CN106301853A - The fault detection method of group system interior joint and device - Google Patents

Abstract

Embodiments of the present invention provide a node fault detection method and device in a cluster system. The method includes: the first node judges whether the first heartbeat message sent by the second node is received within a preset time, and the first node is the first heartbeat message sent by the second node. The neighbor node of the second node, the first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel; in the case that the first node does not receive the heartbeat message sent by the second node Next, send a request message to other neighbor nodes except the first node among all the neighbor nodes of the second node; the first node receives the response message carrying the reception status sent by other neighbor nodes; the first node determines according to the reception status In the case that no heartbeat message is received by other neighbor nodes, the first node determines that the second node fails. The node failure detection method and device in the cluster system provided by the embodiments of the present invention can improve the efficiency of node failure detection.

Description

Node failure detection method and device in cluster system

technical field

Embodiments of the present invention relate to communication technologies, and in particular to a method and device for detecting node faults in a cluster system.

Background technique

In a distributed cluster system, it usually includes a central node and multiple ordinary nodes. When the central node or ordinary nodes fail, it will have a great impact on the reliability of the distributed cluster system. Therefore, how to effectively implement node fault detection is very important.

Fig. 1 is the schematic diagram of the fault detection method of node in the prior art, as shown in Fig. 1, common node (B, C, D, E) sends heartbeat message to central node (M) according to the heartbeat period, and central node (M ) to detect whether a common node is faulty according to the condition of the continuous heartbeat messages received in the detection period, wherein one detection period may include multiple heartbeat periods. At the same time, the central node (M) can also periodically send heartbeat messages to ordinary nodes (B, C, D, E) to inform the ordinary nodes of the role of the central node and whether it is in a normal state. Once the ordinary node (B , C, D, E) If the heartbeat message sent by the central node (M) is not received within the detection period, it will be judged that the central node (M) has failed. At this time, the ordinary node will initiate the operation of re-election of the central node , if the election is successful, the common node will perceive the new central node and send a heartbeat message to the new central node, and then the cluster will perform fault detection.

However, in the prior art, when detecting whether a node fails by judging whether a heartbeat message is received within the detection period, since the heartbeat period for sending the heartbeat message cannot be changed when the cluster size is fixed, The time of the detection cycle cannot be changed, so that node fault detection needs to be detected through multiple heartbeat cycles, resulting in a longer node fault detection cycle and lower efficiency of node fault detection.

Contents of the invention

The embodiment of the present invention provides a node fault detection method and device in a cluster system, which is used to solve the problem in the prior art that node fault detection needs to be detected through multiple heartbeat cycles, resulting in a longer cycle of node fault detection , thus improving the efficiency of node failure detection.

In a first aspect, an embodiment of the present invention provides a method for detecting failures of nodes in a cluster system, including:

The first node judges whether the first heartbeat message sent by the second node is received within the preset time; the first node is a neighbor node of the second node, and the first heartbeat message is the second A heartbeat message sent by the node to each neighbor node of the second node in parallel, the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat cycle, and Less than two heartbeat cycles;

When the first node does not receive the first heartbeat message sent by the second node, the first node sends a message to all neighbor nodes of the second node except the first node Other neighbor nodes send a request message, where the request message is used to inquire whether the other neighbor nodes have received the first heartbeat message;

The first node receives a response message carrying a reception status sent by the other neighbor nodes, and the reception status is used to indicate whether the first heartbeat message is received;

When the first node determines that none of the other neighbor nodes has received the first heartbeat message according to the reception status carried in the received response message sent by each of the other neighbor nodes , the first node determines that the second node fails.

With reference to the first aspect, in a first possible implementation manner of the first aspect, after the first node determines that the second node fails, the method further includes:

The first node generates first voting information, and receives second voting information sent by each of the other neighboring nodes, the first voting information includes the node identifier corresponding to the node elected by the first node; The second voting information includes the node identifier corresponding to the node elected by the neighbor node that sent the second voting information;

The first node counts the number of votes obtained by each node among all elected nodes according to the node identifier in the first voting information and the node identifier in the second voting information sent by each of the other neighbor nodes, and the node with the largest number of votes as the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; the third node All neighbor nodes of the third node include neighbor nodes of the third node itself and neighbor nodes of the second node.

In combination with the first aspect or the first possible implementation of the first aspect, the second possible implementation of the first aspect further includes:

When the first node determines that at least one of the other neighbor nodes has received the first heartbeat message according to the reception status carried in the received response message sent by each of the other neighbor nodes , the first node determines that the link between the node that has not received the first heartbeat message and the second node is faulty; the node that has not received the first heartbeat message includes the Nodes among the first node and the other neighbor nodes that have not received the first heartbeat message.

Combining the first aspect, the first aspect of the first aspect to any second possible implementation manner of the first aspect, in the third possible implementation manner of the first aspect, it also includes:

The first node re-determines the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

In a second aspect, an embodiment of the present invention provides a method for detecting failures of nodes in a cluster system, the method comprising:

The second node sends a first heartbeat message to the first node and other neighbor nodes in parallel; the first node is a neighbor node of the second node, and the other neighbor nodes are all neighbor nodes of the second node For nodes other than the first node, the number of other neighbor nodes is more than one;

The first node judges whether the first heartbeat message is received within a preset time; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods;

When the first node does not receive the first heartbeat message, the first node sends a request message to each of the other neighbor nodes, and the request message is used to ask each of the other neighbor nodes Whether the neighbor node has received the first heartbeat message;

The first node receives a response message carrying a reception status sent by each of the other neighbor nodes, and the reception status is used to indicate whether the first heartbeat message is received;

When the first node determines that none of the other neighbor nodes has received the first heartbeat message according to the receiving status carried in the received response message, the first node determines that the The second node fails.

With reference to the second aspect, in the first possible implementation manner of the second aspect, after the first node determines that the second node fails, the method further includes:

The first node generates first voting information, and receives second voting information sent by each of the other neighboring nodes, the first voting information includes the node identifier corresponding to the node elected by the first node; The second voting information includes the node identifier corresponding to the node elected by the neighbor node that sent the second voting information;

The first node counts the number of votes obtained by each node among all elected nodes according to the node identifier in the first voting information and the node identifier in the second voting information sent by each of the other neighbor nodes, and the node with the largest number of votes as the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; the third node All neighbor nodes of the third node include neighbor nodes of the third node itself and neighbor nodes of the second node.

In combination with the second aspect or the first possible implementation manner of the second aspect, the second possible implementation manner of the second aspect further includes:

When the first node determines that at least one of the other neighbor nodes has received the first heartbeat message according to the reception status carried in the received response message sent by each of the other neighbor nodes , then the first node determines that the link between the node that has not received the first heartbeat message and the second node is faulty; the node that has not received the first heartbeat message includes the Nodes that have not received the first heartbeat message among the first node and the other neighbor nodes.

In combination with the second aspect, any of the first possible implementation manners of the second aspect to the second aspect of the second aspect, the third possible implementation manner of the second aspect further includes:

The first node re-determines the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

In a third aspect, an embodiment of the present invention provides a node failure detection device in a cluster system, including:

A judging module, configured to judge whether a first heartbeat message sent by a second node is received within a preset time; the first node is a neighbor node of the second node, and the first heartbeat message is the A heartbeat message sent by the second node to each neighbor node of the second node in parallel, the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat cycle , and less than two heartbeat cycles;

When the judging module judges that the receiving module has not received the first heartbeat message sent by the second node,

A sending module, configured to send a request message to other neighbor nodes except the first node among all neighbor nodes of the second node, and the request message is used to ask whether the other neighbor nodes have received the first node. A heartbeat message;

The receiving module is further configured to receive a response message carrying a receiving status sent by the other neighbor nodes, and the receiving status is used to indicate whether the first heartbeat message is received;

A determining module, configured to determine, according to the receiving status carried in the response message sent by each of the other neighboring nodes received by the receiving module, whether the other neighboring nodes have not received the first heartbeat message ;

In a case where the determining module determines that none of the other neighbor nodes has received the first heartbeat message, the determining module is further configured to determine that the second node fails.

With reference to the third aspect, in a first possible implementation manner of the third aspect, after the determining module determines that the second node fails, it further includes:

The generating module is further configured to generate first voting information, where the first voting information includes a node identifier corresponding to a node elected by the first node;

The receiving module is further configured to receive second voting information sent by each of the other neighboring nodes, where the second voting information includes a node identifier corresponding to a node elected by the neighboring node that sent the second voting information;

The determining module is further configured to, according to the node identifier in the first voting information and the node identifier in the second voting information sent by each of the other neighbor nodes, count the number of votes obtained by each node among all the nodes elected. The number of votes, and the node with the largest number of votes as the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; the All the neighbor nodes of the third node include the neighbor nodes of the third node itself and the neighbor nodes of the second node.

In combination with the third aspect or the first possible implementation of the third aspect, in the second possible implementation of the third aspect,

The determination module determines that at least one of the other neighbor nodes has received the first heartbeat message according to the receiving status carried in the response message sent by each of the other neighbor nodes received by the receiving module in the case of,

The determination module is also used to determine that the link between the node that has not received the first heartbeat message and the second node is faulty; the node that has not received the first heartbeat message includes the A node that has not received the first heartbeat message among the first node and the other neighbor nodes.

Combining the third aspect, any of the first to second possible implementations of the third aspect, in the third possible implementation of the third aspect,

The determination module is further configured to re-determine the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

In a fourth aspect, an embodiment of the present invention provides a node failure detection system in a cluster system, including a first node, a second node and other neighbor nodes, the first node is a neighbor node of the second node, and the Other neighbor nodes are nodes other than the first node among all neighbor nodes of the second node, and the number of other neighbor nodes is more than one, including:

The second node is configured to send a first heartbeat message to the first node and the other neighbor nodes in parallel;

The first node is configured to determine whether the first heartbeat message is received within a preset time; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods;

In the case that the first node does not receive the first heartbeat message, the first node is further configured to send a request message to each of the other neighbor nodes, and the request message is used to inquire about each Whether the other neighbor nodes have received the first heartbeat message; and, the first node is also used to receive a response message carrying a reception status sent by each of the other neighbor nodes, and the reception status is used for Indicates whether the first heartbeat message is received;

When the first node determines that none of the other neighbor nodes has received the first heartbeat message according to the reception status carried in the received response message sent by each of the other neighbor nodes , the first node is further configured to determine that the second node fails.

With reference to the fourth aspect, in a first possible implementation manner of the fourth aspect, after the first node determines that the second node fails, the method further includes:

The first node is also used for:

Generate first voting information, and receive second voting information sent by each of the other neighbor nodes, the first voting information includes the node identifier corresponding to the node elected by the first node, and the second voting information includes sending The node identifier corresponding to the node elected by the neighbor node of the second voting information;

And, according to the node identification in the first voting information and the node identification in the second voting information sent by each of the other neighboring nodes, count the number of votes obtained by each node in all nodes elected, and vote The node with the largest number is the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; all neighbors of the third node The nodes include neighbor nodes of the third node itself and neighbor nodes of the second node.

In combination with the fourth aspect or the first possible implementation of the fourth aspect, in the second possible implementation of the fourth aspect,

When the first node determines that at least one of the other neighbor nodes has received the first heartbeat message according to the reception status carried in the received response message sent by each of the other neighbor nodes ,

The first node is further configured to determine that the link between the node that has not received the first heartbeat message and the second node has failed; the node that has not received the first heartbeat message includes A neighbor node among the first node and the other neighbor nodes that has not received the first heartbeat message.

Combining the fourth aspect and any of the second possible implementation manners from the first to the fourth aspect of the fourth aspect, in the third possible implementation manner of the fourth aspect,

The first node is further configured to re-determine the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

In the node failure detection method and device in the cluster system provided by the embodiments of the present invention, the first node judges whether it receives the first heartbeat message sent by the second node within a preset time, wherein the first node is the second node neighbor nodes, the first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, and the number of all neighbor nodes of the second node is more than two; the preset time is greater than Or equal to one heartbeat cycle, and less than two heartbeat cycles; the first node asks other neighbor nodes of the second node whether they have received the first heartbeat message if it does not receive the first heartbeat message, and then When it is determined that other neighbor nodes of the second node have not received the first heartbeat message, it is determined that the second node is faulty. Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon can shorten the cycle of fault detection, thereby improving the efficiency of node fault detection.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

FIG. 1 is a schematic structural diagram of a node fault detection method in a cluster system in the prior art;

FIG. 2 is a schematic flow diagram of Embodiment 1 of a node fault detection method in a cluster system provided by the present invention;

Fig. 3 is a schematic diagram 1 of the adjacent relationship between nodes in the cluster system;

FIG. 4 is a second schematic diagram of the adjacent relationship between nodes in the cluster system;

FIG. 5 is a schematic flow diagram of Embodiment 2 of a node fault detection method in a cluster system provided by the present invention;

FIG. 6A is a schematic diagram of the neighbor relationship between nodes before a node failure is detected in the cluster system;

6B is a schematic diagram of re-determining the adjacent relationship between nodes after node failure is detected in the cluster system;

FIG. 7 is a schematic flowchart of Embodiment 3 of a node fault detection method in a cluster system provided by the present invention;

FIG. 8 is a schematic flowchart of Embodiment 4 of a node fault detection method in a cluster system provided by the present invention;

9 is a schematic structural diagram of Embodiment 1 of a node fault detection device in a cluster system of the present invention;

FIG. 10 is a schematic structural diagram of Embodiment 1 of a node fault detection system in a cluster system according to the present invention. FIG. 10 is a schematic structural diagram of Embodiment 1 of a node in the present invention;

FIG. 11 is a schematic structural diagram of Embodiment 1 of a node according to the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

The embodiment of the present invention is applicable to a cluster system, and it is specifically applicable to the scene of node fault detection in a distributed cluster system. The distributed cluster system includes at least two nodes, and the nodes may be computers, for example. Optionally, the difference between the nodes in the cluster system in this embodiment and the existing cluster system is that in the cluster system in this embodiment, all nodes are given the same function, that is, all nodes have The ability to receive heartbeat messages and send heartbeat messages is the same. Therefore, in the cluster system of this embodiment, there is no distinction between central nodes and ordinary nodes, and the central node does not need to manage ordinary nodes. Optionally, the technical solutions of the following embodiments are all introduced using a computer as an execution subject.

FIG. 2 is a schematic flowchart of Embodiment 1 of a node failure detection method in a cluster system provided by the present invention. The method involved in the embodiment of the present invention is applicable to a distributed cluster system. This embodiment is introduced by taking a computer as an execution subject as an example. As shown in Figure 2, the method of this embodiment may include:

Step 201, the first node judges whether it has received the first heartbeat message sent by the second node within the preset time; the first node is the neighbor node of the second node, and the first heartbeat message is sent by the second node in parallel Each neighbor node of the second node sends a heartbeat message, and the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods.

In this embodiment, the second node determines the first node according to the preset rules in the cluster system according to the information of all nodes in the cluster system, wherein the first node is any neighbor node of the second node, and the second node The neighbor nodes of are nodes that have an association relationship with the second node. Figure 3 is a schematic diagram of the adjacent relationship between nodes in the cluster system. As shown in Figure 3, in the cluster system, node E can determine that there are four The neighbor nodes are nodes A, B, C and D respectively. Wherein, the first node may be any one of nodes A, B, C and D. The first node detects whether the second node fails by judging whether it receives the first heartbeat message sent by the second node within a preset time. It should be noted that the second node sends heartbeat messages to all its neighbor nodes in parallel. Therefore, the first heartbeat message is the second node sending heartbeat messages to each neighbor of the second node in parallel at the same time. A heartbeat message sent by the node. In addition, the second node can send the first heartbeat message to all its neighbor nodes in parallel according to the heartbeat period. Therefore, the first node can judge whether to receive the first heartbeat message within a time period greater than or equal to one heartbeat period and less than two heartbeat periods. to the first heartbeat message sent by the second node. For example: Assume that the heartbeat period is 5s, that is, the second node will send a heartbeat message to all its neighbor nodes in parallel every 5s, and for the first heartbeat message sent by the second node at 5s, the first node will It is judged whether the first heartbeat message sent by the second node is received within the time greater than or equal to 5s and less than 10s. The heartbeat period may be set according to experience or actual conditions, and this embodiment does not limit the specific value of the heartbeat period.

In addition, the second node may periodically send the first heartbeat message to the first node through a physical network, but when fault detection is performed based on a single physical network, when a network fault occurs, for example: the management plane network fails, and the service When the flat network is normal, it is often impossible to define whether the second node in the cluster system fails or the link between the second node and the first node fails, or the second node and the first node fail at the same time. , resulting in inaccurate fault detection results. In order to solve this problem, preferably, in this embodiment, the first heartbeat message can also be sent through at least two networks, for example, the first heartbeat message can be sent through two planes, for example: management plane and service plane, The first heartbeat message may also be sent through three planes, for example: management plane, service plane and signaling plane. The first heartbeat message is sent through a multi-physical network to detect whether a node fails, which can improve detection accuracy. It should be noted that, if the number of physical networks is at least two, the at least two physical networks are isolated from each other, so that when some equipment is shared between multiple networks, if the shared equipment fails, thereby The phenomenon that leads to the failure of normal communication between nodes is conducive to improving the accuracy of detection.

Step 202, when the first node does not receive the first heartbeat message sent by the second node, the first node sends a request message to all neighbor nodes of the second node except the first node, The request message is used to inquire whether other neighbor nodes have received the first heartbeat message.

In the prior art, when the heartbeat period sent from common nodes to the central node is fixed, the cluster system cannot increase the common nodes infinitely due to the limitation of the performance of the central node, which affects the scalability of the cluster system. To solve this problem, in the embodiment of the present invention, if the first node does not receive the first heartbeat message sent by the second node within the preset time, it can be preliminarily determined that the second node may have failed. Since the second node sends the first heartbeat message to all its neighboring nodes in parallel, the first node will send a request message to other neighboring nodes of the second node except itself to ask other Whether the neighbor node receives the first heartbeat message sent by the second node. It can be seen that when the first node does not receive the first heartbeat message sent by the second node, the first node can send request messages to other neighbor nodes of the second node, and the non-neighbor nodes of the second node will not The heartbeat message is then sent to the second node, thereby reducing the number of heartbeat messages processed by the second node, thereby reducing the burden on the second node and making the cluster system more scalable.

For example, Figure 4 is a schematic diagram 2 of the adjacent relationship between nodes in the cluster system. As shown in Figure 4, the neighbor nodes of node E are X, A, D, C and G, and node E will Send heartbeat messages to all its neighbor nodes X, A, D, C and G. Assume that node E is used as the second node and node A is used as the first node. After receiving the first heartbeat message sent by the second node E, the first node A will send a request message to other neighbor nodes X, D, C and G to ask whether the nodes X, D, C and G have received the first heartbeat message. A heartbeat message.

Step 203, the first node receives a response message carrying a receiving status sent by other neighboring nodes, and the receiving status is used to indicate whether the first heartbeat message is received.

In this embodiment, after receiving the request message sent by the first node, other neighboring nodes carry the receiving status of whether they have received the first heartbeat message in the response message and send it to the first node.

Step 204, when the first node determines that none of the other neighbor nodes has received the first heartbeat message according to the reception status carried in the received response message sent by each other neighbor node, the first node determines the second heartbeat message. A node fails.

In this embodiment, after each other neighbor node receives the request message sent by the first node, it will return a response message carrying the receiving status to the first node, and the first node sends Carrying the response message with receiving status, judge whether other neighbor nodes have received the first heartbeat message, and determine whether other neighbor nodes have received the first heartbeat message sent by the second node. The second node has failed.

It should be noted that the adjacency relationship between nodes is bidirectional, that is, nodes forming a neighbor relationship can send heartbeat messages to each other, therefore, all neighbor nodes of the second node will individually perform steps 201-204 .

In the node fault detection method in the cluster system provided by the embodiment of the present invention, the first node judges whether it has received the first heartbeat message sent by the second node within a preset time, wherein the first node is a neighbor of the second node node, the first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, and the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to One heartbeat cycle, and less than two heartbeat cycles; the first node inquires whether other neighbor nodes of the second node have received the first heartbeat message if it has not received the first heartbeat message, and determines the When no other neighbor nodes of the second node receive the first heartbeat message, it is determined that the second node is faulty. Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon shortens the cycle of fault detection, thereby improving the efficiency of node fault detection.

FIG. 5 is a schematic flowchart of Embodiment 2 of a node failure detection method in a cluster system provided by the present invention. On the basis of the embodiment shown in FIG. 2 , after the first node determines that the second node fails, each node re-determines an embodiment of a neighbor node, which will be described in detail. As shown in Figure 5, the method of this embodiment may include:

Step 501, the first node generates the first voting information, and receives the second voting information sent by every other neighbor node, the first voting information includes the node identification corresponding to the node elected by the first node; the second voting information includes sending the second voting information The node ID corresponding to the node elected by the neighboring nodes of the voting information.

In this embodiment, after the neighbor nodes of the second node determine that the second node fails, all the neighbor nodes need to recalculate their respective neighbor nodes. For ease of description, any neighbor node of the second node can be used as the first node, and the first node needs to generate first voting information, which includes the node ID corresponding to the node elected by the first node and the voting basis. In addition, the first node also needs to receive the second voting information sent by every other neighboring node, and the second voting information includes the node identification and voting basis corresponding to the node elected by the neighboring node that sent the second voting information. In practical applications, the voting basis is related to many factors, such as: load, node number size, node cache newness, node network bandwidth, etc. For example, the first node can judge which node bears the least load, And carry the node identifier corresponding to the node with the smallest load in the first voting information and send it to other neighbor nodes. Similarly, other neighbor nodes can also send the second voting information to the first node in a similar manner.

Step 502, the first node counts the number of votes obtained by each node among all nodes elected according to the node identifier in the first voting information and the node identifier in the second voting information sent by each other neighbor node, and sends The node with the largest number of votes is the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; all neighbor nodes of the third node include the third node's own neighbor nodes and neighbor nodes of the second node.

In this embodiment, after the first node receives the second voting information sent by every other neighboring node, according to the node identification in the first voting information generated by itself and the node identification in the received second voting information, A third node can be determined. In the specific implementation process, according to the node identification carried in the first voting information and the second voting information, through voting, the number of votes obtained by each node among all elected nodes can be counted, and the number of votes obtained will be The node with the most number acts as the third node. The third node is used to take over the neighbor nodes of the failed second node, that is, to take over the association relationship between the second node and other nodes. Therefore, the third node will replace the second node and provide All neighbor nodes are nodes sending heartbeat messages, wherein all neighbor nodes of the third node include neighbor nodes of the second node in addition to neighbor nodes of the third node itself.

Step 503, the first node re-determines the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in other neighbor nodes.

In this embodiment, after all neighbor nodes of the second node determine the third node through voting, if the first node is the third node, the first node will take over the adjacency relationship of the second node, and other neighbors Nodes can re-determine their neighbor nodes through calculation according to the neighbor relationship after the first node takes over the neighbor nodes of the second node; if the first node is not the third node, the first node will wait for the third node to re-determine the relative After adjacency, according to the neighbor nodes of the third node and the nodes other than the third node in other neighbor nodes, re-determine the neighbor nodes of itself.

For example, FIG. 6A is a schematic diagram of the neighbor relationship between nodes before a node failure is detected in the cluster system, and FIG. 6B is a schematic diagram of re-determining the neighbor relationship between nodes after a node failure is detected in the cluster system. As shown in Figure 6A, assuming that node E is the second node and node A is the first node, when the first node A determines that the second node E has failed, the first node A will generate the first voting information and receive node For the second voting information sent by X, D, C and G, the first node A determines the third node according to the node ID in the first voting information and the node ID in the second voting information, so that the third node can replace the second node, and send heartbeat messages to all neighbor nodes of the third node in parallel. As shown in Figure 6B, if the first node A is determined to be the third node through voting, the second node will be replaced by the first node A, and heartbeat messages will be sent to all neighbor nodes of the first node A in parallel , at this time, the first node A needs to re-determine its neighbor nodes through other neighbor nodes X, D, C and G, and after nodes X, D, C and G wait for the first node A to determine their neighbor nodes, According to the neighbor nodes determined by the first node A, the respective neighbor nodes are re-determined.

In the node fault detection method in the cluster system provided by the embodiment of the present invention, the first node judges whether it has received the first heartbeat message sent by the second node within a preset time, wherein the first node is a neighbor node of the second node , the first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, and the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat cycle, and less than two heartbeat cycles; the first node inquires whether other neighbor nodes of the second node have received the first heartbeat message if it does not receive the first heartbeat message, and determines the first heartbeat message When the other neighbor nodes of the second node do not receive the first heartbeat message, it is determined that the second node is faulty. Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon shortens the cycle of fault detection, thereby improving the efficiency of node fault detection. In addition, after it is determined that the first node fails, the respective neighbor nodes are re-determined, and then the fault detection is continued, thereby improving the accuracy of the fault detection.

Optionally, when the first node determines that at least one other neighbor node has received the first heartbeat message according to the reception status carried in the received response message sent by each other neighbor node, the first node determines that the first heartbeat message is received by the first node. The link between the node that has not received the first heartbeat message and the second node fails.

Specifically, after the first node does not receive the first heartbeat message sent by the second node, and sends a request message to each other node to inquire whether each other neighbor node has received the first heartbeat message, if according to The response message sent by each other node determines that at least one other neighbor node has received the first heartbeat message, then the first node can determine that the second node is normal, and it may be the second node and the first node, and The link between the node that has not received the first heartbeat message and the first node has failed, wherein the nodes that have not received the first heartbeat message include the first node and other neighbor nodes that have not received the first heartbeat message Neighbor nodes of the message.

In the node failure detection method in the cluster system provided by the embodiment of the present invention, when the first node determines that at least one other neighbor node has received the first heartbeat message, the first node determines that the first heartbeat message has not been received The link between the node and the second node fails, so that the fault detection is more comprehensive.

FIG. 7 is a schematic flowchart of Embodiment 3 of a node failure detection method in a cluster system provided by the present invention. The method involved in the embodiment of the present invention is applicable to a distributed cluster system. In this embodiment, a computer is still used as an execution subject for introduction. As shown in Figure 7, the method of this embodiment may include:

Step 701, the second node sends the first heartbeat message to the first node and other neighbor nodes in parallel, the first node is the neighbor node of the second node; the other neighbor nodes are all the neighbor nodes of the second node except the first node For nodes other than , the number of other neighbor nodes is more than one.

In this embodiment, the second node can determine all its neighbor nodes according to the information of the nodes contained in the cluster system and the preset rules in the cluster system, wherein the first node is any neighbor of the second node node, and the neighbor nodes of the second node are nodes associated with the second node. After the second node determines all the neighbor nodes, it will send the first heartbeat message to the first node and other neighbor nodes in parallel.

Step 702, the first node judges whether a first heartbeat packet is received within a preset time; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods.

In this embodiment, the second node can send the first heartbeat message to all its neighbor nodes in parallel according to the heartbeat period. Therefore, the first node can determine whether the heartbeat period is greater than or equal to one heartbeat period and less than two heartbeat periods. Whether the first heartbeat message sent by the second node is received within the time. For example: Assume that the heartbeat period is 5s, that is, the second node will send a heartbeat message to its neighbor nodes in parallel every 5s, and for the first heartbeat message sent by the second node at 5s, the first node will judge Whether the first heartbeat message sent by the second node is received within 5s or more and less than 10s. The heartbeat period may be set according to experience or actual conditions, and this embodiment does not limit the specific value of the heartbeat period.

In addition, the second node may periodically send the first heartbeat message to the first node through a physical network, but when fault detection is performed based on a single physical network, when a network fault occurs, for example: the management plane network fails, and the service When the flat network is normal, it is often impossible to define whether the second node in the cluster system fails or the link between the second node and the first node fails, or the second node and the first node fail at the same time. , resulting in inaccurate fault detection results. In order to solve this problem, preferably, in this embodiment, the first heartbeat message can also be sent through at least two networks, for example, the first heartbeat message can be sent through two planes, for example: management plane and service plane, The first heartbeat message may also be sent through three planes, for example: management plane, service plane and signaling plane. The first heartbeat message is sent through a multi-physical network to detect whether a node fails, which can improve detection accuracy. It should be noted that, if the number of physical networks is at least two, the at least two physical networks are isolated from each other, so that when some equipment is shared between multiple networks, if the shared equipment fails, thereby The phenomenon that leads to the failure of normal communication between nodes is conducive to improving the accuracy of detection.

Step 703. In the case that the first node does not receive the first heartbeat message, the first node sends a request message to each other neighbor node respectively, and the request message is used to inquire whether each other neighbor node has received the first heartbeat message. Heartbeat message.

In this embodiment, if the first node does not receive the first heartbeat message sent by the second node within the preset time, it can be preliminarily determined that the second node may be faulty. Since the second node sends the first heartbeat message to all its neighboring nodes in parallel, the first node will send a request message to other neighboring nodes of the second node except itself to ask other Whether the neighbor node receives the first heartbeat message sent by the second node.

Step 704, the first node receives a response message carrying a receiving status sent by each other neighbor node, and the receiving status is used to indicate whether the first heartbeat message is received.

In this embodiment, after each other neighbor node receives the request message sent by the first node, it carries the receiving status of whether it has received the first heartbeat message in the response message and sends it to the first node.

Step 705. When the first node determines that none of the other neighboring nodes has received the first heartbeat message according to the reception status carried in the received response message, the first node determines that the second node is faulty.

In this embodiment, after each other neighbor node receives the request message sent by the first node, it will return a response message carrying the receiving status to the first node, and the first node sends The response message carrying the receiving status, to determine whether other neighbor nodes have received the first heartbeat message, and when it is judged that other neighbor nodes have not received the first heartbeat message sent by the second node, the second heartbeat message can be determined. A node has failed.

In the node fault detection method in the cluster system provided by the embodiment of the present invention, the second node sends the first heartbeat message to the first node and other neighbor nodes in parallel, and the first node judges whether the first heartbeat message is received within the preset time. The first heartbeat message sent by the two nodes, wherein the first node is a neighbor node of the second node, and the first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, The number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat cycle, and less than two heartbeat cycles; the first node inquires if it does not receive the first heartbeat message. Whether other neighbor nodes of the second node have received the first heartbeat message, and when it is determined that other neighbor nodes of the second node have not received the first heartbeat message, it is determined that the second node has failed . Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon shortens the cycle of fault detection, thereby improving the efficiency of node fault detection.

FIG. 8 is a schematic flowchart of Embodiment 4 of a node failure detection method in a cluster system provided by the present invention. On the basis of the embodiment shown in FIG. 7 , after the first node determines that the second node has failed, each node re-determines an embodiment of a neighbor node, which will be described in detail. As shown in Figure 8, the method of this embodiment may include:

Step 801, the first node generates the first voting information, and receives the second voting information sent by every other neighbor node, the first voting information includes the node identification corresponding to the node elected by the first node; the second voting information includes sending the second The node ID corresponding to the node elected by the neighboring nodes of the voting information.

In this embodiment, after the neighbor nodes of the second node determine that the second node fails, all the neighbor nodes need to recalculate their respective neighbor nodes. For ease of description, any neighbor node of the second node can be used as the first node, and the first node needs to generate first voting information, which includes the node ID corresponding to the node elected by the first node and the voting basis. In addition, the first node also needs to receive the second voting information sent by every other neighboring node, and the second voting information includes the node identification and voting basis corresponding to the node elected by the neighboring node that sent the second voting information. In practical applications, the voting basis is related to many factors, such as: load, node number size, node cache newness, node network bandwidth, etc. For example, the first node can judge which node bears the least load, And carry the node identifier corresponding to the node with the smallest load in the first voting information and send it to other neighbor nodes. Similarly, other neighbor nodes can also send the second voting information to the first node in a similar manner.

Step 802: According to the node ID in the first voting information and the node ID in the second voting information sent by every other neighbor node, the first node counts the number of votes obtained by each node among all nodes elected, and votes The node with the largest number is the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; all neighbor nodes of the third node include the neighbors of the third node node and the neighbor nodes of the second node.

In this embodiment, after the first node receives the second voting information sent by every other neighboring node, according to the node ID in the first voting information generated by itself and the node ID in the received second voting information, A third node can be determined. In the specific implementation process, according to the node identification carried in the first voting information and the second voting information, through voting, the number of votes obtained by each node among all elected nodes can be counted, and the number of votes obtained will be The node with the most number acts as the third node. The third node is used to take over the neighbor nodes of the failed second node, that is, to take over the association relationship between the second node and other nodes. Therefore, the third node will replace the second node and provide All neighbor nodes send a heartbeat message, wherein all neighbor nodes of the third node include neighbor nodes of the second node in addition to neighbor nodes of the third node itself.

Step 803, the first node re-determines the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in other neighbor nodes.

In this embodiment, after all neighbor nodes of the second node determine the third node through voting, if the first node is the third node, the first node will take over the adjacency relationship of the second node, and other neighbors Nodes can re-determine their neighbor nodes through calculation according to the neighbor relationship after the first node takes over the neighbor nodes of the second node; if the first node is not the third node, the first node will wait for the third node to re-determine the relative After adjacency, according to the neighbor nodes of the third node and the nodes other than the third node in other neighbor nodes, re-determine the neighbor nodes of itself.

In the node fault detection method in the cluster system provided by the embodiment of the present invention, the second node sends the first heartbeat message to the first node and other neighbor nodes in parallel, and the first node judges whether the second heartbeat message is received within the preset time. The first heartbeat message sent by the node, wherein the first node is a neighbor node of the second node, the first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, and the first The number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat cycle, and less than two heartbeat cycles; the first node inquires the first heartbeat message when it does not receive the first heartbeat message. Whether other neighbor nodes of the second node have received the first heartbeat message, and when it is determined that other neighbor nodes of the second node have not received the first heartbeat message, it is determined that the second node has failed. Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon shortens the cycle of fault detection, thereby improving the efficiency of node fault detection. In addition, after it is determined that the first node fails, the respective neighbor nodes are re-determined, and then the fault detection is continued, thereby improving the accuracy of the fault detection.

Optionally, when the first node determines that at least one other neighbor node has received the first heartbeat message according to the reception status carried in the received response message sent by each other neighbor node, the first node determines that the first heartbeat message is received by the first node. The link between the node that has not received the first heartbeat message and the second node fails.

Specifically, after the first node does not receive the first heartbeat message sent by the second node, and sends a request message to each other node to inquire whether each other neighbor node has received the first heartbeat message, if according to The response message sent by each other neighbor node determines that at least one other neighbor node has received the first heartbeat message, then the first node can determine that the second node is normal, and it may be that the second node and the first node, And the link between the node that has not received the first heartbeat message and the first node has failed, wherein the node that has not received the first heartbeat message includes the first node and other neighbor nodes that have not received the first heartbeat message. The neighbor node of the heartbeat message.

Optionally, the first node re-determines the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

In the node failure detection method in the cluster system provided by the embodiment of the present invention, when the first node determines that at least one other neighbor node has received the first heartbeat message, the first node determines that the first heartbeat message has not been received The link between the node and the second node fails, so that the fault detection is more comprehensive.

FIG. 9 is a schematic structural diagram of Embodiment 1 of a node fault detection device in a cluster system according to the present invention. As shown in FIG. A receiving module 13 , a determining module 14 and a generating module 15 .

Wherein, the judging module 11 is used to judge whether the receiving module 13 has received the first heartbeat message sent by the second node within a preset time; the first node is a neighbor node of the second node, and the first heartbeat message is The message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, and the number of all neighbor nodes of the second node is more than two; the preset time is greater than Or equal to one heartbeat period, and less than two heartbeat periods; when the judging module 11 judges that the receiving module 13 has not received the first heartbeat message sent by the second node, the sending module 12 is used to Sending a request message to other neighbor nodes except the first node among all neighbor nodes of the second node; the request message is used to inquire whether the other neighbor nodes have received the first heartbeat message; The receiving module 13 is also configured to receive a response message carrying a receiving status sent by the other neighbor nodes, and the receiving status is used to indicate whether the first heartbeat message is received; the determining module 14 is used to determine according to the The receiving module 13 receives the reception status carried in the response message sent by each of the other neighbor nodes, and determines whether the other neighbor nodes have not received the first heartbeat message; in the determination module 14 When it is determined that none of the other neighbor nodes has received the first heartbeat message, the determination module 14 is further configured to determine that the second node fails. When the first node determines that none of the other neighbor nodes has received the first heartbeat message according to the receiving status carried in the received response message, the determining module 14 is configured to determine the The second node fails.

In the node fault detection device in the cluster system provided by the embodiment of the present invention, the judging module judges whether the receiving module receives the first heartbeat message sent by the second node within a preset time, and the first heartbeat message is sent by the second node in parallel A heartbeat message sent to each neighbor node of the second node, the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods; the receiving module In the case that the first heartbeat message is not received, the sending module sends a request message to other neighbor nodes of the second node to inquire whether other neighbor nodes have received the first heartbeat message, and when the determination module determines that the first heartbeat message When the other neighbor nodes of the second node do not receive the first heartbeat message, it is determined that the second node is faulty. Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon shortens the cycle of fault detection, thereby improving the efficiency of node fault detection.

Optionally, the generating module 15 is further configured to generate first voting information, where the first voting information includes a node identifier corresponding to a node elected by the first node;

The receiving module 13 is also configured to receive the second voting information sent by each of the other neighboring nodes, the second voting information including the node identifier corresponding to the node elected by the neighboring node that sent the second voting information;

The determination module 14 is further configured to count the number of votes obtained by each node among all the nodes elected according to the node ID in the first voting information and the node ID in the second voting information sent by each of the other neighboring nodes. The number of votes, and the node with the largest number of votes as the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; the All the neighbor nodes of the third node include the neighbor nodes of the third node itself and the neighbor nodes of the second node.

Optionally, the determining module 14 determines that at least one of the other neighboring nodes has received the In the case of the first heartbeat message mentioned above,

The determining module 14 is also used to determine that the link between the node that has not received the first heartbeat message and the second node has failed; the node that has not received the first heartbeat message includes A node among the first node and the other neighbor nodes that has not received the first heartbeat message.

Optionally, the determination module 14 is further configured to re-determine the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

The node fault detection device in the cluster system of this embodiment can be used to implement the technical solution of the node fault detection method in the cluster system provided by any embodiment of the present invention, its implementation principle and technical effect are similar, and will not be repeated here .

Fig. 10 is a schematic structural diagram of Embodiment 1 of the node fault detection system in the cluster system of the present invention. As shown in Fig. 10, the node fault detection system 20 in the cluster system provided by the embodiment of the present invention includes a first node 21, a second node 22 and other neighbor nodes 23, the first node 21 is a neighbor node of the second node 22, and the other neighbor nodes 23 are all neighbor nodes of the second node 22 except the first node 21 The number of other neighbor nodes 23 is more than one.

Wherein, the second node 22 is used to send the first heartbeat message to the first node and the other neighbor nodes in parallel; the first node 21 is used to judge whether the The first heartbeat message; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods; when the first node does not receive the first heartbeat message, the first node 21 is further configured to send a request message to each of the other neighboring nodes, and the request message is used to inquire whether each of the other neighboring nodes has received the first heartbeat message; the first node 21 also uses Receiving a response message carrying a receiving status sent by each of the other neighbor nodes, the receiving status is used to indicate whether the first heartbeat message is received; at the first node according to each received The reception status carried in the response message sent by the other neighbor nodes, and when it is determined that none of the other neighbor nodes have received the first heartbeat message, the first node 21 is also used to determine the The second node fails.

In the node fault detection system in the cluster system provided by the embodiment of the present invention, the judging module judges whether the receiving module receives the first heartbeat message sent by the second node within the preset time, and the first heartbeat message is the second node parallel A heartbeat message sent to each neighbor node of the second node, the number of all neighbor nodes of the second node is more than two; the preset time is greater than or equal to one heartbeat period and less than two heartbeat periods; receiving When the module does not receive the first heartbeat message, the sending module sends a request message to other neighbor nodes of the second node to inquire whether other neighbor nodes have received the first heartbeat message, and when the determination module determines that the When no other neighbor nodes of the second node receive the first heartbeat message, it is determined that the second node is faulty. Since the preset time is greater than or equal to one heartbeat cycle and less than two heartbeat cycles, when using the technical solution provided by the present invention for fault detection, it avoids the need for multiple heartbeat cycles in the prior art to detect whether a node is faulty The phenomenon shortens the cycle of fault detection, thereby improving the efficiency of node fault detection.

In the above embodiment, after the first node 21 determines that the second node fails, the first node 21 further includes: the first node 21 is further configured to:

Generate first voting information, and receive second voting information sent by each of the other neighbor nodes, the first voting information includes the node identifier corresponding to the node elected by the first node, and the second voting information includes sending The node identifier corresponding to the node elected by the neighbor node of the second voting information;

And, according to the node identification in the first voting information and the node identification in the second voting information sent by each of the other neighboring nodes, count the number of votes obtained by each node in all nodes elected, and vote The node with the largest number serves as a third node, and the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; all neighbors of the third node The nodes include neighbor nodes of the third node itself and neighbor nodes of the second node.

In the above embodiment, the first node determines that at least one of the other neighbor nodes has received the first In the case of a heartbeat message,

The first node 21 is also used to determine that the link between the node that has not received the first heartbeat message and the second node has failed; the node that has not received the first heartbeat message A node that has not received the first heartbeat message among the first node and the other neighbor nodes is included.

In the above embodiment, the first node 21 is further configured to re-determine the first node's neighbor nodes.

The above-mentioned system embodiments can be correspondingly used to implement the technical solutions of the method embodiments, and their implementation principles and technical effects are similar, and will not be repeated here.

Fig. 11 is a schematic structural diagram of the node embodiment 1 of the present invention. As shown in Fig. 11, the node 600 of this embodiment includes a processor 601, a user interface 603, a network interface 604, a memory 605, a transmitter 606, a receiver 607, and a memory 605 may include an operating system 6051, application programs 6052, and the like. The processor 601 may be a central processing unit (Central Processing Unit, CPU). The memory 605 is used to store executable instructions. Processor 601 may execute executable instructions stored in memory 605 . Wherein, the receiver 607 is used to receive the first heartbeat message sent by the second node; the processor 601 is used to judge whether the receiver 607 has received the first heartbeat message sent by the second node within a preset time ; The first heartbeat message is a heartbeat message sent by the second node to each neighbor node of the second node in parallel, and the number of all neighbor nodes of the second node is more than two; The preset time is greater than or equal to one heartbeat period and less than two heartbeat periods; when the processor 601 determines that the receiver 607 has not received the first heartbeat message sent by the second node , the sender 606 is used to send a request message to other neighbor nodes except the first node among all neighbor nodes of the second node, and the request message is used to inquire whether the other neighbor nodes have received the In the first heartbeat message, the first node is a neighbor node of the second node; the receiver 607 is also configured to receive a response message carrying a reception status sent by the other neighbor nodes, and the reception status uses Indicates whether the first heartbeat message is received; the processor 601 is configured to determine whether to None of the other neighbor nodes has received the first heartbeat message; when the processor 601 determines that none of the other neighbor nodes has received the first heartbeat message, the processor 601 It is also used to determine that the second node fails.

The node provided in this embodiment can be used to execute the technical solution of the node fault detection method in the cluster system provided by any embodiment of the present invention, and its implementation principle and technical effect are similar, and will not be repeated here.

Optionally, the processor 601 is further configured to generate first voting information, where the first voting information includes a node identifier corresponding to a node elected by the first node;

The receiver 607 is further configured to receive second voting information sent by each of the other neighboring nodes, where the second voting information includes a node identifier corresponding to a node elected by the neighboring node that sent the second voting information;

The processor 601 is further configured to, according to the node identifier in the first voting information and the node identifier in the second voting information sent by each of the other neighboring nodes, count the votes obtained by each node among all the nodes elected. The number of votes, and the node with the largest number of votes as the third node; the third node is a node that replaces the second node and sends heartbeat messages to all neighbor nodes of the third node in parallel; the All the neighbor nodes of the third node include the neighbor nodes of the third node itself and the neighbor nodes of the second node.

Optionally, the processor 601 determines that at least one of the other neighbor nodes has received the In the case of the first heartbeat message, the processor 601 is further configured to determine that the link between the node that has not received the first heartbeat message and the second node is faulty; The nodes receiving the first heartbeat message include nodes that have not received the first heartbeat message among the first node and the other neighbor nodes.

Optionally, the processor 601 is further configured to re-determine the neighbor nodes of the first node according to the neighbor nodes of the third node and nodes other than the third node in the other neighbor nodes.

The node provided in this embodiment can be used to execute the technical solution of the node fault detection method in the cluster system provided by any embodiment of the present invention, and its implementation principle and technical effect are similar, and will not be repeated here.

Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by program instructions and related hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.

Claims (12)

1. the fault detection method of a group system interior joint, it is characterised in that including:

Primary nodal point judges whether receive the first heartbeat message that secondary nodal point sends in Preset Time； Described primary nodal point is the neighbor node of described secondary nodal point, and described first heartbeat message is described second section The heartbeat message that point sends to each neighbor node of described secondary nodal point concurrently, described second section The number of all neighbor nodes of point is two or more；Described Preset Time is more than or equal to a heart beating week Phase, and less than two heart beat cycles；

In the case of described primary nodal point does not receives the first heartbeat message that described secondary nodal point sends, Described primary nodal point other in addition to described primary nodal point in all neighbor nodes of described secondary nodal point Neighbor node sends request message, and described request message is used for inquiring whether other neighbor nodes described receive To described first heartbeat message；

Described primary nodal point receives the response carrying reception state of described other neighbor nodes transmission and disappears Breath, described reception state is used for indicating whether to receive described first heartbeat message；

The described response sent according to other neighbor nodes each described received at described primary nodal point disappears The reception state carried in breath, determines that other neighbor nodes described all do not receive described first heart beating report In the case of literary composition, described primary nodal point determines that described secondary nodal point breaks down.

Method the most according to claim 1, it is characterised in that described primary nodal point determines described After two nodes break down, also include:

Described primary nodal point generates the first vote information, and receives what each other neighbor nodes described sent Second vote information, described first vote information includes the node that node that described primary nodal point is elected is corresponding Mark；Described second vote information includes the node sending the neighbor node election of described second vote information Corresponding node identification；

Described primary nodal point is according to the node identification in described first vote information and each other neighbours described Node identification in the second vote information that node sends, each node in all nodes that statistics is elected The ballot quantity obtained, and using nodes most for quantity of voting as the 3rd node；Described 3rd node is Substitute described secondary nodal point and send heartbeat message to all neighbor nodes of described 3rd node concurrently Node；All neighbor nodes of described 3rd node include described 3rd node self neighbor node and The neighbor node of described secondary nodal point.

Method the most according to claim 1 and 2, it is characterised in that also include:

The described response sent according to other neighbor nodes each described received at described primary nodal point disappears The reception state carried in breath, determines that at least one other neighbor node described receives described first heart In the case of jumping message, described primary nodal point determines node and the institute not receiving described first heartbeat message The link stated between secondary nodal point breaks down；The described node bag not receiving described first heartbeat message Include the node not receiving described first heartbeat message in described primary nodal point and other neighbor nodes described.

4. the fault detection method of a group system interior joint, it is characterised in that described method includes:

Secondary nodal point sends the first heartbeat message to primary nodal point and other neighbor nodes concurrently；Described One node is the neighbor node of described secondary nodal point, and other neighbor nodes described are the institute of described secondary nodal point Having the node in addition to described primary nodal point in neighbor node, the number of other neighbor nodes described is one Above；

Described primary nodal point judges whether receive described first heartbeat message in Preset Time；Described pre- If the time is more than or equal to a heart beat cycle, and less than two heart beat cycles；

In the case of described primary nodal point does not receives described first heartbeat message, described primary nodal point to Each other neighbor nodes described send request message respectively, and described request message is used for inquiring each described Whether other neighbor nodes receive described first heartbeat message；

Described primary nodal point receives the response carrying reception state that each other neighbor nodes described send Message, described reception state is used for indicating whether to receive described first heartbeat message；

At described primary nodal point according to the reception state carried in the described response message received, determine In the case of other neighbor nodes described all do not receive described first heartbeat message, described primary nodal point is true Fixed described secondary nodal point breaks down.

Method the most according to claim 4, it is characterised in that described primary nodal point determines described After two nodes break down, also include:

Described primary nodal point generates the first vote information, and receives what each other neighbor nodes described sent Second vote information, described first vote information includes the node that node that described primary nodal point is elected is corresponding Mark；Described second vote information includes the node sending the neighbor node election of described second vote information Corresponding node identification；

Described primary nodal point is according to the node identification in described first vote information and each other neighbours described Node identification in the second vote information that node sends, each node in all nodes that statistics is elected The ballot quantity obtained, and using nodes most for quantity of voting as the 3rd node；Described 3rd node is Substitute described secondary nodal point and send heartbeat message to all neighbor nodes of described 3rd node concurrently Node；All neighbor nodes of described 3rd node include described 3rd node self neighbor node and The neighbor node of described secondary nodal point.

6. according to the method described in claim 4 or 5, it is characterised in that also include:

The described response sent according to other neighbor nodes each described received at described primary nodal point disappears The reception state carried in breath, determines that at least one other neighbor node described receives described first heart Jump in the case of message, the most described primary nodal point determine the node not receiving described first heartbeat message with Link between described secondary nodal point breaks down；The described node not receiving described first heartbeat message Including the node not receiving the first heartbeat message in described primary nodal point and other neighbor nodes described.

7. the failure detector of a group system interior joint, it is characterised in that including:

Judge module, for judging whether receiver module receives what secondary nodal point sent in Preset Time First heartbeat message；Described primary nodal point is the neighbor node of described secondary nodal point, described first heart beating report Literary composition is the heart beating report that described secondary nodal point sends to each neighbor node of described secondary nodal point concurrently Literary composition, the number of all neighbor nodes of described secondary nodal point is two or more；Described Preset Time more than or Equal to a heart beat cycle, and less than two heart beat cycles；

Judge that described receiver module does not receives first that described secondary nodal point sends at described judge module In the case of heartbeat message,

Sending module, in all neighbor nodes of described secondary nodal point in addition to described primary nodal point Other neighbor nodes send request message, described request message is used for inquiring that other neighbor nodes described are No receive described first heartbeat message；

Described receiver module, is additionally operable to the reception state that carries of other neighbor nodes transmission described in receiving Response message, described reception state is used for indicating whether to receive described first heartbeat message；

Determine module, send for other neighbor nodes each described received according to described receiver module Described response message in the reception state carried, it is determined whether other neighbor nodes described all do not receive Described first heartbeat message；

Determine that module determines that other neighbor nodes described all do not receive described first heartbeat message described In the case of, described determine module, be additionally operable to determine that described secondary nodal point breaks down.

Device the most according to claim 7, it is characterised in that to determine that module determines described described After secondary nodal point breaks down, also include:

Generation module, is additionally operable to generate the first vote information, and described first vote information includes described first The node identification corresponding to node of node election；

Described receiver module, is additionally operable to receive the second vote information that each other neighbor nodes described send, Described second vote information includes that the node sending the neighbor node election of described second vote information is corresponding Node identification；

Described determine module, be additionally operable to according to the node identification in described first vote information and each described Node identification in the second vote information that other neighbor nodes send, in all nodes that statistics is elected The ballot quantity that each node obtains, and using nodes most for quantity of voting as the 3rd node；Described Three nodes are to substitute described secondary nodal point and send to all neighbor nodes of described 3rd node concurrently The node of heartbeat message；All neighbor nodes of described 3rd node include the neighbour of described 3rd node self Occupy node and the neighbor node of described secondary nodal point.

9. according to the device described in claim 7 or 8, it is characterised in that:

Send at described other neighbor nodes each described determining that module receives according to described receiver module Described response message in the reception state carried, determine that at least one other neighbor node described receives In the case of described first heartbeat message,

Described determine that module is additionally operable to determine the node and described second not receiving described first heartbeat message Link between node breaks down；The described node not receiving described first heartbeat message includes described Primary nodal point and other neighbor nodes described do not receive the node of described first heartbeat message.

10. the fault detection system of a group system interior joint, it is characterised in that include primary nodal point, Secondary nodal point and other neighbor nodes, described primary nodal point is the neighbor node of described secondary nodal point, described Other neighbor nodes be described secondary nodal point all neighbor nodes in joint in addition to described primary nodal point Point, the number of other neighbor nodes described is more than one, including:

Described secondary nodal point, for sending the to described primary nodal point and other neighbor nodes described concurrently One heartbeat message；

Described primary nodal point, for judging whether receive described first heartbeat message in Preset Time； Described Preset Time is more than or equal to a heart beat cycle, and less than two heart beat cycles；

In the case of described primary nodal point does not receives described first heartbeat message, described primary nodal point is also For sending request message respectively to each other neighbor nodes described, described request message is used for inquiring often Whether other neighbor nodes described in receive described first heartbeat message；And, described primary nodal point is also For receiving the response message carrying reception state that each other neighbor nodes described send, described in connect Receipts state is used for indicating whether to receive described first heartbeat message；

The described response sent according to other neighbor nodes each described received at described primary nodal point disappears The reception state carried in breath, determines that other neighbor nodes described all do not receive described first heart beating report In the case of literary composition, described primary nodal point is additionally operable to determine that described secondary nodal point breaks down.

11. systems according to claim 10, it is characterised in that described primary nodal point determines described After secondary nodal point breaks down, also include:

Described primary nodal point is additionally operable to:

Generate the first vote information, and receive the second vote information that each other neighbor nodes described send, Described first vote information includes the node identification that node that described primary nodal point is elected is corresponding, described second The node mark that the node of the neighbor node election that vote information includes sending described second vote information is corresponding Know；

And, send out according to the node identification in described first vote information and each other neighbor nodes described Node identification in the second vote information sent, in all nodes that statistics is elected, each node obtains Ballot quantity, and using nodes most for quantity of voting as the 3rd node, described 3rd node is for substituting institute State secondary nodal point and send the node of heartbeat message concurrently to all neighbor nodes of described 3rd node； All neighbor nodes of described 3rd node include the neighbor node and described second of described 3rd node self The neighbor node of node.

12. according to the system described in claim 10 or 11, it is characterised in that:

The described response sent according to other neighbor nodes each described received at described primary nodal point disappears The reception state carried in breath, determines that at least one other neighbor node described receives described first heart In the case of jumping message,

Described primary nodal point is additionally operable to determine the node and described second not receiving described first heartbeat message Link between node breaks down；The described node not receiving described first heartbeat message includes described Primary nodal point and other neighbor nodes described do not receive the node of described first heartbeat message.