Methods for structuring workloads and tools for CDN nodes and electronic and intermediary devices.

Abstract

DEPCT68 What is provided in this request are the methods and tools for structuring workloads for CDN nodes. And electronic devices and intermediaries, including the assembly method: obtaining traffic characteristics. Regarding the target CP device, which serves as a server for the CDN node; Implementing IO usage of the target CP device that does not exceed the upper limit of IO throughput. As a limitation and based on the traffic characteristics of the target CP device, the decision... Determine the maximum traffic volume of services that can be achieved by the target CP device: The decision to schedule traffic for reference services of the target CP equipment is based on... From the maximum service traffic that can be achieved by the CP target and status. The hardware workload of the target CP device; and the allocation of the CDN node workload to the device. CP target based on traffic of reference service for CP target equipment;

Description

CDN node load configuration method, device, electronic device and medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on December 16, 2022, with application number 202211625759.X and invention name “A load configuration method, device, electronic device and medium for CDN nodes”. The entire contents of the Chinese patent application are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of mobile communication technologies, and in particular to a method, device, electronic device, and medium for load configuration of a CDN node. Background Art

[0004] A Content Distribution Network (CDN) is an advanced traffic distribution network built on the existing Internet. It utilizes global load balancing technology to direct user requests to the nearest, functioning streaming media server, allowing the streaming media server to directly respond to user requests, thereby alleviating network congestion. If a streaming media server doesn't have the content a user is looking for, it automatically fetches the content from the original server based on its configuration and delivers it to the user. This process is called back-to-origin.

[0005] Currently, CDNs utilize a multi-tenant shared service model, providing services to numerous downstream internet content providers (CPs). For CDN nodes, CP devices are equivalent to streaming media servers. Typically, CDN nodes are equipped with CP devices from different internet content providers, each with varying hardware configurations. Therefore, precisely balancing the load of CDN nodes based on the service capabilities of these CP devices is a pressing technical challenge.

[0006] Summary of the Invention

[0007] The purpose of this application is to provide a method, device, electronic device and medium for load configuration of CDN nodes, which can accurately adjust the load of CDN nodes based on the service capabilities of CP devices.

[0008] In order to achieve the above objectives, the embodiments of the present application are implemented as follows:

[0009] In a first aspect, a method for load configuration of a CDN node is provided, comprising: obtaining traffic characteristics of a target CP device, the target CP device serving as a server of the CDN node; determining a maximum service traffic that can be achieved by the target CP device based on the traffic characteristics of the target CP device, with the constraint that IO consumption of the target CP device does not exceed an IO throughput upper limit; determining a reference service traffic of the target CP device based on the maximum service traffic that can be achieved by the target CP and a hardware load status of the target CP device; and allocating the load of the CDN node to the target CP device according to the reference service traffic of the target CP device.

[0010] In a second aspect, a load configuration device for a CDN node is provided, comprising: a feature acquisition module for acquiring traffic features of a target CP device, the target CP device serving as a server of the CDN node; a capacity estimation module for determining a maximum service traffic that can be achieved by the target CP device based on the traffic features of the target CP device, with the constraint that IO consumption of the target CP device does not exceed an IO throughput upper limit; a benchmark determination module for determining a reference service traffic of the target CP device based on the maximum service traffic that can be achieved by the target CP and the hardware load status of the target CP device; and a load adjustment module for allocating the load of the CDN node to the target CP device according to the reference service traffic of the target CP device.

[0011] According to a third aspect, an electronic device is provided, comprising: a processor; and a memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed, cause the processor to execute the method according to the first aspect.

[0012] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store computer-executable instructions, and the computer-executable instructions implement the method described in the first aspect when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0014] FIG1 is a schematic diagram of the architecture of CDN services associated with CP devices.

[0015] FIG2 is a flow chart of a method for configuring a CDN node's load according to an embodiment of the present application.

[0016] FIG3 is a schematic diagram of modeling traffic characteristics of a load configuration method for a CDN node according to an embodiment of the present application.

[0017] FIG4 is a schematic structural diagram of a load configuration device for a CDN node according to an embodiment of the present application.

[0018] FIG5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this specification.

[0020] As mentioned above, CDNs currently utilize a multi-tenant shared service model to provide services to numerous downstream internet content providers (CPs). Typically, CDN nodes are configured with CP devices from different internet content providers, each with its own unique hardware configuration, making load balancing difficult for CDN nodes.

[0021] To this end, the present application aims to propose a technical solution that can accurately estimate the service capabilities of CP devices and adjust the load of CDN nodes according to the service capabilities of the CP devices.

[0022] Refer to Figure 1, which shows the architecture of CDN services within a CP device. The CP device primarily includes a CPU, I / O bus, I / O bridge, main memory, network interface, and disk. When a CP device receives a CDN service request through its network interface, it must perform data lookups, whether in memory or on disk, through the I / O bus. Therefore, it can be argued that the bottleneck in the CP device's service capabilities lies in I / O.

[0023] In view of this, this application uses the IO performance constraints of the CP device (the IO consumption of a single CP device does not exceed its IO throughput limit) to estimate the maximum service traffic that the CP device can achieve, and thus allocates the load of the CDN node according to the maximum service traffic that the CP device can achieve.

[0024] On the one hand, the embodiment of the present application proposes a method for configuring the load of a CDN node, which can be executed by the CDN node. Figure 2 is a flow chart of the load configuration method of the embodiment of the present application, which specifically includes the following steps:

[0025] S202: Obtain traffic characteristics of a target CP device, where the target CP device serves as a server of a CDN node.

[0026] In the embodiment of the present application, the target CP device is configured with an execution program for generating a traffic log; in this step, the traffic log of the target CP device can be analyzed to determine the traffic characteristics of the target CP device.

[0027] Specifically, the embodiment of the present application utilizes global load balancing technology to direct client access to the CDN node closest to the user, which then directly responds to the user's request through its streaming media server. If the CDN node's streaming media server does not have the content the user wants to access, it automatically fetches the corresponding content from the target CP device according to the configuration and provides it to the client.

[0028] Figure 3 is a schematic diagram showing the modeling of the target CP device's traffic characteristics relative to unit time T. This paper defines the stage where the client requests data from the CDN node as the service stage, and the stage where the CDN node requests data from the target CP device as the back-to-source stage.

[0029] The model shown in Figure 3 includes the following traffic characteristics:

[0030] 1. Traffic characteristics in the service phase:

[0031] x: The service traffic requested by the user in unit time T, unit: Gb / s.

[0032] a: the average request size corresponding to the x service flow; a = Avg(a n ),and

[0033] u: The number of requests made by the user in unit time T, unit: Request / s.

[0034] 2. Traffic Characteristics of the Back-to-Source Phase:

[0035] v: The number of times a user returns to the source within a unit time T, unit: Request / s.

[0036] z: The minimum back-to-origin traffic generated by a user request within a unit of time T (theoretical back-to-origin traffic), unit: Gb / s. b: The average request size corresponding to the z service traffic;

[0037] b: The average back-to-source allocation size corresponding to z; where

[0038] y: The total amount of content requested by the user in unit time T, unit: Gb / s.

[0039] It should be noted that the above traffic characteristics x, a, and u combined with the cache capacity D of the CDN node can reflect the hit rate of the service stage; the above traffic characteristics v, z, and b combined with the content capacity P of the target CP device can reflect the hit rate of the back-to-source stage.

[0040] In addition, it also includes traffic characteristics that reflect popularity:

[0041] p: content popularity corresponding to service traffic x, unit: %; where,

[0042] y: The total amount of content requested by the user in unit time T, unit: Gb / s.

[0043] In addition, based on the above, the following parameters are further introduced:

[0044] z': The actual back-to-origin traffic generated by the CDN during unit time T, in Gb / s. Here, z' = λz, where λ∈[1,+∞], λ = 1 indicates equal back-to-origin traffic, and λ > 1 indicates excessive back-to-origin traffic.

[0045] Q: Request hit rate corresponding to service traffic x, unit: %; where,

[0046] q: The theoretical bandwidth hit rate corresponding to service traffic x, unit: %; where,

[0047] q': actual bandwidth hit rate corresponding to service traffic x, unit: %; where,

[0048] λ: back-to-source amplification factor, unit: %; where,

[0049] The traffic characteristics of the target CP device within the unit time T obtained in this step may include a quintuple of either of the following two.

[0050] One quintuple is [u,v,x,y,z]; the other quintuple is [a,b,x,p,q].

[0051] S204 , with the IO consumption of the target CP device not exceeding the IO throughput upper limit as a constraint, and based on the traffic characteristics of the target CP device, determining the maximum service traffic that the target CP device can achieve.

[0052] Referring to the target CP device traffic characteristic model mentioned above, let:

[0053] x: service traffic requested per unit time.

[0054] y: the total amount of content requested per unit time (content popularity: ).

[0055] z: Back-to-origin traffic generated per unit time (content hit rate: ).

[0056] λ: back-to-source amplification factor λ∈[1,+∞], where λ=1 indicates equal back-to-source, and >1 indicates excessive back-to-source.

[0057] D: The disk number of the target CP device.

[0058] R: The upper limit of the IO throughput capacity of each disk in the target CP device (unit: bps).

[0059] θ: The ratio of the I / O throughput consumed by write operations of the same size to the I / O throughput consumed by read operations of the same size.

[0060] Based on the five-tuple [u, v, x, y, z], the formula for calculating the maximum service flow X that the target CP device can achieve is:

[0061] Based on the five-tuple [a, b, x, p, q], the formula for calculating the maximum service flow X that the target CP device can achieve is:

[0062] Here, the calculation formula For example, assume that the target CP device is configured with 24 disks, with an average service slice size a = 512KB and a throughput of 300Mbps per disk. The following are taken: R = 0.3; D = 24; IO = 0.3 × 24 = 7.2.

[0063] Correspondingly, the derivation process of the maximum service flow x is as follows: r +θIO w =RD;

[0064] Assume that disk write operations consume twice as much IO resources as read operations: take θ = 2; IO r +2IO w =7.2;

[0065] Because of: IO r =yq;IO w =θz′=θλz; we can get: yq+θλz=RD; where the disk read IO adopts the total content x hit rate. Here, the mechanism of scheduling content cache into memory ignores the situation where the content itself hits the RAM or SSD disk.

[0066] Further and Substituting this into the formula yq+θλz=RD, we get:

[0067] The quintuple [u,v,x,y,z] corresponds to the target CP device

[0068] The quintuple [a,b,x,p,q] corresponds to the target CP device

[0069] S206 : Determine a reference service flow of the target CP device based on the maximum service flow that can be achieved by the target CP device and the hardware load status of the target CP device.

[0070] It should be understood that in order to more accurately estimate the service capacity of the target CP device, the embodiment of the present application needs to further consider the hardware load status of the target CP device. The hardware load percentage of the target CP device may include: CPU load percentage and network card load percentage, etc., which are not limited here.

[0071] Specifically, if the actual application scenario has idle ratio requirements for the hardware of the target CP device, this step can be based on the formula Calculate the reference service flow of the target CP device. Here, X represents the reference service flow of the target CP device; X represents the maximum service flow that the target CP device can achieve; w represents the hardware load ratio of the target CP device; and α represents the hardware idle ratio of the target CP device under the constraint that the IO consumption of the target CP device does not exceed the IO throughput upper limit.

[0072] Alternatively, if the hardware of the target CP device does not have an idle ratio requirement, α can be omitted in this step, and the reference service flow of the target CP device can be directly calculated based on the formula x=wX.

[0073] S208: Allocate the load of the CDN node to the target CP device according to the reference service traffic of the target CP device.

[0074] It should be understood that the reference service flow of the target CP device finally determined can be regarded as the theoretical actual service capacity of the target CP device per unit time T. Under normal circumstances, the load of the target CP device should be allocated based on the standard that the actual service flow of the target CP device should not exceed the reference service flow.

[0075] Based on the above content, it can be seen that the method of the embodiment of the present application is based on the constraint that the IO consumption of the CP device does not exceed the IO throughput upper limit, and estimates the maximum service flow that can reflect its service capability based on the traffic characteristics of the CP device, and further combines the actual hardware load status of the CP device to determine the reference service flow of the CP device. The reference service flow accurately approaches the upper limit of the actual service capability of the CP device; therefore, after allocating the load of the CDN node to the CP device according to the reference service flow of the CP device, the enabling performance of the CP device can be fully released, while also ensuring the stability of the CDN service.

[0076] Of course, the above describes load adjustment for a single target CP device. Typically, a CDN node is configured with multiple CP devices. For this application, a similar approach can be used to determine the reference service traffic for each CP device corresponding to the CDN node. The reference service traffic for each CP device is then used as a reference to distribute the load across the CDN nodes. For example, under the premise that the actual service traffic of each CP device does not exceed the reference service traffic, a certain amount of CDN node load is allocated to each CP device according to the load balancing strategy.

[0077] The following describes the load configuration of a CDN node by taking a CDN node configured with m CP devices for n consecutive time units as an example.

[0078] It should be understood that the traffic characteristics of CP devices are variable quantities. From the CDN perspective, the traffic characteristics of CP devices can be regarded as a time series (a set of random variables sorted by time). In the case of a CDN node configured with m CP devices running mixed, the traffic characteristics of the mixed CP devices can also be understood as a random sequence and can be represented by the following matrix:

[0079] Here, the following parameters are defined:

[0080] N: Number of CP devices in the group.

[0081] D: The number of disks per CP device.

[0082] R: The upper limit of the IO throughput of each disk (unit: bps).

[0083] θ: The ratio of the I / O throughput consumed by write operations of the same size to the I / O throughput consumed by read operations of the same size.

[0084] i,j,k: lvs / slb, slb / cache, cache / disk balance factors, unit: %, value range i,j,k ≥ 1.

[0085] λ n :CP nThe return-to-source amplification factor, unit: %, value range λ n ≥1.

[0086] x n :CP n Service traffic requested by users.

[0087] y n :CP n The total amount of content requested by users.

[0088] z n :CP n Back-to-origin traffic generated by user requests.

[0089] p n :CP n The popularity of the content requested by the user;

[0090] q n :CP n Bandwidth hit ratio of user requests;

[0091] Assuming that the current CD node group has a total of M CP devices running mixed, the total service bandwidth of the group can be obtained as x:

[0092] Calculate the service flow x′ of a single CP device n :

[0093] Calculate the total IO (consumption) of a single CP device disk:

[0094] Then calculate the IO consumption of a single disk:

[0095] For the packets corresponding to the CP nodes, the packet service traffic model with no quality difference can be obtained:

[0096] By using the grouped service traffic model, the reference service traffic corresponding to the m CP devices in the CDN node in unit time 1 to n can be dynamically determined, and the load of the CDN node can be distributed to the corresponding CP devices according to the reference service traffic.

[0097] On the other hand, the embodiment of the present application also provides a load configuration device for a CDN node. FIG4 is a schematic structural diagram of a load configuration device 400, comprising:

[0098] The feature acquisition module 410 is configured to acquire traffic features of a target CP device, where the target CP device serves as a server of a CDN node.

[0099] The capacity estimation module 420 is configured to determine the maximum service flow that the target CP device can achieve based on the flow characteristics of the target CP device, with the IO consumption of the target CP device not exceeding the IO throughput upper limit as a constraint.

[0100] The benchmark determination module 430 is configured to determine a reference service flow of the target CP device based on a maximum service flow that can be achieved by the target CP and a hardware load status of the target CP device.

[0101] The load adjustment module 440 is configured to distribute the load of the CDN node to the target CP device according to the reference service traffic of the target CP device.

[0102] The apparatus of the embodiment of the present application uses the constraint that the CP device's IO consumption does not exceed its IO throughput upper limit, estimates the maximum service flow that can reflect its service capability based on the traffic characteristics of the CP device, and further determines the reference service flow of the CP device in combination with the actual hardware load status of the CP device. The reference service flow accurately approaches the upper limit of the CP device's actual service capability. Therefore, after allocating the CDN node load to the CP device according to the CP device's reference service flow, the enabling performance of the CP device can be fully unleashed while also ensuring the stability of the CDN service.

[0103] Optionally, the traffic characteristics of the target CP device include: the number of user requests u within a unit time T, the service traffic x requested by the user within a unit time T, the total amount of content requested by the user within a unit time T y, the minimum back-to-source traffic z generated by the user's request within a unit time T, and the minimum back-to-source traffic y generated by the user's request within a unit time T. The capacity estimation module 420 determines the maximum service traffic that the target CP device can achieve based on the traffic characteristics of the target CP device, with the constraint that the IO consumption of the target CP device does not exceed the IO throughput upper limit, including:

[0104] Based on the formula Determine the maximum service flow that the target CP device can achieve. θ represents the ratio of I / O throughput consumption between write operations and read operations of the same size. D represents the number of disks in the target CP device. R represents the upper limit of I / O throughput for each disk in the target CP device. λ represents the back-to-source amplification factor, λ∈[1,+∞], where λ=1 represents equal back-to-source and λ>1 represents excessive back-to-source.

[0105] Optionally, the traffic characteristics of the target CP device include: service traffic x requested by the user within a unit time T, average service fragment size a corresponding to the service traffic x; average back-to-source fragment size a corresponding to the service traffic x; bandwidth hit rate q corresponding to the service traffic x; and content popularity p corresponding to the service traffic x. The capacity estimation module 420 determines the maximum service traffic that the target CP device can achieve based on the traffic characteristics of the target CP device, with the constraint that the IO consumption of the target CP device does not exceed the IO throughput upper limit, including:

[0106] Based on the formula Determine the maximum service flow that the target CP device can achieve;

[0107] Where θ represents the ratio of I / O throughput consumption between write operations and read operations of the same size; D represents the number of disks in the target CP device; R represents the upper limit of I / O throughput of each disk in the target CP device; λ represents the back-to-source amplification factor, λ∈[1,+∞], where λ=1 represents equal-volume back-to-source and λ>1 represents excessive back-to-source.

[0108] Optionally, the benchmark determination module 430 determines the reference service flow of the target CP device based on the maximum service flow that the target CP can achieve and the hardware load status of the target CP device, including:

[0109] Based on the formula Calculate the reference service flow of the target CP device; where x represents the reference service flow of the target CP device; X represents the maximum service flow that the target CP device can achieve; w represents the hardware load ratio of the target CP device; α represents the hardware idle ratio of the target CP device under the constraint that the IO consumption of the target CP device does not exceed the IO throughput upper limit.

[0110] Optionally, the hardware load ratio of the target CP device includes a CPU load ratio and a network card load ratio.

[0111] Optionally, the target CP device is configured with an execution program for generating a traffic log; the feature acquisition module 410 acquires the traffic features of the target CP device, including: analyzing the traffic log of the target CP device to determine the traffic features of the target CP device.

[0112] Optionally, the CDN node is configured with multiple CP devices including the target CP device, and each CP device serves as a server of the CDN node; the load adjustment module 540 distributes the load of the CDN node to the target CP device according to the reference service traffic of the target CP device, including:

[0113] Based on the reference service traffic of the target CP device and the reference service traffic of other CP devices, the load of the CDN node is distributed to the multiple CP devices including the target CP device.

[0114] Obviously, the model load configuration device shown in Figure 4 can be used as the execution subject of the method shown in Figure 2, and thus can implement the steps and corresponding functions of the method shown in Figure 2. Since the principles are the same, this article will not elaborate on them in detail.

[0115] FIG5 is a schematic diagram of the structure of an electronic device according to an embodiment of the present specification. Referring to FIG5 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include internal memory, such as high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include hardware required for other services.

[0116] The processor, network interface, and memory can be interconnected via an internal bus, such as an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. These buses can be categorized as address buses, data buses, and control buses. For ease of illustration, FIG5 shows only one bidirectional arrow, but this does not imply that there is only one bus or only one type of bus.

[0117] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0118] Optionally, the processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming the load configuration device of the CDN node shown in Figure 4 above at the logical level. Correspondingly, the processor executes the program stored in the memory and is specifically used to perform the following operations:

[0119] The traffic characteristics of a target CP device are obtained, where the target CP device serves as a server of a CDN node.

[0120] With the constraint that the IO consumption of the target CP device does not exceed the IO throughput upper limit, the maximum service flow that the target CP device can achieve is determined based on the flow characteristics of the target CP device.

[0121] Based on the maximum service flow that can be achieved by the target CP and the hardware load status of the target CP device, a reference service flow of the target CP device is determined.

[0122] The load of the CDN node is distributed to the target CP device according to the reference service traffic of the target CP device.

[0123] The electronic device in the embodiment of the present application uses the constraint that the CP device's IO consumption does not exceed its IO throughput upper limit, estimates the maximum service flow that can reflect its service capability based on the traffic characteristics of the CP device, and further determines the reference service flow of the CP device in combination with the actual hardware load status of the CP device. The reference service flow accurately approaches the upper limit of the CP device's actual service capability. Therefore, after allocating the CDN node load to the CP device according to the CP device's reference service flow, the enabling performance of the CP device can be fully released while also ensuring the stability of the CDN service.

[0124] The load configuration method disclosed in the embodiments shown in this specification can be applied to a processor and implemented by the processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0125] Of course, in addition to software implementation, the electronic device in this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0126] In addition, an embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions.

[0127] Optionally, when the above instructions are executed by a portable electronic device including multiple applications, the portable electronic device can execute the steps of the method shown in FIG2 , including:

[0128] The traffic characteristics of a target CP device are obtained, where the target CP device serves as a server of a CDN node.

[0129] With the constraint that the IO consumption of the target CP device does not exceed the IO throughput upper limit, the maximum service flow that the target CP device can achieve is determined based on the flow characteristics of the target CP device.

[0130] Based on the maximum service flow that can be achieved by the target CP and the hardware load status of the target CP device, a reference service flow of the target CP device is determined.

[0131] The load of the CDN node is distributed to the target CP device according to the reference service traffic of the target CP device.

[0132] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Thus, this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] The above are merely examples of the present invention and are not intended to limit this specification. For those skilled in the art, various modifications and variations of this specification are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification shall be included within the scope of the claims of this specification. In addition, all other embodiments obtained by those of ordinary skill in the art without creative effort shall fall within the scope of protection of this document.

Claims

DEPCT681. Workload configuration method for a Content Distribution Network (CDN) node consisting of: obtaining the traffic characteristics of the target content provider (CP) device, where the target CP serves as the server of the CDN node; determining the maximum service traffic that can be achieved based on the traffic characteristics of the target CP device by taking the target CP device's input / output (IO) usage not exceeding the upper IO throughput limit as a constraint; determining the reference service traffic of the target CP device based on the maximum service traffic that can be achieved by the target CP device and the target CP device's hardware workload state;And the allocation of CDN node workload to the target CP device based on the traffic of the target CP device's reference service.

2. Method based on claim 1, where the traffic characteristics of the target CP device include: the amount of user request time u within time unit T, the traffic of service x requested by users within time unit T, the total amount of content y requested by users within time unit T, the minimum retrieved traffic z requested by users within time unit T, and the amount of time v retrieved from the user's origin within time unit T; and the determination of the maximum service traffic schedule that can be achieved based on the traffic characteristics of the target CP device by the target CP device by applying the IO usage of the target CP device that does not exceed the upper limit of the IO workload when the limit includes: the determination of the maximum service traffic schedule that can be achieved based on the formula x=(formula) by the target CP device;Where Theta represents the ratio between the IO throughput of write operations and the IO throughput of read operations, and the size of the write operation is the same as the size of the read operation; D represents the number of disks in the target CP device; R represents the upper limit of the IO throughput for each disk in the target CP device; and Lambda represents the amplification factor of the number of retrieves from the origin, Lambda member of [1, +Infinity], Lambda=1 represents equal retrieves from the origin, and Lambda>1 represents excess retrieves from the origin.

3. Method according to claim 1, where the traffic characteristics of the target CP device consist of: the traffic of service x requested by users within a unit of time T; the average service subshare size a corresponding to the traffic of service x; the average source retrieve subshare size b corresponding to the traffic of service x; the bandwidth encounter rate q corresponding to the traffic of service x; and the content popularity p corresponding to the traffic of service x;The determination of the maximum service traffic that can be achieved is based on the traffic characteristics of the target CP device, by taking into account the IO usage of the target CP device that does not exceed the upper limit of IO throughput when the constraints are included: The determination of the maximum service traffic that can be achieved is based on the formula x=(formula) by the target CP device: where theta represents the ratio between the IO throughput of write operations and the IO throughput of read operations and the size of the write operation is the same as the size of the write operation; D represents the number of disks in the target CP device; R represents the upper limit of IO throughput for each disk in the target CP device;Lambda represents the scaling factor of the amount drawn from the origin, lambda member of [1, +Infinity], lambda=1 represents equal draw from the origin, and lambda>1 represents excess draw from the origin.

4. Method according to claim 1, where the determination of the reference service traffic of the target CP device is based on the maximum service traffic that can be achieved by the target CP device and the hardware workload state of the target CP device, comprised of: The determination of the reference service traffic of the target CP device is based on the formula x=(formula), where x represents the reference service traffic of the target CP device; X represents the maximum service traffic that can be achieved by the target device; w represents the hardware workload proportion of the target CP device;Alpha represents the static hardware load ratio of the target CP device under the constraint of the target CP device's IO usage not exceeding the upper limit of the IO throughput.

5. Method according to claim 4, where the hardware load ratio of the target CP device includes the CPU load ratio and the network card load ratio.

6. Any one of claims 1 to 5, where the target CP device is configured with an operating program for generating traffic logs; and obtaining traffic characteristics of the target CP device includes: analyzing the target CP device's traffic logs and determining the traffic characteristics of the target CP device.

7. Any one of claims 1 to 5, where the CDN node is configured with more than one CP device comprising the target CP device, and each CP device serves as a server for the CDN node;The workload allocation of the CDN node to the target CP device based on the reference service traffic of the target CP device includes: allocating the CDN node workload to more than one CP device integrated with the target CP device based on the reference service traffic of the target CP device and the reference service traffic of other CP devices.

8. Workload configuration tools for the integrated CDN node: A feature acquisition module configured to acquire the traffic features of the target CP device, where the target CP device serves as the CDN node's server; a capacity estimation module configured to determine the maximum service traffic that can be achieved based on the traffic features of the target CP device, using the target CP device's IO usage not exceeding the upper IO throughput limit as a constraint;A configurationd reference scheduling module is used to determine the traffic schedule of the target CP's reference service based on the maximum service traffic achievable by the target CP and the target CP's hardware workload status; and a configurationd workload allocation module is used to allocate CDN node workloads to the target CP based on the target CP's reference service traffic.

9. The integrated electronic device consists of: a processor; and memory configured to store executable instructions whereby executable instructions cause the processor to execute one of seven claims 1 through 10. A computer-readable storage medium configured to store executable instructions whereby executable instructions, when executed by the processor, execute one of seven claims 1 through 11.

Images