CN108228110A - A kind of method and apparatus for migrating resource data - Google Patents

Abstract

The invention discloses a kind of method and apparatus for migrating resource data, belong to technical field of data storage.The method includes：The hot spot value of all resource datas stored in the first storage medium and the second storage medium is periodically updated one by one, wherein, the read or write speed of second storage medium is higher than first storage medium；After the hot spot value update of any resource data, the Secondary resource data that hot spot value is minimum in highest first resource data of hot spot value in the first storage medium and the second storage medium are determined；If the hot spot value of the first resource data is higher than the hot spot value of the Secondary resource data, by the first resource Data Migration to second storage medium.The present invention can improve the efficiency for obtaining resource data.

Description

A method and device for migrating resource data

technical field

The invention relates to the technical field of data storage, in particular to a method and device for migrating resource data.

Background technique

The cache server under the CDN (Content Delivery Network) architecture is a server used to store highly accessible resource data (such as video, audio, web page data, etc.), which can distribute locally cached resource data to The node server that is closer to the user enables the user to obtain the required resource data nearby.

Cache servers generally use mechanical hard disks with large data capacity and long service life to cache resource data. After the cache server receives the user's request for a certain resource data, it can first search for the resource data in the mechanical hard disk. If it is found, the cache server can feed back the resource data to the user; if not found, the cache server The above resource data can be obtained from the corresponding origin server, and then the obtained resource data can be fed back to the user.

In the process of realizing the present invention, the inventor finds that there are at least the following problems in the prior art:

The reading and writing speed of the mechanical hard disk is slow. After receiving a resource data acquisition request, the cache server often needs to spend a lot of time to read and write the resource data. The user needs to wait for a long time to obtain the resource data. Data is less efficient.

Contents of the invention

In order to solve the problems in the prior art, embodiments of the present invention provide a method and device for migrating resource data. Described technical scheme is as follows:

In a first aspect, a method for migrating resource data is provided, the method comprising:

periodically updating hotspot values of all resource data stored in the first storage medium and the second storage medium one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium;

After the hotspot value of any resource data is updated, determine the first resource data with the highest hotspot value in the first storage medium, and the second resource data with the lowest hotspot value in the second storage medium;

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, migrating the first resource data to the second storage medium.

Further, the periodic updating of hotspot values of all resource data stored in the first storage medium and the second storage medium one by one includes:

Determine the target resource data of the hotspot value to be updated;

predicting the current number of visits to the target resource data in the current statistical period according to the historical visit times of the target resource data in the historical statistical period;

The hotspot value of the target resource data is updated according to the data amount of the target resource data, the latest access time of the target resource data, and the historical visit times and current visit times of the target resource data.

Further, if the hotspot value of the first resource data is higher than the hotspot value of the second resource data, migrating the first resource data to the second storage medium includes:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, then according to the hotspot value from In order from low to high, start migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium in sequence;

When it is detected that the remaining storage amount is greater than or equal to the data amount of the first resource data, stop migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the the first storage medium, and migrate the first resource data to the second storage medium.

Further, if the hotspot value of the first resource data is higher than the hotspot value of the second resource data, migrating the first resource data to the second storage medium includes:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the standard deviation of the previous access times and the current access times of the first resource data is smaller than a preset threshold, then the second resource data A resource data is migrated to the second storage medium.

Further, the method also includes:

After receiving the storage request of the target resource data, if it is detected that the remaining storage capacity of the second storage medium is greater than the preset storage capacity, the target resource data is stored in the second storage medium, otherwise the The target resource data is stored in the first storage medium.

In a second aspect, a device for migrating resource data is provided, the device comprising:

An update module, configured to periodically update hotspot values of all resource data stored in the first storage medium and the second storage medium one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium;

A judging module, configured to determine the first resource data with the highest hotspot value in the first storage medium and the second resource data with the lowest hotspot value in the second storage medium after the hotspot value of any resource data is updated;

A migration module, configured to migrate the first resource data to the second storage medium if the hotspot value of the first resource data is higher than the hotspot value of the second resource data.

Further, the update module is specifically used for:

Determine the target resource data of the hotspot value to be updated;

predicting the current number of visits to the target resource data in the current statistical period according to the historical visit times of the target resource data in the historical statistical period;

The hotspot value of the target resource data is updated according to the data amount of the target resource data, the latest access time of the target resource data, and the historical visit times and current visit times of the target resource data.

Further, the migration module is specifically used for:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, then according to the hotspot value from In order from low to high, start migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium in sequence;

When it is detected that the remaining storage amount is greater than or equal to the data amount of the first resource data, stop migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the the first storage medium, and migrate the first resource data to the second storage medium.

Further, the migration module is specifically used for:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the standard deviation of the previous access times and the current access times of the first resource data is smaller than a preset threshold, then the second resource data A resource data is migrated to the second storage medium.

Further, the device also includes:

A storage module, configured to store the target resource data in the second storage medium if it detects that the remaining storage capacity of the second storage medium is greater than a preset storage capacity after receiving the storage request of the target resource data , otherwise store the target resource data in the first storage medium.

In a third aspect, a cache server is provided, the cache server includes a processor and a memory, at least one instruction, at least one program, code set or instruction set are stored in the memory, the at least one instruction, the at least A program, the code set or instruction set is loaded and executed by the processor to implement the aforementioned method for migrating resource data.

The beneficial effects brought by the technical solution provided by the embodiments of the present invention are:

In the embodiment of the present invention, the hotspot values of all resource data stored in the first storage medium and the second storage medium are periodically updated one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium; After the hotspot value of is updated, determine the first resource data with the highest hotspot value in the first storage medium, and the second resource data with the lowest hotspot value in the second storage medium; if the hotspot value of the first resource data is higher than the second resource data hotspot value, migrate the first resource data to the second storage medium. In this way, the resource data with high access frequency can always be stored in the second storage medium with fast read and write speed, and then, when the user accesses these resource data, the cache server can quickly read and write them, and the user does not need to wait for a long time The resource data can be obtained, therefore, the efficiency of obtaining resource data can be improved as a whole.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

FIG. 1 is a schematic diagram of a scenario of migrating resource data provided by an embodiment of the present invention;

Fig. 2 is a flow chart of a method for migrating resource data provided by an embodiment of the present invention;

Fig. 3 is a schematic structural diagram of a device for migrating resource data provided by an embodiment of the present invention;

Fig. 4 is a schematic structural diagram of a device for migrating resource data provided by an embodiment of the present invention;

Fig. 5 is a schematic structural diagram of a cache server provided by an embodiment of the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

An embodiment of the present invention provides a method for migrating resource data. The execution subject of the method is a cache server. The cache server may be a cache server under the CDN architecture, and it may be provided with two storage media with different read and write speeds, for example Mechanical hard drives and solid state drives. The application scenario of this embodiment may be shown in FIG. 1 . After receiving the resource data acquisition request sent by the client, the cache server checks whether the resource data is stored in the storage medium, and if found, returns the resource data to the client; The resource data is obtained from the station server, and the obtained resource data is returned to the client. The above-mentioned client may be a terminal device such as a personal computer or a smart phone, and the client may obtain resource data such as video, audio, and website content data from the above-mentioned cache server. The above-mentioned cache server may include a processor, a memory, and a transceiver. The processor may be used to update hotspot values of resource data in the following processes and process resource data migration in storage media. The memory may be used in the storage process The data required as well as the data generated, the transceiver can be used to receive and transmit relevant data during processing.

The following will describe in detail a processing flow for migrating resource data shown in FIG. 2 in combination with specific implementation methods, and the content may be as follows:

Step 201: Periodically update hotspot values of all resource data stored in the first storage medium and the second storage medium one by one.

Wherein, the reading and writing speed of the second storage medium is higher than that of the first storage medium.

In an implementation, there may be at least two storage media with different read and write speeds including the first storage medium and the second storage medium in the cache server, and both the first storage medium and the second storage medium may store a large number of resource data. At the same time, the cache server can record the user's access frequency to each resource data. Specifically, the access frequency of the resource data can be reflected in the form of hotspot values. The higher the hotspot value of the resource data, the higher the access frequency of the corresponding resource data. It can be understood that the user's access frequency to resource data may change at any time. For example, when a program is broadcast, the access frequency of the corresponding resource data is high. will increase again. Therefore, the cache server can periodically update the hotspot value of the resource data to better reflect the latest access frequency of the resource data.

Specifically, for any resource data stored in the first storage medium or the second storage medium, the cache server may, based on the initial storage time of the resource data, every preset statistical period (for example, set the statistical period to six minutes, then One hour contains ten statistical periods), periodically update the hotspot value of the resource data. For example, if the initial storage time of the target resource data is 8:20:15 of a certain day, the cache server may update the hotspot value of the target resource data every six minutes according to the six-minute statistical period. In this way, based on the initial storage time of each resource data, the cache server can periodically update the hotspot values of all resource data one by one.

Optionally, the processing of the cache server to periodically update the hotspot value of the resource data may be as follows: determine the target resource data of the hotspot value to be updated; predict the target resource data in the current statistical period according to the historical access times of the target resource data in the historical statistical period The current access times of the target resource data; update the hotspot value of the target resource data according to the data volume of the target resource data and the latest access time of the target resource data, as well as the historical access times and current access times of the target resource data.

In implementation, the cache server can determine the target resource data whose hotspot value is to be updated at the current time according to the current time and the initial storage time of each resource data, and then, the cache server can calculate the current access times of the target resource data within the current statistical period predict. It is easy to understand that when a certain resource data has been frequently accessed in the past period of time, there is a high probability that it will continue to be frequently accessed in the next period of time. In this way, the cache server can calculate the history of the period based on the set number of consecutive historical statistics. Visit times, calculate the current visit times of the target resource data in the current statistics period.

A specific algorithm for predicting the current number of visits to target resource data is given below: the cache server calculates the number of historical visits in the first historical statistical period before the current statistical period and the historical visits in the second historical statistical period before the current statistical period The difference of the number of times; multiply the difference by the preset value, and add the historical access times of the first three historical statistical periods before the current statistical period to generate the current access times of the target resource data in the current statistical period. For example, the current time is 20:00, and the current statistical period is 20:00-20:06. First, three consecutive historical statistical periods (19:42-19:48, 19:48-19 :54, 19:54-20:00), assuming that the historical statistical times in 19:42-19:48 are 100, the historical statistical times in 19:48-19:54 are 150, 19:54 -The number of historical statistics within 20:00 is 180. After that, calculate the difference between the historical access times of the first historical statistical period 19:54-20:00 and the historical historical access times of the second historical statistical period 9:48-19:54, that is, the difference is 30. Finally, the difference 30 is multiplied by a preset value, for example, the preset value is 3, plus the respective historical access times of the first three historical statistical periods before the current statistical period, and the obtained number of visits 520 is the current statistical period The current number of accesses to the target resource data within.

It can be understood that there are many ways to calculate the current access times of the target resource data. For example, different weight values can be set for the historical access times in different historical statistical periods, and the current access times of the target resource data can also be obtained after calculation. frequency.

After the cache server predicts the current access times of the target resource data within the current statistical period, it can update the target resource data according to the data volume of the target resource data and the latest access time of the target resource data, as well as the historical access times and current access times of the target resource data. Hotspot value for resource data.

Optionally, the process of updating the hotspot value of the target resource data may be specifically as follows: calculate the total number of visits between the historical visit times and the current visit times for a set number of consecutive historical statistical periods, and the latest visit time and current visit time of the target resource data The time difference between moments; divide the total number of visits by the data volume of the target resource data, and divide it by the square of the time difference to generate the updated hotspot value of the target resource data.

In implementation, it is not difficult to understand that the higher the total number of visits to the target resource data, the higher the hotspot value of the target resource data; the smaller the data volume of the target resource data, the easier it is to transmit through the network, and the user can obtain the target resource data The lower the difficulty, the higher the hotspot value of the target resource data to a certain extent; the smaller the time difference between the latest access time and the current time, it means that the target resource data is still accessed by users shortly before the statistics, so the smaller the time difference can indicate the target The hotspot value of resource data is higher. Therefore, you can first calculate the total number of historical visits and current visits for a set number of consecutive historical statistical periods, then calculate the time difference between the latest access time of the target resource data and the current time, and finally divide the total number of visits by the target The data amount of the resource data is divided by the square of the time difference, so as to obtain the hotspot value of the target resource data. For example, if the preset number of historical statistical periods mentioned above is 10 historical statistical periods, then the historical access times in these 10 historical statistical periods are obtained first, assuming 100, 120, 140, 140, 180, 150, 100, 100, 150, 180, the current statistical count obtained after calculation is 520, and the total visit count is 1360; after that, obtain the latest access time of the target resource data, assuming it is 19:59:06, and the current time is 20:00:25, then The time difference between the latest access time and the current time is 79, and at the same time, the data volume of the target resource data is 20MB, then the calculated hotspot value is 1360/20/79/79=0.01089.

Step 202: After the hotspot value of any resource data is updated, determine the first resource data with the highest hotspot value in the first storage medium and the second resource data with the lowest hotspot value in the second storage medium.

In implementation, after the hotspot value of any resource data is updated, the cache server can sort the hotspot values of all resource data, and according to the order of the hotspot values from low to high, the cache server can determine the The first resource data with the highest hotspot value, and the second resource data with the lowest hotspot value in the second storage medium.

Considering that there may be a large amount of resource data, and the arrangement order of hotspot values of resource data often changes, in order to improve the efficiency of hotspot value sorting, a balanced binary tree sorting algorithm can be used to sort the hotspot values of all resource data , thus, the sorting operation on hotspot values of all resource data can evolve into deletion and reinsertion of a balanced binary tree, with a time complexity of 2NlogN. When a balanced binary tree is inserted and deleted, it can be reordered by left rotation and right rotation, so that it can have high sorting efficiency. Of course, other sorting algorithms can also be used to sort the hotspot values, such as bubble sorting algorithm or selection sorting algorithm.

Step 203: If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, migrate the first resource data to the second storage medium.

In implementation, when the first resource data with the highest hotspot value in the first storage medium and the second resource data with the lowest hotspot value in the second storage medium are determined, if the hotspot value of the first resource data is higher than that of the second resource The hotspot value of data indicates that the access frequency of the first resource data exceeds the access frequency of the second resource data. At this time, the first resource data can be migrated to the second storage medium with faster read and write speeds to ensure that the second The resource data stored in the second storage medium has a higher access frequency than the first storage medium. In this way, the cache server can not only take advantage of the fast reading and writing speed of the second storage medium, significantly shorten the reading and writing time of resource data with high hotspot values, improve the cache service quality of the cache server, but also take advantage of the large resource data capacity of the first storage medium. Advantages, significantly reducing the cost of using the cache server.

Optionally, since the storage capacity of the second storage medium is limited, before migrating the first resource data to the second storage medium, it may also be considered whether the remaining storage capacity of the second storage medium is sufficient to store the first resource data, and accordingly The processing can be as follows:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, start to store In the second storage medium, the resource data whose hotspot value is smaller than the hotspot value of the first resource data are migrated to the first storage medium in turn; The resource data whose hotspot value in the medium is smaller than the hotspot value of the first resource data is migrated to the first storage medium, and the first resource data is migrated to the second storage medium.

In practice, since the data volume of each resource data varies, after resource data migration, the remaining storage capacity of the second storage medium changes dynamically. For example, before resource data migration with a storage capacity of 50M, The remaining storage capacity of the second storage medium is 100M. When the migration is completed, the remaining storage capacity of the second storage medium will become 50M. When the data volume of the resource data to be migrated next time is 20M, when the migration is completed, The remaining storage capacity of the second storage medium will become 30M. When the remaining storage capacity of the second storage medium is not enough to complete the migration of resource data, that is, the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, then the cache server can follow the order of hotspot values from low to high, Start to migrate the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium in turn, so that the storage capacity of the second storage medium can be released until it is detected that the remaining storage capacity is greater than or equal to the first resource data When the amount of data exceeds the data size, stop migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium. At this time, the cache server can migrate the first resource data to the second storage medium medium.

It is easy to understand that when all resource data in the second storage medium whose hotspot value is smaller than the hotspot value of the first resource data is migrated to the first storage medium, the data volume of the first resource data is still greater than the remaining storage data of the second storage medium amount, it indicates that the remaining storage capacity of the second storage medium is not enough to store the first resource data. At this time, the cache server cannot migrate the first resource data to the second storage medium, so the first resource data can be kept in the first storage medium. medium.

Optionally, when the cache server migrates resource data, it can also reduce the migration cost by avoiding the migration of resource data with high access frequency in a short period of time. The corresponding processing can be as follows: if the first resource data If the hotspot value is higher than the hotspot value of the second resource data, and the standard deviation between the previous access times and the current access times of the first resource data is smaller than a preset threshold, the first resource data is migrated to the second storage medium.

In practice, in the actual access process, there is also a type of resource data that has a high frequency of access in a short period of time and a low frequency of access thereafter. If this type of resource data is migrated to the second storage medium, it will still be It needs to be migrated back to the first storage medium, thereby increasing the migration cost. The degree of change in access frequency of resource data within a certain period of time can be reflected by the standard deviation of previous access times and current access times of resource data. Therefore, a preset threshold of standard deviation can be set. When the hotspot value of the first resource data The first resource data is migrated to the second storage medium only when the hotspot value of the second resource data is higher than the standard deviation of the previous access times and the current access times of the first resource data is less than a preset threshold.

For example, when the hotspot value of the first resource data is higher than the hotspot value of the second resource data, the previous access times of the first resource data are 100, 120, 140, 140, 180, 150, 100, 100, 150, 180, The calculated current number of statistics is 520. After calculation, the standard deviation between the previous access times and the current access times of the first resource data is 117.03. If the standard deviation 117.03 of the first resource data is less than the preset threshold, for example, the preset threshold is 120, the first resource data is migrated to the second storage medium; if the standard deviation 117.03 of the first resource data is greater than the preset threshold, for example, when the preset threshold is 110, the first resource data is not migrated to the second storage medium medium.

Optionally, when the cache server needs to store new resource data, it also needs to determine whether the storage medium storing the resource data is the first storage medium or the second storage medium, and the corresponding processing can be as follows: After the request, if it is detected that the remaining storage capacity of the second storage medium is less than the preset storage capacity, the target resource data is stored in the first storage medium, otherwise, the target resource data is stored in the second storage medium.

In implementation, on the one hand, during the initial period when the cache server caches resource data, its first storage medium and second storage medium may not store resource data or have just stored a small amount of resource data, due to the high read and write speed of the second storage medium Therefore, in order to obtain better caching service quality, when the cache server starts caching resource data, it can preferentially store the resource data to be stored in the second storage medium, and store the remaining resource data in the second storage medium After the amount reaches the preset storage amount, the resource data to be stored is stored in the first storage medium. On the other hand, after the cache server provides the cache service for a period of time, the resource data stored in the first storage medium and the second storage medium both have a certain hotspot value. At this time, the cache server will judge the size of the hotspot value way to decide whether to migrate the resource data to the second storage medium.

Specifically, after receiving the storage request of the target resource data, the cache server first detects the remaining storage capacity of the second storage medium, and if it detects that the remaining storage capacity of the second storage medium is greater than the preset storage capacity, then stores the target resource data In the second storage medium; if it is detected that the remaining storage capacity of the second storage medium is less than or equal to the preset storage capacity, storing the target resource data in the first storage medium. For example, the above preset storage capacity is 100M, if the remaining storage capacity of the second storage medium is greater than 100M, such as 200M, 300M or the maximum storage capacity (that is, the second storage medium is in a blank state where no resource data is stored), then the target The resource data is stored in the second storage medium; if the remaining storage capacity of the second storage medium is less than or equal to 100M, such as 50M, then the target resource data is stored in the first storage medium.

In the embodiment of the present invention, the hotspot values of all resource data stored in the first storage medium and the second storage medium are periodically updated one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium; After the hotspot value of is updated, determine the first resource data with the highest hotspot value in the first storage medium, and the second resource data with the lowest hotspot value in the second storage medium; if the hotspot value of the first resource data is higher than the second resource data hotspot value, migrate the first resource data to the second storage medium. In this way, the resource data with high access frequency can always be stored in the second storage medium with fast read and write speed, and then, when the user accesses these resource data, the cache server can quickly read and write them, and the user does not need to wait for a long time The resource data can be obtained, therefore, the efficiency of obtaining resource data can be improved as a whole.

Based on the same technical concept, the embodiment of the present invention also provides a device for migrating resource data, as shown in Figure 3, the device includes:

An update module 301, configured to periodically update hotspot values of all resource data stored in the first storage medium and the second storage medium one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium;

A judging module 302, configured to determine the first resource data with the highest hotspot value in the first storage medium and the second resource data with the lowest hotspot value in the second storage medium after the hotspot value of any resource data is updated;

A migration module 303, configured to migrate the first resource data to the second storage medium if the hotspot value of the first resource data is higher than the hotspot value of the second resource data.

Optionally, the updating module 301 is specifically used for:

Determine the target resource data of the hotspot value to be updated;

predicting the current number of visits to the target resource data in the current statistical period according to the historical visit times of the target resource data in the historical statistical period;

The hotspot value of the target resource data is updated according to the data amount of the target resource data, the latest access time of the target resource data, and the historical visit times and current visit times of the target resource data.

Optionally, the migration module 303 is specifically used for:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, then according to the hotspot value from In order from low to high, start migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium in sequence;

When it is detected that the remaining storage amount is greater than or equal to the data amount of the first resource data, stop migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the the first storage medium, and migrate the first resource data to the second storage medium.

Optionally, the migration module 303 is specifically used for:

If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the standard deviation of the previous access times and the current access times of the first resource data is smaller than a preset threshold, then the second resource data A resource data is migrated to the second storage medium.

Optionally, as shown in Figure 4, the device further includes:

The storage module 304 is configured to store the target resource data in the second storage medium if it is detected that the remaining storage capacity of the second storage medium is greater than the preset storage capacity after receiving the storage request of the target resource data. medium, otherwise, store the target resource data in the first storage medium.

In the embodiment of the present invention, the hotspot values of all resource data stored in the first storage medium and the second storage medium are periodically updated one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium; After the hotspot value of is updated, determine the first resource data with the highest hotspot value in the first storage medium, and the second resource data with the lowest hotspot value in the second storage medium; if the hotspot value of the first resource data is higher than the second resource data hotspot value, migrate the first resource data to the second storage medium. In this way, the resource data with high access frequency can always be stored in the second storage medium with fast read and write speed, and then, when the user accesses these resource data, the cache server can quickly read and write them, and the user does not need to wait for a long time The resource data can be obtained, therefore, the efficiency of obtaining resource data can be improved as a whole.

It should be noted that: when the device for migrating resource data provided by the above-mentioned embodiment migrates resource data, it only uses the division of the above-mentioned functional modules for illustration. In practical applications, the above-mentioned functions can be assigned to different function Module completion means that the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device for migrating resource data provided by the above embodiment and the embodiment of the method for migrating resource data belong to the same idea, and its specific implementation process is detailed in the method embodiment, and will not be repeated here.

FIG. 5 is a schematic structural diagram of a cache server provided by an embodiment of the present invention. The cache server 500 may have relatively large differences due to different configurations or performances, and may include one or more central processing units 522 (for example, one or more processors) and memory 532, and one or more storage application programs 542 or Storage medium 530 for data 544 (eg, one or more mass storage devices). Wherein, the memory 532 and the storage medium 530 may be temporary storage or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the cache server. Furthermore, the central processing unit 522 may be configured to communicate with the storage medium 530 , and execute a series of instruction operations in the storage medium 530 on the cache server 500 .

The cache server 500 may also include one or more power supplies 529, one or more wired or wireless network interfaces 550, one or more input and output interfaces 558, one or more keyboards 556, and/or, one or more operating systems 541, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM and so on.

The cache server 500 may include a memory, and one or more programs, wherein the one or more programs are stored in the memory, and are configured to be executed by one or more processors, including for performing Instructions for migrating resource data above.

Through the above description of the implementations, those skilled in the art can clearly understand that each implementation can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic Discs, optical discs, etc., include several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection of the present invention. within range.

Claims (11)

1. A method for migrating resource data, characterized in that the method comprises: periodically updating hotspot values of all resource data stored in the first storage medium and the second storage medium one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium; After the hotspot value of any resource data is updated, determine the first resource data with the highest hotspot value in the first storage medium, and the second resource data with the lowest hotspot value in the second storage medium; If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, migrating the first resource data to the second storage medium. 2. The method according to claim 1, wherein the periodic updating of hotspot values of all resource data stored in the first storage medium and the second storage medium one by one comprises: Determine the target resource data of the hotspot value to be updated; predicting the current number of visits to the target resource data in the current statistical period according to the historical visit times of the target resource data in the historical statistical period; The hotspot value of the target resource data is updated according to the data amount of the target resource data, the latest access time of the target resource data, and the historical visit times and current visit times of the target resource data. 3. The method according to claim 1, wherein if the hotspot value of the first resource data is higher than the hotspot value of the second resource data, the first resource data is migrated to the The second storage medium includes: If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, then according to the hotspot value from In order from low to high, start migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium in sequence; When it is detected that the remaining storage amount is greater than or equal to the data amount of the first resource data, stop migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the the first storage medium, and migrate the first resource data to the second storage medium. 4. The method according to claim 1, wherein if the hotspot value of the first resource data is higher than the hotspot value of the second resource data, the first resource data is migrated to the The second storage medium includes: If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the standard deviation of the previous access times and the current access times of the first resource data is smaller than a preset threshold, then the second resource data A resource data is migrated to the second storage medium. 5. The method according to claim 1, characterized in that the method further comprises: After receiving the storage request of the target resource data, if it is detected that the remaining storage capacity of the second storage medium is greater than the preset storage capacity, the target resource data is stored in the second storage medium, otherwise the The target resource data is stored in the first storage medium. 6. A device for migrating resource data, characterized in that the device comprises: An update module, configured to periodically update hotspot values of all resource data stored in the first storage medium and the second storage medium one by one, wherein the read and write speed of the second storage medium is higher than that of the first storage medium; A judging module, configured to determine the first resource data with the highest hotspot value in the first storage medium and the second resource data with the lowest hotspot value in the second storage medium after the hotspot value of any resource data is updated; A migration module, configured to migrate the first resource data to the second storage medium if the hotspot value of the first resource data is higher than the hotspot value of the second resource data. 7. The device according to claim 6, wherein the update module is specifically used for: Determine the target resource data of the hotspot value to be updated; predicting the current number of visits to the target resource data in the current statistical period according to the historical visit times of the target resource data in the historical statistical period; The hotspot value of the target resource data is updated according to the data amount of the target resource data, the latest access time of the target resource data, and the historical visit times and current visit times of the target resource data. 8. The device according to claim 6, wherein the migration module is specifically used for: If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the data volume of the first resource data is greater than the remaining storage capacity of the second storage medium, then according to the hotspot value from In order from low to high, start to migrate the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the first storage medium in sequence; When it is detected that the remaining storage amount is greater than or equal to the data amount of the first resource data, stop migrating the resource data whose hotspot value in the second storage medium is smaller than the hotspot value of the first resource data to the the first storage medium, and migrate the first resource data to the second storage medium. 9. The device according to claim 6, wherein the migration module is specifically used for: If the hotspot value of the first resource data is higher than the hotspot value of the second resource data, and the standard deviation of the previous visit times and the current visit times of the first resource data is less than a preset threshold, then the second A resource data is migrated to the second storage medium. 10. The device according to claim 6, further comprising: A storage module, configured to store the target resource data in the second storage medium if it detects that the remaining storage capacity of the second storage medium is greater than a preset storage capacity after receiving the storage request of the target resource data , otherwise store the target resource data in the first storage medium. 11. A cache server, characterized in that the cache server includes a processor and a memory, at least one instruction, at least one section of program, code set or instruction set are stored in the memory, the at least one instruction, the at least A program, the code set or instruction set is loaded and executed by the processor to implement the method for migrating resource data as claimed in any one of claims 1 to 5.