Method and device for reducing father bandwidth based on global cooling and heating

Through real-time interaction between edge scheduling components and content scheduling center, the MD5 value is used to determine the hot and cold attributes of requests, update the cache data, and realize hot and cold scheduling, which solves the problem of delay and resource imbalance in the existing technology when stating global hot and cold information in the existing technology. , reduces the back-to-parent bandwidth and improves the resource utilization efficiency of video websites.

CN118921368AActive Publication Date: 2024-11-08CHINA TELECOM CLOUD TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202410928132.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-11
Publication Date
2024-11-08
Estimated Expiration
2044-07-11

AI Technical Summary

Technical Problem

When the existing technology calculates global hot and cold information, the link is long and the time delay is large, and the real-time hot and cold attributes of resources cannot be flexibly feedback, and it cannot effectively deal with the sudden scenes of video websites, resulting in waste of back-to-parent bandwidth.

Method used

Through the edge scheduling component, the request data in a unit time is summarized, the request is initiated to the content scheduling center query is uniformly issued, the hot and cold attributes are judged using the MD5 value, and the cache data is updated through the load-balanced content scheduling service to realize hot and cold scheduling and reduce edge scheduling execution Time consuming and content scheduling center pressure.

Benefits of technology

Reduces the first packet time of customer requests, reduces the number of interactions between edge scheduling and content scheduling centers, improves the accuracy of resource hot and cold judgments, solves the problems of unbalanced request distribution and hot spot burst scenarios, and realizes cross-regional Regional planning saves back-to-parent bandwidth and reduces back-to-parent cost.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921368A_ABST
    Figure CN118921368A_ABST
Patent Text Reader

Abstract

The invention provides a father-back bandwidth reduction method and device based on global cold and hot, and the method comprises the steps: receiving user requests, and summarizing the user requests according to a preset unit time, and obtaining a request set; performing cache query on the request set through a timed task to obtain a query result at least comprising cold and hot attributes corresponding to the user request; establishing a plurality of load-balanced content scheduling services, and updating the cache data by the plurality of content scheduling services according to the cache result to obtain updated cache data; caching is carried out according to the updated cache data, and cold and hot scheduling is carried out according to the cold and hot attributes; and the gateway responds to the jump based on cold and hot scheduling and serves the user request. According to the method, the problems that the request distribution is unbalanced, the overall situation is hot and the single machine is cold possibly existing in single machine statistics are solved, and meanwhile, the url hot spot emergency scene can be effectively dealt with.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of Internet technology, and in particular relates to a method and device for reducing parent bandwidth based on global hot and cold return. Background Art

[0002] Through the analysis of CDN acceleration requests for video websites, we know that most of the requests are cold requests, and the majority of the website's return bandwidth is caused by these cold requests. More return bandwidth will cause a waste of parent node bandwidth costs. An effective way to save return costs is to perform 302 scheduling for such cold requests, and redirect the cold requests to the same server through HTTP's 302 redirect method, ensuring that only one copy is cached, thereby reducing return bandwidth.

[0003] The traditional technical means of counting global hot and cold data usually involves collecting request logs at the edge, aggregating request logs at the support center, counting the number of requests per unit time for each request URL of the domain name, calculating the hot and cold information of each request URL, and then sending the hot and cold information to each edge machine in the form of a data file. However, for a video website with a large number of request URLs, this is an implementation method that not only has a long link and high latency, but also a huge amount of data. It cannot flexibly feedback the real-time hot and cold properties of resources and cannot effectively respond to emergencies. Summary of the invention

[0004] In view of the above deficiencies in the prior art, the purpose of the invention is to provide a method and device for reducing the parent bandwidth based on global hot and cold.

[0005] The first aspect of the present invention provides a method for reducing the bandwidth of a parent based on global hot and cold, comprising:

[0006] S1: receiving user requests, and aggregating the user requests according to a preset unit time to obtain a request set;

[0007] S2: Query the request set in cache through a scheduled task to obtain a query result including at least the hot and cold attributes corresponding to the user request;

[0008] S3: establishing multiple load-balanced content scheduling services, and having the multiple content scheduling services update cached data according to the cache results to obtain updated cached data;

[0009] S4: caching according to the updated cache data, and performing hot and cold scheduling according to the hot and cold attributes;

[0010] S5: The gateway responds to the jump based on the hot and cold scheduling and serves the user request.

[0011] According to a global hot-cold back-to-parent bandwidth reduction method provided by the present invention, the request set in step S1 includes a request URL and a request number.

[0012] According to a method for reducing the global hot-cold return bandwidth provided by the present invention, step S2 further includes:

[0013] S21: The edge scheduling component sends the request set to the content scheduling center through a scheduled task;

[0014] S22: The content scheduling center calculates the MD5 value of the request set;

[0015] S23: The content scheduling center performs a cache query based on the MD5 value. When there is no cache item corresponding to the MD5 value, the hot and cold attributes are determined based on the statistical values ​​in the request set. When there is a cache item corresponding to the MD5 value, the hot and cold attributes are determined based on the statistical values ​​in the cache to obtain a query result.

[0016] According to a global hot-cold back-to-parent bandwidth reduction method provided by the present invention, in step S21, the edge scheduling component sends the request set to the content scheduling center via HTTP.

[0017] According to a global hot-cold back-to-parent bandwidth reduction method provided by the present invention, in step S3, multiple load-balanced content scheduling services are implemented by mounting LVS technology.

[0018] According to a method for reducing the parent bandwidth based on global hot and cold data provided by the present invention, in step S4, when the edge scheduling component caches according to the updated cache data, it also includes:

[0019] Clean up expired cache data.

[0020] According to a method for reducing the global hot-cold parent bandwidth provided by the present invention, the hot-cold scheduling in step S4 specifically includes:

[0021] When the hot / cold attribute of the user request is a cold request, a serviceable virtual IP address is obtained by hashing within the planned area coverage to hit the cache; when the hot / cold attribute of the user request is a hot request, it is served by the local machine.

[0022] The second aspect of the present invention further provides a global hot-cold return bandwidth reduction device, comprising:

[0023] Aggregation module: used to receive user requests and aggregate the user requests according to a preset unit time to obtain a request set;

[0024] Query module: used to perform cache query on the request set through a scheduled task to obtain query results including at least the hot and cold attributes corresponding to the user request;

[0025] Update module: used to establish multiple load-balanced content scheduling services, and the multiple content scheduling services update the cached data according to the cache results to obtain updated cached data;

[0026] Scheduling module: used for caching according to the updated cache data and performing hot and cold scheduling according to the hot and cold attributes;

[0027] Execution module: used for performing gateway jump in response to the hot and cold scheduling and serving the user request.

[0028] A third aspect of the present invention provides a global hot-cold return bandwidth reduction device, comprising:

[0029] A memory and at least one processor, wherein instructions are stored in the memory;

[0030] At least one of the processors calls the instructions in the memory to enable a global hot-cold-back-to-parent bandwidth reduction device to execute a global hot-cold-back-to-parent bandwidth reduction method as described in any one of the above items.

[0031] A fourth aspect of the present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, a method for reducing parent-back bandwidth based on global hot and cold is implemented as described in any one of the above.

[0032] The beneficial effects of the present invention are as follows:

[0033] The present invention provides a method, device, equipment and storage medium for reducing the bandwidth back to the parent based on global hot and cold. The edge scheduling component aggregates the request URL data within a unit time, and then uniformly initiates a request to the content scheduling center for query. On the one hand, it can reduce the time consumption of edge scheduling execution and reduce the impact on the first packet time of customer requests. On the other hand, it can reduce the number of interactions between edge scheduling and the content scheduling center, reduce the pressure of the content scheduling center, and ensure the high availability of the server. Secondly, by aggregating the statistical data of the edge machines of the entire network to calculate the hot and cold of the request URL, the judgment of the hot and cold of the resource is more accurate. It also solves the problem of the uneven request distribution that may exist in the statistics of a single machine. Balanced, global hot and single machine cold problems; in addition, the edge scheduling component and the content scheduling component interact in real time, and continuously update the number of requests for the request URL to ensure the latest data statistics, make the statistics more timely, and effectively solve the scenario of sudden hot spots in the request URL; for traditional coverage planning, it is basically planned to the regional granularity. There may also be multiple caches of cold resources across provinces. Therefore, this solution proposes a regional planning method that can realize cross-regional coverage, automatically plan the coverage of each area to the same area, set up an area across several areas, and implement cold resource hashing in this area to save the bandwidth back to the parent and reduce the cost of back to the parent. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0035] Figure 1 A schematic flow chart of a method for reducing the parent bandwidth based on global hot and cold return provided by an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of the structure of a global hot-cold return bandwidth reduction device provided in an embodiment of the present invention.

[0037] Reference numerals:

[0038] 100, summary module; 200, query module; 300, update module; 400, scheduling module; 500, execution module. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0040] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0041] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0043] According to the following Figure 1 to Figure 2 Embodiments of the present invention are described.

[0044] like Figure 1 As shown, the present invention provides a method for reducing the parent bandwidth based on global hot and cold, including:

[0045] S1: receiving user requests, and aggregating the user requests according to a preset unit time to obtain a request set;

[0046] The request set in step S1 includes a request URL and a request number.

[0047] In this stage, the edge scheduling component first summarizes the requests within a unit time. Specifically, after receiving the client request, the edge scheduling component aggregates the requests by unit time and counts the number of requests for each request URL in the planned area within the unit time. For example, within 5 seconds, the number of requests for the request URL http: / / www.abc.com / 1.jpg is cumulatively 10 times.

[0048] S2: Query the request set in cache through a scheduled task to obtain a query result including at least the hot and cold attributes corresponding to the user request;

[0049] Wherein, step S2 further includes:

[0050] S21: The edge scheduling component sends the request set to the content scheduling center through a scheduled task;

[0051] Furthermore, the edge scheduling component first initiates cache query regularly. Specifically, the edge scheduling component reports the request URLs and the number of requests gathered within a unit time to the content scheduling center in the form of http requests in the form of scheduled tasks.

[0052] Furthermore, the edge scheduling component periodically performs certain operations by executing scheduled tasks, that is, executing preset tasks at preset time intervals. This mechanism helps reduce the waste of system resources and ensures that data is processed and reported at the appropriate time.

[0053] Wherein, in step S21, the edge scheduling component sends the request set to the content scheduling center via HTTP.

[0054] Furthermore, the http request body can be in, but is not limited to, json format.

[0055] S22: The content scheduling center calculates the MD5 value of the request set;

[0056] S23: The content scheduling center performs a cache query based on the MD5 value. When there is no cache item corresponding to the MD5 value, the hot and cold attributes are determined based on the statistical values ​​in the request set. When there is a cache item corresponding to the MD5 value, the hot and cold attributes are determined based on the statistical values ​​in the cache to obtain a query result.

[0057] In steps S21 to S23, after receiving the query request from the edge scheduling, the content scheduling system calculates the MD5 value of the url+area, and then queries the cache based on the MD5 value. If it does not exist, the hot and cold attributes of the url are determined based on the reported statistical values ​​combined with the hot and cold thresholds. If it does exist, the statistical values ​​in the cache are accumulated and combined with the hot and cold thresholds to determine the hot and cold attributes of the url.

[0058] Furthermore, in order to efficiently manage and query the cache, the system will combine the requested URL with the region where the request comes from to calculate an MD5 value, which is used as a unique identifier for subsequent cache query and update operations. The system will then evaluate the hot and cold properties of the URL based on the reported statistical values. Specifically, if the cache does not exist, these statistical values ​​will be compared with the preset hot and cold thresholds. If the access frequency is higher than the hot threshold or lower than the cold threshold, it will be marked as hot content or cold content respectively. If the cache exists, the system will read the existing statistical values ​​of the URL from the cache and accumulate (or update) them to reflect the latest access situation. Then, it also uses these accumulated statistical values ​​to compare with the hot and cold thresholds to re-evaluate or confirm the hot and cold properties of the URL.

[0059] The hot and cold statistics method of content scheduling can be implemented by maintaining time slots. In a specific embodiment, the implementation method is as follows: Assume that the statistical period is 300s and the number of time slots is 5. The specific steps are: 1) The time slot statistics process is as follows: 0~60s, statistics to the 1st time slot; 60s~120s, statistics to the 2nd time slot; 120s~180s, statistics to the 3rd time slot; 180s~240s, statistics to the 4th time slot; 240s~300s, statistics to the 0th time slot; 300s~360s, statistics to the 1st time slot; ...; 1320s~1380s, statistics to the 2nd time slot; ...; 2) Accumulate the statistical values ​​of the 5 time slots before the current time, which is the total statistical value; 3) When the time slot is reused, the total statistical value needs to deduct the original statistical value of the reused time slot in advance;

[0060] 4) When the request interval spans multiple time slots, it is necessary to clean up the expired time slot statistics.

[0061] S3: establishing multiple load-balanced content scheduling services, and having the multiple content scheduling services update cached data according to the cache results to obtain updated cached data;

[0062] In step S3, the content scheduling center needs to face requests from a large number of edge machines. In order to ensure the high availability of the system, the multi-pod mode can be implemented by mounting LVS. Each content scheduling service can handle all requests and implement load balancing by LVS. Multiple content scheduling pods update cache data by grabbing distributed locks.

[0063] Specifically, when the content scheduling grabs the distributed lock, it first determines whether the lock grabbing is successful. If not, the logic is jumped out. If the lock grabbing is successful, the data is obtained from the queue to be updated of redis in batches, and then the statistical values ​​of the URLs to be updated are aggregated, and the current statistical values ​​of the URLs to be updated are read from redis in batches. Subsequently, the statistical values ​​are updated through the configured time statistical window, and finally the statistical value data of the URLs are updated in batches to redis, and the execution ends.

[0064] Among them, in step S3, multiple load-balanced content scheduling services are implemented by hanging LVS technology.

[0065] In the Linux environment, LVS is a high-performance and highly available server cluster technology based on Linux. It achieves load balancing by distributing network traffic to multiple servers. The way LVS is mounted, that is, its deployment and configuration method, mainly depends on its working mode (such as NAT mode, DR mode, TUN mode, etc.) and the specific system environment and requirements.

[0066] S4: caching according to the updated cache data, and performing hot and cold scheduling according to the hot and cold attributes;

[0067] In step S4, the edge scheduling component first receives the response from the content scheduling center and performs periodic caching. Specifically, after receiving the query response, the edge scheduling component caches the hot and cold attributes of the responsive URL and periodically cleans up expired cached data. Through the continuous interaction between the edge scheduling component and the content scheduling component, the hot and cold attributes of the URL can be kept up to date, and URLs that have not been updated for a long time will also be cleaned up due to expiration.

[0068] Wherein, in step S4, when the edge scheduling component caches according to the updated cache data, it also includes:

[0069] Clean up expired cache data.

[0070] The hot and cold scheduling in step S4 specifically includes:

[0071] Among them, when the hot and cold attributes of the user request are cold requests, hashing is performed to obtain a serviceable virtual IP address within the planned area coverage to hit the cache; when the hot and cold attributes of the user request are hot requests, the service is performed locally.

[0072] The above-mentioned cold requests refer to content requests with low access frequency or recently appeared. These requests usually do not occur frequently, but if the content is obtained from the original server every time, a lot of bandwidth and resources will be consumed. For cold requests, the system will select one or more virtual IP addresses (VIP) within the planned area coverage according to the source of the user request and a certain hash algorithm. The above-mentioned planned area coverage refers to the geographical area or network area pre-defined by the system to optimize content distribution. The hash algorithm is used to generate a unique identifier based on certain characteristics of the request (such as URL, user ID, etc.) for subsequent cache lookup or content distribution decisions. After selecting the VIP, the system will try to use this VIP to query the cache. If the corresponding content exists in the cache, the content can be directly read from the cache and returned to the user without obtaining it from the original server. This can greatly reduce the number of visits to the original server, reduce bandwidth consumption and improve response speed.

[0073] The above-mentioned hot requests refer to content requests with very high access frequency. These requests usually correspond to popular content in the system and need to be accessed quickly and frequently. For hot requests, the system usually chooses to provide services directly on the server that handles the request, that is, local services. This means that when a user initiates a hot request, the system immediately reads the content from local storage or memory and returns it to the user without going through additional steps such as network transmission or cache lookup. This ensures that hot content can be accessed by users with the lowest latency and highest throughput.

[0074] S5: The gateway responds to the jump based on the hot and cold scheduling and serves the user request.

[0075] Furthermore, when a 302 redirect occurs, the server will set a Location field in the HTTP response header while returning a 302 status code. This field contains the address of the redirect target URL (URL B). Then, after the browser receives the 302 status code and Location field returned by the server, it will automatically send a new request to the URL (URL B) and display the content of the URL.

[0076] Ultimately, the gateway will provide actual services for user requests based on the results of hot and cold scheduling. The services provided include reading content from the cache, obtaining content from the backend server, or directly returning some form of response. Regardless of the method used, the goal of the gateway is to meet user requests as quickly and accurately as possible while optimizing system performance and resource usage.

[0077] like Figure 2 As shown, the present invention also provides a global hot-cold return bandwidth reduction device, comprising:

[0078] Aggregation module 100: used to receive user requests and aggregate the user requests according to a preset unit time to obtain a request set;

[0079] Query module 200: used to perform cache query on the request set through a scheduled task to obtain a query result including at least the hot and cold attributes corresponding to the user request;

[0080] Update module 300: used to establish multiple load-balanced content scheduling services, and the multiple content scheduling services update the cached data according to the cache results to obtain updated cached data;

[0081] Scheduling module 400: used for caching according to the updated cache data, and performing hot and cold scheduling according to the hot and cold attributes;

[0082] Execution module 500: used to perform gateway jump in response to the hot-cold scheduling and serve the user request.

[0083] The present invention also provides a global hot-cold return bandwidth reduction device, comprising:

[0084] A memory and at least one processor, wherein instructions are stored in the memory;

[0085] At least one of the processors calls the instructions in the memory to enable a global hot-cold-back-to-parent bandwidth reduction device to execute a global hot-cold-back-to-parent bandwidth reduction method as described in any one of the above items.

[0086] The present invention also provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, a method for reducing parent-back bandwidth based on global hot and cold is implemented as described in any one of the above.

[0087] Furthermore, a global hot-cold-back-to-parent bandwidth reduction device provided by the present invention may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPUs), for example, one or more processors and memories, one or more storage media for storing application programs or data, such as one or more massive storage devices, wherein the memories and storage media may be short-term storage or persistent storage, and the program stored in the storage medium may include one or more modules, each module may include a series of instruction operations in a global hot-cold-back-to-parent bandwidth reduction device, and further, the processor may be configured to communicate with the storage medium to execute a series of instruction operations in the storage medium on a global hot-cold-back-to-parent bandwidth reduction device.

[0088] It may also include one or more power supplies, one or more wired or wireless network interfaces, one or more input and output interfaces, and one or more operating systems, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the global hot and cold return bandwidth reduction device structure provided by the present invention does not constitute a limitation on the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily thought of by those skilled in the art within the technical scope disclosed in the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for reducing the parent bandwidth based on global hot and cold return, characterized in that: include: S1: receiving user requests, and aggregating the user requests according to a preset unit time to obtain a request set; S2: Query the request set in cache through a scheduled task to obtain a query result including at least the hot and cold attributes corresponding to the user request; S3: establishing multiple load-balanced content scheduling services, and having the multiple content scheduling services update cached data according to the cache results to obtain updated cached data; S4: caching according to the updated cache data, and performing hot and cold scheduling according to the hot and cold attributes; S5: The gateway responds to the jump based on the hot and cold scheduling and serves the user request.

2. According to claim 1, a method for reducing the global hot-cold return bandwidth is characterized in that: The request set in step S1 includes request URL and request times.

3. The method for reducing the bandwidth of the parent channel based on global hot and cold according to claim 1, characterized in that: Step S2 further includes: S21: The edge scheduling component sends the request set to the content scheduling center through a scheduled task; S22: The content scheduling center calculates the MD5 value of the request set; S23: The content scheduling center performs a cache query based on the MD5 value. When there is no cache item corresponding to the MD5 value, the hot and cold attributes are determined based on the statistical values ​​in the request set. When there is a cache item corresponding to the MD5 value, the hot and cold attributes are determined based on the statistical values ​​in the cache to obtain a query result.

4. The method for reducing the bandwidth of the parent channel based on global hot and cold according to claim 3, characterized in that: In step S21, the edge scheduling component sends the request set to the content scheduling center via HTTP.

5. The method for reducing the global hot-cold return bandwidth according to claim 1, characterized in that: In step S3, multiple load-balanced content scheduling services are implemented by attaching LVS technology.

6. The method for reducing the bandwidth of the parent channel based on global hot and cold according to claim 3, characterized in that: In step S4, when the edge scheduling component caches according to the updated cache data, it also includes: Clean up expired cache data.

7. The method for reducing the bandwidth of the parent circuit based on global hot and cold according to claim 1, characterized in that: The hot and cold scheduling in step S4 specifically includes: When the hot / cold attribute of the user request is a cold request, a serviceable virtual IP address is obtained by hashing within the planned area coverage to hit the cache; when the hot / cold attribute of the user request is a hot request, it is served by the local machine.

8. A device for reducing the parent bandwidth based on global hot and cold, characterized in that: include: Aggregation module: used to receive user requests and aggregate the user requests according to a preset unit time to obtain a request set; Query module: used to perform cache query on the request set through a scheduled task to obtain query results including at least the hot and cold attributes corresponding to the user request; Update module: used to establish multiple load-balanced content scheduling services, and the multiple content scheduling services update the cached data according to the cache results to obtain updated cached data; Scheduling module: used for caching according to the updated cache data and performing hot and cold scheduling according to the hot and cold attributes; Execution module: used for performing gateway jump in response to the hot and cold scheduling and serving the user request.

9. A global hot and cold return bandwidth reduction device, characterized in that: include: A memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable a global hot-cold-back-to-parent bandwidth reduction device to execute a global hot-cold-back-to-parent bandwidth reduction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, a method for reducing parent-back bandwidth based on global hot and cold is implemented as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Hotspot equalization method and system for cache nodes of content delivery network

    CN112104752A

  • Method and system for improving PCDN network request hit rate

    CN113507522A

  • Hot data pull-up method and device, equipment and medium

    CN113687781A

  • Cache distribution method and device, medium and equipment

    CN114422522A

  • Data scheduling method and device based on DNS protocol and electronic equipment

    CN114500459A