CN111737000A - Method for realizing load balance - Google Patents
Method for realizing load balance Download PDFInfo
- Publication number
- CN111737000A CN111737000A CN202010576925.6A CN202010576925A CN111737000A CN 111737000 A CN111737000 A CN 111737000A CN 202010576925 A CN202010576925 A CN 202010576925A CN 111737000 A CN111737000 A CN 111737000A
- Authority
- CN
- China
- Prior art keywords
- order
- server
- processing
- data
- queue
- 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
Links
Images
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]
- G06F9/5005—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
-
- 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
- G06F9/5038—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 execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for realizing load balance, which solves the defect that the prior art does not support a large amount of concurrency, and can be divided into asynchronous processing and synchronous processing according to the requirements of users; when asynchronous processing is carried out, a queue cache method is used, orders are processed linearly, and the problem of concurrency can be solved directly; and a smooth weighted polling method for judging the state of the server is used during synchronous processing, so that the pressure of a single server can be relieved, and the concurrency number can be increased. Compared with the prior art, the method can ensure the reasonability of distribution and the reliability of the server, and has the characteristics of flexibility, easiness in expansion, low cost and high reliability.
Description
Technical Field
The invention relates to the technical field of load balancing, in particular to a method for realizing load balancing.
Background
With the increase of the traffic volume and the rapid increase of the access volume and the data volume of each core part of the existing network, the processing capacity and the computing intensity of the core part of the existing network are correspondingly increased, and the core part of the existing network cannot bear the load by using a single server device at all.
The load balancing is that a plurality of servers form a server set in a symmetrical mode, each server has an equivalent status and can provide services to the outside independently without the assistance of other servers. By some load sharing technology, the request sent from outside is distributed to some server in the server set according to some strategy, and the server receiving the request responds to the request of the client independently. Load balancing solves the problem of large numbers of concurrent access services with the goal of achieving performance approaching that of a mainframe with minimal investment.
However, if a large amount of hardware upgrade is performed on the basis of the existing equipment, resource waste is caused, and if next service volume is increased, high cost investment for hardware upgrade is caused again; if one or more additional software is/are simply installed on an operating system to realize load balancing, load distribution is uneven, a server with strong load capacity cannot fully function, and distribution is caused by failure in judging the availability state of the server, so that the reliability is low.
Therefore, it is desirable to provide a method for implementing load balancing on the basis that hardware upgrade is not required, and the situations of uneven load distribution and low reliability are avoided. The invention adopts different algorithms for analyzing the service level, thus saving the cost and better realizing the function of load balancing.
Disclosure of Invention
The invention aims at the problem that a large amount of concurrency is generated along with the increase of data volume in a network, and the method for realizing load balancing is substantially the defect that the prior art does not support the large amount of concurrency; the software load balancing is divided into a plurality of load balancing algorithms, the common polling method, the random method and the minimum link method do not consider the performance difference of each server and judge the state of the server, and the reasonability of distribution and the reliability of the server cannot be ensured. The method can be divided into asynchronous processing and synchronous processing according to the requirements of users. When asynchronous processing is carried out, a queue cache method is used, orders are processed linearly, and the problem of concurrency can be solved directly; and a smooth weighted polling method for judging the state of the server is used during synchronous processing, so that the pressure of a single server can be relieved, and the concurrency number can be increased. Compared with the prior art, the method can ensure the reasonability of distribution and the reliability of the server, and has the characteristics of flexibility, easiness in expansion, low cost and high reliability.
The invention realizes the purpose through the following technical scheme:
a method for realizing load balancing comprises the following steps:
and S1, inputting the order. Multiple clients send requests to process orders simultaneously, with a large number of concurrent possibilities. The incoming order is data in a Json format, and comprises picture data, synchronous and asynchronous zone bits, priority level of order processing, a verified token and some parameters required by other businesses.
And S2, verifying data. All parameters for the incoming order are checked. The data verification can quickly filter out some abnormal orders, and the processing pressure of the server is reduced. The data check includes token (accesstken) check, parameter integrity check, check whether the incoming picture is valid, and judgment whether the incoming order is the incoming order according to the MD5 value of the picture. If the order is checked to be passed, the method starts to S3 to continue processing the order, otherwise, the result is returned, and the order processing is ended. And the MD5 value is checked to judge whether the order picture is identified before, if the order picture is not identified, the check is passed, if the order picture is identified, the inquiry and identification result is returned, and the order processing is finished.
S3, the processing is performed by determining the data return method. And the method is divided into a synchronous return mode and an asynchronous return mode according to the real-time property of returning the order processing result.
If the order is in a synchronous return mode, the order result is returned in real time, and a smooth weighted polling algorithm is used, specifically: assuming that n servers S ═ S0, S1, S2, …, Sn }, weights are assigned according to the performance of the servers processing orders, with default weights W ═ W0, W1, W2, …, Wn }, and current weights CW ═ CW0, CW1, CW2, …, CWn }. The default weight represents the original weight of the server, the current weight represents the weight recalculated after each access, the initial value of the current weight is the default weight, the server with the largest current weight is assumed to be maxWeightServer, the sum of all default weights is weightSum, the server list is serverList, and the algorithm can be described as follows:
(1) finding out a server maxWeightServer with the maximum current weight value;
(2) calculating the sum weightSum of default weights { W0, W1, W2, …, Wn };
(3) c, converting maxweight server, cw-weight sum;
(4) recalculating the current weight CW of { S0, S1, S2, …, Sn } with the calculation formula Sn.CW ═ Sn.CW + Sn.Wn;
(5) returns maxWeightServer.
And judging the state of the server after obtaining the address of the server, if the state of the server is unavailable, re-executing the smooth weighted polling algorithm to obtain the address of the server, and continuously judging the state of the server. If the order is available, sending data to the server, processing the order while setting the state of the server as unavailable, changing the state of the server to be available after the processing is finished, synchronously returning the result, and finishing the processing of the order.
If the order processing method is an asynchronous return mode, a plurality of servers are not required to be configured, the order processing result can be asynchronously pushed, a plurality of order processing priorities can be set according to the emergency degree of the order, and a queue cache method is used. Comprises the following steps:
and S31, storing the order into a queue. And establishing a corresponding queue according to the number of the priorities, acquiring the priority required by the incoming order, and putting the order into the queue corresponding to the priority.
And S32, judging whether the queue is empty or not. The null here indicates that all the priority queues are null if their sizes are 0 at the same time. If it is null, ending the asynchronous flow, if it is not null, executing S33;
s33, judging the working state of the background service, if it is Disable, returning to S32, if it is Enable, proceeding to S34
And S34, sequentially judging whether orders exist in each priority queue from high priority to low priority according to the priority of the orders, if so, taking out data, sending the data to a background service for processing, and simultaneously modifying the service working state flag bit to Disable.
And S35, after the background service finishes the processing, returning the result and modifying the service working state flag bit into Enable.
And S36, the load balancer asynchronously pushes the result returned by the server, circularly judges the size of the queue and executes S32. And asynchronously processing the order, and taking the empty data stored in the queue as a mark for finishing the work of the load balancer.
The invention has the beneficial effects that:
the method for realizing load balancing has two synchronous and asynchronous processing modes according to the requirements of the client, can overcome the defect that the prior art does not support a large number of concurrencies, and realizes load balancing. The invention can select a corresponding load balancing algorithm according to the user requirements, ensure that tasks are uniformly and reliably distributed according to the weight and the state during synchronous requests, reduce the pressure of a single server and increase the concurrency number. The asynchronous request has priority processing capability, and the background service cannot be concurrent, so that the normal and stable operation of the background service is ensured. The method has the characteristics of flexibility, simplicity, easy expansion, low cost and high reliability.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the embodiments or the drawings needed to be practical in the prior art description, and obviously, the drawings in the following description are only some embodiments of the embodiments, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a flow chart of data verification according to the present invention;
FIG. 3 is a flow chart of the asynchronous processing of data of the present invention;
FIG. 4 is a flow chart of the priority processing of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
In any embodiment, as shown in fig. 1, a method for implementing load balancing according to the present invention includes:
s1: an order is introduced. If a plurality of clients send requests to the server at the same time, if a great deal of concurrent possibility exists in the process of directly identifying the service to the bottom layer without load balancing, partial orders are lost or the server is abnormal, and the like. The specific data is
{
“accessToken”：”NjN1MjZ1OGUwOD1jNDk3NWJhMzd1NDM1MjBhMTBjODE＝”
″imageData″：″http://csza.chfcloud.com/download/group1/M00/14/59/CgREPV0I16mALt6TA ABvufypxsE832.jpg″，
″dataBackWay″：″tb″，
″level″：″1″，
″orderNo″：″800CW00181000046-888-66″，
″type″：″1000006″
}
Wherein: accessToken is the token, imageData is the ur1 of the picture of the order, dataBackWay is the data return mode (tb: synchronous, yb: asynchronous) level is the priority level of the order (including from high to low 1-5 priority levels), orderNo is the order number, type is the code of the type of the picture.
S2: and (6) data checking. As shown in fig. 2, the data check includes a token (accessToken) check, a parameter integrity check, a check whether the incoming picture is valid, and a determination of whether the incoming order is determined by the MD5 value of the picture. Firstly, performing accessToken verification, performing verification according to an encryption rule agreed with a client, and entering parameter integrity verification if the encryption rule passes the verification; the parameter integrity check is to check whether all necessary parameters are transmitted in, and if all the necessary parameters are transmitted in, the picture check is carried out; the picture verification is to judge whether the incoming url is a valid picture url, and if the incoming url is a valid picture, the MD5 value verification is carried out; the MD5 value verification is to judge whether the picture is recognized before according to the MD5 value of the picture, if the picture is not recognized, the verification is passed, if the picture is recognized, the recognition result is inquired and returned to the client, and the order processing of the current time is finished. If one of the above checks is failed, the result is returned directly, and if the check is passed, S3 is started to continue processing the order.
S3: and judging the data returning mode and respectively processing.
Here the request is a synchronous return, and a smooth weighted round robin method will be used to obtain the server address. It is assumed here that there are 4 identification server addresses and default weight values set according to server processing capacity, respectively, as shown in the following table, where the current weight is initialized to the default weight.
Table-server address and weight assignment
| Serial number | Service address | Default weight | Current weight |
| 01 | 10.4.21.50：8001 | 1 | 1 |
| 02 | 10.4.21.51：8002 | 2 | 2 |
| 03 | 10.4.21.53：8003 | 3 | 3 |
| 04 | 10.4.21.53：8004 | 4 | 4 |
The specific steps of the first request are as follows:
(1) finding out that the server maxweightServer with the largest current weight value is the server number 04;
(2) finding the sum weightSum of the default weights {1, 2, 3, 4} to be 10;
(3) the current weight of the server with the largest current weight value: cw-weight sum-6;
(4) recalculating the current weights CW of the four servers in table one, wherein the calculation formula is sn.cw + sn.wn, that is, the current weights of the servers with serial numbers 01 to 04 are {2, 4, 6, -2 };
(5) maxWeightServer, server number 04, is the selected instance.
The second request is to continue to be executed from the step (1) on the basis of the current data, and so on. The above algorithm executes 11 requests, and the scheduling process is shown in table two:
scheduling process data changes
It can be seen that, in the 11 th scheduling, the current weight is again consistent with the default weight, so that the subsequent scheduling operation can be repeated all the time, the scheduling sequence is very uniformly dispersed, and the load balancing function can be realized.
It can be known from table two that the service number 04 is selected at the first request, the order is sent to the service processing, meanwhile, the state of the service is modified to Disable, if the order processing result returned by the service is received, the state is changed to Enable, and the result is synchronously returned, and one order processing is finished. If the identification service address obtained in the 4 th request is also the 04 number service, two situations occur: (1) if the service is in the disabled state, the system judges that the service address cannot be used, and a 5 th request is made; (2) at this time, the service status is Enable, which indicates that the last order has been processed and can continue to work, and the instance is selected. By judging the state of the server, the reliability of order processing can be improved.
If the mode is asynchronous return mode, the method of queue buffer is used. As shown in fig. 3, the method comprises the following steps
S31: the order is placed in a queue. Knowing that 1-4 priorities exist, a Redis cache database is used for establishing four queues corresponding to the priorities, at the moment, the priority of an incoming order is 1, order information is put into the queue with the priority of 1, a response is made to a client, and asynchronous order processing is started.
S32: and judging whether the queue is empty or not. I.e. to determine whether there is data in the four queues. If all queues have no data, the flow ends, and if not, S33 is executed.
S33: judging the working state of the background service, if the working state is Disable, returning to S32, if the working state is Enable, proceeding to S34
S34: the order is taken from the queue. As shown in fig. 4, it is first determined whether there is data in the queue with Level 1, if there is data, the queue is taken out and sent to the background identification service for corresponding processing, and meanwhile, the working status flag bit of the identification service is modified to Disable, which indicates that the queue is working and in an unavailable state, so as to ensure that no concurrency occurs; if not, judging the queue with Level being 2, and so on.
S35: and after the background service is processed, returning the result, simultaneously modifying the service working state flag bit into available Enable, continuously executing S32, and circularly processing the order. And asynchronously processing the order, and taking the empty data stored in the queue as a mark for finishing the work of the load balancer.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims. It should be noted that the various technical features described in the above embodiments can be combined in any suitable manner without contradiction, and the invention is not described in any way for the possible combinations in order to avoid unnecessary repetition. In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the spirit of the present invention.
Claims (4)
1. A method for realizing load balancing is characterized by comprising the following steps:
s1, the client end transmits an order;
s2, verifying data;
s3, judging the returning mode of the data and processing respectively; dividing the order into a synchronous return mode and an asynchronous return mode according to the real-time property of the order processing result;
if the order is in a synchronous return mode, the order result is returned in real time, and a smooth weighted polling algorithm is used, specifically: assuming that n servers S ═ { S0, S1, S2, …, Sn }, weights are assigned according to the performance of the servers processing orders, with default weights W ═ { W0, W1, W2, …, Wn }, and current weights CW ═ CW0, CW1, CW2, …, CWn }; the default weight represents the original weight of the server, the current weight represents the weight recalculated after each access, the initial value of the current weight is the default weight, the server with the largest current weight is assumed to be maxweightServer, the sum of all the default weights is weightSum, and the server list is serverList;
judging the state of the server after obtaining a server address, if the state of the server is unavailable, re-executing the smooth weighted polling algorithm to obtain a server address, and continuously judging the state of the server; if the order is available, sending data to the server, processing the order, setting the state of the server as unavailable, changing the state of the server into available after the processing is finished, synchronously returning a result, and finishing the processing of one order;
if the order processing mode is an asynchronous return mode, a plurality of servers are not required to be configured, the order processing result can be asynchronously pushed, a plurality of order processing priorities can be set according to the emergency degree of the order, and a queue cache method is used; comprises the following steps:
s31, storing the order into a queue; establishing a corresponding queue according to the number of the priorities, acquiring the priority required by the incoming order, and putting the order into the queue corresponding to the priority;
s32, judging whether the queue is empty; null here means that all the priority queues are null if the size is 0 at the same time; if it is null, ending the asynchronous flow, if it is not null, executing S33;
s33, judging the working state of the background service, if it is Disable, returning to S32, if it is Enable, proceeding to S34
S34, sequentially judging whether an order exists in each priority queue from high priority to low priority according to the priority of the order, if so, taking out data, sending the data to a background service for processing, and simultaneously modifying a service working state flag bit to Disable;
s35, after the background service is finished, returning a result and modifying the service working state flag bit to Enable;
s36, the load balancer asynchronously pushes the result returned by the server, circularly judges the size of the queue and executes S32; and asynchronously processing the order, and taking the empty data stored in the queue as a mark for finishing the work of the load balancer.
2. The method according to claim 1, wherein in S1, a plurality of clients send requests to process orders at the same time, and there is a possibility of a great number of concurrencies; the incoming order is data in a Json format, and at least comprises picture data, synchronous and asynchronous zone bits, priority level of order processing and a verified token.
3. The method according to claim 1, wherein in S2, all parameters of the incoming order are checked; data verification can quickly filter some abnormal orders, and the pressure of server processing is reduced; the data check comprises token check, parameter integrity check, whether the incoming picture is valid or not and whether the incoming order is judged through the MD5 value of the picture or not; if the order passes the verification, starting to S3 to continue processing the order, otherwise, returning the result and ending the order processing; and the MD5 value is checked to judge whether the order picture is identified before, if the order picture is not identified, the check is passed, if the order picture is identified, the inquiry and identification result is returned, and the order processing is finished.
4. The method of claim 1, wherein the server list serverList has an algorithm of:
(1) finding out a server maxWeightServer with the maximum current weight value;
(2) calculating the sum weightSum of default weights { W0, W1, W2, …, Wn };
(3) c, converting maxweight server, cw-weight sum;
(4) recalculating the current weight CW of { S0, S1, S2, …, Sn } with the calculation formula Sn.CW ═ Sn.CW + Sn.Wn;
(5) returns maxWeightServer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010576925.6A CN111737000A (en) | 2020-06-22 | 2020-06-22 | Method for realizing load balance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010576925.6A CN111737000A (en) | 2020-06-22 | 2020-06-22 | Method for realizing load balance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111737000A true CN111737000A (en) | 2020-10-02 |
Family
ID=72650522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010576925.6A Pending CN111737000A (en) | 2020-06-22 | 2020-06-22 | Method for realizing load balance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111737000A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112416576A (en) * | 2020-11-04 | 2021-02-26 | 北京人大金仓信息技术股份有限公司 | Database load balancing method and device |
| CN112630821A (en) * | 2020-12-30 | 2021-04-09 | 核工业北京地质研究院 | Variable frequency control device applied to seismic data acquisition and control method thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261592A (en) * | 2007-03-07 | 2008-09-10 | 国际商业机器公司 | Method and apparatus for scheduling task request |
| CN101753444A (en) * | 2009-12-31 | 2010-06-23 | 卓望数码技术（深圳）有限公司 | Method and device for load balancing |
| CN103118076A (en) * | 2013-01-11 | 2013-05-22 | 烽火通信科技股份有限公司 | Upgraded server cluster system and load balancing method thereof |
| CN106789726A (en) * | 2016-12-20 | 2017-05-31 | 兴唐通信科技有限公司 | A kind of high concurrent service resource allocation method based on service priority |
| CN110049143A (en) * | 2019-05-31 | 2019-07-23 | 华迪计算机集团有限公司 | Load-balancing method and device |
| CN110189206A (en) * | 2019-06-04 | 2019-08-30 | 苏州程旅网络科技有限公司 | Asynchronous ordering system and ordering method from the background |
-
2020
- 2020-06-22 CN CN202010576925.6A patent/CN111737000A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101261592A (en) * | 2007-03-07 | 2008-09-10 | 国际商业机器公司 | Method and apparatus for scheduling task request |
| US20080222640A1 (en) * | 2007-03-07 | 2008-09-11 | International Business Machines Corporation | Prediction Based Priority Scheduling |
| CN101753444A (en) * | 2009-12-31 | 2010-06-23 | 卓望数码技术（深圳）有限公司 | Method and device for load balancing |
| CN103118076A (en) * | 2013-01-11 | 2013-05-22 | 烽火通信科技股份有限公司 | Upgraded server cluster system and load balancing method thereof |
| CN106789726A (en) * | 2016-12-20 | 2017-05-31 | 兴唐通信科技有限公司 | A kind of high concurrent service resource allocation method based on service priority |
| CN110049143A (en) * | 2019-05-31 | 2019-07-23 | 华迪计算机集团有限公司 | Load-balancing method and device |
| CN110189206A (en) * | 2019-06-04 | 2019-08-30 | 苏州程旅网络科技有限公司 | Asynchronous ordering system and ordering method from the background |
Non-Patent Citations (3)
| Title |
|---|
| 左晓麟: "基于Nginx负载均衡的智能家居研究与实现", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 志波同学: "负载均衡算法--平滑加权轮询法（Smooth Weight Round Robin）", 《HTTPS://BLOG.CSDN.NET/CLARAM/ARTICLE/DETAILS/90272318》 * |
| 葛钰: "面向云服务的web服务器负载均衡设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112416576A (en) * | 2020-11-04 | 2021-02-26 | 北京人大金仓信息技术股份有限公司 | Database load balancing method and device |
| CN112630821A (en) * | 2020-12-30 | 2021-04-09 | 核工业北京地质研究院 | Variable frequency control device applied to seismic data acquisition and control method thereof |
| CN112630821B (en) * | 2020-12-30 | 2024-01-12 | 核工业北京地质研究院 | Variable frequency control device applied to seismic data acquisition and control method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9015227B2 (en) | Distributed data processing system | |
| WO2020173287A1 (en) | Systems and methods for determining network shards in blockchain network | |
| CN108933829A (en) | A kind of load-balancing method and device | |
| US9930107B2 (en) | Method and apparatus for load balancing in communication system | |
| CN111460504B (en) | Service processing method, device, node equipment and storage medium | |
| CN110289999B (en) | Data processing method, system and device | |
| JPWO2018220708A1 (en) | Resource allocation system, management device, method and program | |
| CN111737000A (en) | Method for realizing load balance | |
| CN109413202B (en) | System and method for sorting block chain transaction information | |
| CN105978938A (en) | Service processing equipment service status determining method and scheduling equipment | |
| CN110035128B (en) | Live broadcast scheduling method and device, live broadcast system and storage medium | |
| CN112235428B (en) | Call request processing method and device, computer equipment and storage medium | |
| CN108459926B (en) | Data remote backup method and device and computer readable medium | |
| KR20230073315A (en) | Resource scheduling method and system, electronic device, and computer readable storage medium | |
| WO2016206433A1 (en) | Method and apparatus for balancing server load | |
| CN115952003A (en) | Method, device, equipment and storage medium for cluster server load balancing | |
| CN116483570A (en) | Dynamic capacity expansion and contraction method, device and equipment for stateful service and storage medium | |
| CN108200185B (en) | Method and device for realizing load balance | |
| CN113867942B (en) | Method, system and computer readable storage medium for mounting volume | |
| CN112001800B (en) | Method and device for processing business in block chain system | |
| CN113783919B (en) | Access request distribution method, system, equipment and storage medium | |
| CN112019630B (en) | Load balancing method and device | |
| CN116684098A (en) | Block chain-based data processing method, device, equipment, medium and product | |
| CN114090604A (en) | Request processing method and device | |
| CN109474705B (en) | Session maintaining method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201002 |