Adaptive content management in structured P2P communities

Jussi Kangasharju, Keith Ross, David A. Turner

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    A fundamental paradigm in P2P is that of a large community of intermittently-connected nodes that cooperate to share files. Because nodes are intermittently connected, the P2P community must replicate and replace files as a function of their popularity to achieve satisfactory performance. We develop a suite of distributed, adaptive algorithms for replicating and replacing content in a P2P community. We do this for structured P2P communities, in which a distributed hash table (DHT) overlay is available for locating the node responsible for a key. In particular, we develop the Top-K MFR replication and replacement algorithm, which can be layered on top of a DHT overlay, and in addition adaptively converges to a nearly-optimal replication profile. Furthermore, we evaluate the file transfer load caused by the adaptive algorithms on each peer, and present two approaches for achieving a better load balance. Our evaluation shows that with our two algorithms, an arbitrary load distribution is possible, hence allowing each peer to serve requests at the rate it wishes.

    Original languageEnglish (US)
    Title of host publicationProceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06
    Volume152
    DOIs
    StatePublished - 2006
    Event1st International Conference on Scalable Information Systems, InfoScale '06 - Hong Kong, China
    Duration: May 30 2006Jun 1 2006

    Other

    Other1st International Conference on Scalable Information Systems, InfoScale '06
    CountryChina
    CityHong Kong
    Period5/30/066/1/06

    Fingerprint

    Adaptive algorithms

    ASJC Scopus subject areas

    • Human-Computer Interaction

    Cite this

    Kangasharju, J., Ross, K., & Turner, D. A. (2006). Adaptive content management in structured P2P communities. In Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06 (Vol. 152). [1146871] https://doi.org/10.1145/1146847.1146871

    Adaptive content management in structured P2P communities. / Kangasharju, Jussi; Ross, Keith; Turner, David A.

    Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06. Vol. 152 2006. 1146871.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kangasharju, J, Ross, K & Turner, DA 2006, Adaptive content management in structured P2P communities. in Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06. vol. 152, 1146871, 1st International Conference on Scalable Information Systems, InfoScale '06, Hong Kong, China, 5/30/06. https://doi.org/10.1145/1146847.1146871
    Kangasharju J, Ross K, Turner DA. Adaptive content management in structured P2P communities. In Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06. Vol. 152. 2006. 1146871 https://doi.org/10.1145/1146847.1146871
    Kangasharju, Jussi ; Ross, Keith ; Turner, David A. / Adaptive content management in structured P2P communities. Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06. Vol. 152 2006.
    @inproceedings{6dc5f81f9f7c4ee1933ef6bd86435319,
    title = "Adaptive content management in structured P2P communities",
    abstract = "A fundamental paradigm in P2P is that of a large community of intermittently-connected nodes that cooperate to share files. Because nodes are intermittently connected, the P2P community must replicate and replace files as a function of their popularity to achieve satisfactory performance. We develop a suite of distributed, adaptive algorithms for replicating and replacing content in a P2P community. We do this for structured P2P communities, in which a distributed hash table (DHT) overlay is available for locating the node responsible for a key. In particular, we develop the Top-K MFR replication and replacement algorithm, which can be layered on top of a DHT overlay, and in addition adaptively converges to a nearly-optimal replication profile. Furthermore, we evaluate the file transfer load caused by the adaptive algorithms on each peer, and present two approaches for achieving a better load balance. Our evaluation shows that with our two algorithms, an arbitrary load distribution is possible, hence allowing each peer to serve requests at the rate it wishes.",
    author = "Jussi Kangasharju and Keith Ross and Turner, {David A.}",
    year = "2006",
    doi = "10.1145/1146847.1146871",
    language = "English (US)",
    isbn = "1595934286",
    volume = "152",
    booktitle = "Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06",

    }

    TY - GEN

    T1 - Adaptive content management in structured P2P communities

    AU - Kangasharju, Jussi

    AU - Ross, Keith

    AU - Turner, David A.

    PY - 2006

    Y1 - 2006

    N2 - A fundamental paradigm in P2P is that of a large community of intermittently-connected nodes that cooperate to share files. Because nodes are intermittently connected, the P2P community must replicate and replace files as a function of their popularity to achieve satisfactory performance. We develop a suite of distributed, adaptive algorithms for replicating and replacing content in a P2P community. We do this for structured P2P communities, in which a distributed hash table (DHT) overlay is available for locating the node responsible for a key. In particular, we develop the Top-K MFR replication and replacement algorithm, which can be layered on top of a DHT overlay, and in addition adaptively converges to a nearly-optimal replication profile. Furthermore, we evaluate the file transfer load caused by the adaptive algorithms on each peer, and present two approaches for achieving a better load balance. Our evaluation shows that with our two algorithms, an arbitrary load distribution is possible, hence allowing each peer to serve requests at the rate it wishes.

    AB - A fundamental paradigm in P2P is that of a large community of intermittently-connected nodes that cooperate to share files. Because nodes are intermittently connected, the P2P community must replicate and replace files as a function of their popularity to achieve satisfactory performance. We develop a suite of distributed, adaptive algorithms for replicating and replacing content in a P2P community. We do this for structured P2P communities, in which a distributed hash table (DHT) overlay is available for locating the node responsible for a key. In particular, we develop the Top-K MFR replication and replacement algorithm, which can be layered on top of a DHT overlay, and in addition adaptively converges to a nearly-optimal replication profile. Furthermore, we evaluate the file transfer load caused by the adaptive algorithms on each peer, and present two approaches for achieving a better load balance. Our evaluation shows that with our two algorithms, an arbitrary load distribution is possible, hence allowing each peer to serve requests at the rate it wishes.

    UR - http://www.scopus.com/inward/record.url?scp=34547339025&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34547339025&partnerID=8YFLogxK

    U2 - 10.1145/1146847.1146871

    DO - 10.1145/1146847.1146871

    M3 - Conference contribution

    SN - 1595934286

    SN - 9781595934284

    VL - 152

    BT - Proceedings of the 1st International Conference on Scalable Information Systems, InfoScale '06

    ER -