Wide-area cooperative storage with CFS

Dabek, Frank; Kaashoek, M. Frans; Karger, David R.; Morris, Robert; Stoica, Ion

doi:10.1145/502034.502054

Cited by 801 publications

(267 citation statements)

References 15 publications

Supporting

Mentioning

265

Contrasting

Unclassified

Order By: Relevance

“…Many of the load balancing schemes are based on the notion of virtual servers [11][12][13]. Each peer is assigned several virtual servers, each of which is responsible for a portion of the ID space (i.e., hash space) of the DHT, and a load distribution is conducted by migrating virtual servers among peers.…”

Section: Task Migration Based Approachesmentioning

confidence: 99%

“…A query counter for counting total number of incoming queries is used at every peer (line 1). If peer n i exceeds the threshold of query load T 0 (line 2), then the following process is used to justify the main cause of this overloading (line [4][5][6][7][8][9][10][11]. If this overloading is mainly caused by the response load (line 4), n i will choose an index replica of d i for its neighbor peer n j , where d i and n j are selected by sorting w(d i , n j ), which is maintained by peer n i (line 5-6).…”

Section: Passive Index Replicationmentioning

confidence: 99%

See 1 more Smart Citation

Cost-Effective Replication Schemes for Query Load Balancing in DHT-Based Peer-to-Peer File Searches

Cao

Fujita

2014

Journal of Information Processing Systems

View full text Add to dashboard Cite

In past few years, distributed hash table (DHT)-based P2P systems have been proven to be a promising way to manage decentralized index information and provide efficient lookup services. However, the skewness o regarding keywords contained in a multi-keyword query causes a query load imbalance that combines both routing and response load. This imbalance means long file retrieval latency that negatively influences the overall system performance. Although index replication has a great potential for alleviating this problem, existing schemes did not explicitly address it or incurred high cost. To overcome this issue, we propose, in this paper, an integrated solution that consists of three replication schemes to alleviate query load imbalance while minimizing the cost. The first scheme is an active index replication that is used in order to decrease routing load in the system and to distribute response load of an index among peers that store replicas of the index. The second scheme is a proactive pointer replication that places location information of each index to a predetermined number of peers for reducing maintenance cost between the index and its replicas. The third scheme is a passive index replication that guarantees the maximum query load of peers. The result of simulations indicates that the proposed schemes can help alleviate the query load imbalance of peers. Moreover, it was found by comparison that our schemes are more cost-effective on placing replicas than PCache and EAD.

show abstract

Section: Task Migration Based Approachesmentioning

confidence: 99%

Section: Passive Index Replicationmentioning

confidence: 99%

Cost-Effective Replication Schemes for Query Load Balancing in DHT-Based Peer-to-Peer File Searches

Cao

Fujita

2014

Journal of Information Processing Systems

View full text Add to dashboard Cite

show abstract

“…All of them are distributed hash table (DHT) based approaches, which divide and distribute the routing lookup table to all participating nodes of the network. Systems for the general-purpose of file storage and exchange have been built on top of these routing protocols, e.g., CFS [6] on Chord [22], and PAST [20] on Pastry [21]. However, to retrieve the content, these systems can only operate in a "download mode".…”

Section: Related Workmentioning

confidence: 99%

PeerStreaming: design and implementation of an on-demand distributed streaming system with digital rights management capabilities

Cui

Chang

2007

Multimedia Systems

View full text Add to dashboard Cite

We have developed PeerStreaming, an on-demand peer-to-peer (P2P) media streaming system. The behavior of a PeerStreaming client is very much like an ordinary media player: it streams and plays whatever media the user desires, starting at whatever point he/she desires. Under the hood, however, the media is delivered from multiple peers to the client. The serving peers can be the media server, but more commonly they are the clients that have received the media in a previous streaming session. Leveraging the network and storage resources of the P2P network and retrieving a major part of the media from nearby peers, PeerStreaming greatly improves streaming media quality, reduces server load, and eases traffic on the network. We describe the design and implementation of the PeerStreaming system in this paper, with a focus on a number of key components. They include: (1) peer discovery and content location, (2) scalable coded and randomly accessible media format, (3) receiver-driven streaming, (4) digital rights management, and (5) architecture for the media rendering, caching and serving system.

show abstract

“…However, network locality has not been amply exploited (except in case of Pastry). Examples of P2P systems include CFS [11] on top of Chord [30], and PAST [27] on top of Pastry [26]. Another example is Pixie [25]: a P2P content exchange architecture.…”

Section: Related Workmentioning

confidence: 99%

“…In a P2P system, peers communicate directly with each other for the sharing of data as well as other resources such as storage and CPU cycles. Paralleling research in other aspects of P2P, such as lookup [23,26,30], storage [11,27], and multicast [1,9,32], we in this paper focus on P2P media streaming, which poses more stringent bandwidth requirement than general file sharing. More specifically, as first addressed in our earlier work [33], for a media streaming session with playback rate R 0 , a single sending peer may not be able or willing to contribute the full outbound bandwidth of R 0 .…”

Section: Introductionmentioning

confidence: 99%

CollectCast: A peer-to-peer service for media streaming

Hefeeda

Habib

et al. 2005

Multimedia Systems

View full text Add to dashboard Cite

We present CollectCast, a peer-to-peer (P2P) service for media streaming where a receiver peer is served by multiple sender peers. CollectCast operates at the application level but infers underlying network properties to correlate end-to-end connections between peers. The salient features of CollectCast include: (1) a novel multisender selection method that exploits the performance correlation and dependency among connections between different candidate senders and the receiver, (2) a customization of network tomography techniques and demonstration of improved practicality and efficiency, and (3) an aggregation-based P2P streaming mechanism that sustains receiver-side quality in the presence of sender/network dynamics and degradation. We have performed both real-world (on PlanetLab) and simulation evaluation of CollectCast. Our simulation results show that for a receiver, CollectCast makes better selection of multiple senders than other methods that do not infer underlying network properties. Our PlanetLab experiments are performed using a P2P media streaming application (called PROMISE) which we developed on top of CollectCast. Both packet-level and frame-level performance of MPEG-4 video streaming demonstrates the practicality and effectiveness of CollectCast.

show abstract

Wide-area cooperative storage with CFS

Cited by 801 publications

References 15 publications

Cost-Effective Replication Schemes for Query Load Balancing in DHT-Based Peer-to-Peer File Searches

Cost-Effective Replication Schemes for Query Load Balancing in DHT-Based Peer-to-Peer File Searches

PeerStreaming: design and implementation of an on-demand distributed streaming system with digital rights management capabilities

CollectCast: A peer-to-peer service for media streaming

Contact Info

Product

Resources

About