CN105786909A - Message queue backlog load self-adaptive application triggering method and system - Google Patents
Message queue backlog load self-adaptive application triggering method and system Download PDFInfo
- Publication number
- CN105786909A CN105786909A CN201410826747.2A CN201410826747A CN105786909A CN 105786909 A CN105786909 A CN 105786909A CN 201410826747 A CN201410826747 A CN 201410826747A CN 105786909 A CN105786909 A CN 105786909A
- Authority
- CN
- China
- Prior art keywords
- duty
- locally applied
- message
- overstocked
- service end
- 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
Landscapes
- Computer And Data Communications (AREA)
Abstract
The embodiment of the invention discloses a message queue backlog load self-adaptive application triggering method and system, and relates to the technical field of data transmission. The method and the system are used for solving the problems that the data processing efficiency is reduced greatly and the integral performance of the system is reduced after data processing logic is imported in a message-oriented middleware, in the prior art. The message queue backlog load self-adaptive application triggering method and system provided by the invention comprises that a server obtains a backlog message quantity from a message queue; the server judges whether the backlog message quantity in the message queue is more than or equal to a preset value; if the backlog message quantity in the message queue is more than or equal to the preset value, the server starts a new native application process to process the backlog messages according to the backlog message quantity. The embodiment of the invention is mainly used for automatically triggering and starting the application program according to the backlog condition of the message queue in data transmission products.
Description
Technical field
The present invention relates to technical field of data transmission, particularly relate to a kind of self adaptation message queue and overstock the applications trigger method and system of load.
Background technology
Common data transmission series products (such as message-oriented middleware product that is commercial or that increase income) can support the tradition application scenarios such as the exchange of centralized single service center data central authorities, distributed multi-stage service center data topological transmission.Along with the development of the new industry such as the Internet, cloud computing, data transmission is proposed new requirement, the simple data transmission series products meeting tradition application scenarios, it is not enough to supporting business demand.For Internet industry, electricity business's platform as well-known in Taobao, Jingdone district etc., and various cloud computing platform, data transmission module therein, to adapt to magnanimity communication access on the one hand, the data being also performed to equivalent amount level on the other hand process.Data are all transmitted series products and are proposed new function and performance requirement by this.
In order to adapt to above-mentioned new function and performance requirement, some are increased income and commercial data transmission series products, propose corresponding solution respectively, by technology such as external load balancing soft (firmly) part system, high-availability cluster, with requirements such as satisfying magnanimity elasticity communication access and resilient expansion.But, introduce various external system, too increase hardware and software cost and the O&M cost of total solution simultaneously.
After tested, when hardware resource is enough, single machine adopt centralized single service centre pattern dispose message-oriented middleware, its Message Queuing resource nonexistence energy bottleneck.Being embodied in: under this environment, individually send (depositing) message and to message queue or individually receive (reading) message from message queue, its disposal ability is all more than 100,000.When not introducing data process method, this performance data is enough to support the miscellaneous service requirement including the Internet and cloud computing.But, once introduce data process method, different according to the complexity of data process method, its disposal ability (TPS, TransactionperSecond) will significantly loss, process message count per second from more than 100,000, be reduced to 10,000, thousands of pen, even hundreds of pen not etc..
In the process realizing the present invention, inventor have found that prior art at least exists following technical problem:
Existing message-oriented middleware is after introducing data process method, and the large percentage of shared duration in whole message lifecycle consuming time of data process method, data-handling efficiency declines to a great extent, and the overall performance of system reduces.
Summary of the invention
Self adaptation message queue provided by the invention overstocks the applications trigger method and system of load, it is possible to make whole system make full use of hardware resource, thus improving data-handling efficiency, promotes the overall performance of system.
On the one hand, the present invention provides a kind of self adaptation message queue to overstock the applications trigger method of load, including:
Service end obtains the overstocked message count in message queue;
Service end judges that whether the overstocked message count in described message queue is more than or equal to preset value;
If the overstocked message count in described message queue is more than or equal to preset value, then service end starts the new overstocked message of locally applied process process according to described overstocked message count.
On the other hand, the present invention provides a kind of self adaptation message queue to overstock the applications trigger system of load, including service end and locally applied process, wherein,
Described service end, for obtaining the overstocked message count in message queue, judge that whether the overstocked message count in described message queue is more than or equal to preset value, when the overstocked message count in described message queue is more than or equal to preset value, starts new locally applied process according to described overstocked message count and process overstocked message.
Self adaptation message queue provided by the invention overstocks the applications trigger method and system of load, message-oriented middleware can be realized and overstock situation automatically according to the message in message queue, Parallel Scheduling plays the data handling utility service routine that quantity is suitable, concurrent by data handling utility service routine, improve whole system making full use of hardware resource, thus improving data-handling efficiency, farthest reduce the ratio of shared duration in whole message lifecycle consuming time of data process method, promote the overall performance of system;And then make not introducing external system, do not increase extra hardware and software cost, under the premise of O&M cost, efficiently utilize hardware system resource to greatest extent, under limited facility environment, realize message-oriented middleware and automatically adapt to traffic pressure, traffic handing capacity resilient expansion and performance undamaged, better adapt to the Internet for message-oriented middleware and cloud computing provides strong technical guarantee.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme in the embodiment of the present invention, below the accompanying drawing used required during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 overstocks the flow chart of the applications trigger method of load for the self adaptation message queue that the embodiment of the present invention provides;
Fig. 2 sends the flow chart of message for the application interface that the embodiment of the present invention provides;
Fig. 3 receives the flow chart of message for the application interface that the embodiment of the present invention provides;
The flow chart of the service end monitoring process that Fig. 4 provides for the embodiment of the present invention;
The flow chart of the service end queue monitoring process that Fig. 5 provides for the embodiment of the present invention;
The flow chart of the service end consumer registration that Fig. 6 provides for the embodiment of the present invention;
The flow chart that Fig. 7 nullifies for the service end consumer that the embodiment of the present invention provides.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, all other embodiments that those of ordinary skill in the art obtain under not making creative work premise, broadly fall into the scope of protection of the invention.
The embodiment of the present invention provides a kind of self adaptation message queue to overstock the applications trigger method of load, as it is shown in figure 1, the applications trigger method that described self adaptation message queue overstocks load includes:
S11, service end obtain the overstocked message count in message queue;
S12, service end judge that whether the overstocked message count in described message queue is more than or equal to preset value;
If the overstocked message count in the described message queue of S13 is more than or equal to preset value, then service end starts the new overstocked message of locally applied process process according to described overstocked message count.
The self adaptation message queue that the embodiment of the present invention provides overstocks the applications trigger method of load, message-oriented middleware can be realized and overstock situation automatically according to the message in message queue, Parallel Scheduling plays the data handling utility service routine that quantity is suitable, concurrent by data handling utility service routine, improve whole system making full use of hardware resource, thus improving data-handling efficiency, farthest reduce the ratio of shared duration in whole message lifecycle consuming time of data process method, promote the overall performance of system;And then make not introducing external system, do not increase extra hardware and software cost, under the premise of O&M cost, efficiently utilize hardware system resource to greatest extent, under limited facility environment, realize message-oriented middleware and automatically adapt to traffic pressure, traffic handing capacity resilient expansion and performance undamaged, better adapt to the Internet for message-oriented middleware and cloud computing provides strong technical guarantee.
Specifically, the described locally applied process process overstocked message new according to the startup of described overstocked message count includes: can trigger the number of message according to described overstocked message count and single locally applied process, obtain the number of required locally applied process;Start the locally applied process suitable with described number and process overstocked message.
Further, described method also includes:
The locally applied state of a process that service end monitor in real time has been turned on;
When the described locally applied state of a process having been turned on is changed to non-duty by duty, service end record is in non-duty duration;
When be in non-duty duration exceed Preset Time time, service end closes the locally applied process of non-duty of being in.
Further, after described service end starts the new overstocked message of locally applied process process according to described overstocked message count, described method also includes:
The login state of the locally applied process started is revised as duty by idle condition;
It is respectively modified the number of the locally applied process being in idle condition and duty.
Further, after the described locally applied state of a process having been turned on is changed to non-duty by duty, also include:
The login state being changed to the locally applied process having been turned on of non-duty is changed to non-duty by duty;
It is respectively modified the number of the locally applied process of in running order and non-duty.
Further, after being in the locally applied process of non-duty described in described service end is closed, also include:
The login state of the locally applied process being in non-duty closed is revised as idle condition by non-duty;
It is respectively modified the number of the locally applied process being in non-duty and idle condition.
As in figure 2 it is shown, the idiographic flow that application interface sends message is as follows:
S201, message sink interface are started working;
S202, record current process login state are " previous status ";
S203, amendment process registers state are A_WORK, and previous status process instance number subtracts 1, and WorkNum adds 1, and time-out time initializes;
S204, each exception exit: amendment process registers state is " previous status ", and WorkNum subtracts 1, and previous status process instance number adds 1, and time-out time initializes;
S205, to service end core send instruction;
The response instruction that S206, reception service end core return;
S207, way of submission are for automatically submitting to: amendment process registers state is A_NOTWORK, and NotWorkNum adds 1, and previous status process instance number subtracts 1, and time-out time initializes;
S208, each exception exit way of submission are manually submitted to for application: amendment process registers state is " previous status ", and WorkNum subtracts 1, and previous status process instance number adds 1, and time-out time initializes.
Wherein, data process application is as shown in table 1 at the enrollment status of service end:
Table 1
Grand name | Grand value | Implication | Whether enable |
A_WORK | 2 | Application process works | Enable |
A_READY | 3 | Application process is idle | Enable |
A_NOTWORK | 4 | Application process does not work | Enable |
Wherein, service end application process registration table is as shown in table 2:
Table 2
Type | Field name | Field meanings |
int | Id | COS |
int | MaxNum | Maximum process numbers |
int | InitNum | Initial processes number (triggers the maximum instance number of process) |
Signed char | Flag | Program Type |
char | RunPara[PARALEN+1] | Application program operational parameter control |
char | Name[EXEPRGNAMELEN+1] | Executable program title |
int | ReadyNum | It is in the process instance number of Ready state |
int | WorkNum | It is in the process instance number of Work state |
int | NotWorkNum | It is in the process instance number of NotWork state |
As it is shown on figure 3, the idiographic flow that application interface receives message is as follows:
S301, message authentication interface are started working;
S302, each exception exit: amendment process registers state is that A_NOTWORK, NotWorkNum add 1, and previous status process instance number subtracts 1, and time-out time initializes;
S303, to service end core send instruction;
The response instruction that S304, reception service end core return;
S305, amendment process registers state are that A_NOTWORK, NotWorkNum add 1, and previous status process instance number subtracts 1, and time-out time initializes.
As shown in Figure 4, the idiographic flow of service end monitoring process is as follows:
The registration example monitoring of S401, message-oriented middleware core monitoring process, periodically starts to perform;
S402, scanning application example registration table, one by one instance processes;
S403, judge scanning whether terminate, if the end of scan, then return perform step S401;If scanning does not terminate, then perform step S404;
S404, judge that whether instant example correspondence program is dead, if dead, then perform step S405;If there is no death, then perform step S406;
S405, amendment application program describe table, and the instance number of corresponding login state subtracts 1, returns and performs step S402;
Time-out time in S406, registration table deducts a core cycle;
S407, judge whether that time-out and login state are A_WORK or A_NOTWORK, if so, then kill the application program that instant example is corresponding, return and perform step S402;Step S402 is performed if it is not, then return.
As it is shown in figure 5, the idiographic flow of service end queue monitoring process is as follows:
S501, message-oriented middleware queue monitoring process trigger are monitored, and periodically start to perform;
S502, scan all local queues of this unit, queue processing one by one;
S503, judge scanning whether terminate, if the end of scan, then return perform step S501;If scanning does not terminate, then perform step S504;
S504, judge whether current local queue trigger mode is D, if D, then perform step S505;If not D, then return and perform step S502;
Whether the trigger ID that S505, current local queue are specified exists, if existing, then performs step S506;If being absent from, then return and perform step S502;
S506, locking statistics effective status example sum;
S507, judge process instance sum whether not enough initial number, if so, then perform step S508;If it is not, then perform step S509;
S508, startup application example, startup number is difference, or starts to initial number InitNum;
S509, judge whether process instance sum exceedes the upper limit, if so, then perform S510;If it is not, then perform step 511;
S510, application example state are Ready, and time-out time is-1, then amendment time-out time is 0, and process number is difference, or until instance number reaches InitNum, return and perform step S502;
S511, judge that process instance sum is whether equal to the upper limit, if so, then return and perform step S502;If process instance sum is less than the upper limit, then perform step S512;
Application program number appnum required for S512, the message calculated in current queue;
Wherein, appnum=MsgNum/TrigAmount, MsgNum is the maximum number of messages allowing in current queue to deposit, and TrigAmount is the number that single application program can trigger message,
S513, compare the size of appnum and process instance sum, if appnum is more than process instance sum, then perform step S514;If appnum is less than process instance sum, then returns and perform step S510;
S514, startup application example, starting number is the two difference, or starts to maximum number MaxNum, returns execution step S502.
As shown in Figure 6, the idiographic flow of service end consumer registration is as follows:
S601, core registered customers start;
S602, consumer register complete;
S603, amendment process registers state are that A_READY, ReadyNum add 1, WorkNum or NotWorkNum subtracts 1, and time-out time initializes.
As it is shown in fig. 7, the idiographic flow that service end consumer is nullified is as follows:
S701, core are nullified consumer and are started;
S702, consumer nullify complete;
S703, amendment process registers state are that A_WORK, WorkNum add 1, and ReadyNum subtracts 1, and time-out time initializes.
In the above-described embodiments, the configuration of message-oriented middleware system is as shown in table 3:
Table 3
Configure little section name | [Program] [program unit trifle] |
Configuration record name | [ProgramRecord] [program unit record] |
Configuration field name | PrgRunPara[program operational parameter control] |
Data type | Character string |
New field | The maximum process instance number of MaxNum[] |
Data type | Integer |
Span | Positive integer |
The configuration of message-oriented middleware queue control unit is as shown in table 4:
Table 4
The embodiment of the present invention also provides for a kind of self adaptation message queue and overstocks the applications trigger system of load, and described system includes service end and locally applied process, wherein,
Described service end, for obtaining the overstocked message count in message queue, judge that whether the overstocked message count in described message queue is more than or equal to preset value, when the overstocked message count in described message queue is more than or equal to preset value, starts new locally applied process according to described overstocked message count and process overstocked message.
Specifically, described service end, it is additionally operable to can trigger according to described overstocked message count and single locally applied process the number of message, obtains the number of required locally applied process, start the locally applied process process suitable with described number and overstock message.
Further, described service end, it is additionally operable to the locally applied state of a process that monitor in real time has been turned on, when the described locally applied state of a process having been turned on is changed to non-duty by duty, record is in non-duty duration;When be in non-duty duration exceed Preset Time time, close the locally applied process of non-duty of being in.
Further, described service end, it is additionally operable to after starting new locally applied process according to described overstocked message count and processing overstocked message, the login state of the locally applied process started is revised as duty by idle condition, is respectively modified the number of the locally applied process being in idle condition and duty.
Further, described service end, it is additionally operable to after the described locally applied state of a process having been turned on is changed to non-duty by duty, the login state being changed to the locally applied process having been turned on of non-duty is changed to non-duty by duty, is respectively modified the number of the locally applied process of in running order and non-duty.
Further, described service end, it is additionally operable to after being in the locally applied process of non-duty described in closing, the login state of the locally applied process being in non-duty closed is revised as idle condition by non-duty, is respectively modified the number of the locally applied process being in non-duty and idle condition.
Self adaptation message queue provided by the invention overstocks the applications trigger system of load, message-oriented middleware can be realized and overstock situation automatically according to the message in message queue, Parallel Scheduling plays the data handling utility service routine that quantity is suitable, concurrent by data handling utility service routine, improve whole system making full use of hardware resource, thus improving data-handling efficiency, farthest reduce the ratio of shared duration in whole message lifecycle consuming time of data process method, promote the overall performance of system;And then make not introducing external system, do not increase extra hardware and software cost, under the premise of O&M cost, efficiently utilize hardware system resource to greatest extent, under limited facility environment, realize message-oriented middleware and automatically adapt to traffic pressure, traffic handing capacity resilient expansion and performance undamaged, better adapt to the Internet for message-oriented middleware and cloud computing provides strong technical guarantee.
Embodiment of the present invention self adaptation message queue overstocks the applications trigger method and system of load, the overstocked situation data are transmitted in series products (such as message-oriented middleware product that is commercial or that increase income) according to message queue that goes for triggers and starts application program automatically, but is not limited only to this.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, can be by the hardware that computer program carrys out instruction relevant to complete, described program can be stored in a computer read/write memory medium, this program is upon execution, it may include such as the flow process of the embodiment of above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-OnlyMemory, ROM) or random store-memory body (RandomAccessMemory, RAM) etc..
The above; being only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any those familiar with the art is in the technical scope that the invention discloses; the change that can readily occur in or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with scope of the claims.
Claims (12)
1. the applications trigger method of the overstocked load of self adaptation message queue, it is characterised in that including:
Service end obtains the overstocked message count in message queue;
Service end judges that whether the overstocked message count in described message queue is more than or equal to preset value;
If the overstocked message count in described message queue is more than or equal to preset value, then service end starts the new overstocked message of locally applied process process according to described overstocked message count.
2. method according to claim 1, it is characterized in that, the described locally applied process new according to the startup of described overstocked message count processes overstocked message and includes: can trigger the number of message according to described overstocked message count and single locally applied process, obtain the number of required locally applied process;Start the locally applied process suitable with described number and process overstocked message.
3. method according to claim 1, it is characterised in that described method also includes:
The locally applied state of a process that service end monitor in real time has been turned on;
When the described locally applied state of a process having been turned on is changed to non-duty by duty, service end record is in non-duty duration;
When be in non-duty duration exceed Preset Time time, service end closes the locally applied process of non-duty of being in.
4. method according to claim 1 and 2, it is characterised in that after described service end starts the new overstocked message of locally applied process process according to described overstocked message count, described method also includes:
The login state of the locally applied process started is revised as duty by idle condition;
It is respectively modified the number of the locally applied process being in idle condition and duty.
5. method according to claim 3, it is characterised in that after the described locally applied state of a process having been turned on is changed to non-duty by duty, also include:
The login state being changed to the locally applied process having been turned on of non-duty is changed to non-duty by duty;
It is respectively modified the number of the locally applied process of in running order and non-duty.
6. method according to claim 3, it is characterised in that after being in the locally applied process of non-duty described in described service end is closed, also include:
The login state of the locally applied process being in non-duty closed is revised as idle condition by non-duty;
It is respectively modified the number of the locally applied process being in non-duty and idle condition.
7. the applications trigger system of the overstocked load of self adaptation message queue, it is characterised in that include service end and locally applied process, wherein,
Described service end, for obtaining the overstocked message count in message queue, judge that whether the overstocked message count in described message queue is more than or equal to preset value, when the overstocked message count in described message queue is more than or equal to preset value, starts new locally applied process according to described overstocked message count and process overstocked message.
8. system according to claim 7, it is characterized in that, described service end, it is additionally operable to can trigger the number of message according to described overstocked message count and single locally applied process, obtain the number of required locally applied process, start the locally applied process process suitable with described number and overstock message.
9. system according to claim 7, it is characterized in that, described service end, it is additionally operable to the locally applied state of a process that monitor in real time has been turned on, when the described locally applied state of a process having been turned on is changed to non-duty by duty, record is in non-duty duration;When be in non-duty duration exceed Preset Time time, close the locally applied process of non-duty of being in.
10. the system according to claim 7 or 8, it is characterized in that, described service end, it is additionally operable to after starting new locally applied process according to described overstocked message count and processing overstocked message, the login state of the locally applied process started is revised as duty by idle condition, is respectively modified the number of the locally applied process being in idle condition and duty.
11. system according to claim 9, it is characterized in that, described service end, it is additionally operable to after the described locally applied state of a process having been turned on is changed to non-duty by duty, the login state being changed to the locally applied process having been turned on of non-duty is changed to non-duty by duty, is respectively modified the number of the locally applied process of in running order and non-duty.
12. system according to claim 9, it is characterized in that, described service end, it is additionally operable to after being in the locally applied process of non-duty described in closing, the login state of the locally applied process being in non-duty closed is revised as idle condition by non-duty, is respectively modified the number of the locally applied process being in non-duty and idle condition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410826747.2A CN105786909A (en) | 2014-12-25 | 2014-12-25 | Message queue backlog load self-adaptive application triggering method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410826747.2A CN105786909A (en) | 2014-12-25 | 2014-12-25 | Message queue backlog load self-adaptive application triggering method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105786909A true CN105786909A (en) | 2016-07-20 |
Family
ID=56388577
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410826747.2A Pending CN105786909A (en) | 2014-12-25 | 2014-12-25 | Message queue backlog load self-adaptive application triggering method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105786909A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107483288A (en) * | 2017-08-18 | 2017-12-15 | 郑州云海信息技术有限公司 | A kind of monitoring service intelligent dispatching method and device |
CN108664337A (en) * | 2018-03-23 | 2018-10-16 | 北京奇艺世纪科技有限公司 | A kind of the message decompression method and device of distributed system |
CN109063025A (en) * | 2018-07-13 | 2018-12-21 | 江苏满运软件科技有限公司 | A kind of log processing method and system and a kind of intelligent terminal |
CN110351203A (en) * | 2019-07-12 | 2019-10-18 | 苏州亿歌网络科技有限公司 | A kind of message treatment method, device, system, server and storage medium |
WO2019205371A1 (en) * | 2018-04-24 | 2019-10-31 | 平安科技(深圳)有限公司 | Server, message allocation method, and storage medium |
CN110489225A (en) * | 2018-05-15 | 2019-11-22 | 中国移动通信集团浙江有限公司 | A kind of service expansion method, device and equipment based on message queue |
CN110502402A (en) * | 2019-08-28 | 2019-11-26 | 中国联合网络通信集团有限公司 | Message treatment method, equipment and terminal device |
CN112463314A (en) * | 2020-11-06 | 2021-03-09 | 贝壳技术有限公司 | Asynchronous queue processing method and device, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101403980A (en) * | 2008-11-12 | 2009-04-08 | 西安交通大学 | Multithreading processing method for electronic product code |
CN102117309A (en) * | 2010-01-06 | 2011-07-06 | 卓望数码技术(深圳)有限公司 | Data caching system and data query method |
CN103297395A (en) * | 2012-02-24 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Achievement method, system and device of internet business |
CN103605571A (en) * | 2013-11-20 | 2014-02-26 | 国家电网公司 | Control method of database connection pool |
CN103793266A (en) * | 2012-10-30 | 2014-05-14 | 腾讯科技(深圳)有限公司 | Plug-in management device |
-
2014
- 2014-12-25 CN CN201410826747.2A patent/CN105786909A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101403980A (en) * | 2008-11-12 | 2009-04-08 | 西安交通大学 | Multithreading processing method for electronic product code |
CN102117309A (en) * | 2010-01-06 | 2011-07-06 | 卓望数码技术(深圳)有限公司 | Data caching system and data query method |
CN103297395A (en) * | 2012-02-24 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Achievement method, system and device of internet business |
CN103793266A (en) * | 2012-10-30 | 2014-05-14 | 腾讯科技(深圳)有限公司 | Plug-in management device |
CN103605571A (en) * | 2013-11-20 | 2014-02-26 | 国家电网公司 | Control method of database connection pool |
Non-Patent Citations (1)
Title |
---|
马登邑: ""基于Hadoop存储的文件管理系统的研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107483288A (en) * | 2017-08-18 | 2017-12-15 | 郑州云海信息技术有限公司 | A kind of monitoring service intelligent dispatching method and device |
CN108664337A (en) * | 2018-03-23 | 2018-10-16 | 北京奇艺世纪科技有限公司 | A kind of the message decompression method and device of distributed system |
WO2019205371A1 (en) * | 2018-04-24 | 2019-10-31 | 平安科技(深圳)有限公司 | Server, message allocation method, and storage medium |
CN110489225A (en) * | 2018-05-15 | 2019-11-22 | 中国移动通信集团浙江有限公司 | A kind of service expansion method, device and equipment based on message queue |
CN109063025A (en) * | 2018-07-13 | 2018-12-21 | 江苏满运软件科技有限公司 | A kind of log processing method and system and a kind of intelligent terminal |
CN110351203A (en) * | 2019-07-12 | 2019-10-18 | 苏州亿歌网络科技有限公司 | A kind of message treatment method, device, system, server and storage medium |
CN110351203B (en) * | 2019-07-12 | 2020-05-12 | 苏州亿歌网络科技有限公司 | Message processing method, device, system, server and storage medium |
CN110502402A (en) * | 2019-08-28 | 2019-11-26 | 中国联合网络通信集团有限公司 | Message treatment method, equipment and terminal device |
CN110502402B (en) * | 2019-08-28 | 2023-03-21 | 中国联合网络通信集团有限公司 | Message processing method and device and terminal device |
CN112463314A (en) * | 2020-11-06 | 2021-03-09 | 贝壳技术有限公司 | Asynchronous queue processing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105786909A (en) | Message queue backlog load self-adaptive application triggering method and system | |
CN109639521B (en) | Block chain performance testing method, device, equipment and storage medium | |
US10585889B2 (en) | Optimizing skewed joins in big data | |
CN109885410A (en) | Message method, device, computer equipment and storage medium | |
US8516492B2 (en) | Soft partitions and load balancing | |
CN105376100B (en) | A kind of distributed warning rule evaluation method suitable for cloud platform monitoring resource | |
CN102916953A (en) | Method and device for realizing concurrent service on basis of TCP (transmission control protocol) connection | |
EP3201717B1 (en) | Monitoring of shared server set power supply units | |
CN104199739B (en) | A kind of speculating type Hadoop dispatching methods based on load balancing | |
CN110383764A (en) | The system and method for usage history data processing event in serverless backup system | |
CN103310460A (en) | Image characteristic extraction method and system | |
CN105491150A (en) | Load balance processing method based on time sequence and system | |
US20110131288A1 (en) | Load-Balancing In Replication Engine of Directory Server | |
CN105681426B (en) | Heterogeneous system | |
CN104144202A (en) | Hadoop distributed file system access method, system and device | |
US20230017632A1 (en) | Reducing the environmental impact of distributed computing | |
CN113867957A (en) | Method and device for realizing elastic expansion of number of cross-cluster containers | |
CN105868030A (en) | Log data communication processing apparatus and method as well as mobile terminal | |
Yang et al. | An energy-efficient storage strategy for cloud datacenters based on variable K-coverage of a hypergraph | |
CN102970349B (en) | A kind of memory load equalization methods of DHT network | |
Thamsen et al. | Mary, Hugo, and Hugo*: Learning to schedule distributed data‐parallel processing jobs on shared clusters | |
CN114461384A (en) | Task execution method and device, computer equipment and storage medium | |
Liu et al. | KubFBS: A fine‐grained and balance‐aware scheduling system for deep learning tasks based on kubernetes | |
CN116302580A (en) | Method and device for scheduling calculation force resources of nano relay | |
CN204425400U (en) | Application server system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160720 |
|
RJ01 | Rejection of invention patent application after publication |