Maintaining distributed hash tables in an overlay network
AssigneeTelefonaktiebolaget L M Ericsson (publ)
InventorJouni Mäenpää
Life of this patent
Estimating the term…
Loading patent…
AssigneeTelefonaktiebolaget L M Ericsson (publ)
InventorJouni Mäenpää
Estimating the term…
A method of maintaining routing tables at nodes of an overlay network, where a routing table of a given node contains, for each of a set of neighboring successor and predecessor nodes, a mapping between an overlay network address of the node and a physical locator of the node. The method comprises, upon or immediately prior to departure of a node from the overlay network, sending a Leave request from the departing node (or one of the neighboring nodes of the departing node aware of the departure) to each neighboring node (or each other neighboring node of the departing node), indicating the departure and containing one or more mappings for nodes not contained within the routing table of the recipient node. Each neighboring node (or each other neighboring node) receives the Leave request and uses said mapping(s) to update its routing table.
A method of maintaining a plurality of routing tables at a respective plurality of nodes of a Distributed Hash Table (DHT) based overlay network, with each of the plurality of routing tables being maintained for a respective one of the nodes, the method comprising:
A method of maintaining a plurality of routing tables at a respective plurality of nodes of a Distributed Hash Table (DHT) based overlay network, with each of the plurality of routing tables being maintained for a respective one of the nodes, the method comprising:
A method of maintaining a plurality of routing tables with each of the plurality of routing tables being maintained at a respective plurality of nodes of a Distributed Hash Table, (DHT) based overlay network, with each of the plurality of routing tables being maintained for a respective one of the nodes, comprising:
A node for use within a Distributed Hash Table (DHT) based overlay network comprising:
A method of maintaining a plurality of routing tables with each of the plurality of routing tables being maintained for a respective node of an overlay network, the method comprising:
A method of maintaining a routing table at a given node of a plurality of nodes of a Distributed Hash Table (DHT) based overlay network, wherein a respective routing table is provided for each of the plurality of nodes of the DHT based overlay network, the method comprising:
Dependencies are inferred from the claim text.
Drawings are temporarily unavailable. Open the PDF at USPTO
From the US filing history. Foreign family members aren’t listed.
In which an application is distributed across nodes in the network: peer-to-peer [P2P] networks
Group management mechanisms: departure or maintenance mechanisms
Using node-based peer discovery mechanisms: discovery involving distributed pre-established resource-based relationships among peers, e.g. based…
Digital communication
About 2 years 2 months of term left · ends 3 Jan 2029 (estimated)
This application is a 35 U.S.C. §371 national stage application of PCT International Application No. PCT/EP2008/056376, filed on 23 May 2008, the disclosure and content of which is incorporated by reference herein in its entirety. The above-referenced PCT International Application was published in the English language as International Publication No. WO 2009/141013 A1 on Nov. 26, 2009.
The present invention relates to a mechanism for maintaining distributed hash tables in an overlay network. The invention is applicable in particular to an optimised procedure for handling the leaving of a node from an overlay network
Peer-to-peer or P2P networks make use of the pooled resources of participating nodes including processing capabilities and communication bandwidth to facilitate a wide variety of services including file sharing and VoIP telephony. In the absence of central servers, particular P2P services may make use of “overlay networks” to optimise resource location. An overlay network comprises nodes connected by virtual links representing paths extending across possibly many physical links in the underlying network (e.g. the Internet). Each node in the overlay network maintains a routing table containing a set of links to certain other nodes within the overlay network. Resource requests are passed between nodes until they arrive at a node which is responsible for that resource.
FIG. 1 illustrates schematically a DHT-based ring overlay network comprising a number of nodes;
FIG. 2 further illustrates a DHT-based ring overlay network, showing neighbourhood relations between nodes;
FIG. 3 illustrates schematically a node of the overlay network of FIG. 2;
The optimized DHT leave operation described here relies upon a node assisting a neighbouring node to quickly update its routing tables in the event that the neighbouring node's routing table is affected by the departure of a node from the network. The departing node may be the neighbouring node, i.e. in the graceful departure scenario, or another neighbouring node in the case of an ungraceful departure. These two scenarios will now be considered in detail.
Reference is made again to FIG. 2 which shows an example of a Chord DHT-based overlay network using a ring topology. Whilst Chord DHT is used here by way of example, the procedures described are equally applicable to other DHT-based overlay networks. In the example illustrated, it is assumed that each node in the DHT-based overlay network maintains pointers to six neighbours: namely three predecessor nodes and three successor nodes. Of course, the proposed mechanism works with any number of successor and predecessor pointers.
In FIG. 2, a Node X has three successors: S1, S2, and S3. If the overlay network is experiencing heavy “churn”, all of the successors of Node X might choose to leave the overlay network within a short time frame. Assuming that the nodes depart gracefully, they will send Leave requests to their neighbours. However, as described above, Node X may not have time to identify any other successor nodes before all three successors have left the network. In order to avoid a partitioning of the network in this scenario, each node that intends to leave the overlay helps its neighbours to fill their routing tables with alternative neighbour nodes, before actually leaving the network.