WO2009143738A1 - Management method, content querying method, system and apparatus of distributed network - Google Patents

Abstract

A management method, content querying method, system and apparatus of distributed network are disclosed by the embodiment of the present invention. The method includes that: when a node joins a distributed network, by querying content, a demand content list of said content is generated; when a node is the virtual server VS of said content, clustered management of said content is performed according to the demand content list. The solution provided by the embodiment of the present invention can ensure the steady distribution of content in network, and the effectivity and efficiency of querying content.

Description

 Distributed network management method, content query method, system and device

 The embodiments of the present invention relate to the field of network technologies, and in particular, to a management method, a content query method, a system, and a device for a distributed network. Background technique

 A P2P (Peer-to-peer) network is an emerging, distributed content sharing structure. In a P2P network, each node plays the role of a client and a server at the same time, providing content either as a content sharer or as a content consumer. When a node needs to use content, it finds the node that stores the content by keyword or key value, and obtains the desired content from those nodes.

 In carrying out the process of the present invention, the inventors have found that the prior art has at least the following problems:

 In the early P2P networks, content was only stored on the node that owns the content, and the node that needs the content can obtain the content by connecting the node that owns the content. However, when a large number of nodes need the same content, the node that owns the content cannot satisfy the query requirements of all nodes; on the other hand, when the node that owns the content fails or exits, other nodes in the network cannot obtain the content again.

 In order to solve the above problem, the concept of copying is introduced in the late P2P network, and the copy refers to the content that the node that does not own the content acquires and caches through the query. After the introduction of the replica in the network, although the burden on the node is reduced, the efficiency of the query is improved, but a new problem is also introduced. In a P2P network, there is no effective management between the copy of content and content. When the content stored on the node that owns the content is modified, how to simultaneously modify all the copies, and ensure that all nodes query the latest version of the content. Moreover, due to the transient nature of the nodes in the P2P network, the frequent replacement of nodes in the network, and the frequent changes in the content of the nodes, it is difficult to form a stable distribution. The efficiency of the node's search for content and the tracking of content changes are also affected by the migration and replacement of nodes.

There is currently a lack of nodes that allow content to be stably distributed across the network and require a certain content. A mechanism for quickly locating and obtaining valid content in the network. Summary of the invention

 The embodiment of the invention provides a distributed network management method, a content query method, a system and a device, so as to establish a novel network model of P2P content stable distribution, realize efficient searching of content, and track content changes, Content and its copies are controlled and managed.

 An embodiment of the present invention provides a method for managing a distributed network, including: when a node joins a distributed network, by searching for content, generating a required content table of the content;

 When the node is the virtual server VS of the content, cluster management of the content is performed according to the demand content table.

 An embodiment of the present invention provides a content query method for a distributed network, which includes:

 Receiving a query request of the content, the query request carrying a key value of the content; when the key value management range of the node does not include the key value of the content, obtaining a key value distance from the content according to the required content table The smallest node forwards the query request to the node with the smallest key-value from the content.

 An embodiment of the present invention provides a distributed network management system, including: a requirement content table generating node, configured to generate a content content table of the content by searching for content when the nodes respectively join the distributed network, and Routing and forwarding messages according to the demand content table;

 And a cluster management node, configured to perform cluster management of the content according to the demand content table.

An embodiment of the present invention provides a distributed network management system, including: a virtual server, configured to perform clustering management of the content according to a required content table; and a strong consistent node, configured to perform content update operations on the content, Sending an update request to the virtual server VS of the content; a weakly consistent node, configured to send a version verification request, when the version is the latest version of the content, perform a content update operation, and send an update request to the VS of the content; and the control node is configured to detect the content When the VS fails to leave, the content new VS is appointed, and when the content does not exist VS, the node that queried the content becomes the vs of the content.

 An embodiment of the present invention provides a weakly consistent node, including:

 a query module for finding content;

 a route forwarding module, configured to perform route routing of the message according to the stored content table of requirements;

 The first update operation module is configured to send a version verification request, and when the version is the latest version of the content, perform a content update operation, and send an update request to the VS of the content.

 An embodiment of the present invention provides a strong consistent node, including:

 a query module for finding content;

 a route forwarding module, configured to perform route routing of the message according to the stored content table of requirements;

 And a second update operation module, configured to perform a content update operation on the content, and send an update request to the VS of the content.

 An embodiment of the present invention provides a virtual server, which includes:

 a query module for finding content;

 a route forwarding module, configured to perform route routing of the message according to the stored content table of requirements;

 a clustering management module, configured to perform clustering management of the content according to the stored demand content table when accepting an update request for the content, detecting that the CP of the content or the CRP of the content fails to leave .

 An embodiment of the present invention provides a control node, which includes:

 a query module for finding content;

a route forwarding module, configured to perform routing and forwarding of messages according to the stored content table of requirements; a third detecting module, configured to detect whether the VS of the content is alive every other timer period;

 An appointment management module, configured to appoint the content new VS when the third detection module detects that the VS of the content is detached, and when the content does not exist VS, appoint a node that queries the content to become The content of the vs.

 Compared with the prior art, the technical solution of the embodiment of the present invention has the following advantages: The embodiment of the present invention can form a network with a regular topology structure by constructing a content and its copy and routing information, so that the content is stably distributed in the network; Ensure the efficiency of content search; effectively update and control the content and its copy, ensure the validity of the content and its copy; and reduce the entire network when the node moves and replaces and the node's content needs change Impact. DRAWINGS

 1 is a schematic diagram of a two-layer structure in an embodiment of the present invention;

 2 is a schematic diagram of adjacency connection between nodes in an embodiment of the present invention;

 3 is a data structure of a node in an embodiment of the present invention;

 4 is a schematic flowchart of a method for managing a distributed network according to Embodiment 1 of the present invention; FIG. 5 is a schematic diagram of CAN routing in Embodiment 2 of the present invention;

 6 is a schematic diagram of an improved route in Embodiment 2 of the present invention;

 FIG. 7 is a schematic flowchart of processing after a single node receives a query request according to Embodiment 2 of the present invention;

 8 is a schematic flow chart of a node performing content search and acquisition according to a second embodiment of the present invention;

 FIG. 9 is a schematic flowchart of a node performing content update and release according to a third embodiment of the present invention;

FIG. 10 is a timing diagram of a normal departure of a CP in Embodiment 4 of the present invention; FIG. 11 is a timing diagram of a CP in a normal departure according to Embodiment 4 of the present invention; FIG. 13 is a timing diagram of the VS in the fourth embodiment of the present invention when leaving the abnormal departure; FIG. 14 is a timing diagram of converting an IRP into an IRP according to Embodiment 5 of the present invention; FIG. 15 is a timing diagram of converting a CRP into an IRP according to Embodiment 5 of the present invention; FIG. 16 is a weak consensus node according to an embodiment of the present invention; schematic diagram;

 17 is a schematic diagram of a strong consistent node in an embodiment of the present invention;

 FIG. 18 is a schematic diagram of a virtual server according to an embodiment of the present invention; FIG.

 FIG. 19 is a schematic diagram of a control node according to an embodiment of the present invention. detailed description

 Embodiments of the present invention provide a method and an apparatus for managing a distributed network.

 The specific embodiments of the present invention are further described in detail below with reference to the accompanying drawings and embodiments.

 As shown in FIG. 1, the embodiment of the present invention logically divides the system into a layer structure, with the upper layer being the content distribution and the lower layer being the node distribution. Nodes use CAN (Controller Area Network) to establish d-dimensional key values. (All information in the registry is saved in various forms of key-value item data. Key-value items are represented by key-value names and data types. And the key value is composed of three parts, the format is: "key name: data type: key value") The basic route distribution of the space, and the content is mapped to the key value according to the DHT (Distributed Hash Table) mechanism. On a close node, one content and multiple nodes form a one-to-many relationship.

 As shown in Figure 1, each content is mapped by DHT to a node with the closest key value. This node is called the CAN CP (Control Peer) of the content, and the node PI is the CP of content A, each content. There is a unique CP at the same time in the system. The CP itself is not responsible for the management and update of the content, but serves as a backup node to store the information of the content and serves as the index node for the query.

Each content may be needed by other nodes that access the content, store the content, called a copy of the content, and possibly manipulate or update the content. These nodes are called RPs for the content (Replica Peer, Copy node), as shown in Figure 1, the node connected to the dotted line is the RP, and nodes P2, P3, P4, and P6 are all inside. Rong A's RP. The role of RP is to: Maintain and update content and replicas by establishing a hierarchy. There are three types of RPs: VS (Virtual Server), CRP (Control Replica Peer), and IRP (Infirm Replica Peer).

 VS is a normal node selected from the RP and is responsible for updating and publishing the content. The VS and CP maintain a two-way connection and periodically detect survival.

 CRP is a node that is consistent with VS. The copy of the content stored on the CRP remains the latest version. After the content is updated, CRP will receive the update information released by the VS. The CRP maintains a bidirectional connection with the VS and maintains a timer. If there is no interaction information within a certain period, it will actively send information to detect the survival.

 The IRP is a weakly consistent node with the VS. The copy stored on the IRP may be an old version. After the content is updated, the update information released by the VS will not be received. Before the IRP uses the content, you need to verify the version information with VS to maintain the consistency of the content.

 The connections between nodes and nodes in the embodiments of the present invention fall into two categories: adjacency connections and remote connections. Adjacency connection refers to the connection between adjacent nodes generated according to the routing distribution of CAN, such as the connection between nodes P2 and P3 in Figure 2. Remote connection refers to the connection between the nodes of the required content generated by the node's demand for content and the responsible content node, such as the connection between nodes P1 and P4 in Figure 1. The connection between the CP and the RP, the connection between the VS and the CRP and the IRP are remote connections. The remote connection may be bidirectional, such as a connection between the CP and the VS, or it may be unidirectional, such as a connection between VS and IRP. Remote connection is equivalent to the "shortcut" in the small world theory, which can reduce the length of the query path.

In the embodiment of the present invention, for any common node, as long as there is content in the key space occupied by the node, the node is responsible for the content as the CP. When the node needs other content and needs to keep it, the node becomes the RP of the content. Therefore, a common node may have the same content of CP, VS, CRP, and IRP of different contents; for the same content, the node may be one of the contents of the content such as CP, VS, CRP, or IRP, and the structure is as shown in FIG. 3 . Including: its own key value, key-value space range, structure routing table, structure content table, and requirements content table. The structure routing table is generated by the CAN protocol, and records the key value and address information of all nodes adjacent to the node. Nodes added to a structured network have a routing table.

 The structure content table records information about all the contents of the node as the CP, including: the key value of the content, the specific information of the content, the key value and address information of the VS related to the content.

 The demand content table records the key values of all the content required by the node, the specific information of the content, and the key value and address information of the CP where the content is located. If the node is VS, the key value and address information of all CRPs are also saved; if the node is a CRP or IRP of the desired content, the related VS key value and address information are also saved.

 In the embodiment of the present invention, the rule effective topology of the routing information is realized by the adjacency connection and the remote connection between the nodes; the rule topology of the content and the copy thereof is realized by dividing the nodes into different types according to the requirements of the content. .

 A first embodiment of the present invention provides a method for managing a distributed network. As shown in FIG. 4, the method includes:

 Step s401: When the node joins the distributed network, the content table of the content of the content is generated by searching for content.

 Step s402: Perform routing and forwarding of the message according to the required content table. Specifically, the routing and forwarding of the message are performed according to the structure routing table and the structure content table generated before the step s401, and the required content table generated in step s401.

 This step specifically includes:

 Step S402.1: The node receives a query request for content, and the query request carries a key value of the content.

 Step S402.2, when the key value management range of the node does not include the key value of the content, the node acquires a key with the content according to the locally stored structure routing table, the structure content table, and the requirement content table. a node having the smallest value distance, and forwarding the query request to a node having the smallest distance from the content of the content;

Step S402.3, when the key value management range of the node includes the key value of the content, the node is the CP of the query content, when the content does not exist VS, the The node becomes a VS of the content, and establishes a bidirectional connection with the CP of the content; when the content exists in the VS, the node becomes an IRP of the content, and establishes a connection with the VS of the content.

 Step s403: When the node is the virtual server VS of the content, performing cluster management of the content according to the required content table. The cluster management includes: content search and retrieval, content update and release, node join and leave, CRP and IRP management.

 In this embodiment, the content routing table, the structure content table, and the requirement content table are used to quickly locate and search the content, and the VS of the content is used for cluster management, thereby ensuring that the information stored on the CRP of the content remains consistent. .

 The following describes the content search and acquisition, content update and release, node join and leave, CRP and IRP management in detail through specific embodiments.

 Embodiment 2: Searching and obtaining content

 Since the node not only stores the information of the neighbor nodes, but also stores the information of some distant nodes because of the remote connection, these remote connections are equivalent to the "shortcut" in small-world, by routing these "shortcuts" and CAN routing algorithms. Combined, a smaller average query path length can be obtained.

 When a node needs content, it routes through the key value of the content, searches for all adjacency connections and remote connections, and finds the node with the closest key value to send a query request, and then repeats it until it finds the CP responsible for the content. This search process is different from the continuous approach of the CAN in the key-value space, but there is a jump approximation. For example, node P5 needs to find content A. If it is a routing algorithm through CAN, find the content A along the path of P5_>P4_>P3_>P1_>A, as shown in Figure 5. However, if there is a cluster connection between P4 and P1, the search can find content A along the path of P5_>P4_>P1_>A, as shown in Figure 6.

 The processing flow after a single node receives the query information is shown in Figure 7. The corresponding program processing is as follows:

Receive Search (Key, Address)〃 Node P receives a request for the node whose address is Address is the key content. If (Key belongs to the range of key values of node P) 〃 itself is the target node

 Return (content information, CP information of the content, VS address of the content) else / / itself is not the target node

PeerNearest=P;

 For (Retrieve all neighbor nodes (NeighborP) in CAN routing table) If ( Distance ( NeighborP, Key ) ) <Distance ( PeerNearest, Key ) )

 PeerNearest=NeighborP;

 For (all as the responsibility of the CP in the CAN content table)

 If ( Distance ( VS , Key ) of the content <Distance ( PeerNearest, Key )

 PeerNearest: the VS of the content;

 For (all content in required content table)

If (P is the VS of the content)

If ( Distance (CP of the content, Key) <Distance ( PeerNearest, Key )

 PeerNearest: the content of the CP;

 For (all CRP for this content)

 If ( Distance (CRP of the content, Key) <Di ( PeerNearest, Key )

 CRP of the PeerNearest content; else 〃P is the CRP or IRP of the content

If ( Distance (CP of the content, Key) <Distance ( PeerNearest, Key )

 PeerNearest: the content of the CP;

 If ( Distance ( VS , Key ) of the content <Distance ( PeerNearest, Key )

 PeerNearest=i: the VS of the content;

Transmit Search ( Key, Address ) to PeerNearest forwards the node whose current associated node key is closest to the target node.

Distance ( P, Key )〃 The distance between the node P and the target key value Key distance=0;

 For ( i=l ; i<=d; i++ ) //d is the dimension of the key-value space

 The distanced node P is the key value of the i-th dimension - the key value of the key in the i-th dimension; the routing of the message by the node according to the structure routing table, the structure content table, and the requirement content table includes:

 Step s701, the node P receives the query request. The request contains the address information (Address ) of the original node and the key value ( Key ) of the search content.

 Step s702: Determine whether the key value of the search content is in the key value management range of the node P, if the node P is the target node of the query request, that is, the CP of the search content, go to step s703, otherwise, the relay of the query request Node, go to step s704.

 Step s703, returning metadata of the search content to the original node and the content of the search content

VS address information.

 Step s704: Obtain a node with the smallest distance from the search content key value from the CAN routing table.

Step s705, obtaining a minimum distance from the CAN content table and the search content key value Node.

 Step s706: Obtain a node with the smallest distance from the search content key value from the requirement content table.

 Step s707: Obtain a node having the smallest distance from the search content key value from steps s704 to s706, and continue forwarding the query request to the node having the smallest distance from the search content key.

 After the node finds the desired content, the CP directly returns the specific information of the content and the VS address of the content. If the node only needs the current value of the content, and does not need to pay attention to the change or operation of the content information, only the returned content is stored and used. As shown in Figure 8, if the node needs to continuously focus on the content or operate on the content, the node establishes a connection with the VS and becomes the IRP node of the content. If the content does not have an RP, and there is no VS, the node obtains specific information of the content from the CP, automatically becomes the VS of the content, and establishes a bidirectional connection with the CP, and the VS of the content performs clustering of the content according to the demand content table. management. In this embodiment, the method of clustering connections and routing by content key values ensures the efficiency of content search.

 Figure 8 includes the following steps:

 Step s801: Search the structure routing table, the content routing table, and the requirement content table according to the key value of the content, and find the node with the closest key value to send the query request.

 Step s802: After a number of times of forwarding, the CP that finds the content obtains the content and the address information of the VS of the content.

 In step s803, it is judged whether it is necessary to continuously pay attention to the change of the content or operate the content, if yes, go to step s805; otherwise, go to step s804.

 Step s804, storing and using the content.

Step S805, the content has been further determined whether VS, then go to step S806 is, otherwise, go to step _S 807.

 Step s806, becoming an IRP of the content, establishing a connection with the VS.

 Step s807, becomes the VS of the content, and establishes a bidirectional connection with the CP.

In this embodiment, the node is quickly located and the content is searched, and the content is divided. In the case of a cloth, the node that obtains the content may become a VS or an IRP of the content to continue to pay attention or operate on the content.

 Example 3, content update and release

 Since a copy of the content is kept on the RP for all content, multiple copies of the content exist throughout the network. In order to ensure that all nodes can obtain new and effective content and perform legitimate operations on the content under lower traffic, the present invention uses a mixed push/pull content update and distribution protocol for content and its copy. Control and update.

 In order to reduce the traffic, the embodiment of the present invention determines the type of the node according to the frequency of the node's demand for the content, sets the node that frequently accesses the content to CRP, and sets the node that accesses the content to the IRP. Moreover, in order to be able to distinguish different versions of the content after the content is updated, each content has a version number, and the VS of the content operates on the version number after each legal update.

 The entire content update and release process is divided into three steps: update request, update review, update release. The basic process is shown in Figure 9:

 Step s901, update the request.

 When an RP wants to operate on content, it first determines its type. If it is CRP, the node itself stores the latest version of the content, can directly operate on the content, and sends an update request to the VS, the request includes: the operation result and the current version number. If it is an IRP, the copy stored on the node may be an old version. The current version number needs to be sent to the VS to detect the version information. If the version number is the same as the current version stored on the VS, the VS returns a confirmation message. Then VS returns the content information of the current latest version. The IRP then operates on the content and issues an update request in the same way as CRP.

 Step s902, update the audit.

After receiving the updated content, the VS first determines whether the version number of the content is the latest version number, and if so, accepts the update and modifies the version number, and returns a confirmation message; otherwise, the update is rejected, and the latest version information is returned. If two RPs submit the update results at the same time, the VS determines the validity of the update based on the timestamp of the update request. E.g: Accept older updates with timestamps.

 Step s903, update the release.

 After the VS accepts the update, the updated content and the new version number are sent to the CP and all CRPs. Since there is a weak agreement between IRP and VS, there is no need to release updates to the IRP.

 In this embodiment, the VS is released with the update information of the content, so that the copy information of the content stored in the CRP of the content in the network is consistent.

 Embodiment 4: Joining and leaving a node

 If the node wants to join the network, it can join the algorithm through the node in the CAN to complete the node joining process. The node joins the distributed network to generate a structure routing table and a structure content table; if there is content in the key space to which the node is assigned, the node automatically becomes the CP of the content. When the node requests to find other content, it will further become the RP of other content through the route lookup protocol. When the node searches for content, it generates a content table of the content of the content. The entire node join process only affects the neighbor nodes around the node's last location, and does not affect most nodes in the network.

 A node leaving the network may cause a change in CP, a change in VS, and a change in the number of CRPs. Therefore, depending on the identity of the node, the node will leave the network normally and will leave the network in a different way.

 Since the mapping between the CP and the content is mapped by the DHT mechanism, the key values of the CP and the content do not change, so the replacement of the CP occurs only when the CP leaves the system or the content disappears.

 The CP leaving the system includes both normal leaving and failing away.

Normal departure: As shown in Figure 10, when the CP leaves normally, the key space occupied by the CP is responsible for the adjacent node of the CP according to the CAN protocol. The CP can transfer content related information (including: specific information of the content, VS information) while transferring the key space, and notify the VS CP of the replacement. After learning the CP replacement, the VS sends the new CP information to all CRP nodes. Although the IRP does not receive information on CP replacement, it can be found by asking VS or via CAN routing when needed. New CP.

 Failure to leave: As shown in Figure 11, after the CP fails, the neighboring node automatically divides the key space occupied by the node after learning that the node is invalid, but does not know the content information on the key space. Since the VS periodically detects whether the CP is alive, the VS will find a failure when the CP fails. After the VS finds that the CP has failed, it copies the content information and its own information to the new CP and notifies all CRP CPs of the replacement.

 When the VS leaves as an RP, VS replacement will occur, including normal replacement and failover.

 Normal replacement: As shown in Figure 12, when the VS wants to leave the system, a better performing node will be selected from the remaining CRPs as the new VS, and all CRP information of the content will be transmitted to the new VS, and Send your own departure and new VS information to all CRPs and CPs. All CRP and CP update the stored VS information. If the VS is the last CRP of the content, the information about the leaving of the CP is sent only to the CP, and the CP deletes the VS related information until the new node becomes the RP or the original IRP is used to query the VS information and is automatically upgraded to VS. And get the latest version information of the content from the CP. A node with better performance here refers to a node with a long online time and a large bandwidth. Of course, VS can also be selected through other standards, such as: network delay or geographical location.

 Failover replacement: In the following 4 cases, the node will find VS failure: 1. CRP timer expires and probes VS; 2. CRP needs to submit updates; 3. IRP needs to verify content version status when using content; 4. New When the IRP joins, the CP returns the address information of the original VS, when the new IRP attempts to connect to the original VS. When the node finds that the VS has failed, it will actively notify the CP. After receiving the failure report, the CP will actively detect the VS and confirm the failure:

 If the CRP is reported, the node to be reported will be set as the new VS, and the content information stored by itself will be the latest version of the content, as shown in Figure 13-A;

 If the IRP is reported, the CP waits for a CRP timer cycle to wait for the CRP to report, and thereafter processes the same as above, as shown in Figure 13-B;

If the IRP is reported, the CP waits for a timer period of the CRP, but If there is no CRP to report, it means that there is no CRP, then the IRP that is reported to be directly set to the new VS, and the content stored by itself is sent to the new VS as the latest version, and the information of the new VS is sent to All IRPs that report failures are shown in Figure 13-C.

 After that, if other IRPs or CRPs come to report the original VS failure, the address information of the new VS is directly sent to them, and they reconnect to the new VS to restore the previous topology.

 When the CRP leaves the network normally, it will actively notify the VS. If the CRP fails, the VS will also find that the CRP has failed after one clock cycle. At the same time, the VS of the content deletes the key value and address information of the CRP that normally leaves or lapses in the content requirement table of the node when the CRP of the content leaves or leaves the content normally.

 When the IRP leaves normally or fails to leave the network, it has no effect on the entire network and does not need to notify or transfer information to any node.

 When a node leaves the network, it first causes the key space of the node to be repartitioned, which only affects the neighbor nodes of the node. Thereafter, depending on the type of the node, different effects will occur. If the node is a CP, it only affects the VS of the content; if the node is a VS, it affects the CP of the content and all CRPs; if the node is a CRP, it only affects the VS of the content; If the node is an IRP, it will not affect other nodes.

 In this embodiment, the CP, VS, and CRP of the content are normally or inactively separated by a periodic detection of the timer or by interaction (for example, content search and verification) to form a stable distribution. When a node that holds the content in the network is replaced and migrated, it is guaranteed that the search and management of the content is not affected. The node replacement process will only affect neighbor nodes of the node, as well as specific nodes related to specific content, and most nodes and content of the entire network will not be affected. And because the content is stored on the VS and all CRPs and backed up on the CP, the content is not lost even if the node suddenly fails.

 Example 5, CRP and IRP management

The difference between CRP and IRP is the frequency of access to content. The node has just become an RP It is usually added as an IRP. If an IRP frequently accesses and uses content, it will be upgraded to CRP. If a CRP has less access to content, it will be downgraded to an IRP.

 To measure the frequency of CRP/IRP access to content, each CRP/IRP records its frequency of access to content in the most recent period of time and piggybacks when sending messages to VS. When the VS receives a request for each update information, it also calculates the frequency of the content update for a recent period of time, and sets the threshold for upgrading to CRP and downgrading to IRP according to the frequency of the content update. The threshold for upgrade and downgrade is determined by the frequency of content update. It can be set to exactly equal to the frequency of content update. You can also set the upgrade threshold to the frequency of content update* ( 1+p ) and the downgrade threshold to content update. Frequency * ( lp ), where 0.5 < ρ < 1.

 If the frequency of accessing content in an IRP message is greater than the upgrade threshold, the IRP is upgraded to CRP. VS will keep the address of this new CRP and inform the node that it has been upgraded to CRP with the initial settings of the timer. After receiving the upgrade information, the RP modifies its own state and initializes a timer to start timing. As shown in Figure 14.

 If the frequency of accessing content in a CRP message is lower than the degradation threshold, the CRP is downgraded to an IRP. VS deletes the information about the node and notifies the node to change the status. After receiving the downgrade information, the node changes its state and deletes the timer, as shown in Figure 15.

 In this embodiment, the VS-level management of the IRP and the CRP of the content satisfies the promotion requirements of the node, reduces the traffic caused by frequent detection of the CRP with low access frequency, and release of update information, and also enhances the traffic. The user experience.

 In this embodiment, the number of remote connections per node is not fixed, but is constantly changing according to the popularity of the content. The more popular the content, the more nodes there are, and the more remote connections are built, which can further speed up the search rate of popular content.

The embodiment of the invention further provides a distributed network management system, comprising: a virtual server, configured to perform clustering management of the content according to a requirement content table; And performing a content update operation on the content, and sending an update request to the VS of the content; the weakly consistent node is configured to send a version verification request, and when the version is the latest version of the content, performing a content update operation, Sending an update request to the VS of the content; a control node, configured to appoint the new VS of the content when the VS of the content is detected to be detached, and appointing the content when the content does not exist The node becomes the vs of the content.

 The embodiment of the present invention provides a weakly consistent node. As shown in FIG. 16, the method includes: a query module 1 for searching content; a storage module 2, configured to store a structure routing table, a structure content table, and a search according to the query module 1. The content generation requirement content table; the routing forwarding module 3 is configured to perform routing and forwarding of the message according to the structure routing table, the structure content table, and the requirement content table stored by the storage module 2. The first update operation module 5 is configured to send a version verification request to the storage module 2, and when the version is the latest version of the content, perform a content update operation, and send an update request to the VS of the content.

 The embodiment of the present invention provides a strong consistent node. As shown in FIG. 17, the method includes: a query module 1 for searching for content; a storage module 2, configured for storing a structure routing table, a structure content table, and searching according to the query module 1 The content generation requirement content table; the routing forwarding module 3 is configured to perform routing and forwarding of the message according to the structure routing table, the structure content table, and the requirement content table stored by the storage module 2. The second update operation module 15 is configured to perform a content update operation on the content, and send an update request to the VS of the content. The first detecting module 20 is configured to detect whether the VS of the content is alive every other timer period. The first reporting module 25 is configured to report to the CP of the content that the VS of the content fails to leave when the first detecting module 20 detects that the VS of the content fails to leave.

The embodiment of the present invention provides a virtual server, as shown in FIG. 18, including: a query module 1 for searching content; a storage module 2, configured to store a structure routing table, a structure content table, and content searched according to the query module 1 The generated request content table; the route forwarding module 3 is configured to perform routing and forwarding of the message according to the structure routing table, the structure content table, and the requirement content table stored by the storage module 2. Version verification module 25, Determining whether the IRP version of the content is the latest version of the content when receiving the version verification request of the IRP of the content; the update review module 26, after receiving the update request of the content, Determining whether the version number of the content is the latest version number, if yes, accepting an update operation on the content and modifying a version number of the content; receiving multiple updates to the content update operation on the content When the request is made, the update audit is performed according to the timestamp of the update request; the second detecting module 27 is configured to detect whether the CP of the content and the CRP of the content are alive every other timer period; the cluster management module 28, For receiving the update request for the content in the update auditing module 26, the second detecting module 27 detects that the CP of the content or the CRP of the content fails to leave, according to the required content table stored by the storage module 2 a cluster management of the content; a level management module 29, configured to upgrade an IRP of the content when an access frequency of the content of the IRP is higher than a set upgrade threshold a CRP for the content; degrading the CRP of the content to an IRP of the content when the access frequency of the CRP of the content is lower than a set degradation threshold.

 The embodiment of the present invention provides a control node. As shown in FIG. 19, the method includes: a query module 1 for searching content; a storage module 2, configured to store a structure routing table, a structure content table, and content searched according to the query module 1. The generated request content table; the route forwarding module 3 is configured to perform routing and forwarding of the message according to the structure routing table, the structure content table, and the requirement content table stored by the storage module 2. a third detecting module 35, configured to detect whether the VS of the content is alive every other timer period; and an appointment management module 36, configured to: when the third detecting module 35 detects that the VS of the content fails to leave, The content new VS, when the content does not exist VS, the node that queried the content becomes the VS of the content.

 Since a node may have the same identity of CP, VS, CRP, and IRP for different contents, and the processing mechanisms of CP, VS, CRP, and IRP of different contents are similar, the figure will be CP, VS, CRP and the same content. The IRP is displayed centrally on one node. Does not affect a distributed network, a node can only be one of the CP, VS, CRP, or IRP of the same content.

Embodiments of the present invention provide a distributed network management system, including: a table generation node, configured to: when the nodes respectively join the distributed network, generate a content list of the content by searching for content, and perform routing and forwarding of the message according to the required content table; Clustering management of the content is performed according to the demand content table.

 Embodiments of the present invention have the following beneficial effects:

 The nodes are classified according to the frequency of access of the nodes to the content, and a hierarchical structure is established between different types of nodes to implement content control. In this embodiment, the content update and release mode of the node is determined according to the access frequency of the node (also referred to as the demand frequency): By actively publishing updates to all CRPs, a large amount of inquiry information brought by CRP frequent access to the content is avoided. The IRP is actively queried to the VS for the latest version of the content before using the content, thereby avoiding the traffic caused by frequent updates to the IRPs that are less frequently accessed. Therefore, the embodiment of the present invention implements management and control of content and its copy under lower traffic, ensuring that all nodes obtain the freshest version when accessing the content, and ensure that all update operations are performed. It is cumulatively added on the basis of the latest version, and there is no update operation for the old version. In addition, it effectively reduces system traffic and can adapt to the needs of dynamically changing environments. The node replacement process only affects the neighbor nodes of the node, as well as the specific nodes associated with a particular content, and most nodes and content of the entire network are not affected. And since the content is stored on the VS and all CRPs and backed up on the CP, the content is not lost even if the node suddenly fails.

 The method provided by the embodiment of the present invention satisfies the content and the copy and routing information thereof to form a topology structure with relatively strict rules in the network; ensures the efficiency of content search; effectively updates and controls the content and its copy, and ensures the content and The validity of the copy; when the node moves and replaces and the node's content needs change, it ensures less impact on the topology structure, the efficiency of content search, and the validity of the content and its copy.

 A person skilled in the art can understand that the drawings are only schematic diagrams of a preferred embodiment, and the modules or processes in the drawings are not necessarily required to implement the invention.

Those skilled in the art can understand that the modules in the device in the embodiment can follow The description of the embodiments is distributed in the apparatus of the embodiment, and the corresponding changes may also be made in one or more apparatuses different from the embodiment. The modules of the above embodiments may be combined into one module, or may be further split into multiple sub-modules.

 The serial numbers of the embodiments of the present invention are merely for the description, and do not represent the advantages and disadvantages of the embodiments. The solution described in the claims is also the scope of protection of the embodiments of the present invention. Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present invention can be embodied in the form of a software product that can be stored in a non-volatile storage medium.

(may be a CD-ROM, a USB flash drive, a removable hard drive, etc.), including a number of instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present invention.

 In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and scope of the present invention are intended to be included within the scope of the present invention.

Claims

Rights request A method for managing a distributed network, comprising:  When the node joins the distributed network, by searching for content, a demand content table of the content is generated;  When the node is the virtual server VS of the content, cluster management of the content is performed according to the demand content table.  2. The method according to claim 1, wherein after the generating the content table of the content, the method further comprises:  Generating a structure routing table and a structure content table, and performing routing and forwarding of messages according to the structure routing table, the structure content table, and the requirement content table.  3. The method of claim 2, wherein the structure routing table records key value and address information of a node adjacent to the node.  The method according to claim 2, wherein the structure content table records a key value, specific information, and a VS key of the content of the content as the control node CP of the content. Value and address information.  5. The method according to claim 4, wherein, when the node joins the distributed network, if the key space occupied by the node has content, the node is a CP of the content.  The method according to claim 1, wherein the required content table records a key value of the content searched by the node, specific information of the content, a key value of a CP where the content is located, and Address information;  When the node is a VS of the content, recording key value and address information of all strong consistent nodes CRP of the content;  When the node is a CRP of the content or a weakly consistent node IRP, the key value and address information of the VS of the content are recorded.  The method according to claim 1, wherein the VS of the content performs cluster management of the content according to the required content table, including: The VS of the content acquires update information of the content; The VS of the content issues update information of the content to the CP of the content and all CRPs of the content according to the required content table.  The method according to claim 7, wherein before the VS of the content acquires the update information of the content, the method further includes:  The IRP of the content sends a version verification request to the VS of the content, and after the VS of the content verifies that the version of the content held by the IRP of the content is the latest version, the content is updated. The VS of the content sends an update request;  The VS of the content updates the update operation of the content after receiving the update request, and after the audit is successful, accepts an update operation on the content and modifies the version number of the content to obtain the content. Update information.  The method according to claim 7, wherein before the VS of the content acquires the update information of the content, the method further includes:  The CRP of the content performs an update operation on the content, and sends an update request to the VS of the content;  The VS of the content updates the update operation of the content after receiving the update request, and after the audit is successful, accepts an update operation on the content and modifies the version number of the content to obtain the content. Update information.  The method according to claim 8 or 9, further comprising: a timestamp according to the update request when the VS of the content receives a plurality of update requests for performing an update operation on the content Perform an update review.  The method according to claim 1, wherein the VS of the content performs cluster management of the content according to the required content table, including:  The VS of the content, when the CP of the content normally leaves, sends a replacement message of the CP of the content to all CRPs of the content according to the requirement content table;  Or The VS of the content, when detecting that the CP of the content is invalidated, copies the content and the information of the VS of the content of the content to the new CP of the content, according to the required content table. The replacement message of the CP of the content is sent to the CRP of all the content. 12. The method of claim 1, further comprising:  The VS of the content selects a new VS of the content when it leaves normally, sends all CRP information of the content to a new VS of the content, and sends the content to the content according to the content table. All CRPs send replacement messages for the VS of the content.  13. The method of claim 1, further comprising:  After the original VS of the content expires, the CP of the content selects the new VS of the content, and sends the new VS information of the content to the VS that reports the content to quit and query the content. CRP and IRP of the content.  14. The method according to claim 13, wherein the selecting the content of the new VS comprises:  The CP of the content sets the CRP of the content that has come to the VS of the content to be invalidated as the new VS of the content.  15. The method according to claim 14, wherein the CP of the content further includes a CRP of the content that has been reported to the VS of the content to be invalid before the new VS of the content is further included. :  The CRP of the content fails to detect the VS of the content in a timer period, and the CP of the content reports that the VS of the content has expired; or  The CRP of the content detects that the VS of the content is invalidated when the update request is sent to the VS of the content, and the CP of the content reports that the VS of the content has expired.  16. The method according to claim 13, wherein the selecting the content of the new VS comprises:  The CP of the content sets the CRP of the content that has failed to report the VS of the content to the CRP of the content when the CRP of the content does not come to report the VS failure of the content in a timed period. The new VS of the content.  The method according to claim 16, wherein the setting of the CRP of the content that has failed to report the content of the content to the new VS of the content further includes: When the IRP of the content sends a version verification request to the VS of the content, it detects that the original VS of the content is invalidated, and the CP of the content reports the VS of the content. Expire to leave; or  When the IRP of the content joins the network as a new node, the CP of the content returns the VS information of the content, and the IRP of the content is connected to the CP of the content according to the VS information of the content. The VS that reported the content was invalidated.  18. The method of claim 6, further comprising:  The VS of the content deletes the key value and address information of the CRP that is normally left or lapsed in the content requirement table of the node when the CRP of the content is normally left or expired.  A content query method for a distributed network, comprising: a query request for receiving content by an original node, wherein the query request carries a key value of the content;  When the key value management range of the node does not include the key value of the content, the original node acquires a node with the smallest key value from the content according to the required content table, and has a minimum distance to the key value of the content. The node forwards the query request.  The method according to claim 19, further comprising: after the original node receives the query request of the content, the method further includes:  When the key management range of the original node includes the key value of the content, the original node is the CP of the query content, and when the content does not exist, the original node becomes the VS of the content. And establishing a two-way connection with the CP of the content; when the content exists in the VS, the original node becomes a weak consistent node IRP of the content, and establishes a connection with the VS of the content.  The method according to claim 20, wherein after the original node becomes the VS of the content and establishes a bidirectional connection with the CP of the content, the method further includes: the VS and the CP remain Periodic survival detection.  The method according to claim 20, further comprising: after the original node becomes an IRP of the content,  When the access frequency of the IRP of the content is higher than the upgrade threshold of the VS setting of the content, the VS of the content upgrades the IRP of the content to the CRP of the content. The method of claim 22, further comprising: The VS of the content degrades the CRP of the content to an IRP of the content when the access frequency of the CRP of the content is lower than a set degraded threshold.  24. A distributed network management system, comprising:  a requirement content table generating node, configured to: when the nodes respectively join the distributed network, generate a content list of the content by searching for content, and perform routing and forwarding of the message according to the demand content table;  And a cluster management node, configured to perform cluster management of the content according to the demand content table.  25. A distributed network management system, comprising:  a virtual server, configured to perform clustering management of the content according to the required content table; a strong consistent node, configured to perform a content update operation on the content, and send an update request to the virtual server VS of the content;  a weakly consistent node, configured to send a version verification request, when the version is the latest version of the content, perform a content update operation, and send an update request to the VS of the content; and the control node is configured to detect the content When the VS fails to leave, the content new VS is appointed, and when the content does not exist in the VS, the node that queried the content becomes the VS of the content.  26. A weakly consistent node, characterized by comprising:  a query module for finding content;  a route forwarding module, configured to perform route routing of the message according to the stored content table of requirements;  The first update operation module is configured to send a version verification request, and when the version is the latest version of the content, perform a content update operation, and send an update request to the VS of the content.  The weakly consistent node according to claim 26, further comprising: a storage module, configured to store a required content table generated according to the searched content. 28. A strong consistent node, characterized by comprising:  a query module for finding content; a route forwarding module, configured to perform routing routing of messages according to the stored content table of requirements hair;  And a second update operation module, configured to perform a content update operation on the content, and send an update request to the VS of the content.  The strong consistent node according to claim 28, further comprising: a first detecting module, configured to detect whether the VS of the content is alive every other timer period;  The first reporting module is configured to notify the CP of the content that the VS of the content is invalidated when the first detecting module detects that the VS of the content is detached.  30. A virtual server, comprising:  a query module for finding content;  a route forwarding module, configured to perform route routing of the message according to the stored content table of requirements;  And a clustering management module, configured to perform clustering management of the content according to the stored requirement content table when accepting an update request for the content, where the CP of the content or the CRP of the content fails to leave.  The virtual server according to claim 30, further comprising: a version verification module, configured to verify whether an IRP version of the content is the content when receiving a version verification request sent by an IRP of the content The latest version;  An update review module, configured to: after receiving the update request of the content, determine whether the version number of the content is the latest version number, and if yes, accept an update operation on the content and modify the version of the content When the plurality of update requests for performing the content update operation on the content are received, the update audit is performed according to the timestamp of the update request; the second detecting module is configured to detect the content every other timer period. Whether the CP and the CRP of the content are alive; a level management module, configured to upgrade an IRP of the content to a CRP of the content when an access frequency of the IRP of the content is higher than a set upgrade threshold; and a CRP access frequency of the content is lower than a setting The CRP of the content is degraded to the IRP of the content when the degraded threshold is determined. 32. A control node, comprising:  a query module for finding content;  a route forwarding module, configured to perform route routing of the message according to the stored content table of requirements;  a third detecting module, configured to detect whether the VS of the content is alive every other timer period;  An appointment management module, configured to appoint the content new VS when the third detection module detects that the VS of the content is detached, and when the content does not exist VS, appoint a node that queries the content to become The content of the vs.