CN105591964A - Device and method for overload protection for Internet system - Google Patents
Device and method for overload protection for Internet system Download PDFInfo
- Publication number
- CN105591964A CN105591964A CN201510665499.2A CN201510665499A CN105591964A CN 105591964 A CN105591964 A CN 105591964A CN 201510665499 A CN201510665499 A CN 201510665499A CN 105591964 A CN105591964 A CN 105591964A
- Authority
- CN
- China
- Prior art keywords
- request
- backend application
- protection
- backend
- load
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer And Data Communications (AREA)
Abstract
A device of overload protection for an Internet system comprises: an acquisition module configured to acquire data from a flow mirror image of a network flow prior to the acquisition module reaching a rear-end application; a decision module configured to determine the load degree about the rear-end application according to the data and determine the protection strategy; and a protective module configured to execute the protection strategy.
Description
Technical field
Embodiments of the invention relate to network computer system load control, and relate more specifically to for interconnectedThe overload protection arrangement of net system and method.
Background technology
The introduction of this part can promote to understand better aspect of the present invention. Correspondingly, the statement of this part should be justAnd this is by reading, and should not be understood to admit that what belongs to prior art or what does not belong to existing skillArt.
When in the face of the portfolio of sudden high pressure, especially Internet application system of network computer systemDisposal ability can decline gradually because of overload. This will cause the time of system processing service request elongated, and userConstantly refresh the page because losing patience and further increased the pressure of system, cause avalanche effect. In this feelingsUnder condition, each request of system processing by because of service ability overtime and invalid so that system presents outside severalBe 0. For avoiding this experience, general processing mode is to restart system. Industry will directly be affected but so doThe use of the service that the processing of business and user provide system.
Summary of the invention
Comprise for the overload protection arrangement of internet system: acquisition module, it is from arriving before backend applicationThe traffic mirroring image data of network traffics, decision-making module, it is determined about this backend application according to these dataDegree of load, and determine protection strategy, protection module, it carries out this protection strategy.
Alternatively, protection module is configured to carry out according to this protection strategy: receive the request from client,Judge that whether this request is overtime; If this request is overtime, return and reply to this client, and not to thisBackend application forwards, if this request is not overtime,, according to the degree of load of being calculated by decision-making module, judges after thisWhether end application can process this request; If this backend application can be processed this request, to this backend applicationForward this request, if this backend application can not be processed this request, postpone to forward this request.
Alternatively, this decision-making module is configured to determine according to these data the type of service of these network traffics, protection mouldPiece is configured to carry out according to this protection strategy: receive the request from client, according to the industry of these network trafficsBusiness type, judges that whether this request is core business request, if this request is core business request, shouldRequest is transmitted to high-performance passage, and this high-performance passage is made up of the node over half in this backend application,If this request is core business request, this request is transmitted to general passage, this generality passage is by removingNode composition beyond node in described high-performance passage.
Alternatively, the degree of load about this backend application that this decision-making module is determined according to these data, is configured toCarry out: in the time judging that described degree of load exceedes threshold value, send automatic expansion order to cloud dispatch server, makeThis cloud dispatch server notice cloud O&M platform extension produces can be for carrying out from after the request of client newEnd application.
Alternatively, protection module is configured to carry out according to this protection strategy: receive the request from client,If this request is not overtime, according to the degree of load calculated by decision-making module, judge that this backend application whether canProcess this request; If this backend application can be processed this request, forward this request to this backend application, asThis backend application of fruit can not be processed this request, forwards this request to the backend application in standby resources pond, itsDescribed in be deployed with in advance multiple backend application that started in standby resources pond.
Alternatively, described data comprise error rate, response time, number of request per second.
A kind of overload protection method for internet system comprises: from arriving backend application network traffics beforeTraffic mirroring image data, determine about the degree of load of this backend application according to these data, and determine protection planSlightly, carry out this protection strategy.
Alternatively, according to this protection strategy execution: receive the request from client, judge that whether this request is superTime; If this request is overtime, return and reply to this client, and do not forward to this backend application, asThis request of fruit is not overtime, according to described degree of load, judges whether this backend application can process this request; AsThis backend application of fruit can be processed this request, forwards this request to this backend application, if this backend application is notCan process this request, postpone to forward this request.
Alternatively, determine the type of service of these network traffics according to these data, according to this protection strategy execution: connectReceive the request from client, according to the type of service of these network traffics, judge whether this request is core businessRequest, if this request is core business request, is transmitted to high-performance passage by this request, and this high-performance is logicalRoad is made up of the node over half in this backend application, if this request is core business request, shouldRequest is transmitted to general passage, and this generality passage is by the node the node in described high-performance passageComposition.
Alternatively, according to the degree of load of this backend application, carry out: in the time judging that described degree of load exceedes threshold value,Send automatic expansion order to cloud dispatch server, this cloud dispatch server notice cloud O&M platform extension is producedLife can be for the new backend application of carrying out from the request of client.
Alternatively, according to this protection strategy execution: receive the request from client, if this request is not overtime,, according to described degree of load, judge whether this backend application can process this request; If this backend application canProcess this request, forward this request to this backend application, if this backend application can not be processed this request,Forward this request to the backend application in standby resources pond, in wherein said standby resources pond, be deployed with in advance manyThe individual backend application having started.
The one or more embodiment of the present invention adopt the bypass monitoring of mirror image flow, its packet to original transmissionCan not produce any impact; Application responds error rate, application response time, application by application are per secondNumber of request judges that whether application self is in overload more accurately; And be to provide multiple protection and arrangedExecute. The present invention has following one or more advantage: the in the situation that of the sudden high pressure of systems face, and systemService ability can not drop to 0, but the maximum processing capability of the external display systems of meeting; For follow-up dilatation,Emergent reserve the time, can break in service; After sudden high pressure request recovers normally, automatically adjust shapeState; System can be moved continually and steadily, and the user who has improved in burst high pressure situation experiences.
In the time reading by reference to the accompanying drawings following description, also will understand further feature and the advantage of embodiments of the invention, itsMiddle accompanying drawing shows the principle of embodiments of the invention by means of example.
Brief description of the drawings
By means of example, from following the detailed description and the accompanying drawings, each embodiment of the present invention above-mentioned and otherIt is more obvious that aspect, feature and benefit will become.
Fig. 1 illustrates the schematic diagram in system according to the overload protection arrangement of the embodiment of the present invention.
Fig. 2 illustrates the flow chart that postpones forwarding and overtime advanced processing according to the realization of the embodiment of the present invention.
Fig. 3 illustrates exemplary sudden high pressure curve map.
Fig. 4 illustrates the exemplary sudden high pressure curve map through peak clipping.
Fig. 5 illustrates according to the flow chart of the realization protection key business of the embodiment of the present invention.
Fig. 6 illustrates according to the overload protection arrangement of realizing resource automatic expansion of the embodiment of the present invention in systemSchematic diagram.
Fig. 7 illustrates according to the schematic diagram of the overload protection in the employing standby resources pond of the embodiment of the present invention.
Detailed description of the invention
Hereinafter, with reference to embodiment, principle of the present invention and purport are described. Should be understood that, provideEmbodiment is only used to those skilled in the art and understands better the present invention and further put into practice the present invention, andDo not limit the scope of the invention. For example, can as the part feature illustrated or that describe of an embodimentBe combined with another embodiment and produce another one embodiment. For clarity, in this manual notAll features of actual embodiment are described. Obviously, be understandable that the actual of any this embodiment and grindIn sending out, for realizing developer's specific objective, such as meeting constraint that system is relevant and the constraint of traffic aided,Embodiment is by different.
Referring now to accompanying drawing, disclosed theme is described. In the drawings schematic representation various structures, system andEquipment, this is only for purposes of illustration but not these is described and well known to a person skilled in the art that details is mixedConfuse. But, comprise that accompanying drawing is the illustrative example in order to describe and explain disclosed theme.
Fig. 1 illustrates the schematic diagram in system according to the overload protection arrangement of the embodiment of the present invention. As shown in Figure 1,System is made up of client and server end. Server end receives the request from client, processes this request,And the result of processing is returned to client. Server end is provided with the load balancing network equipment conventionally for controllingLoad balancing, Web application for the treatment of page logic and backend application for the treatment of service logic. Wherein,Request from client is mainly calculated by backend application. Here, backend application can be multiple calculating jointsPoint. The computing node that possesses disposal ability can be the independent server existing with physical form, can be alsoBe present in the virtual computing unit in server. Therefore server end comprises that one or more backend application processService request.
Embodiments of the invention carry out overload protection by overload protection arrangement is set at server end to system. AsShown in Fig. 1, overload protection arrangement can be arranged on the load balancing network equipment, Web application or rear end shouldWith, with before request from client arrives the backend application of being responsible for carrying out Practical Calculation work to this ask intoRow pretreatment so as not to system because of overload cause computing capability reduce. As shown in the figure, overload protection arrangement, loadEqualising network equipment, Web application layer form overload protection layer jointly. Overload protection arrangement comprise acquisition module,Decision-making module, protection module. Alternatively, regulation engine and traffic mirroring module also can be arranged on overload guarantorIn protection unit.
According to embodiments of the invention, acquisition module is configured to from arriving network traffics before backend applicationTraffic mirroring image data, decision-making module is configured to determine the load about this backend application according to these dataDegree, and determine protection strategy, and protection module is configured to carry out this protection strategy.
Acquisition module, decision-making module, protection module, regulation engine and traffic mirroring module are below described in processMutual in protection process. First, traffic mirroring module is mirrored to arriving backend application network traffics beforeShunting environment, as the data source of acquisition module. Carry out bypass monitoring by generation traffic mirroring and can avoid rightThe impact of regular traffic processing. But, from traffic mirroring image data, for example, can comprise mistake by acquisition moduleThe key indexs such as mistake rate, response time, number of request per second. Then, decision-making module provides according to acquisition moduleData are carried out the calculating of the degree of load of backend application, and can be according to the different loads degree configuring in regulation engineThe strategy of Shi Butong, notice protection module is carried out corresponding strategy. Finally, protection module receives from decision-making moduleAfter notice, implementation strategy is protected backend application. Protection module can be answered at load-balancing device or WEBUse in the mode of F5+Apache or LVS+Nginx and realize. Protection module is being carried out decision-making module rootAfter the strategy generating according to the data that gather, can again carry out decision-making module basis and think what the data of collection generatedStrategy, forms a closed forward dynamical feedback thus.
Postpone to forward and overtime advanced processing
Fig. 2 illustrates the flow chart that postpones forwarding and overtime advanced processing according to the realization of the embodiment of the present invention. As figureShown in 2, this process comprises the following steps:
In step 201, receive the request from client;
In step 202, judge that whether this request is overtime;
If this request is overtime, return and reply to this client in step 203, and should not to this rear endWith forwarding, thus this request of advanced processing;
If this request is not overtime, the degree of load of being calculated by decision-making module in step 204 basis, judges after thisWhether end application can process this request, or whether the disposal ability of this backend application reaches capacity;
If this backend application can be processed this request, forward this request in step 206 to this backend application,
If this backend application can not be processed this request, postpone to forward this request in step 205.
The strategy execution that above-mentioned steps can be generated according to decision-making module by protection module. Postpone to forward and overtime carryingThe request pressure that pre-treatment can guarantee to be transmitted to backend application is no more than the maximum processing capability of backend application, withThereby and control the request rate that application forwards to the back-end and realize peak clipping effect, and it is every that backend application is processedThe time of individual request keeps stable. On the other hand, for the request that exceedes the client timeout time, no longerForward toward backend application, just return and reply in advance at overload protection layer, thus the pressure of minimizing backend applicationPower.
Fig. 3 and Fig. 4 exemplarily illustrate according to the forwarding of delay shown in Fig. 2 and overtime advanced processing step and can reachThe effect signal of the overload protection arriving. Fig. 3 illustrates exemplary sudden high pressure curve map. Fig. 4 illustratesThe sudden high pressure curve map through peak clipping of example. Fig. 3 represents that the system under sudden high pressure scene gulps downThe curve map of the amount of telling TPS, horizontal dotted line represents the maximum processing capability of backend application, when TPS curve exceedes waterFlat dotted line, backend application there will be the abnormal conditions of overload. Forward by delay, in Fig. 3 more than horizontal dotted lineThe request representing with inclination solid line, can be moved to the part that inclination solid line represents. Thereby can realize as Fig. 4Shown TPS curve map, wherein TPS curve is all below horizontal dotted line.
Protection key business
Fig. 5 shows according to the flow chart of the realization protection key business of the embodiment of the present invention. As shown in Figure 5,In step 501, judge whether request is core business request; If this request is core business request,In step 502, this request is transmitted to high-performance passage; If this request is core business request, in stepIn rapid 504, this request is transmitted to general passage. High-performance passage is by the most of node in this backend applicationComposition, the remaining fraction node in backend application forms general passage. For example, high-performance passage is by thisNode composition over half in backend application, this generality passage is by the node except in described high-performance passageNode composition in addition. Alternatively, can also by decision-making module according to from the Data Dynamic of acquisition module drawDivide high-performance passage and general passage. For example, decision-making module can be according to the current disposal ability of each nodeDynamically divide high-performance passage and general passage. In conjunction with the overload protection arrangement shown in Fig. 1, this decision-makingModule is configured according to the type of service of determining these network traffics from the data of acquisition module, protection module basisThis protection strategy is configured to carry out: receive the request from client, according to the type of service of these network trafficsForward this business. Thus, can guarantee that core business request is by preferential fast processing; The industry of non-critical pathBusiness request is queued processing.
Resource automatic expansion
Fig. 6 shows according to the overload protection arrangement of realizing resource automatic expansion of the embodiment of the present invention in systemSchematic diagram. As shown in Figure 6, decision-making module can determine according to the data that gather about this backend applicationDegree of load, is configured to carry out: in the time judging that described degree of load exceedes threshold value, send certainly to cloud dispatch serverMoving explosion command, this cloud dispatch server notice cloud O&M platform extension is produced can be for carrying out from clientThe new backend application of request. Cloud O&M platform is according to the notice automatic expansion rear end from cloud dispatch serverApplication, the new application node of pull-up automatically. After expansion completes, cloud dispatch server reinforms decision-making module.Decision-making module can configure overload protection strategy according to the concrete condition of node expansion, thereby is carried out by protection moduleNew protection strategy. For example, protection module is follow-up asks that the node application to new expansion forward.
Standby resources pond
Fig. 7 illustrates according to the schematic diagram of the overload protection in the employing standby resources pond of the embodiment of the present invention. As Fig. 7Shown in, utilize standby resources pond to dispose in advance multiple backend application, and start backend application, so work as systemHave overload when risk without carrying out again real-time extension. Standby resources pond can be shared to improve by multiple different applicationResource utilization. For example, when the degree of load of a backend application reaches after threshold value, passable from outside requestBe scheduled and point task the corresponding backend application in standby resources pond. It is below a step that uses resource standby poolRapid example,
1. overload protection layer receives the request of applying to the back-end A;
2. judge whether backend application A has reached the limit of disposal ability;
If 3. do not reach capacity, apply to the back-end A and forward;
If 4. reach capacity, forward to the application A in standby resources pond;
5. return to the 1st step and continue to process subsequent request.
In conjunction with the overload protection arrangement in Fig. 1 or Fig. 6, protection module can be configured to according to protection strategyCarry out:
Receive the request from client,
If this request is not overtime,, according to the degree of load of being calculated by decision-making module, whether judge this backend applicationCan process this request;
If this backend application can be processed this request, forward this request to this backend application,
If this backend application can not be processed this request, forwarding to the backend application in standby resources pond shouldAsk, in wherein said standby resources pond, be deployed with in advance multiple backend application that started.
Usually, various exemplary embodiments can be implemented in software. Can be by controller, microprocessor or itsIts calculation element is carried out above-mentioned software, although the invention is not restricted to this. Although exemplary embodiment of the present inventionVarious aspects can be shown and described as block diagram, flow chart or illustrate and retouch with some other diagrammatic representationState, but be well understood that, these pieces described herein, device, system can be as limiting examplesHardware, software, firmware, special circuit or logic circuit, common hardware or controller or other calculation element orIn its some combination, implement.
Each frame shown in Fig. 2, Fig. 5 can be regarded as method step and/or be regarded as due to operation computer journeyOrder code and the operation that causes and/or be regarded as being configured to multiple couplings of implementing correlation function (several function)The logic circuit component closing.
Although this description comprises many concrete implementation details, these details should not be interpreted as anyBright scope maybe may be required the restriction of scope of protection, but should be regarded as can be specific to specific inventionThe description of the feature of specific embodiment. Some spy who describes in this manual in the context of embodiment separatelyLevy also and can be combined in single embodiment and implement. That in the context of single embodiment, describes on the contrary, is eachPlant feature also can implement respectively in multiple embodiment or in any suitable sub-portfolio. In addition, although specialLevy and can be described to particular combinations in the above and even as advocated at first, play a role, but comeOne or more features from combination required for protection can be removed in some cases from this combination, andAnd combination required for protection can be for the variation of sub-portfolio or sub-portfolio.
Similarly, although operation described in the drawings by specific order, this should not be understood to require according toShown particular order or carry out these operations by order successively, or requires all illustrative operations to be performed,To do the trick. In some cases, multi-task parallel processing may be favourable. In addition, upperThe separation of the various system components in the described embodiment of literary composition should not be understood to require to enter in all embodimentThis separation of row, and should be understood to that described program assembly and system can be integrated conventionallyIn single software product or be packaged into multiple software products.
Therefore, should be understood that, embodiments of the invention are not limited to disclosed specific embodiment, and becomeShape example and other embodiment are intended to contain within the scope of the appended claims.
Claims (12)
1. for an overload protection arrangement for internet system, it is characterized in that, comprising:
Acquisition module, it is from arriving the traffic mirroring image data of the network traffics before backend application,
Decision-making module, it determines the degree of load about this backend application according to these data, and determines protection strategy,
Protection module, it carries out this protection strategy.
2. overload protection arrangement as claimed in claim 1, is characterized in that,
Protection module is configured to carry out according to this protection strategy:
Receive the request from client,
Judge that whether this request is overtime;
If this request is overtime, return and reply to this client, and do not forward to this backend application,
If this request is not overtime,, according to the degree of load of being calculated by decision-making module, whether judge this backend applicationCan process this request;
If this backend application can be processed this request, forward this request to this backend application,
If this backend application can not be processed this request, postpone to forward this request.
3. overload protection arrangement as claimed in claim 1, is characterized in that,
This decision-making module is configured to determine according to these data the type of service of these network traffics,
Protection module is configured to carry out according to this protection strategy:
Receive the request from client,
According to the type of service of these network traffics, judge whether this request is core business request,
If this request is core business request, this request is transmitted to high-performance passage, this high-performance passageFormed by the node over half in this backend application,
If this request is core business request, this request is transmitted to general passage, this generality passageFormed by the node the node in described high-performance passage.
4. overload protection arrangement as claimed in claim 1, is characterized in that,
The degree of load about this backend application that this decision-making module is determined according to these data, is configured to carry out:
In the time judging that described degree of load exceedes threshold value, send automatic expansion order to cloud dispatch server, make thisCloud dispatch server notice cloud O&M platform extension produces can be for the new rear end of carrying out from the request of clientApplication.
5. overload protection method as claimed in claim 1, is characterized in that,
Protection module is configured to carry out according to this protection strategy:
Receive the request from client,
If this request is not overtime,, according to the degree of load of being calculated by decision-making module, whether judge this backend applicationCan process this request;
If this backend application can be processed this request, forward this request to this backend application,
If this backend application can not be processed this request, forwarding to the backend application in standby resources pond shouldAsk, in wherein said standby resources pond, be deployed with in advance multiple backend application that started.
6. overload protection method as claimed in claim 1, is characterized in that,
Described data comprise error rate, response time, number of request per second.
7. for an overload protection method for internet system, it is characterized in that, comprising:
From arriving the traffic mirroring image data of backend application network traffics before,
Determine the degree of load about this backend application according to these data, and determine protection strategy,
Carry out this protection strategy.
8. overload protection method as claimed in claim 7, is characterized in that,
According to this protection strategy execution:
Receive the request from client,
Judge that whether this request is overtime;
If this request is overtime, return and reply to this client, and do not forward to this backend application,
If this request is not overtime, according to described degree of load, judge whether this backend application can be processed this and askAsk;
If this backend application can be processed this request, forward this request to this backend application,
If this backend application can not be processed this request, postpone to forward this request.
9. overload protection method as claimed in claim 7, is characterized in that,
Determine the type of service of these network traffics according to these data,
According to this protection strategy execution:
Receive the request from client,
According to the type of service of these network traffics, judge whether this request is core business request,
If this request is core business request, this request is transmitted to high-performance passage, this high-performance passageFormed by the node over half in this backend application,
If this request is core business request, this request is transmitted to general passage, this generality passageFormed by the node the node in described high-performance passage.
10. overload protection method as claimed in claim 7, is characterized in that,
According to the degree of load of this backend application, carry out:
In the time judging that described degree of load exceedes threshold value, send automatic expansion order to cloud dispatch server, make thisCloud dispatch server notice cloud O&M platform extension produces can be for the new rear end of carrying out from the request of clientApplication.
11. overload protection methods as claimed in claim 7, is characterized in that,
According to this protection strategy execution:
Receive the request from client,
If this request is not overtime, according to described degree of load, judge whether this backend application can be processed this and askAsk;
If this backend application can be processed this request, forward this request to this backend application,
If this backend application can not be processed this request, forwarding to the backend application in standby resources pond shouldAsk, in wherein said standby resources pond, be deployed with in advance multiple backend application that started.
12. overload protection methods as claimed in claim 7, is characterized in that,
Described data comprise error rate, response time, number of request per second.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510665499.2A CN105591964B (en) | 2015-10-14 | 2015-10-14 | A kind of overload protection arrangement and method for internet system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510665499.2A CN105591964B (en) | 2015-10-14 | 2015-10-14 | A kind of overload protection arrangement and method for internet system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105591964A true CN105591964A (en) | 2016-05-18 |
| CN105591964B CN105591964B (en) | 2019-08-13 |
Family
ID=55931196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510665499.2A Active CN105591964B (en) | 2015-10-14 | 2015-10-14 | A kind of overload protection arrangement and method for internet system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105591964B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108206841A (en) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | A kind of data processing method and system |
| CN109785606A (en) * | 2019-02-02 | 2019-05-21 | 中能瑞通（北京）科技有限公司 | A kind of power information acquisition system acquisition quality analysis method and device |
| CN111447113A (en) * | 2020-03-25 | 2020-07-24 | 中国建设银行股份有限公司 | System monitoring method and device |
| CN111814024A (en) * | 2020-08-14 | 2020-10-23 | 北京斗米优聘科技发展有限公司 | Distributed data acquisition method, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102123179A (en) * | 2011-03-28 | 2011-07-13 | 中国人民解放军国防科学技术大学 | Load balancing method and system applied to distributed application system |
| CN102420867A (en) * | 2011-12-01 | 2012-04-18 | 浪潮电子信息产业股份有限公司 | Cluster storage entry resolution method based on real-time load balancing mechanism |
| CN102811157A (en) * | 2011-06-01 | 2012-12-05 | 阿尔卡特朗讯公司 | Method and device for flow control |
| CN103179217A (en) * | 2013-04-19 | 2013-06-26 | 中国建设银行股份有限公司 | Load balancing method and device applicable to WEB application server group |
-
2015
- 2015-10-14 CN CN201510665499.2A patent/CN105591964B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102123179A (en) * | 2011-03-28 | 2011-07-13 | 中国人民解放军国防科学技术大学 | Load balancing method and system applied to distributed application system |
| CN102811157A (en) * | 2011-06-01 | 2012-12-05 | 阿尔卡特朗讯公司 | Method and device for flow control |
| CN102420867A (en) * | 2011-12-01 | 2012-04-18 | 浪潮电子信息产业股份有限公司 | Cluster storage entry resolution method based on real-time load balancing mechanism |
| CN103179217A (en) * | 2013-04-19 | 2013-06-26 | 中国建设银行股份有限公司 | Load balancing method and device applicable to WEB application server group |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108206841A (en) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | A kind of data processing method and system |
| CN108206841B (en) * | 2016-12-16 | 2021-05-14 | 北京酷我科技有限公司 | Data processing method and system |
| CN109785606A (en) * | 2019-02-02 | 2019-05-21 | 中能瑞通（北京）科技有限公司 | A kind of power information acquisition system acquisition quality analysis method and device |
| CN111447113A (en) * | 2020-03-25 | 2020-07-24 | 中国建设银行股份有限公司 | System monitoring method and device |
| CN111447113B (en) * | 2020-03-25 | 2021-08-27 | 中国建设银行股份有限公司 | System monitoring method and device |
| CN111814024A (en) * | 2020-08-14 | 2020-10-23 | 北京斗米优聘科技发展有限公司 | Distributed data acquisition method, system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105591964B (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6457447B2 (en) | Data center network traffic scheduling method and apparatus | |
| Lu et al. | Size-based scheduling policies with inaccurate scheduling information | |
| CN105591964A (en) | Device and method for overload protection for Internet system | |
| CN108023967B (en) | Data balancing method and device and management equipment in distributed storage system | |
| CN106233269A (en) | Fine granulation bandwidth supply in Memory Controller | |
| JP2018532172A (en) | Method and system for resource scheduling | |
| CN104301404A (en) | Method and device for regulating resources of service system based on virtual machines | |
| US10579299B2 (en) | Method, apparatus, server and storage medium of erasing cloud host in cloud-computing environment | |
| CN109845192B (en) | Computer system and method for dynamically adapting a network and computer readable medium | |
| CN105446653A (en) | Data merging method and device | |
| CN113760541B (en) | Method and device for allocating edge resources | |
| CN107239347B (en) | Equipment resource allocation method and device in virtual scene | |
| CN109597800B (en) | Log distribution method and device | |
| WO2017112324A1 (en) | Ranking system | |
| CN103488538B (en) | Application extension device and application extension method in cloud computing system | |
| CN105302907A (en) | Request processing method and device | |
| CN106164888A (en) | The sequencing schemes of network and storage I/O request for minimizing interference between live load free time and live load | |
| WO2016026436A1 (en) | Service provision | |
| CN102137091A (en) | Overload control method, device and system as well as client-side | |
| CN103902401A (en) | Virtual machine fault tolerance method and device based on monitoring | |
| CN105335362B (en) | The processing method and system of real time data, instant disposal system for treating | |
| CN103442033A (en) | Running state information synchronizing method and device | |
| CN106412257B (en) | Positioning service control method and system | |
| Madan et al. | On a batch arrival queue with second optional service, random breakdowns, delay time for repairs to start and restricted availability of arrivals during breakdown periods | |
| CN112866131B (en) | Traffic load balancing method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |