CN105812419A - Data processing system and method - Google Patents

Abstract

The invention provides a data processing system applied to a plurality of servers. At least one server comprises a processing module, a storage module and a redirection module. A processing module in the server contains the information of a client and is used for receiving an operation request output by the client. The operation request comprises the reference time of a standard time zone corresponding to the operation request outputting moment of the client. The storage module comprises the peak time periods of the plurality of corresponding servers that correspond to the standard time zone. The processing module is used for judging whether the peak time period of at least one server contains the reference time or not. When the peak time period of at least one server does not contain the reference time, the redirection module forwards the operation request to the above server that does not contain the reference time within the peak time period thereof. The invention also provides a data processing method. Based on the data processing system and the data processing method, the operation request can be forwarded to the server that does not contain the reference time within the peak time period thereof. Therefore, the electricity consumption amounts of data centers in all regions are balanced.

Description

Data processing system and method

technical field

The invention relates to a data processing system and method.

Background technique

Today's data center operators often have multiple data centers around the world to meet the needs of data processing in various places. However, users in various places (such as users in the United States and users in the United Kingdom) use different time periods, which may make the power consumption of data centers in various places different at the same time. Therefore, how to balance the power consumption of data centers in various places has become an urgent problem in the industry.

Contents of the invention

In view of the above, it is necessary to provide a data processing system and method that can balance the power consumption of data centers in various places.

A data processing system applied to a server containing information of a client, the data processing system comprising:

A processing module, used to receive the operation request output by the client computer, wherein the operation request includes a reference time corresponding to a standard time zone when the client computer outputs the operation request; the processing module is also used to determine whether there is at least The peak time period of a server does not include the reference time; wherein the priority list is stored in a storage module, the priority list includes a number of servers corresponding to the peak time period of the standard time zone; and

A redirection module, when there is at least one server whose peak time period does not include the reference time, the redirection module forwards the operation request information to the server whose peak time period does not include the reference time.

A data processing method applied to a server including a client information, the data processing method comprising:

receiving an operation request output by the client computer, wherein the operation request includes a reference time corresponding to a standard time zone when the client computer outputs the operation request;

judging whether there is at least one peak time period of a server in a priority list that does not include the reference time; wherein, the priority list includes peak time periods corresponding to a plurality of servers corresponding to the standard time zone; and

When there is at least one server whose peak time period does not include the reference time, the operation request information is forwarded to the server whose peak time period does not include the reference time.

The above data processing system and method forward the calculation request output by the client to the server with the highest priority for processing by the server, which is beneficial to balance the power consumption of each data center.

Description of drawings

Fig. 1 is a schematic diagram of a preferred embodiment of the data processing system of the present invention.

FIG. 2 is a block diagram of a preferred embodiment of the server in FIG. 1 .

FIG. 3 is a block diagram of a preferred embodiment of the priority list of FIG. 2. FIG.

FIG. 4 and FIG. 5 are flow charts of preferred embodiments of the data processing method of the present invention.

Description of main component symbols

server 102 The internet 100 Client computer 106 processing module 200 redirect module 202 storage module 204 priority list 205 data center 10

The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings.

detailed description

Below in conjunction with accompanying drawing and preferred embodiment the present invention is described in further detail:

Referring to FIG. 1 , the data processing system of the present invention includes several servers 102 and a client 106 communicating with the servers 102 through a network 100 . In this embodiment, each server 102 is located in the data center 10 in different places. In other embodiments, different data centers 10 may contain several servers 102 .

The client 106 is used to output an operation request. In this embodiment, the operation request includes the IP address information of the client 106 , the time information of outputting the operation request, the time zone information of the client 106 and the geographic location information of the client 106 . In other embodiments, the operation request may also include the IP address information of the client computer 106, the reference time relative to a standard time zone (such as Greenwich MeanTime, Greenwich Mean Time) when outputting the operation request, and the geographic location of the client computer 106. location information.

Please refer to FIG. 2 and FIG. 3 , each server 102 includes a processing module 200 , a redirection module 202 and a storage module 204 . In this embodiment, the storage module 204 stores client information corresponding to several users included in the server 102 , such as IP address information of the client 106 .

The processing module 200 is used for receiving the operation request output by the client 106 included in the server 102 through the network 100 .

The storage module 204 also stores a priority list 205, which includes time zone information, geographic location information, IP address information and peak time periods corresponding to the standard time zone of several servers. In this embodiment, each server 102 may be located in different time zones, and users in different time zones have different usage habits. When the number of users of a server 102 increases, the power consumption of the server 102 may be relatively high (power consumption peak), so that the server 102 generates a corresponding peak time period. For example, the priority list 205 stores a first server, a second server and a third server. Wherein the time zone where the first server is located is GMT (GreenwichMeanTime)+8, the IP address of the first server is a first IP address, and the geographic location of the first server is a first location located in China, the first server The peak time period is GMT0~GMT8 (converted to the time corresponding to the standard time zone); the time zone where the second server is located is GMT-8, the IP address of the second server is a second IP address, and the second server The geographic location is a second location located in the west of the United States, the peak time period of the second server is GMT16~GMT24; the time zone where the third server is located is GMT0, and the IP address of the third server is a third IP address , the geographic location of the third server is a third location located in the United Kingdom, and the peak time period of the third server is GMT8~GMT16. In other implementations, the priority list 205 may include geographic location information including locations of several servers, IP address information, and peak time periods corresponding to the standard time zone.

The redirection module 202 is used for forwarding the operation request to the server with the highest priority in the priority list 205 according to the operation request.

In this embodiment, the processing module 200 is used to obtain the corresponding reference according to the time zone information of the client 106 in the operation request output by the client 106, the time information of the operation request output by the client 106, and the time in the standard time zone. time. In other implementations, the reference time can also be converted and output by the client 106 .

The processing module 200 is also used to determine whether there is at least one peak time period of the server in the priority list 205 that does not include the reference time; Forward the operation request to the server whose peak time period does not include the reference time. In this embodiment, the redirection module 202 forwards the calculation request to the server 102 through the IP address of the server whose peak time period does not include the reference time, so that the server 102 can perform calculation operations. The server 102 is also used to return the operation result to the client 106 , for example, return to the client 106 through the IP address of the client 106 . In this embodiment, the redirection module 202 forwards the operation request to the server not in the peak time period instead of forwarding the operation request to the server in the peak time period, so that the power consumption of the server in the peak time period can be avoided The increase is also conducive to balancing the energy consumption of data centers in various places.

In this embodiment, the processing module 200 is also used to judge whether there are at least two peak time periods of servers that do not include the reference time; when there are at least two server peak time periods that do not include the reference time, the processing module 200 will The first geographic information included in the operation request and the second geographic information corresponding to at least two servers that do not include the peak time period of the reference time are used to obtain the server with the shortest distance between the at least two servers and the client, so , the redirection module 202 forwards the operation request to the server with the shortest distance between the client 106 and the at least two servers. In this embodiment, the redirection module 202 forwards the operation request to the server with the shortest distance from the client 106, which is beneficial for the operation request to be processed as soon as possible.

For example, assuming that the current time is GMT9:30, the client 106 is located in Japan, and the first server is used to receive the computing request output by the client 106, at this time the processing module 200 of the first server determines that the server is not in the rush hour Including the first server and the third server. For the client 106 located in Japan, the distance between the client 106 and the first server is smaller than the distance between the client 106 and the third server, therefore, the redirection module 202 of the first server will The computing request output by the client computer 106 is forwarded to the first server, that is, the first server itself, to be processed by the first server, and the first server is also used to return the processing result to the client computer located in Japan 106.

In other implementations, the processing module 200 is further configured to determine whether there are at least two servers with the same and shortest distances from the client 106 among the at least two servers in the peak time period not including the reference time; When two servers with the same shortest distance, it means that there is a server with the shortest distance between the client computer 106, at this time, the redirection module 202 forwards the operation request to the server with the shortest distance from the client computer 106; when there is at least When there are two servers with the same shortest distance, it means that there are at least two servers with the same shortest distance to the client 106. At this time, the redirection module 202 randomly forwards the operation request to one of the servers with the shortest distance to the client .

Please refer to Fig. 4 and Fig. 5, the preferred embodiment of the data processing method of the present invention comprises steps:

Step S300, the client computer 106 outputs a calculation request, wherein the calculation request includes the IP address information of the client computer 106, the time information of outputting the calculation request, the time zone information of the client computer, and the geographic location information of the client computer.

In step S302, the server 102 including the client 106 receives the operation request output by the client 106.

Step S304, the server 102 obtains the corresponding reference time according to the time information and time zone information in the operation request output by the client 106.

Step S308, the server 102 judges whether there is at least one server whose peak time period does not include the reference time in the priority list 205; when there is at least one server whose peak time period does not include the reference time, perform step S310; When the peak time periods of all servers in the priority list 205 include the reference time, step S309 is executed.

In step S309, the server 102 randomly forwards the operation request information to a server in the priority list 205, and executes step S318.

Step S310, the server 102 judges whether there are at least two server peak time periods that do not include the reference time; when there are at least two server peak time periods that do not include the reference time, perform step S312; when there is a server peak time When the segment does not contain the reference time, execute step S311.

In step S311, the server 102 forwards the operation request output by the client 106 to the server whose peak time period does not include the reference time, and executes step S318.

Step S312, the server 102 judges whether there is a server with the shortest distance to the client in the priority list according to the geographic location information of the client; when there is a server with the shortest distance to the client 106, step S316 is executed; When there are at least two servers with the shortest distances from the client 106, step S314 is executed.

In step S314, the server 102 randomly outputs the computing request output by the client 106 to one of the servers with the shortest distance to the client, and executes step S318.

In step S316, the server 102 forwards the calculation request to the server with the shortest distance to the client 106, and executes step S318.

Step S318, the server performs calculation processing, and returns the calculation result to the client.

The above data processing system and method forward the computing request output by the client 106 to a server that is not in the peak time period, which is conducive to balancing the power consumption of each data center; when there are at least two servers that are not in the peak time period , the operation request is forwarded to the server closest to the client 106, which is conducive to processing data as soon as possible and reducing the return time of processing results.

Claims (10)

1. a data handling system, is applied to a server comprising a client information, and this data handling system includes:

One processing module, for the computing request of subscribing client output, wherein this computing is asked to include this client computer and is exported the reference time of corresponding time zone during this computing request；This processing module is additionally operable to judge that the peak hour section that whether there is at least one server in a priority list does not comprise this reference time；Wherein this priority list is stored in a memory module, and this priority list includes some servers to should the peak hour section of time zone；And

One redirection module, when the peak hour section that there is at least one server does not comprise this reference time, this computing solicited message is forwarded to peak hour section and does not comprise the server of this reference time by this redirection module.

2. data handling system as claimed in claim 1, it is characterised in that: this peak hour section is corresponding to the time period on the power consumption peak of this server；When the peak hour Duan Jun that this processing module judges Servers-all in this priority list comprises this reference time, this redirection module is by this computing request random forwarding a to server.

3. data handling system as claimed in claim 1 or 2, it is characterised in that: this computing request also includes the first geography information of this client computer position；This priority list also stores the second geography information of corresponding server position；This processing module is additionally operable to judge whether that the peak hour Duan Jun of at least two servers does not comprise this reference time；When the peak hour Duan Jun that there are at least two servers does not comprise the reference time, during this processing module is asked according to this computing, second geography information corresponding at least two servers of the first geography information of comprising and the peak hour section that do not comprise this reference time obtains server the shortest with this client computer distance in this at least two server；This computing request is forwarded in this at least two server with this client computer apart from the shortest server by this redirection module.

4. such as data handling system that claim 3 is stated, it is characterised in that: this processing module is additionally operable to judge not comprise whether to there are at least two servers at least two servers of the peak hour section of this reference time identical with the beeline of this client computer；When being absent from the identical server of at least two beelines, this computing request is forwarded to the server the shortest with this client computer distance by this redirection module；When the server that existence at least two beelines are identical, this computing request is forwarded to wherein any one server the shortest with this client computer distance by this redirection module.

5. data handling system as claimed in claim 4, it is characterized in that: each server in this priority list also includes the IP address information of correspondence, this computing request is forwarded to the server of correspondence by this redirection module by this IP address information, to be carried out calculation process by this server, and operation result is transmitted back to this client computer.

6. a data processing method, is applied to a server comprising a client information, and this data processing method includes:

Receiving the computing request of this client computer output, wherein this computing is asked to include this client computer and is exported the reference time of corresponding time zone during this computing request；

Judge that the peak hour section that whether there is at least one server in a priority list does not comprise this reference time；Wherein, this priority list includes corresponding some servers to should the peak hour section of time zone；And

When the peak hour section that there is at least one server does not comprise this reference time, this computing solicited message is forwarded to peak hour section and does not comprise the server of this reference time.

7. data processing method as claimed in claim 6, it is characterised in that: this peak hour section is corresponding to the time period on the power consumption peak of this server；This data processing method also includes:

When in this priority list, the peak hour Duan Jun of Servers-all comprises this reference time, by this computing request random forwarding a to server.

8. data processing method as claimed in claims 6 or 7, it is characterised in that: this computing request also includes the first geography information of this client computer position；This priority list also stores the second geography information of corresponding server position；This data processing method also includes:

Judge whether that the peak hour Duan Jun of at least two servers does not comprise this reference time；

When the peak hour Duan Jun that there are at least two servers does not comprise the reference time, second geography information corresponding at least two servers of the first geography information comprised in asking according to this computing and the peak hour section not comprising this reference time obtains server the shortest with this client computer distance in this at least two server；

This computing request is forwarded in this at least two server with this client computer apart from the shortest server.

9. such as data processing method that claim 8 is stated, it is characterised in that: this data processing method also includes:

Judge not comprise the distance that whether there is at least two servers and this client computer at least two servers of the peak hour section of this reference time the shortest and identical；

When being absent from least two from client computer when short and the most identical server, this computing request is forwarded to the server the shortest with this client computer distance；

When there is the identical server of at least two beelines, this computing request is forwarded to a wherein server the shortest with this client computer distance.

10. data processing method as claimed in claim 9, it is characterised in that: each server in this priority list also includes the IP address information of correspondence, and this data processing method also includes:

By this IP address information, this computing request is forwarded to the server of correspondence, to be carried out calculation process by this server, and operation result is transmitted back to this client computer.