CN117149408A - Server cluster management method, device, computer equipment and storage medium - Google Patents

Server cluster management method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN117149408A
CN117149408A CN202310967567.5A CN202310967567A CN117149408A CN 117149408 A CN117149408 A CN 117149408A CN 202310967567 A CN202310967567 A CN 202310967567A CN 117149408 A CN117149408 A CN 117149408A
Authority
CN
China
Prior art keywords
server
utilization rate
type
resource utilization
combination
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310967567.5A
Other languages
Chinese (zh)
Inventor
郑泽奇
张立强
张教萌
周晓萌
郝婷
张学庆
陈颖
李归韵
郭龙飞
王兆朋
祝捷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202310967567.5A priority Critical patent/CN117149408A/en
Publication of CN117149408A publication Critical patent/CN117149408A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer And Data Communications (AREA)

Abstract

The application relates to a server cluster management method, a server cluster management device, a computer device, a storage medium and a computer program product. The method comprises the following steps: determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; sequencing servers of the server cluster according to the resource utilization rate to obtain a server ranking sequence; pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; and transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transferring is lower than a first utilization rate threshold value. By adopting the method, the load of the server cluster can be balanced.

Description

Server cluster management method, device, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a server cluster management method, an apparatus, a computer device, a storage medium, and a computer program product.
Background
With the development of computer technology, internet technology has emerged. In the internet, clients and servers are the primary roles, clients being programs that provide local services to users, and servers being computer devices in the network that are able to provide services to other machines. With the increasing growth of internet users and traffic, higher demands are placed on server performance, and server clusters have grown. The server cluster is a collection of combining a plurality of physical servers together to jointly process workload, and compared with independent servers, the server cluster can provide higher performance, reliability and expandability, and each server in the server cluster can be connected with a plurality of clients and provide services for the clients through the established connection.
However, when each server in a server cluster serves a client, the server cluster may have a problem of unbalanced load.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a server cluster management method, apparatus, computer device, storage medium, and computer program product that enable load balancing of server clusters.
In a first aspect, the present application provides a server cluster management method. The method comprises the following steps:
determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the servers of the server cluster are sequenced according to the resource utilization rate, and a server ranking sequence is obtained;
pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
and transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transferring is lower than the first utilization rate threshold value.
In a second aspect, the application further provides a server cluster management device. The device comprises:
the data processing module is used for determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the sequencing module is used for sequencing the servers of the server cluster according to the resource utilization rate to obtain a server ranking sequence;
the pairing module is used for respectively pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
and the transfer module is used for transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transfer is lower than the first utilization rate threshold value.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the servers of the server cluster are sequenced according to the resource utilization rate, and a server ranking sequence is obtained;
pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
And transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transferring is lower than the first utilization rate threshold value.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the servers of the server cluster are sequenced according to the resource utilization rate, and a server ranking sequence is obtained;
pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
And transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transferring is lower than the first utilization rate threshold value.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the servers of the server cluster are sequenced according to the resource utilization rate, and a server ranking sequence is obtained;
pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
And transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transferring is lower than the first utilization rate threshold value.
The server cluster management method, the device, the computer equipment, the storage medium and the computer program product are used for sequencing servers of the server cluster according to the resource utilization rate to obtain a server ranking sequence, and at least one combination for transferring the client in the combination can be rapidly determined by pairing at least one part of servers in symmetrical ranks in the server ranking sequence; because the first type server and the first type server in each combination are respectively positioned at two ends of the average resource utilization rate and are symmetrically arranged, at least one client connected with the first type server in each combination through long connection is transferred to the second type server in the same combination, so that the servers in the same combination can reach the load balancing level, and the load balancing of the whole server cluster is realized.
Drawings
FIG. 1 is a diagram of an application environment for a server cluster management method in one embodiment;
FIG. 2 is a flow chart of a method for server cluster management in one embodiment;
FIG. 3 is a flowchart illustrating a step of transferring at least one client connected through a long connection to a second type of server in the same group so that the resource usage rate of the transferred servers in the same group is lower than a first usage rate threshold value;
FIG. 4 is a flowchart illustrating steps performed by a server cluster management core in one embodiment;
FIG. 5 is a schematic diagram of module connection relationships in one embodiment;
FIG. 6 is a block diagram of a server cluster management device in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The server cluster management method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the management server 102 may communicate with the server cluster 104, and the servers in the server cluster 104 are configured to establish long connections with clients and perform data interactions through the established long connections. The management server 102 may determine an average resource usage rate of hardware resources of the server cluster 104 based on the resource usage rate of hardware resources of each server in the server cluster 104, the management server 102 may rank the servers of the server cluster 104 according to the resource usage rate, obtain a server rank sequence, pair at least a portion of the servers in the symmetric ranks in the server rank sequence, obtain at least one combination, transfer at least one client connected through a long connection to a second server in the same combination, and make the resource usage rate after the transfer of the servers in the same combination lower than a first usage rate threshold. The management server 102 may be implemented by an independent server, or may be implemented by a cluster formed by a plurality of servers. The server cluster 104 is made up of multiple independent servers.
In one embodiment, as shown in fig. 2, a server cluster management method is provided, and this embodiment is described by taking the application of the method to the management server 102 in fig. 1 as an example, the method includes the following steps:
step 202, determining an average resource utilization rate of hardware resources of a server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection.
Wherein a server is a computer device in a network that is capable of providing services to other machines. The client is an application program installed on the terminal device to provide local services for users. A long connection is a connection that can continuously transmit a plurality of data packets during connection maintenance. Unlike short connections, long connections can remain connected after data is transmitted once, so that both parties of the connection can continuously send data to each other. The data interaction is to send data to each other, and may specifically be to send data packets to each other.
A hardware resource is a resource provided by a hardware device on a server. The hardware resources may include computing resources, storage resources, or other provided by the hardware device. The hardware devices may include a central processing unit (CPU, central Processing Unit), memory (storage), disk (Disk), or others.
Resource usage is the proportion of hardware resources used by a computer program running on a server to the hardware resources that the server can provide. The resource usage may be a usage of hardware resources provided by a hardware device of the server, such as CPU usage, memory usage, or hard disk usage; or the utilization rate of the hardware resources provided by various hardware devices of the integrated server. The average resource usage is an average of the sum of the resource usage of the servers in the server cluster.
In one embodiment, the management server may periodically obtain the resource usage of the hardware resources of each server in the server cluster, calculate an average value of the resource usage of the hardware resources of each server in the server cluster, and obtain the average resource usage of the hardware resources of the server cluster.
Wherein the period may be every preset period length, such as 1 minute, 10 minutes, 1 hour, etc. The resource utilization rate of each server obtained each time may be the resource utilization rate of the hardware resource of the server at the obtaining time point; the average value of the resource utilization rates of the hardware resources of the server taken at intervals within a preset time before the acquisition time point can also be obtained. The preset duration is a preset length of time, such as 30 seconds, 1 minute, 10 minutes, or others. The preset interval duration is a preset interval duration such as 10 seconds, 30 seconds, 1 minute, or others. For example, the acquisition time point may be 10:00:00, and the plurality of resource usage rates within the preset duration may be resource usage rates of hardware resources taken every 10 seconds between 10:00:00 and 10:01:00.
In one embodiment, the management server may obtain, for each server in the server cluster, a CPU usage, a memory usage, and a disk usage of the targeted server, calculate an average value for the obtained CPU usage, memory usage, and disk usage, determine the calculated average value as a resource usage of a hardware resource of the targeted server, and obtain the resource usage of the hardware resource of each server in the server cluster.
Step 204, the servers of the server cluster are ordered according to the resource utilization rate, and a server ranking sequence is obtained.
Wherein the server rank sequence is a sequence that characterizes the rank positions in which the servers of the server cluster are located. The server ranking sequence may specifically be a sequence formed by server identifiers, where the ranking positions where the server identifiers are located characterize ranking positions of resource usage rates of servers corresponding to the server identifiers in the server cluster. The server identification is an identification that distinguishes between different servers, such as a server number, a server ID (Identity document, an identification number), or others.
In one embodiment, the management server may obtain server identifiers of servers in the server cluster, and rank the obtained server identifiers according to a high-to-low resource usage rate, to obtain a server ranking sequence.
In one embodiment, the management server may obtain server identities of servers in the server cluster, and rank the obtained server identities according to a low-to-high resource usage rate, to obtain a server ranking sequence.
Step 206, pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type of server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value.
Wherein the symmetrical ranks are two ranks at the same distance from the center of the server rank sequence. For example, when the server rank sequence is a, b, c, d, e, the center of the server rank sequence is c in the third order, and the symmetrical ranks may be a in the first order and e in the fifth order. Pairing is to form a pair, and may be to establish a mapping relationship. The combination is a server group comprising a first type of server and a second type of server formed by pairing server ranking sequences.
The first type of server is a server in the server cluster where the utilization of the resource is greater than or equal to a first utilization threshold. The second type of server is a server in the server cluster for which the utilization of the resource is less than or equal to a second utilization threshold. The first usage threshold is a value higher than the average resource usage and the difference from the average resource usage is a preset positive value. The second usage threshold is a value lower than the average resource usage and having a difference from the average resource usage of a preset negative value. The preset positive value is a preset value greater than zero. The preset negative value is a preset value smaller than zero. The predetermined positive value may be the same as or different from the absolute value of the predetermined negative value.
In one embodiment, the management server may determine a first usage threshold and a second usage threshold, and when there are a first type of server with a resource usage higher than the first usage threshold and a second type of server with a resource usage lower than the second usage threshold in the server cluster, pair at least a portion of the servers in a symmetric rank in the server rank sequence respectively to obtain at least one combination, such that each combination includes one first type of server and one second type of server.
In one embodiment, the server ranking sequence may characterize the resource usage of the servers from high to low ranking. In this embodiment, the management server may determine, from a direction from a first position to a middle position of the server ranking sequence, that the server whose resource usage rate is not lower than the first usage rate threshold is a first type server, determine, from a direction from a last position to the middle position, that the server whose resource usage rate is not higher than the second usage rate threshold is a second type server, and pair the first type server and the second type server which are symmetrically ranked to obtain at least one combination.
Step 208, transferring at least one client connected through a long connection to the first type of server in each combination to the second type of server in the same combination, so that the resource utilization rate after transferring the servers in the same combination is lower than the first utilization rate threshold.
Wherein the transfer is a process of transferring a long connection established by a server and a client in the same combination to another server.
In one embodiment, the management server may determine, for each combination, the clients on the servers of the first type in the combination in turn that connect through the long connection, instruct the clients to disconnect the long connection with the servers of the first type in the combination in question, and establish the long connection with the servers of the second type in the combination in question, so as to implement the transfer of the long connection corresponding to one client, until the resource usage rate after the transfer of the servers in the combination in question is lower than the first usage rate threshold.
In the server cluster management method, the servers of the server clusters are ordered according to the resource utilization rate, a server ranking sequence is obtained, at least one part of servers in symmetrical ranks in the server ranking sequence are paired, and at least one combination for transferring the client in the combination can be rapidly determined; because the first type server and the first type server in each combination are respectively positioned at two ends of the average resource utilization rate and are symmetrically arranged, at least one client connected with the first type server in each combination through long connection is transferred to the second type server in the same combination, so that the servers in the same combination can reach the load balancing level, and the load balancing of the whole server cluster is realized.
In one embodiment, as shown in FIG. 3, step 208 includes steps 302 through 308 described below.
Step 302, for each combination, determines a set of clients having correspondingly long connections with the first type of server in the combination.
Wherein the client set is a set formed by at least one client connected by a long connection on a first type of server.
In one embodiment, the management server may determine, for each combination, a set of clients having respective long connections with the first type of servers in the combination, and obtain connection information corresponding to each client in the set of clients. The connection information is information required by the client for establishing a long connection with the server. The connection information may include an IP address (Internet Protocol Address ) and a port number.
Step 304, the target client is selected from the client set based on the index data of the data interaction of the client set through the corresponding long connection.
The index data is data under the index type for measuring data interaction between the client and the server. The index data may specifically be an index value of an index type. The target client is a client for transferring a corresponding long connection transfer from a first type of server to a second type of server.
In one embodiment, the management server may sort each client in the client set based on index data of the client set for data interaction through the corresponding long connection, obtain a sorting result, and filter out the target client according to the sorting result.
Step 306, instruct the first type server in the directed combination to send a connection transfer instruction to the target client, so that the target client disconnects the long connection with the first type server in the directed combination and establishes the long connection with the second type server in the directed combination.
Wherein the connection transfer instruction is an instruction indicating to transfer the corresponding long connection from the first type of server to the second type of server.
In one embodiment, the management server may obtain an IP address and port number of the second type of server in the combination in question, instruct the first type of server in the combination in question to send a connection transfer instruction to the target client. Wherein the connection transfer instruction may indicate the IP address and port number of the second type of server in the combination in question.
In one embodiment, the target client may disconnect the long connection with the first type of server in the set for after receiving the connection transfer instruction, and establish the long connection with the second type of server in the set for by the IP address and port number of the target client and the IP address and port number of the second type of server in the set for.
Step 308, when the first type of server exists after the combination is transferred and the server with the resource usage rate lower than the first usage rate threshold exists after the transfer, using the server with the resource usage rate lower than the first usage rate threshold after the transfer of the combination as the second type of server, updating the client set corresponding to the first type of server in the combination, executing index data for data interaction through corresponding long connection based on the client set, and screening out target clients from the client set until the resource usage rates of the servers in the combination are lower than the first usage rate threshold.
In one embodiment, when there is a first type of server after the transfer of the combination and there is a server with a resource usage rate below the first usage rate threshold after the transfer, the management server may take the server with a resource usage rate below the first usage rate threshold after the transfer of the combination as a second type of server, reject the target client that has been transferred out of the first type of server from the client set to update the client set, and execute steps 304 to 306 until the resource usage rate after the transfer of the server in the combination is below the first usage rate threshold.
In this embodiment, the target clients connected by long connection on the first type of servers are transferred to the second type of servers one by one, so that the resource usage rate after the transfer of the servers in the combination is lower than the first usage rate threshold, that is, is close to the average resource usage rate, thereby realizing load balancing of the server cluster.
In one embodiment, the index data is index data for a plurality of index types, step 304 includes: according to index data under multiple index types of data interaction of the client set through corresponding long connection, respectively sequencing the client set to obtain a client ranking sequence under each index type; determining a comprehensive ranking sequence of the client set according to the client ranking sequence under each index type and the preset weight corresponding to the same index type; and screening the target clients from the client set based on the comprehensive ranking sequence.
The index type is the type of index for measuring data interaction between the client and the server. The plurality of index types may include at least two of an amount of interaction data, a last interaction time, and an interaction frequency, and may also include other types. The interactive data volume is the volume of data that the client and the server send to each other over a long connection. The last interaction time is the time the client and server sent data over the long connection. The interaction frequency is the ratio of the number of times of data interaction through the long connection to the long connection establishment time after the long connection is established between the client and the server.
The client ranking sequence is a sequence that characterizes the ordering positions in which clients in the client set are located. The client ranking sequence under each index type is a sequence of characterization ranking positions obtained by ranking clients in a client set according to the index type under the same index type. The comprehensive ranking sequence is a ranking sequence formed by integrating client ranking sequences under multiple index types. The preset weights are preset weights, and each index type can correspond to one preset weight.
In this embodiment, the client ranking sequence sorts the client sets according to the index data under the multiple index types of data interaction through the corresponding long connection, and the client ranking sequence can characterize the data interaction condition under the corresponding index types, so as to synthesize the client ranking sequence under the multiple index types, determine the target client, and enable the subsequent transfer of the target client to the second type server, thereby rapidly reducing the resource utilization rate of the first type server and improving the efficiency of completing the load balancing of the server cluster.
In one embodiment, the management server may sort the client sets from high to low according to the index value of the interactive data amount, obtain a client ranking sequence under the interactive data amount, sort the client sets from near to far according to the index value of the last interactive time, obtain a client ranking sequence under the last interactive time, and sort the client sets from high to low according to the index value of the interactive frequency, so as to obtain a client ranking sequence under the interactive frequency.
In one embodiment, the management server may calculate, for each client in the set of clients, a product of a preset score corresponding to a ranking position of the client under each index type, where the client is located, and a preset weight corresponding to the same index type, to obtain an index score of the client under the same index type, and sum the index scores of the clients under multiple index types, respectively, to obtain a comprehensive score of the client; and sequencing the client sets according to the comprehensive score of each client in the client sets to obtain a comprehensive ranking sequence of the client sets. The preset scores corresponding to the sorting positions are sequentially reduced from high to low according to the sorting positions. For example, the preset score corresponding to the first bit is 50 points, the preset score corresponding to the second bit is 40 points, and the preset score corresponding to the third bit is 20 points.
In one embodiment, the management server may select the top ranked client from the comprehensive ranking sequence, and determine the top ranked client as the target client selected from the set of clients.
In one embodiment, the server cluster management method further includes the following steps: when the average resource utilization rate of the server cluster is between a preset capacity expansion trigger threshold and a preset capacity contraction trigger threshold, and the difference value between the highest resource utilization rate and the lowest resource utilization rate in the server cluster is not lower than a fluctuation value, executing the step of pairing at least one part of servers in symmetrical arrangement in a server arrangement sequence; the preset capacity expansion trigger threshold is larger than the preset capacity shrinkage trigger threshold; the fluctuation value is the sum of the absolute values of a preset positive value and a preset negative value.
The preset capacity expansion trigger threshold is a threshold for triggering the server cluster to increase servers. The preset capacity reduction triggering threshold is a preset threshold for triggering a server cluster to reduce servers. The highest resource usage is the highest resource usage among the resource usage of the servers in the server cluster. The lowest resource usage is the lowest resource usage of the resource usage of each server in the server cluster.
In this embodiment, under the condition that the capacity expansion or contraction of the server cluster is not achieved and a certain gap exists between the resource utilization rates of the servers in the server cluster, the step of pairing at least a part of the servers in symmetrical ranks in the server rank sequence is executed, that is, the servers with unbalanced loads in the server cluster are adjusted, resource waste caused by adjusting the servers under the condition that the capacity expansion or contraction is required or the server cluster is balanced in load is avoided, and resources of the management server can be saved.
In one embodiment, when the average resource usage of the server cluster is between the preset capacity expansion trigger threshold and the preset capacity contraction trigger threshold, and the difference between the highest resource usage and the lowest resource usage in the server cluster is not lower than the fluctuation value, steps 206 to 208 are performed.
In one embodiment, the server cluster management method further includes the following steps: when the average resource utilization rate of the server cluster is not lower than a preset capacity expansion trigger threshold, determining a cluster standby server configured for the server cluster; and selecting at least one server from the cluster standby servers to be added to the server cluster, so that the average resource utilization rate of the added server cluster is lower than a preset capacity expansion trigger threshold and higher than a preset capacity contraction trigger threshold.
The cluster standby server is a server which is configured for a server cluster and serves as a standby. The clustered standby servers may include at least one standby server. It will be appreciated that the resource usage of the servers added to the server cluster is low, e.g. the resource usage may be zero, and thus the average resource usage of the server cluster after the added servers may be reduced.
In this embodiment, when the average resource usage rate of the server cluster is not lower than the preset capacity expansion trigger threshold, the load condition of the server cluster is represented to be at a higher level, and the server is added to the server cluster, so that the problem that the server cluster cannot respond to a new client request is avoided, and the performance of the server cluster can be improved.
In one embodiment, the server cluster management method further includes the following steps: when the average resource utilization rate of the server cluster is not higher than a preset capacity-shrinking triggering threshold value, determining a target server with the lowest resource utilization rate from the server cluster; transferring all clients connected through long connection on the target servers to at least one server except the target server in the server cluster, so that the resource utilization rate of the at least one server after transfer is lower than a preset upper limit value; the preset upper limit value is higher than a preset capacity-shrinking triggering threshold value and lower than a preset capacity-expanding triggering threshold value; the transferred target server is moved out of the server cluster, and the server cluster is updated; and under the condition that the average resource utilization rate of the updated server cluster is not higher than a preset capacity-shrinking triggering threshold value, executing the step of determining the target server with the lowest resource utilization rate from the server cluster until the average resource utilization rate of the updated server cluster is higher than the preset capacity-shrinking triggering threshold value.
The target server is a server with the lowest resource utilization rate in the server cluster. The preset upper limit value is a preset upper limit value. The preset upper limit value is smaller than a preset capacity expansion trigger threshold, for example, the preset capacity expansion trigger threshold may be 85%, and the preset upper limit value may be 70%.
In this embodiment, when the average resource usage rate of the server cluster is not higher than the preset capacity reduction triggering threshold, the load condition of the server cluster is represented to be at a lower level, and the client of the target server in the server cluster is transferred to other servers, so as to improve the average resource usage rate of the server cluster to be above the preset capacity reduction triggering threshold, that is, reduce the number of server clusters and save the hardware resources of the server under the condition that the average resource usage rate of the server cluster is ensured to be at a normal level.
In one embodiment, the management server may remove the transferred target server from the server cluster and add the removed target server to the cluster standby server.
In one embodiment, in a specific application scenario, the flow chart of the steps of the server cluster management method may be shown in the flow chart of the server cluster management core step of fig. 4, and may be implemented by a resource usage collection module, a long connection management module, a resource usage calculation module, and a long connection transfer module, where the connection relationship between the modules may be shown in fig. 5, and based on fig. 4 and 5, the server cluster management method may specifically include the following steps.
The management server can collect CPU utilization rate, memory utilization rate and disk utilization rate of the targeted server through the resource utilization rate collection module aiming at each server in the server cluster; calculating an average value of the collected CPU utilization rate, memory utilization rate and disk utilization rate through a resource utilization rate calculation module, determining the calculated average value as the resource utilization rate of the hardware resources of the aimed servers, obtaining the resource utilization rate of the hardware resources of each server in the server cluster, and sequencing the servers of the server cluster from high to low according to the resource utilization rate to obtain a server ranking sequence. The number of servers in the server cluster may be k, and then the resource utilization rate of each server in the server ranking sequence may be sequentially recorded as m1, m2, m3, …, mk.
The management server can calculate the average value of the resource utilization rate of the hardware resources of each server in the server cluster through the resource utilization rate calculation module, so as to obtain the average resource utilization rate of the hardware resources of the server cluster. Wherein the average resource usage can be noted as mp, mp= (m1+m2+ … +mk)/k.
The management server can pair at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type of server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value. For example, a first type of server with a resource utilization of m1 is paired with a second type of server with a resource utilization of mk to form one combination, and a first type of server with a resource utilization of m2 is paired with a second type of server with a resource utilization of mk-1 to form another combination.
The management server can obtain the number of long connections established between the server corresponding to the server ranking sequence and the client through the long connection management module, and the number of long connections of the server corresponding to the server ranking sequence is recorded as n1, n2, n 3; and a corresponding relation between the resource utilization rate of the server and the corresponding long connection number is established through the resource utilization rate calculation module, for example, m1 corresponds to n1, m2 corresponds to n2, and m3 corresponds to n3.
The management server can determine, for each combination, a target client connected with the first type of service in the combination through a long connection through the long connection management module, determine an IP address and a port number of the target client for establishing the long connection, and determine an IP address and a port number of the second type of service in the combination for establishing the long connection; and the long connection transfer module indicates the first type server in the aimed combination to send a connection transfer instruction to the target client, so that the target client breaks long connection with the first type server in the aimed combination and establishes long connection with the second type server in the aimed combination.
When a first type of server exists after the transfer of the combination is performed, and a server with the resource utilization rate lower than a first utilization rate threshold value exists after the transfer, the management server can take the server with the resource utilization rate lower than the first utilization rate threshold value after the transfer of the combination as a second type of server, and the management server can execute the steps of determining a target client connected with the first type of service in the combination through a long connection management module, determining an IP address and a port number of the target client for establishing the long connection, and determining an IP address and a port number of the second type of server in the combination for establishing the long connection; and a step of indicating the first type server in the aimed combination to send a connection transfer instruction to the target client through the long connection transfer module, so that the target client breaks long connection with the first type server in the aimed combination and establishes long connection with the second type server in the aimed combination until the resource utilization rate after the server in the same combination is transferred is lower than a first utilization rate threshold value.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a server cluster management device for realizing the above-mentioned server cluster management method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of one or more server cluster management devices provided below may refer to the limitation of the server cluster management method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 6, there is provided a server cluster management apparatus 600, including: a data processing module 610, a sorting module 620, a pairing module 630, and a transfer module 640, wherein:
a data processing module 610, configured to determine an average resource usage of hardware resources of the server cluster based on the resource usage of hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection.
The ranking module 620 is configured to rank the servers of the server cluster according to the resource usage rate, and obtain a server ranking sequence.
Pairing module 630, configured to pair at least a portion of servers in a symmetric rank in the server rank sequence respectively, to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type of server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value.
And a transferring module 640, configured to transfer at least one client connected through a long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource usage rate after the transfer of the servers in the same combination is lower than the first usage rate threshold.
In one embodiment, the transfer module 640 is further configured to determine, for each combination, a set of clients that have a corresponding long connection with a first type of server in the combination being targeted; screening target clients from the client set based on index data of data interaction of the client set through corresponding long connection; the method comprises the steps of indicating a first type server in a targeted combination to send a connection transfer instruction to a target client, enabling the target client to disconnect long connection with the first type server in the targeted combination and establish long connection with a second type server in the targeted combination; when a first type of server exists after the combination is transferred and a server with the resource utilization rate lower than a first utilization rate threshold value exists after the combination is transferred, the server with the resource utilization rate lower than the first utilization rate threshold value exists after the combination is transferred is used as a second type of server, a client set corresponding to the first type of server in the combination is updated, index data for data interaction through corresponding long connection based on the client set is executed, and a target client is screened out from the client set until the resource utilization rate of the server in the combination after the transfer is lower than the first utilization rate threshold value.
In one embodiment, the index data is index data under multiple index types; the transfer module 640 is further configured to sort the client sets according to index data under multiple index types of data interaction performed by the client sets through corresponding long connections, so as to obtain a client ranking sequence under each index type; determining a comprehensive ranking sequence of the client set according to the client ranking sequence under each index type and the preset weight corresponding to the same index type; and screening the target clients from the client set based on the comprehensive ranking sequence.
In one embodiment, the server cluster management apparatus 600 further includes a control module, where the control module is configured to, when an average resource usage rate of the server cluster is between a preset capacity expansion trigger threshold and a preset capacity contraction trigger threshold, and a difference between a highest resource usage rate and a lowest resource usage rate in the server cluster is not lower than a fluctuation value, instruct the pairing module 630 to perform pairing of at least a portion of servers in a symmetric rank in a server rank sequence to obtain at least one combination, instruct the transfer module 640 to perform transferring at least one client connected through a long connection to a second type of server in the same combination, so that a resource usage rate after transferring the servers in the same combination is lower than the first usage rate threshold; the preset capacity expansion trigger threshold is larger than the preset capacity shrinkage trigger threshold; the fluctuation value is the sum of the absolute values of a preset positive value and a preset negative value.
In one embodiment, the server cluster management device 600 further includes a capacity expansion module, where the capacity expansion module is configured to determine a cluster standby server configured for the server cluster when an average resource usage rate of the server cluster is not lower than a preset capacity expansion trigger threshold; and selecting at least one server from the cluster standby servers to be added to the server cluster, so that the average resource utilization rate of the added server cluster is lower than a preset capacity expansion trigger threshold and higher than a preset capacity contraction trigger threshold.
In one embodiment, the server cluster management apparatus 600 further includes a capacity shrinking module, where the capacity shrinking module is configured to determine, from the server cluster, a target server with a lowest resource usage rate when an average resource usage rate of the server cluster is not higher than a preset capacity shrinking trigger threshold; transferring all clients connected through long connection on the target servers to at least one server except the target server in the server cluster, so that the resource utilization rate of the at least one server after transfer is lower than a preset upper limit value; the preset upper limit value is higher than a preset capacity-shrinking triggering threshold value and lower than a preset capacity-expanding triggering threshold value; the transferred target server is moved out of the server cluster, and the server cluster is updated; and under the condition that the average resource utilization rate of the updated server cluster is not higher than a preset capacity-shrinking triggering threshold value, executing the step of determining the target server with the lowest resource utilization rate from the server cluster until the average resource utilization rate of the updated server cluster is higher than the preset capacity-shrinking triggering threshold value.
The modules in the server cluster management device may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data to be stored for executing server cluster management. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a server cluster management method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (10)

1. A method for server cluster management, the method comprising:
determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the servers of the server cluster are sequenced according to the resource utilization rate, and a server ranking sequence is obtained;
Pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
and transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transferring is lower than the first utilization rate threshold value.
2. The method according to claim 1, wherein transferring the first type of server in each group to the second type of server in the same group at least one client connected by a long connection such that the resource usage rate after transferring the servers in the same group is lower than the first usage rate threshold comprises:
For each combination, determining a set of clients having respective long connections with the first type of server in the combination;
screening target clients from the client set based on index data of data interaction of the client set through corresponding long connection;
instructing a first type server in the aimed combination to send a connection transfer instruction to the target client, so that the target client breaks long connection with the first type server in the aimed combination and establishes long connection with a second type server in the aimed combination;
when a first type of server exists after the combination is transferred and a server with the resource utilization rate lower than the first utilization rate threshold exists after the transfer is performed, the server with the resource utilization rate lower than the first utilization rate threshold exists after the transfer is used as a second type of server, a client set corresponding to the first type of server in the combination is updated, the step of screening target clients from the client set based on index data of the client set for data interaction through corresponding long connection is performed until the resource utilization rate of the server in the combination after the transfer is lower than the first utilization rate threshold.
3. The method of claim 2, wherein the index data is index data for a plurality of index types; the screening the target client from the client set based on the index data of the data interaction of the client set through the corresponding long connection includes:
according to index data of the client set under multiple index types of data interaction through corresponding long connection, sequencing the client set respectively to obtain a client ranking sequence under each index type;
determining a comprehensive ranking sequence of the client set according to the client ranking sequence under each index type and the preset weight corresponding to the same index type;
and screening target clients from the client set based on the comprehensive ranking sequence.
4. A method according to any one of claims 1 to 3, further comprising:
when the average resource utilization rate of the server cluster is between a preset capacity expansion trigger threshold and a preset capacity contraction trigger threshold, and the difference value between the highest resource utilization rate and the lowest resource utilization rate in the server cluster is not lower than a fluctuation value, executing the step of pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence respectively; the preset capacity expansion trigger threshold is larger than the preset capacity shrinkage trigger threshold; the fluctuation value is the sum of the absolute values of the preset positive value and the preset negative value.
5. The method according to claim 4, wherein the method further comprises:
when the average resource utilization rate of the server cluster is not lower than the preset capacity expansion trigger threshold, determining a cluster standby server configured for the server cluster;
and selecting at least one server from the cluster standby servers and adding the server to the server cluster, so that the average resource utilization rate of the added server cluster is lower than the preset capacity expansion trigger threshold and higher than the preset capacity contraction trigger threshold.
6. The method according to claim 4, wherein the method further comprises:
when the average resource utilization rate of the server cluster is not higher than the preset capacity-shrinking triggering threshold value, determining a target server with the lowest resource utilization rate from the server cluster;
transferring all clients connected through long connection to at least one server except a target server in the server cluster, so that the resource utilization rate of the at least one server after transfer is lower than a preset upper limit value; the preset upper limit value is higher than the preset capacity-shrinking triggering threshold value and lower than the preset capacity-expanding triggering threshold value;
Removing the transferred target server from the server cluster, and updating the server cluster;
and under the condition that the average resource utilization rate of the updated server cluster is not higher than the preset capacity reduction triggering threshold, executing the step of determining the target server with the lowest resource utilization rate from the server cluster until the average resource utilization rate of the updated server cluster is higher than the preset capacity reduction triggering threshold.
7. A server cluster management apparatus, the apparatus comprising:
the data processing module is used for determining the average resource utilization rate of the hardware resources of the server cluster based on the resource utilization rate of the hardware resources of each server in the server cluster; the server is used for establishing long connection with the client and performing data interaction through the established long connection;
the sequencing module is used for sequencing the servers of the server cluster according to the resource utilization rate to obtain a server ranking sequence;
the pairing module is used for respectively pairing at least one part of servers in symmetrical arrangement in the server arrangement sequence to obtain at least one combination; each combination comprises a first type server and a second type server; the resource utilization rate of the first type of server is not lower than a first utilization rate threshold, and the difference value between the first utilization rate threshold and the average resource utilization rate is a preset positive value; the resource utilization rate of the second type server is not higher than a second utilization rate threshold, and the difference value between the second utilization rate threshold and the average resource utilization rate is a preset negative value;
And the transfer module is used for transferring at least one client connected through long connection to the first type of servers in each combination to the second type of servers in the same combination, so that the resource utilization rate of the servers in the same combination after transfer is lower than the first utilization rate threshold value.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
CN202310967567.5A 2023-08-02 2023-08-02 Server cluster management method, device, computer equipment and storage medium Pending CN117149408A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310967567.5A CN117149408A (en) 2023-08-02 2023-08-02 Server cluster management method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310967567.5A CN117149408A (en) 2023-08-02 2023-08-02 Server cluster management method, device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117149408A true CN117149408A (en) 2023-12-01

Family

ID=88910963

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310967567.5A Pending CN117149408A (en) 2023-08-02 2023-08-02 Server cluster management method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117149408A (en)

Similar Documents

Publication Publication Date Title
CN111027736B (en) Micro-service combined deployment and scheduling method under multi-objective optimization
CN110798517B (en) Decentralized cluster load balancing method and system, mobile terminal and storage medium
CN109189751A (en) Method of data synchronization and terminal device based on block chain
CN109117275B (en) Account checking method and device based on data slicing, computer equipment and storage medium
CN109189578B (en) Storage server allocation method, device, management server and storage system
CN113655969B (en) Data balanced storage method based on streaming distributed storage system
CN105516347A (en) Method and device for load balance allocation of streaming media server
Hassanzadeh-Nazarabadi et al. Decentralized utility-and locality-aware replication for heterogeneous DHT-based P2P cloud storage systems
CN104063501B (en) copy balance method based on HDFS
CN107317764B (en) Traffic load balancing method, system, device and computer readable storage medium
CN109413202B (en) System and method for sorting block chain transaction information
CN112764920A (en) Edge application deployment method, device, equipment and storage medium
CN110765092A (en) Distributed search system, index distribution method, and storage medium
CN111324429B (en) Micro-service combination scheduling method based on multi-generation ancestry reference distance
CN114461407B (en) Data processing method, data processing device, distribution server, data processing system, and storage medium
CN117176796A (en) Message pushing method, device, computer equipment and storage medium
CN118316881A (en) Big data network communication coordination method and system
CN117149408A (en) Server cluster management method, device, computer equipment and storage medium
CN106657333B (en) Centralized directory data exchange system and method based on cloud service mode
EP2439907A1 (en) Method of data storing in a distributed data storage system and corresponding device
CN115952003A (en) Method, device, equipment and storage medium for cluster server load balancing
CN112860384B (en) Multi-dimensional resource load balancing-oriented VNF multiplexing and migration method
CN115378962A (en) High-availability communication method and system of storage cluster based on iSCSI protocol
CN113608870A (en) Load balancing method and device of message queue, electronic equipment and storage medium
Furuya et al. Load balancing method for data management using high availability distributed clusters

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination