CN106257456A - The method of data base's stability, Apparatus and system is improved under high concurrent request - Google Patents
The method of data base's stability, Apparatus and system is improved under high concurrent request Download PDFInfo
- Publication number
- CN106257456A CN106257456A CN201610537733.8A CN201610537733A CN106257456A CN 106257456 A CN106257456 A CN 106257456A CN 201610537733 A CN201610537733 A CN 201610537733A CN 106257456 A CN106257456 A CN 106257456A
- Authority
- CN
- China
- Prior art keywords
- request
- data
- team
- current limliting
- data base
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/217—Database tuning
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides the raising method of data base's stability, Apparatus and system under a kind of high concurrent request, it is possible to when processing high concurrent request, pass through blocking request, it is ensured that data base's stable operation；And binding cache technology, alleviates the pressure accessing data base.The method includes: step one: intercept all requests, then judges whether request to be carried out Current limited Control according to request strategy, if without current limliting, the most directly carries out step 4, if desired current limliting, then proceeds step 2；Step 2: request is added in current limliting queue；Step 3: according to going out the request that team's rule selects to allow out team to perform；Step 4: perform request, wherein, it is judged that whether caching existing the data of described request needs, if existing, then returning the data read from caching, if not existing, then return the data read from data base and described data are cached.
Description
Technical field
The present invention relates to computer technology and software field, particularly relate under a kind of high concurrent request, improve data base stable
The method of property, Apparatus and system.
Background technology
Along with the high speed development of internet industry, high concurrent request becomes the technical bottleneck of legacy system.In order to solve this
One problem, uses caching to store data, promotes response speed, improve Consumer's Experience, reduce database access in prior art
Pressure.But in actual application, once caching system goes wrong, such as caching server may be delayed machine, will faced by
All request of data directly access the database server, cause database server pressure excessive.
Therefore, prior art often uses following measures to avoid caching server may delay machine:
1, the data persistence strategy of caching server self recovers.After having the server machine of delaying to restart, by number
According to the configuration strategy of persistence, data are recovered；
2, synchronization caching server data.When the server machine of delaying is restarted, read from data base by program and need to add
Data in caching, are synchronized in caching server；
3, application program controlling.First judge whether caching exists the data of request needs, if it does not exist, then call number
According to storehouse, read data by data base, by data syn-chronization to caching.
But, above-mentioned avoid the delay measure of machine of caching server to be not sufficient to reach reduce data base during high concurrent request and visit
Ask the purpose of pressure:
1, the configuration strategy of caching server data persistence, it is common that by daily record or the data of book server record
Storage file recovers.But the data recovered can only be the data snapshot in that moment of machine of delaying at server, if
During the machine of delaying, there is new data cached generation, then cannot be synchronized in caching；
2, synchronizing to there may be certain time-delay, data realtime uniform cannot ensure；
3, in caching during no data, the pressure of request data all concentrates on data base's aspect, easily causes data base
Server is delayed machine；
4, in the case of height concurrent write operation concurrency is big, increasing the mode of caching also cannot the pressure in sharing data storehouse
Power, the write operation that moment increases can cause database server to be delayed machine.
Summary of the invention
In view of this, the present invention provides the raising method of data base's stability, Apparatus and system under a kind of high concurrent request,
Blocking request can be passed through, it is ensured that data base's stable operation when processing high concurrent request；And binding cache technology, alleviates
Access the pressure of data base.
For achieving the above object, according to an aspect of the invention, it is provided improve data base under a kind of high concurrent request
The method of stability.
The method improving data base's stability under a kind of high concurrent request of the present invention includes: step one: to all requests
Intercept, then judge whether request to be carried out Current limited Control according to request strategy, if without current limliting, the most directly walk
Rapid four, if desired current limliting, then proceed step 2；Step 2: request is added in current limliting queue；Step 3: according to going out team
Rule selects the request allowing out team to perform；Step 4: perform request, wherein, it is judged that whether there is described request in caching needs
The data wanted, if exist, then return from caching read data, if not existing, then return from data base read data and
Described data are cached.
Alternatively, described request strategy is: in judging the unit interval, whether request amount is more than request amount threshold value, if being more than,
Then carry out Current limited Control.
Alternatively, going out team's rule described in is: judges that certain asks whether be positioned in current limliting queue to go out head of the queue position, and judges
Whether database connection pool exists the connection of free time, if two conditions meet simultaneously, then allows this to ask out team to perform, if two
Meet during individual condition difference, then continue to block this request.
Alternatively, described method also includes: if certain request exceedes duration threshold value blocking time in current limliting queue, then delete
This request.
For achieving the above object, according to a further aspect in the invention, it is provided that under a kind of high concurrent request, improve data base
The device of stability.
The device improving data base's stability under a kind of high concurrent request of the present invention includes: blocking module, for institute
There is request to intercept, then judge whether request to be carried out Current limited Control, if without current limliting, the most directly according to request strategy
Request is performed by performing module, if desired current limliting, then continue to be operated by module of joining the team；Join the team module, for request is added
Enter in current limliting queue；Select module, for according to going out the request that team's rule selects to allow out team to perform；Perform module, be used for holding
Row request, wherein, it is judged that whether caching existing the data of described request needs, if existing, then returning the number read from caching
According to, if not existing, then return the data read from data base and described data are cached.
Alternatively, described request strategy is: in judging the unit interval, whether request amount is more than request amount threshold value, if being more than,
Then carry out Current limited Control.
Alternatively, going out team's rule described in is: judges that certain asks whether be positioned in current limliting queue to go out head of the queue position, and judges
Whether database connection pool exists the connection of free time, if two conditions meet simultaneously, then allows this to ask out team to perform, if two
Meet during individual condition difference, then continue to block this request.
Alternatively, described selection module is additionally operable to: if certain request exceedes duration threshold value, then blocking time in current limliting queue
Delete this request.
For achieving the above object, in accordance with a further aspect of the present invention, it is provided that under a kind of high concurrent request, improve data base
The system of stability.
The system improving data base's stability under a kind of high concurrent request of the present invention includes: memorizer and processor, its
In, described memory store instruction；Described processor is configured to according to described instruction execution the following step: step one: to institute
There is request to intercept, then judge whether request to be carried out Current limited Control, if without current limliting, the most directly according to request strategy
Carry out step 4, if desired current limliting, then proceed step 2；Step 2: request is added in current limliting queue；Step 3: root
According to going out the request that team's rule selects to allow out team to perform；Step 4: perform request, wherein, it is judged that whether caching exists described
The data that request needs, if existing, then return the data read from caching, if not existing, then return the number read from data base
According to and described data are cached.
Alternatively, described request strategy is: in judging the unit interval, whether request amount is more than request amount threshold value, if being more than,
Then carry out Current limited Control.
According to technical scheme, by when processing high concurrent request, interception request, and connect according to data base
Whether condition adjudgement performs request, thereby may be ensured that data base's stable operation, and by binding cache technology, reaches to alleviate
The purpose accessing pressure of data base；By before request is added current limliting queue, judging whether according to request strategy need to be right
Request carries out Current limited Control, such that it is able to judge whether flexibly request is carried out current-limiting operation, if unrestricted necessity, performing please
Ask and request need not be added and current limliting queue is waited in line, such that it is able to the situation flexible approach according to database access please
Ask；By judging whether request exceedes threshold value blocking time, can judge whether in time to abandon request, return request execution in time
Situation, such that it is able to the access improving user is experienced.
Accompanying drawing explanation
Accompanying drawing is used for being more fully understood that the present invention, does not constitute inappropriate limitation of the present invention.Wherein:
Fig. 1 is the key step of the method improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram；
Fig. 2 is the main flow of the method improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram；
Fig. 3 is the main modular of the device improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram；
Fig. 4 is the major part of the system improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram.
Detailed description of the invention
Below in conjunction with accompanying drawing, the one exemplary embodiment of the present invention is explained, various including the embodiment of the present invention
Details is to help understanding, it should they are thought the most exemplary.Therefore, those of ordinary skill in the art it should be noted that
Arrive, the embodiments described herein can be made various changes and modifications, without departing from scope and spirit of the present invention.With
Sample, for clarity and conciseness, eliminates the description to known function and structure in description below.
Along with a large amount of requests access being continuously increased of the demand of application system, can not reach simply by caching server
The intended purpose alleviating database access pressure, utilizes queue mechanism in the embodiment of the present invention, by the way of blocking current limliting,
Realize a kind of dynamic database access to limit, it is ensured that data base's stable operation.
Fig. 1 is the key step of the method improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram.
As it is shown in figure 1, under the high concurrent request of the embodiment of the present invention improve data base's stability method mainly include as
Lower step:
Step one: intercept all requests, then judges whether request to be carried out current limliting control according to request strategy
System, if without current limliting, the most directly carries out step 4, if desired current limliting, then proceeds step 2.The purpose of this step is,
A large amount of concurrent requests are intercepted, then whether request is carried out current-limiting operation according to the access condition adjudgement of data base.
In the embodiment of the present invention, first all requests are intercepted, judge whether that needs limit according to request strategy
Flow control.Wherein request strategy is the visit capacity that can carry according to data base and resource utilization is determined, by manually joining
Put the unit interval request amount threshold value in (such as but not limited to per second), then judge whether the request amount in the unit interval is more than
Request amount threshold value, if being more than, then carries out current-limiting operation, if being not more than, the most not giving current limliting, directly performing request.
After the judgement of this step, if desired carry out current-limiting operation, then start to process from step 2.
Step 2: request is added in current limliting queue.If needing to carry out flow-control, then give request distribution identity (i.e.
Distribution unique identity), request is added in current limliting queue.
Specifically, in the embodiment of the present invention, request distribution unique identity to be equivalent to map the key in (Map)
(Key) distributing unique identity after, adding enqueue is in order to rotary access caching server when, it is possible to know certain
Request position in queue, it is judged that whether it can go out team.
Additionally, the embodiment of the present invention can use Redis as distributed queue, naturally it is also possible to but be not limited to utilize
This kind of independent caching server of Memcached replaces Redis, mainly utilizes they queues and high speed access by principle
Function.But such as ActiveMQ, Kafka etc., it is primarily to transmission message, although internal have a queue to message, but also
The function of access queue is not provided.Therefore, in embodiments of the present invention and inapplicable.
Step 3: according to going out the request that team's rule selects to allow out team to perform.The request intercepted is added FIFO team
After row, judge whether to perform request according to going out team's order.
Specifically, it is judged that certain request be whether queue goes out head of the queue position and judge current database connection pool is
The no connection that there is the free time, when meeting above-mentioned two condition, then allows to ask out team, performs request；Judge if asynchronously meeting
Condition, then continue to block this request.If certain request exceedes default duration threshold value blocking time in current limliting queue, then deleting should
Request.
Step 4: perform request, wherein, it is judged that whether caching existing the data of described request needs, if existing, then returning
Return the data read from caching, if not existing, then return the data read from data base and described data are cached.
Fig. 2 is the main flow of the method improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram.The idiographic flow of the method see Fig. 2.
Specifically, the main flow bag of the method for data base's stability is improved under the high concurrent request of the embodiment of the present invention
Include:
1, ask in a large number to access, all requests are intercepted；
2, read requests strategy, obtains request amount threshold value；
3, judge according to the size of request amount in the current one time with request amount threshold value, if need to carry out current limliting
Operation.If it is required, then give request distribution unique identity, and it is pending to be added into current limliting queue etc.；Otherwise performing please
Ask；
4, in current limliting queue, judge whether it is positioned in queue according to the unique identity of current request and go out head of the queue
Position, and whether have availability database to connect；If two conditions meet simultaneously, delete asking in queue according to unique identity
Ask, it is allowed to ask out team to perform；Otherwise judge that the obstruction duration of current request is the most overtime, if it is, abandon this request,
And delete the request in queue according to identity, if it is not, then proceed the judgement of 4；
5, request is performed: judge the most whether the content of request exists, if there is the most directly returning result, if
There is not the then execution current request operation to data base, if read operation writes the result into caching.
The method of data base's stability is improved it can be seen that pass through at place under high concurrent request according to embodiments of the present invention
When managing high concurrent request, interception request, and judge whether to perform request according to data base's connection status, thereby may be ensured that data
Storehouse stable operation, and by binding cache technology, reach to alleviate the purpose accessing pressure of data base；By request is being added
Before entering current limliting queue, judge whether request to be carried out Current limited Control, such that it is able to judge whether flexibly according to request strategy
Request is carried out current-limiting operation, if unrestricted necessity, performs request and request need not be added and current limliting queue is waited in line,
Such that it is able to ask according to the situation flexible approach of database access；By judging whether request exceedes threshold value blocking time, can
To judge whether in time to abandon request, return request implementation status in time, such that it is able to the access improving user is experienced.
Fig. 3 is the main modular of the device improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram.
As it is shown on figure 3, the device 30 improving data base's stability under the high concurrent request of the embodiment of the present invention mainly includes
Such as lower module: blocking module 301, module of joining the team 302, selection module 303 and execution module 304, wherein,
Blocking module 301 for all requests are intercepted, then according to request strategy judge whether need to ask into
Row Current limited Control, if without current limliting, is then directly performed request by execution module 304, and if desired current limliting then continues by module of joining the team
302 operate；Module of joining the team 302 is for adding request in current limliting queue；Select module 303 for according to going out team's rule choosing
Select the request allowing out team to perform；Perform module 304 to be used for performing request, wherein, it is judged that whether caching exists described request
The data needed, if existing, then return the data read from caching, if not existing, then return from the data of data base's reading also
And described data are cached.
Wherein, in request strategy may is that and judges the unit interval, whether (such as but not limited to per second) request amount is more than asking
The amount of asking threshold value, if being more than, then carries out Current limited Control.
Go out team's rule to may is that and judge that what whether certain request be positioned in current limliting queue goes out head of the queue position, and judge data base
Whether connection pool exists the connection of free time, if two conditions meet simultaneously, then allows this to ask out team to perform, if two conditions
Asynchronously meet, then continue to block this request.
It addition, select module 303 can be additionally used in: if certain request exceedes duration threshold value, then blocking time in current limliting queue
Delete this request.
Fig. 4 is the major part of the system improving data base's stability under high concurrent request according to embodiments of the present invention
Schematic diagram.
As shown in Figure 4, the system 40 improving data base's stability under the high concurrent request of the embodiment of the present invention mainly includes
Such as lower part: memorizer 401 and processor 402, wherein,
Memorizer 401 storage instruction；
Processor 402 is configured to according to described instruction execution the following step:
Step one: intercept all requests, then judges whether request to be carried out current limliting control according to request strategy
System, if without current limliting, the most directly carries out step 4, if desired current limliting, then proceeds step 2；
Step 2: request is added in current limliting queue；
Step 3: according to going out the request that team's rule selects to allow out team to perform；
Step 4: perform request, wherein, it is judged that whether caching existing the data of described request needs, if existing, then returning
Return the data read from caching, if not existing, then return the data read from data base and described data are cached.
Wherein, request strategy may is that in judging the unit interval, whether request amount is more than request amount threshold value, if being more than, then
Carry out Current limited Control.
From the above, it can be seen that pass through when processing high concurrent request, interception request, and connect shape according to data base
State judges whether to perform request, thereby may be ensured that data base's stable operation, and by binding cache technology, reaches to alleviate number
The purpose accessing pressure according to storehouse；By before request is added current limliting queue, judging whether according to request strategy need to be to asking
Ask and carry out Current limited Control, such that it is able to judge whether flexibly request is carried out current-limiting operation, if unrestricted necessity, perform request
And request need not be added and current limliting queue is waited in line, such that it is able to ask according to the situation flexible approach of database access；
By judging whether request exceedes threshold value blocking time, can judge whether in time to abandon request, return request execution feelings in time
Condition, such that it is able to the access improving user is experienced.
Above-mentioned detailed description of the invention, is not intended that limiting the scope of the invention.Those skilled in the art should be bright
White, depend on that design requires and other factors, various amendment, combination, sub-portfolio and replacement can occur.Any
Amendment, equivalent and the improvement etc. made within the spirit and principles in the present invention, should be included in scope
Within.
Claims (10)
1. the method improving data base's stability under a high concurrent request, it is characterised in that including:
Step one: intercept all requests, then judges whether request to be carried out Current limited Control according to request strategy, if
Without current limliting, the most directly carry out step 4, if desired current limliting, then proceed step 2；
Step 2: request is added in current limliting queue；
Step 3: according to going out the request that team's rule selects to allow out team to perform；
Step 4: perform request, wherein, it is judged that whether caching exists described request needs data, if existence, then return from
The data that caching reads, if not existing, then return the data read from data base and cache described data.
Method the most according to claim 1, it is characterised in that described request strategy is: judge request amount in the unit interval
Whether more than request amount threshold value, if being more than, then carry out Current limited Control.
Method the most according to claim 1, it is characterised in that described in go out team's rule and be: judge whether certain request is positioned at limit
Flow queue goes out head of the queue position, and judges whether database connection pool exists the connection of free time, if two conditions are simultaneously full
Foot, then allow this to ask out team to perform, if meeting during two condition differences, then continues to block this request.
Method the most according to claim 1, it is characterised in that described method also includes: if certain request is in current limliting queue
Exceed duration threshold value blocking time, then delete this request.
5. improve the device of data base's stability under a high concurrent request, it is characterised in that including:
Blocking module, for intercepting all requests, then judges whether request to be carried out current limliting according to request strategy
Control, if without current limliting, then directly performed request by execution module, if desired current limliting, then continue to be operated by module of joining the team；
Join the team module, for by request addition current limliting queue；
Select module, for according to going out the request that team's rule selects to allow out team to perform；
Performing module, be used for performing request, wherein, it is judged that whether caching existing the data of described request needs, if existing, then
Return the data read from caching, if not existing, then return the data read from data base and described data are cached.
Device the most according to claim 5, it is characterised in that described request strategy is: judge request amount in the unit interval
Whether more than request amount threshold value, if being more than, then carry out Current limited Control.
Device the most according to claim 5, it is characterised in that described in go out team's rule and be: judge whether certain request is positioned at limit
Flow queue goes out head of the queue position, and judges whether database connection pool exists the connection of free time, if two conditions are simultaneously full
Foot, then allow this to ask out team to perform, if meeting during two condition differences, then continues to block this request.
Device the most according to claim 5, it is characterised in that described selection module is additionally operable to: if certain request is in current limliting team
In row, blocking time exceedes duration threshold value, then delete this request.
9. improve the system of data base's stability under a high concurrent request, it is characterised in that including:
Memorizer and processor, wherein,
Described memory store instruction；
Described processor is configured to according to described instruction execution the following step:
Step one: intercept all requests, then judges whether request to be carried out Current limited Control according to request strategy, if
Without current limliting, the most directly carry out step 4, if desired current limliting, then proceed step 2；
Step 2: request is added in current limliting queue；
Step 3: according to going out the request that team's rule selects to allow out team to perform；
Step 4: perform request, wherein, it is judged that whether caching exists described request needs data, if existence, then return from
The data that caching reads, if not existing, then return the data read from data base and cache described data.
System the most according to claim 9, it is characterised in that described request strategy is: judge request amount in the unit interval
Whether more than request amount threshold value, if being more than, then carry out Current limited Control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610537733.8A CN106257456A (en) | 2016-07-08 | 2016-07-08 | The method of data base's stability, Apparatus and system is improved under high concurrent request |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610537733.8A CN106257456A (en) | 2016-07-08 | 2016-07-08 | The method of data base's stability, Apparatus and system is improved under high concurrent request |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106257456A true CN106257456A (en) | 2016-12-28 |
Family
ID=57714261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610537733.8A Pending CN106257456A (en) | 2016-07-08 | 2016-07-08 | The method of data base's stability, Apparatus and system is improved under high concurrent request |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106257456A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815354A (en) * | 2017-01-22 | 2017-06-09 | 上海易贷网金融信息服务有限公司 | A kind of database data buffered method |
| CN106875226A (en) * | 2017-02-24 | 2017-06-20 | 湖南安良信息科技有限公司 | One kind panic buying behavior monitoring method and system |
| CN108920283A (en) * | 2018-08-06 | 2018-11-30 | 成都知道创宇信息技术有限公司 | Server guard method based on Prometheus performance monitoring system |
| CN109117432A (en) * | 2017-06-22 | 2019-01-01 | 北京京东尚科信息技术有限公司 | A kind of method and device obtaining data |
| CN110147508A (en) * | 2017-10-26 | 2019-08-20 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of system current limliting |
| CN110275918A (en) * | 2019-06-17 | 2019-09-24 | 浙江百应科技有限公司 | A kind of million rank excel data quick and stable import systems |
| CN110955681A (en) * | 2019-10-14 | 2020-04-03 | 京东数字科技控股有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111651631A (en) * | 2020-04-28 | 2020-09-11 | 长沙证通云计算有限公司 | High-concurrency video data processing method, electronic equipment, storage medium and system |
| CN113852663A (en) * | 2021-08-18 | 2021-12-28 | 北京达佳互联信息技术有限公司 | Network request processing method and device and network request processing system |
| CN115174479A (en) * | 2022-07-19 | 2022-10-11 | 天翼云科技有限公司 | Flow control method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102915374A (en) * | 2012-11-07 | 2013-02-06 | 北京搜狐新媒体信息技术有限公司 | Method, device and system for controlling access to database resources |
| EP2790113A1 (en) * | 2013-04-11 | 2014-10-15 | Hasso-Plattner-Institut für Softwaresystemtechnik GmbH | Aggregate query-caching in databases architectures with a differential buffer and a main store |
| CN104539713A (en) * | 2014-12-31 | 2015-04-22 | 北京奇虎科技有限公司 | Service request processing method and device |
| CN104572974A (en) * | 2014-12-31 | 2015-04-29 | 北京奇虎科技有限公司 | Service request processing method and device |
| CN105023049A (en) * | 2014-04-30 | 2015-11-04 | 中国电信股份有限公司 | On-line seat-picking method and system, and overload protection device |
-
2016
- 2016-07-08 CN CN201610537733.8A patent/CN106257456A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102915374A (en) * | 2012-11-07 | 2013-02-06 | 北京搜狐新媒体信息技术有限公司 | Method, device and system for controlling access to database resources |
| EP2790113A1 (en) * | 2013-04-11 | 2014-10-15 | Hasso-Plattner-Institut für Softwaresystemtechnik GmbH | Aggregate query-caching in databases architectures with a differential buffer and a main store |
| CN105023049A (en) * | 2014-04-30 | 2015-11-04 | 中国电信股份有限公司 | On-line seat-picking method and system, and overload protection device |
| CN104539713A (en) * | 2014-12-31 | 2015-04-22 | 北京奇虎科技有限公司 | Service request processing method and device |
| CN104572974A (en) * | 2014-12-31 | 2015-04-29 | 北京奇虎科技有限公司 | Service request processing method and device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815354A (en) * | 2017-01-22 | 2017-06-09 | 上海易贷网金融信息服务有限公司 | A kind of database data buffered method |
| CN106875226A (en) * | 2017-02-24 | 2017-06-20 | 湖南安良信息科技有限公司 | One kind panic buying behavior monitoring method and system |
| CN109117432A (en) * | 2017-06-22 | 2019-01-01 | 北京京东尚科信息技术有限公司 | A kind of method and device obtaining data |
| CN110147508A (en) * | 2017-10-26 | 2019-08-20 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of system current limliting |
| CN108920283A (en) * | 2018-08-06 | 2018-11-30 | 成都知道创宇信息技术有限公司 | Server guard method based on Prometheus performance monitoring system |
| CN110275918A (en) * | 2019-06-17 | 2019-09-24 | 浙江百应科技有限公司 | A kind of million rank excel data quick and stable import systems |
| CN110955681A (en) * | 2019-10-14 | 2020-04-03 | 京东数字科技控股有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111651631A (en) * | 2020-04-28 | 2020-09-11 | 长沙证通云计算有限公司 | High-concurrency video data processing method, electronic equipment, storage medium and system |
| CN111651631B (en) * | 2020-04-28 | 2023-11-28 | 长沙证通云计算有限公司 | High concurrency video data processing method, electronic equipment, storage medium and system |
| CN113852663A (en) * | 2021-08-18 | 2021-12-28 | 北京达佳互联信息技术有限公司 | Network request processing method and device and network request processing system |
| CN115174479A (en) * | 2022-07-19 | 2022-10-11 | 天翼云科技有限公司 | Flow control method and device |
| CN115174479B (en) * | 2022-07-19 | 2023-10-13 | 天翼云科技有限公司 | Flow control method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106257456A (en) | The method of data base's stability, Apparatus and system is improved under high concurrent request | |
| US9959313B2 (en) | Database management system and method capable of dynamically issuing inputs/outputs and executing operations in parallel | |
| US9858052B2 (en) | Decentralized operating system | |
| US20180307535A1 (en) | Computer system and method for controlling computer | |
| US20090248870A1 (en) | Server system and control method for same | |
| US9678995B2 (en) | System and method for planned migration of service connections | |
| CN104580437A (en) | Cloud storage client and high-efficiency data access method thereof | |
| JPH0954754A (en) | Customer-information control system and method in loosely-coupled parallel processing environment | |
| US9514072B1 (en) | Management of allocation for alias devices | |
| CN107133112B (en) | A kind of method and mobile terminal of asynchronous process fsync | |
| CN102541984A (en) | File system of distributed type file system client side | |
| US20140068165A1 (en) | Splitting a real-time thread between the user and kernel space | |
| CN111753065A (en) | Request response method, system, computer system and readable storage medium | |
| US10298709B1 (en) | Performance of Hadoop distributed file system operations in a non-native operating system | |
| CN112052291A (en) | Method and system for accessing distributed block storage system by user mode | |
| KR20150007698A (en) | Load distribution system for virtual desktop service | |
| JP2013152541A (en) | Processing device, method and program capable of performing distributed context-aware processing | |
| US10313450B2 (en) | Method for transparently connecting augmented network socket operations | |
| US8447951B2 (en) | Method and apparatus for managing TLB | |
| CN108933813B (en) | Method, system and storage medium for preventing reader starvation | |
| CN106598502B (en) | Data storage method and system | |
| US10002077B2 (en) | Persistent memory controller based atomicity assurance | |
| Huai et al. | {XFUSE}: An Infrastructure for Running Filesystem Services in User Space | |
| US8327380B2 (en) | Method and interprocess communication driver for managing requests of a database client to a database server | |
| CN102760155A (en) | Database-based transaction control method and device |
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: 20161228 |
|
| RJ01 | Rejection of invention patent application after publication |