non-spam as spam. To restore email's reliability,
	a recent spam control approach grants quotas of stamps to senders
	and has the receiver communicate with a well-known quota enforcer
	to verify that the stamp on the email is fresh and to cancel the
	stamp to prevent reuse. The literature has several proposals based
	on this general idea but no complete system design and implementation
	that: scales to today's email load (which requires the enforcer to
	be distributed over many hosts and to tolerate faults in them), imposes
	minimal trust assumptions, resists attack, and upholds today's email
	privacy. This paper describes the design, implementation, analysis,
	and experimental evaluation of DQE, a spam control system that meets
	these challenges. DQE's enforcer occupies a point in the design spectrum
	notable for simplicity: mutually untrusting nodes implement a storage
	abstraction but avoid neighbor maintenance, replica maintenance,
	and heavyweight cryptography.},
  location = {San Jose, CA},
  url = {http://www.usenix.org/events/nsdi06/tech/walfish.html}
}

@INPROCEEDINGS{Walsh06ExperiencewithObject,
  author = {Kevin Walsh and Emin G{\"u}n Sirer},
  title = {Experience with an object reputation system for peer-to-peer filesharing},
  booktitle = {NSDI '06: Proc. 3rd USENIX symposium on Networked Systems Design
	\& Implementation},
  year = {2006},
  pages = {1--1},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {In this paper, we describe Credence, a decentralized object reputation
	and ranking system for large-scale peer-to-peer filesharing networks.
	Credence counteracts pollution in these networks by allowing honest
	peers to assess the authenticity of online content through secure
	tabulation and management of endorsements from other peers. Our system
	enables peers to learn relationships even in the absence of direct
	observations or interactions through a novel, flow-based trust computation
	to discover trustworthy peers. We have deployed Credence as an overlay
	on top of the Gnutella filesharing network, with more than 10,000
	downloads of our client software to date. We describe the system
	design, our experience with its deployment, and results from a long-term
	study of the trust network built by users. Data from the live deployment
	shows that Credence's flow-based trust computation enables users
	to avoid undesirable content. Honest Credence clients can identify
	three quarters of the decoys encountered when querying the Gnutella
	network.},
  location = {San Jose, CA},
  url = {http://www.usenix.org/events/nsdi06/tech/walsh.html}
}

@INPROCEEDINGS{Yu06Availabilityofmulti-object,
  author = {Haifeng Yu and Phillip~B. Gibbons and Suman Nath},
  title = {Availability of multi-object operations},
  booktitle = {NSDI '06: Proc. 3rd USENIX symposium on Networked Systems Design
	\& Implementation},
  year = {2006},
  pages = {16--16},
  address = {Berkeley, CA, USA},
  publisher = {USENIX Association},
  abstract = {Highly-available distributed storage systems are commonly designed
	to optimize the availability of individual data objects, despite
	the fact that user level tasks typically request multiple objects.
	In this paper, we show that the assignment of object replicas (or
	fragments, in the case of erasure coding) to machines plays a dramatic
	role in the availability of such multi-object operations, without
	affecting the availability of individual objects. For example, for
	the TPC-H benchmark under real-world failures, we observe differences
	of up to four nines between popular assignments used in existing
	systems. Experiments using our wide-area storage system prototype,
	MOAT, on the PlanetLab, as well as extensive simulations, show which
	assignments lead to the highest availability for a given setting.},
  location = {San Jose, CA},
  url = {http://www.usenix.org/events/nsdi06/tech/yu.html}
}