CN117130777A

CN117130777A - Method and device for evaluating stability of server, electronic equipment, chip and medium

Info

Publication number: CN117130777A
Application number: CN202311003375.9A
Authority: CN
Inventors: 钱才伟
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Suzhou Software Technology Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Suzhou Software Technology Co Ltd
Priority date: 2023-08-10
Filing date: 2023-08-10
Publication date: 2023-11-28

Abstract

The disclosure provides a server stability assessment method, a device, electronic equipment, a chip and a medium, which are applied to a CDN server and relate to the field of edge calculation. The method comprises the following steps: acquiring a first index in a first period and average time delay in a second period; determining a first health loss according to a first index in a first number of first periods; determining a second health loss according to the average time delay of the second number of first periods and the second period; and determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree. By the technical scheme provided by the disclosure, the problem that the stability of the CDN server lacks an effective and reasonable evaluation method is solved, the reliability of the edge network is improved, and the robustness and safety of the edge service operation are ensured.

Description

Method and device for evaluating stability of server, electronic equipment, chip and medium

Technical Field

The disclosure relates to the field of edge computing, and in particular relates to a server stability assessment method, a device, electronic equipment, a chip and a medium.

Background

With the continuous expansion of the internet scale, the edge network is used as an extension and perfection of the core network, so that faster and more reliable digital service can be provided for end users in a college and expandable mode, and the edge network is widely built and put into use. The content delivery (Content Delivery Network, CDN) server is an important component of the edge network, the main purpose of which is to store content as close as possible to the requesting client machine, thereby reducing latency and shortening page loading time. At present, the stability detection and alarm of the existing server are mainly monitored by single dimension of multiple indexes or mixed monitoring of a few indexes, and the existing server is not applicable to an edge network CDN server.

Disclosure of Invention

The disclosure provides a server stability evaluation method, a device, electronic equipment, a chip and a medium, so as to solve the problem that the stability of a CDN server lacks an effective and reasonable evaluation method. The average time delay data is collected and recorded periodically, the periodic collection comprises the dimensions such as CPU occupancy rate, memory use rate, disk use rate and the like of the CDN server, the health loss degree of each index dimension is calculated, then the periodic health loss degree of the time delay is taken as a main part, the periodic health loss degree of other indexes is combined, the target health loss degree of the CDN server in the period is calculated, the reliability of the edge network is accurately evaluated, the reliability of the edge network is improved, and the stability and the safety of the edge service operation are ensured.

An embodiment of a first aspect of the present disclosure provides a server stability evaluation method, applied to a CDN server, including:

acquiring a first index in a first period and average time delay in a second period;

determining a first health loss according to a first index in a first number of first periods;

determining a second health loss according to the average time delay of the second number of first periods and the second period;

and determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree.

In some embodiments, determining the first health loss based on the first indicator for the first number of first cycles comprises:

continuously collecting a first index in a first number of first periods;

a first health loss is determined based on the first indicator and the first quantity.

In some embodiments, determining the second health loss based on the second number of average delays of the first period and the second period comprises:

determining a single-cycle health loss degree according to the average time delay in the second cycle;

determining the average time delay health loss degree according to the average time delay and the second number corresponding to the single-period health loss degree meeting the first condition;

The average time delay health loss is taken as a second health loss.

In some embodiments, determining the single cycle health loss based on the average time delay of the second cycle comprises:

if the average time delay in the second period is smaller than the first time delay threshold value, setting the single period health loss degree as a first preset loss value;

if the average time delay in the second period is in the first time delay interval, setting a single period health loss degree according to the average time delay in the second period, the upper limit value of the first time delay interval and the lower limit value of the first time delay interval;

and if the average time delay in the second period is greater than a second time delay threshold value, setting the single-period health loss degree as a second preset loss value.

In some embodiments, determining the target health loss and the alert level based on the first health loss and the second health loss comprises:

when the second health loss degree is in different loss intervals, determining a target health loss degree according to the statistical parameters of the first health loss degree;

and triggering different alarms according to different total loss intervals where the target health loss degree is located.

In some embodiments, determining the target health loss based on the statistical parameter of the first health loss comprises:

And carrying out weighted summation based on the statistical parameters of the first health loss degree to obtain a target health loss degree, wherein the statistical parameters of the first health loss degree comprise at least one of the maximum value, the average value and the current value of the first health loss degree.

In some embodiments, the first indicator includes at least one of CPU utilization, memory utilization, disk utilization.

An embodiment of a second aspect of the present disclosure proposes a server stability evaluation device, characterized in that the device includes:

the acquisition module is used for acquiring a first index in a first period and average time delay in a second period;

a first determining module, configured to determine a first health loss degree according to a first index in a first number of first periods;

a second determining module, configured to determine a second health loss degree according to a second number of average delays of the first period and the second period;

and the evaluation module is used for determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree.

An embodiment of a third aspect of the present disclosure proposes an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the embodiments of the first aspect of the present disclosure.

An embodiment of a fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of the embodiments of the first aspect of the present disclosure.

A fifth aspect embodiment of the present disclosure proposes a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the embodiments of the first aspect of the present disclosure.

A sixth aspect of the present disclosure provides a chip comprising one or more interface circuits and one or more processors; the interface circuit is for receiving a signal from a memory of the electronic device and sending the signal to the processor, the signal comprising computer instructions stored in the memory, which when executed by the processor cause the electronic device to perform the method of any of the embodiments of the first aspect.

In summary, according to the server stability evaluation method provided by the present disclosure, a first index in a first period and an average time delay in a second period are obtained; determining a first health loss according to a first index in a first number of first periods; determining a second health loss according to the average time delay of the second number of first periods and the second period; and determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree. Through the technical scheme, the average time delay in the first index and the second index in the first period is obtained, and a data source is provided for stability evaluation of the CDN server. And determining a first health loss degree according to a first index in a first period of a first number, and obtaining delay influence caused by a CPU, a memory, a disk and the like in the CDN server. And determining a second health loss degree according to the average time delay of the second number of the first periods and the second periods, and obtaining the influence caused by the average time delay in the CDN server. And determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree, so as to judge the stability of the CDN server and alarm under an abnormal scene. The method and the device provide accurate assessment for the stability of the CDN server, improve the reliability of the edge network and ensure the robustness and safety of the edge service operation.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

Fig. 1 is a flowchart of a server stability evaluation method according to an embodiment of the present disclosure.

FIG. 2 is a flow chart of determining a first health loss based on a first index over a first number of first cycles in accordance with an embodiment of the present disclosure.

Fig. 3 is a schematic diagram of a first health loss degree corresponding to the index and each period data acquisition value according to an embodiment of the disclosure.

FIG. 4 is a flow chart of determining a second health loss based on a second number of first cycles and an average time delay of the second cycles, in accordance with an embodiment of the present disclosure.

Fig. 5 is a schematic diagram of determining an average latency health loss by an average latency meeting a first condition according to an embodiment of the present disclosure.

Fig. 6 is a flow chart of determining a single period health loss based on an average time delay of a second period according to an embodiment of the present disclosure.

FIG. 7 is a schematic diagram of determining a single cycle health loss degree according to an embodiment of the present disclosure.

FIG. 8 is a schematic diagram of determining a single cycle health loss degree according to an embodiment of the present disclosure.

FIG. 9 is a flow chart of determining a target health loss level and an alert level based on a first health loss level and a second health loss level according to an embodiment of the present disclosure.

FIG. 10 is a flow chart of determining a target health loss based on statistical parameters of a first health loss according to an embodiment of the present disclosure.

FIG. 11 is a flow chart of a method for computing and alerting of CDN server stability in accordance with an embodiment of the present disclosure.

Fig. 12 is a schematic structural diagram of a server stability evaluation device according to an embodiment of the disclosure.

Fig. 13 is a block diagram of an electronic device for implementing the server stability assessment method of the present disclosure, according to an example embodiment.

Detailed Description

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals identify the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.

The CDN server is a part of a content delivery network (Content Delivery Network), is a distributed network architecture, and is used for caching the content of a website to a server which is closer to a user by deploying the servers at different geographic positions, so that the access speed and experience of the user are improved.

At present, the detection and alarm for the stability of the server are mainly to effectively monitor through different monitoring indexes, such as a CPU, a memory, a storage, network traffic and the like. By acquiring the state and performance information of each index, the running condition of each module can be quickly known. Meanwhile, a monitoring index threshold is artificially set for each index, and when the acquired data exceeds the index threshold, an alarm can be triggered to inform relevant network management personnel of paying attention to and solving the problem. Or by sending heartbeat or requesting specified service to the server, and judging the stability of the server by requesting the result.

In the related art, the server stability detection and alarm mainly uses single-dimensional monitoring of multiple indexes or mixed monitoring of few indexes. However, different servers have different job assignments, and different job tasks are different for important rows of the respective indexes of the servers. Some server CPUs are important metrics, but CPU is less important than memory for other servers. And in addition, the indexes such as CPU, memory and stored resource utilization rate and the like acquired each time in the related technology are subjected to single stability calculation, the sample is insufficient, the CPU and the memory suddenly increase at a certain moment and fall back, the calculation result is inaccurate in the scene, the serious contingency exists, and false alarm is easy to generate.

The related art also has a technique of judging the stability of a server by sending a heartbeat request or requesting a specified service to the server and requesting result information. The frequent downloading and request in the direction occupies network bandwidth, wastes network resources and is not applicable to the edge network CDN server.

For a CDN server, a service capability is required that provides a high quality network experience and ultra-low latency, which is an indicator of important detection of server stability. Aiming at the problems of the related technology and the scheme, which are lack of an effective and reasonable evaluation method for the stability of the CDN server, the disclosure provides a server stability evaluation method which is applied to the CDN server. The health loss degree of each index dimension is calculated through periodically collecting and recording average time delay data, and periodically collecting the dimensions including CPU occupancy rate, memory utilization rate, disk utilization rate and the like of the CDN server, and then the health loss degree of the CDN server in the period is calculated by taking the time delay periodic health loss degree as a main part and combining with the periodic health loss degrees of other indexes, so that the stability of the CDN server is judged, and an alarm is given in an abnormal scene. According to the implementation mode, network resources are not occupied, the stability of the CDN server can be accurately and completely evaluated in a mode of combining multiple indexes and multiple weights by taking time delay as a main part through periodic multiple samples, so that the reliability of an edge network is improved, and the robustness and the safety of edge service are ensured.

The method provided by the disclosure is applied to the fields of cloud computing, big data, edge computing and the like, and provides accurate assessment for the running performance of the CDN server. The method can be further applied to aspects such as unmanned, internet of things, intelligent home, intelligent traffic, intelligent manufacturing, intelligent cities and the like, the capacity of request load balancing of CDN clusters is further optimized, the reliability of an edge network is improved while the same service capacity is provided, and the robustness and safety of edge service are ensured. The application scenario is not limited in the embodiments of the present disclosure.

The server stability evaluation method provided by the application is described in detail below with reference to the accompanying drawings.

Fig. 1 is a flowchart of a server stability evaluation method according to an embodiment of the present disclosure. As shown in fig. 1, the server stability evaluation method includes:

step 101, obtaining a first index in a first period and an average time delay in a second period.

In the present disclosure, the first index includes at least one of CPU utilization, memory utilization, and disk utilization. Preferably, the first index includes a CPU utilization, a memory utilization, and a disk utilization. The first period is a sampling period set by a first index of the acquisition server, the second period is a sampling period set by the average time delay of all requests in the statistics server, and in order to obtain the average time delay in time, quick statistics is needed, and the second period is far smaller than the first period.

Step 102, determining a first health loss according to a first index in a first number of first periods.

In the present disclosure, the first number is a positive integer, and is used to represent a first index that counts a plurality of first periods to determine a first health loss degree. The first health loss degree indicates a loss degree affecting the health state of the server caused by server abnormality caused by server hardware such as a CPU, a memory, a disk, and the like.

Step 103, determining a second health loss according to the average time delay in the second number of the first periods and the second periods.

In the disclosure, the second number is a positive integer, and is used for representing statistics of average time delays in a plurality of first periods, and determining a second health loss degree based on the statistics of the average time delays in the plurality of first periods and the average time delays in a single second period, where the second health loss degree is a loss degree in the server, which is caused by time delays caused by non-hardware factors such as a network, a system, an application, and the like, and affects the health state of the server.

Step 104, determining a target health loss degree and an alarm level according to the first health loss degree and the second health loss degree.

In the disclosure, the target health loss degree is a parameter for evaluating the overall stability of the CDN server, and the alarm level is that when the target health loss degree caused by the server in an abnormal scenario is large, the current abnormal condition is prompted by an alarm mode, and the abnormal condition is classified into different abnormal levels to alarm.

In summary, according to the server stability evaluation method provided by the present disclosure, the first index in the first period and the average delay in the second period are obtained, and a data source is provided for the stability evaluation of the CDN server. And determining a first health loss degree according to a first index in a first period of a first number, and obtaining the time delay influence caused by hardware such as a CPU, a memory, a disk and the like in the CDN server. And determining a second health loss degree according to the average time delay of the second number of the first periods and the second periods, and obtaining the influence caused by the time delay generated by non-hardware factors such as a system or a network in the CDN server. And determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree, so as to judge the stability of the CDN server and alarm under an abnormal scene. The method and the device provide accurate assessment for the stability of the CDN server, improve the reliability of the edge network and ensure the robustness and safety of the edge service operation.

FIG. 2 is a flow chart of determining a first health loss based on a first index over a first number of first cycles in accordance with an embodiment of the present disclosure. Fig. 2 is a further illustration of step 102 of the embodiment of fig. 1, which, in the embodiment shown based on fig. 2, comprises the steps of:

Step 201, a first index for a first number of first periods is continuously acquired.

And continuously collecting CPU, memory and disk utilization rates of the CDN server host in a first number of first periods.

For example, the indexes such as CPU utilization, memory utilization, hard disk utilization, etc. of the CDN server host are continuously collected for 30 periods. And the usage is expressed by retaining a two-bit decimal form.

Step 202, determining a first health loss degree according to the first index and the first number.

According to the first index and the set first number acquired in the above step 201, the first health loss degree may be calculated according to the mapping relationship between the data acquisition value and the first health loss degree in each period.

In one implementation of this embodiment, the mapping relationship between the data acquisition value and the first health loss degree of each period may be represented by the following formula:

where x is the data acquisition value for each cycle, M is the total number of cycles, i is the first number, i is the first health loss from the first cycle, and HDWM is the first health loss.

Fig. 3 is a schematic diagram of a first health loss degree corresponding to the index and each period data acquisition value according to an embodiment of the disclosure. In this embodiment, m=30, and the first period is 10s, and the health loss degree of each index within 30×10s/60 s=5 minutes can be calculated according to the above formula. As shown, X is an acquisition value for M first cycles, which is from 0 to 100. The health loss degree HDWM of the index obtained by calculation according to the above formula is shown as Y in the figure.

In this embodiment, the mapping relationship between the data collection value and the first health loss degree of each period is obtained by data collection and modeling in a laboratory.

In this embodiment, the first health loss degree is calculated by continuously collecting the first index in the first period of the first number according to the first index and the first number by the above mapping relation. The first health loss degree can reflect the influence of the abnormality of hardware such as a CPU, a memory, a disk and the like of the current CDN server host on the stability. After analyzing the abnormality generated by the hardware in the server host, the abnormality caused by the time delay generated by the non-hardware caused by the system, the network, the application software and the like needs to be considered.

FIG. 4 is a flow chart of determining a second health loss based on a second number of first cycles and an average time delay of the second cycles, in accordance with an embodiment of the present disclosure. Fig. 4 is a further illustration of step 103 of the embodiment of fig. 1, which, in the embodiment shown on the basis of fig. 4, comprises the following steps:

step 401, determining the health loss degree of a single period according to the average time delay in the second period.

The single cycle health loss is a single cycle health loss. According to the average time delay in the second period acquired in step 101 in fig. 1, different single-period health loss degrees are determined based on the average time delay in different intervals.

Step 402, determining the average time delay health loss degree according to the average time delay and the second number corresponding to the single-period health loss degree meeting the first condition.

The first condition is the judgment condition that the single-cycle health loss degree is greater than 0 in the above step 401, and the situation that the health loss occurs in the server is reserved, namely, the delayed data is reserved. The average time delay health loss degree can be calculated by the average time delay corresponding to the single-period health loss degree which accords with the first condition judgment and the preset second quantity. The average delay health loss degree is used for reflecting the loss degree of normal operation caused by delay caused by non-hardware factors such as a system, a network, an application and the like in the CDN server. The larger the value, the greater the latency, the more serious the anomaly that exists in the server.

Fig. 5 is a schematic diagram of determining an average latency health loss by an average latency meeting a first condition according to an embodiment of the present disclosure. Fig. 5 is a further illustration of step 402 of the embodiment of fig. 4, where in the embodiment shown in fig. 5, the average time delay data with the single-cycle health loss degree greater than 0 is retained, and the average time delay health loss degree is calculated by using the sampling value with the single-cycle health loss degree greater than 0 in the set time, and the mapping relationship between the total number M of all the first periods N with the single-cycle health loss degree greater than 0 and the average time delay health loss degree in the set time.

In one implementation manner of this embodiment, the mapping relationship between the total number m=30 of all the first periods n=10s with the single-period health loss degree greater than 0 and the average time-delay health loss degree in the set time and the average time-delay health loss degree in m×n/60 s=5 minutes of the calculation server may be expressed by the following formula:

where x is a value with a health loss greater than 0 in 5 minutes, M is all cycles with a health loss greater than 0 in 5 minutes, i represents the average time-lapse health loss calculated from the first cycle, and HDWM. As shown, X is an acquisition value for M first cycles, which is from 0 to 100. Calculated by the above formulaThe average delay health loss HDWM to this index is shown as Y in the figure.

And step 403, taking the average time delay health loss degree as a second health loss degree.

The average time-lapse health loss calculated by step 402 above is taken as the second health loss.

In the embodiment, the health loss degree of a single period is determined through the average time delay in the second period, and the health loss degree in the single period caused by the average time delay is obtained; determining the average time delay health loss degree according to the average time delay and the second number corresponding to the single-period health loss degree meeting the first condition; the health loss degree in a single period caused by the average time delay in the second period is determined, the data with the time delay in the health loss degree in the single period are reserved, the average time delay health loss degree is calculated based on the data with the time delay and the second number, and is used as the second health loss degree, so that data preparation is provided for calculating the overall target health loss degree of the CDN server.

Fig. 6 is a flow chart of determining a single period health loss based on an average time delay of a second period according to an embodiment of the present disclosure. Fig. 6 is a further illustration of step 401 of the embodiment of fig. 4, which, in the embodiment shown based on fig. 6, comprises the steps of:

in step 601, if the average time delay in the second period is smaller than the first time delay threshold, the health loss degree of the single period is set to be a first preset loss value.

The average time delay in the second period obtained in step 101 in the embodiment of fig. 1 is determined, and if the average time delay in the second period is smaller than the first time delay threshold, the first preset loss value is set to be the health loss degree of a single period. The first delay threshold is a boundary threshold of obvious delay of the server, preferably, the first delay threshold is 20ms, the first preset loss value is 0, that is, for average delay in the second period is less than 20ms, calculation of average delay health loss degree is not included.

Step 602, if the average delay in the second period is within the first delay interval, setting a single-period health loss according to the average delay in the second period, the upper limit value of the first delay interval, and the lower limit value of the first delay interval.

If the average time delay in the second period is in the first time delay interval, calculating the single-period health loss degree by using the average time delay in the second period, the upper limit value and the lower limit value of the first time delay interval. Preferably, the first delay period is [20ms,30ms ], i.e. the upper limit of the first delay period is 30ms, and the lower limit of the first delay period is 20ms.

In one implementation of this embodiment, the single cycle health loss HDWNM is calculated according to the following formula.

HDWNM＝(nd-dl) ² *90/(nd ² +(dm-nd) ² ) Where nd (x) is the current period average delay value, dl is the current interval lower limit, dm is the current interval upper limit, and HDWNM is the current health loss. Preferably, dl=20, dm=30. FIG. 7 is a schematic diagram of determining a single cycle health loss degree according to an embodiment of the present disclosure.

If the first delay interval is [30ms,100ms ], the single cycle health loss degree HDWNM is calculated according to the following formula.

HDWNM＝(nd-20) ² *69/((nd-dl) ² +(dm-nd) ² ) As in the above embodiment, +10, nd is the current period average delay value, dl is the current period lower limit value, and dm is the current period upper limit value. FIG. 8 is a schematic diagram of determining a single cycle health loss degree according to an embodiment of the present disclosure.

Step 603, if the average time delay in the second period is greater than the second time delay threshold, setting the single-period health loss degree as a second preset loss value.

The average time delay in the second period obtained in step 101 in the embodiment of fig. 1 is determined, and if the average time delay in the second period is greater than the second time delay threshold, the second preset loss value is set to be the health loss degree of a single period. The second delay threshold is a delay boundary threshold at which a server has obvious abnormality, preferably, the second delay threshold is 100ms, the first preset loss value is 100, that is, for the average delay in the second period is greater than 100ms, the single-period health loss degree is set to be the maximum value of 100.

In this embodiment, if the average time delay in the second period is smaller than the first time delay threshold, the health loss degree of the single period is set to be a first preset loss value. If the average time delay in the second period is in the first time delay interval, setting the single-period health loss degree according to the average time delay in the second period, the upper limit value of the first time delay interval and the lower limit value of the first time delay interval. And if the average time delay in the second period is greater than a second time delay threshold value, setting the single-period health loss degree as a second preset loss value. Through the three ranges of the average time delay in the second period, the corresponding single-period health loss degree is obtained, and data preparation is provided for calculating the average time delay health loss degree. The first health loss degree and the second health loss degree are obtained through calculation, and the health loss degree of the whole server can be further determined.

FIG. 9 is a flow chart of determining a target health loss level and an alert level based on a first health loss level and a second health loss level according to an embodiment of the present disclosure. Fig. 9 is a further illustration of step 104 of the embodiment of fig. 1, which, in the embodiment shown based on fig. 9, includes the steps of:

step 901, determining the target health loss according to the statistical parameter of the first health loss when the second health loss is in different loss intervals.

The statistical parameter of the first health loss degree includes at least one of a maximum value, an average value, and a current value of the first health loss degree. Preferably, the statistical parameter of the first health loss degree comprises a maximum value, an average value and a current value of the first health loss degree.

In one implementation of this embodiment, the second health loss degree calculated based on step 403 in the embodiment of fig. 4 is analyzed, and if the second health loss degree is 0, the total health loss degree HDM of the CDN server is calculated according to the following formula.

Hdm=max loss 0.7+avg loss 0.3, wherein MAX loss is the maximum value of the first health loss and AVG loss is the average of the first health losses.

Obviously, if the second health loss degree, i.e. the current time delay health loss degree does not exist, i.e. the influence of the stability of the CDN server is indicated to come from the first health loss degree, the largest one of the second health loss degree and the first health loss degree is given a larger weight through analysis of the first health loss degree, so that the current stability influencing factor is highlighted. For example, when the loss degree of the CPU, the memory and the hard disk is 70, 20 and 10 respectively, the CPU has the greatest influence on the current stability of the server, and the loss degree caused by the CPU is given a larger weight.

In one implementation of this embodiment, if the loss interval of the second health loss is [0,10], if the CPU, the memory and the storage index health loss of the first health loss are both lower than 60, the total health loss of the CDN server is calculated according to the following weighting formula: hdm=average delay loss 0.7+avg loss 0.3. If the CPU of the first health loss degree exists that the memory and storage index health loss degree is larger than 60, calculating the total health loss degree of the CDN server according to the following weighted formula: hdm=average delay loss 0.4+max loss 0.5+avg loss 0.1. Wherein the AVG penalty does not include an average delay penalty.

Obviously, there is less influence on stability in the current second health loss degree, and then the total health degree of the current CDN server is affected by the sum of the MAX loss degree, the AVG loss degree, and the second health loss degree in the first health loss degree.

In one implementation of this embodiment, if the second health loss is greater than 10, if the CPU, memory and storage finger health loss of the first health loss are all lower than 60, the total health loss of the CDN server is calculated according to the following weighted formula: hdm=average delay loss degree 0.9+avg loss degree 0.1, wherein AVG loss degree does not include average delay loss degree. If the CPU of the first health loss degree exists that the memory and storage finger table health loss degree is more than 60, calculating the total health loss degree of the CDN server according to the following weighted formula: hdm=average delay loss 0.7+max loss 0.2+avg loss 0.1. Wherein the AVG penalty does not include an average delay penalty.

Obviously, when the second health loss degree is larger, the main influence of the stability of the current CDN server comes from the average delay loss degree, and the average delay loss degree is given larger weight in the total health loss degree so as to highlight the influence of the average delay on the stability of the CDN server.

Step 902, triggering different alarms according to different total loss intervals where the target health loss degree is located.

Based on the range division for different target health loss degrees, different alarms are triggered.

In one implementation of this embodiment, when the second health loss is 0, if the CDN server total health loss HDM is in the interval of [0-60], no alert is triggered. If the total health loss degree HDM of the CDN server is in the [60, 100] interval, triggering a first-level alarm.

In one implementation of this embodiment, when the second health loss is (0, 10), the total health loss of the CDN server is in the interval [0-25], no alarm is triggered, the total health loss of the CDN server is in the interval [25-60], a primary alarm is triggered, the total health loss of the CDN server is in the interval [60-100], and a serious alarm is triggered.

In one implementation of this embodiment, when the second health loss is greater than 10, the CDN server total health loss is in the interval of [0-10 ], and triggers a primary alert. The total health loss degree of the CDN server is in the range of [10-60 ], and a serious alarm is triggered. The total health loss degree of the CDN server is in the range of [60-100], and a deadly alarm is triggered.

In this embodiment, when the second health loss degree is in different loss intervals, the target health loss degree is determined according to the statistical parameter of the first health loss degree, and different alarms are triggered according to different total loss intervals in which the target health loss degree is located, so that a manager can feel intuitive about the stability problem of the CDN server, and the manager can process the abnormal situation technically.

FIG. 10 is a flow chart of determining a target health loss based on statistical parameters of a first health loss according to an embodiment of the present disclosure. Fig. 10 is an illustration of a first degree of health loss in the embodiment of fig. 9, and in an embodiment based on that shown in fig. 10, includes the steps of:

step 1001, performing weighted summation based on the statistical parameter of the first health loss degree to obtain the target health loss degree, wherein the statistical parameter of the first health loss degree includes at least one of a maximum value, an average value and a current value of the first health loss degree.

In this embodiment, the statistical parameter of the first health loss degree includes at least one of a maximum value, an average value and a current value obtained by statistics from the first health loss degree, and preferably, the statistical parameter of the first health loss degree includes the maximum value, the average value and the current value at the same time. And calculating the target health loss degree by carrying out weighted summation on the statistical parameters of the first health loss degree. The method for calculating the total health loss degree of the CDN server by adopting different weights for different health loss degrees can more accurately evaluate the stability of the CDN server, can avoid the problem of sudden increase of the utilization rate of resources such as occasional CPU, memory and the like, and can more completely and comprehensively reflect the stability condition degree of the CDN server.

In the embodiment of fig. 11, the steps include the following:

s1, periodically acquiring indexes such as CPU, memory and storage utilization rate of a CDN server host computer in N seconds (for example, 10S), acquiring average time delay (in ms) of all requests in a 1-second period, and storing acquired records and corresponding time.

S2, calculating the health loss degree of each according to indexes such as CPU, memory, storage utilization rate and the like in M (30) periods.

S3, comparing and calculating the average time delay value in the N x M period with 4 preset time intervals of time delay, and calculating the health loss degree of each time through different formulas.

And S4, calculating the health loss degree of the CDN server according to the multi-period multi-dimension index health loss degree and combining different weights.

S5, judging whether the health loss degree of the server triggers an alarm or not.

And if the stability of the server reaches a preset alarm value, triggering an alarm.

According to the server stability assessment method, a first index in a first period and average time delay in a second period are obtained; determining a first health loss according to a first index in a first number of first periods; determining a second health loss according to the average time delay of the second number of first periods and the second period; and determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree. Through the technical scheme, the average time delay in the first index and the second index in the first period is obtained, and a data source is provided for stability evaluation of the CDN server. And determining a first health loss degree according to a first index in a first period of a first number, and obtaining delay influence caused by a CPU, a memory, a disk and the like in the CDN server. And determining a second health loss degree according to the average time delay of the second number of the first periods and the second periods, and obtaining the influence caused by the average time delay in the CDN server. And determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree, so as to judge the stability of the CDN server and alarm under an abnormal scene. The method and the device provide accurate assessment for the stability of the CDN server, improve the reliability of the edge network and ensure the robustness and safety of the edge service operation.

Corresponding to the methods provided in the above embodiments, the present disclosure further provides a server stability evaluation device, and since the apparatus provided in the embodiments of the present disclosure corresponds to the methods provided in the above embodiments, implementation of the method is also applicable to the apparatus provided in the embodiments, and will not be described in detail in the embodiments.

Fig. 12 is a schematic structural diagram of a server stability evaluation apparatus 1200 according to an embodiment of the disclosure. As shown in fig. 12, the server stability evaluation device includes:

an acquisition module 1210 is configured to acquire a first color space representation and a second color space representation of an image to be corrected.

A first determination module 1220 is configured to determine skin tone pixels in the image to be corrected based on the first color space representation and the second color space representation.

A second determination module 1230 corrects skin tone pixels.

An evaluation module 1240 for determining a target health loss level and an alert level based on the first health loss level and the second health loss level.

In some embodiments, the first determination module 1220 determines the first degree of health loss from the first indicator for the first number of first periods in a manner that includes:

Continuously collecting a first index in a first number of first periods; a first health loss is determined based on the first indicator and the first quantity.

In some embodiments, the second determination module 1230 determines the second health loss based on the second number of first periods and the average time delay of the second period by:

the average time delay health loss is taken as a second health loss.

In some embodiments, the second determining module 1230 determines the single cycle health loss based on the average latency of the second cycle by:

In some embodiments, the evaluation module 1240 determines the target health loss level and the alert level from the first health loss level and the second health loss level in the following manner:

In some embodiments, the evaluation module 1240 determines the target health loss from the statistical parameters of the first health loss in the following manner:

In some embodiments, the first index of the server stability assessment apparatus 1200 includes at least one of CPU utilization, memory utilization, disk utilization.

In summary, the server stability evaluation device obtains a first index in a first period and an average time delay in a second period; determining a first health loss according to a first index in a first number of first periods; determining a second health loss according to the average time delay in the second number of first cycles and the second cycles; and determining the target health loss degree and the alarm grade according to the first health loss degree and the second health loss degree. The device solves the problem that the stability of the CDN server lacks an effective and reasonable evaluation method, improves the reliability of the edge network, and ensures the robustness and safety of the edge service operation.

In the embodiment provided by the application, the method and the device provided by the embodiment of the application are introduced. In order to implement the functions in the method provided by the embodiment of the present application, the electronic device may include a hardware structure, a software module, and implement the functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Some of the functions described above may be implemented in a hardware structure, a software module, or a combination of a hardware structure and a software module.

Fig. 13 is a block diagram of an electronic device 1300 for implementing the server stability assessment method described above, according to an example embodiment.

For example, electronic device 1300 may be a mobile phone, computer, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, and the like.

Referring to fig. 13, an electronic device 1300 may include one or more of the following components: a processing component 1302, a memory 1304, a power component 1306, a multimedia component 1308, an audio component 1310, an input/output (I/O) interface 1312, a sensor component 1314, and a communication component 1316.

The processing component 1302 generally controls overall operation of the electronic device 1300, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 1302 may include one or more processors 1320 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 1302 can include one or more modules that facilitate interactions between the processing component 1302 and other components. For example, the processing component 1302 may include a multimedia module to facilitate interaction between the multimedia component 1308 and the processing component 1302.

The memory 1304 is configured to store various types of data to support operations at the electronic device 1200. Examples of such data include instructions for any application or method operating on the electronic device 1300, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 1304 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply assembly 1306 provides power to the various components of the electronic device 1300. The power components 1306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 1300.

The multimedia component 1308 includes a screen between the electronic device 1300 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or sliding action, but also the duration and pressure associated with the touch or sliding operation. In some embodiments, the multimedia component 1308 includes a front-facing camera and/or a rear-facing camera. When the electronic device 1300 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 1310 is configured to output and/or input audio signals. For example, the audio component 1310 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 1300 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 1304 or transmitted via the communication component 1316. In some embodiments, the audio component 1310 also includes a speaker for outputting audio signals.

The I/O interface 1312 provides an interface between the processing component 1302 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 1314 includes one or more sensors for providing status assessment of various aspects of the electronic device 1300. For example, the sensor assembly 1314 may detect an on/off state of the electronic device 1300, a relative positioning of the components, such as a display and keypad of the electronic device 1300, the sensor assembly 1314 may also detect a change in position of the electronic device 1300 or a component of the electronic device 1300, the presence or absence of a user's contact with the electronic device 1300, an orientation or acceleration/deceleration of the electronic device 1300, and a change in temperature of the electronic device 1300. The sensor assembly 1314 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1314 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1316 is configured to facilitate communication between the electronic device 1300 and other devices, either wired or wireless. The electronic device 1300 may access a wireless network based on a communication standard, such as WiFi,2G or 3G,4G LTE, 5G NR (New Radio), or a combination thereof. In one exemplary embodiment, the communication component 1316 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1316 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 1300 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as memory 1304, including instructions executable by processor 1320 of electronic device 1300 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Embodiments of the present disclosure also propose a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the server stability evaluation method described in the above embodiments of the present disclosure.

Embodiments of the present disclosure also propose a computer program product comprising a computer program which, when executed by a processor, performs the server stability assessment method described in the above embodiments of the present disclosure.

Embodiments of the present disclosure also provide a chip including one or more interface circuits and one or more processors; the interface circuit is for receiving a signal from a memory of the electronic device and sending the signal to the processor, the signal including computer instructions stored in the memory, which when executed by the processor, cause the electronic device to perform the server stability assessment method described in the above embodiments of the present disclosure.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

In the description of the present specification, reference is made to the description of the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., meaning that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, system that includes a processing module, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (control method) with one or more wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It should be understood that portions of embodiments of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, and the program may be stored in a computer readable storage medium, where the program when executed includes one or a combination of the steps of the method embodiments.

Furthermore, functional units in various embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented as software functional modules and sold or used as a stand-alone product. The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.

While embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations of the above embodiments may be made by those of ordinary skill in the art within the scope of the present disclosure.

Claims

1. A server stability assessment method, applied to a CDN server, comprising:

determining a first health loss according to a first number of the first indicators within the first period;

determining a second health loss based on a second number of the average time delays over the first period and the second period;

and determining a target health loss degree and an alarm level according to the first health loss degree and the second health loss degree.

2. The method of claim 1, wherein said determining a first health loss based on said first indicator for a first number of said first cycles comprises:

continuously acquiring the first index for the first number of the first periods;

And determining the first health loss degree according to the first index and the first quantity.

3. The method of claim 1, wherein said determining a second health loss based on a second number of average time delays of said first period and said second period comprises:

determining the average time delay health loss degree according to the average time delay corresponding to the single-period health loss degree meeting the first condition and the second quantity;

and taking the average time delay health loss degree as the second health loss degree.

4. A method according to claim 3, wherein said determining a single cycle health loss degree based on said average time delay of the second cycle comprises:

if the average time delay in the second period is smaller than a first time delay threshold value, setting the single period health loss degree as a first preset loss value;

if the average time delay in the second period is in a first time delay interval, setting a single period health loss degree according to the average time delay, a first time delay interval upper limit value and a first time delay interval lower limit value in the second period;

5. The method of claim 1, wherein determining a target health loss level and an alert level based on the first health loss level and the second health loss level comprises:

when the second health loss degree is in different loss intervals, determining the target health loss degree according to the statistical parameter of the first health loss degree;

6. The method of claim 5, wherein determining the target health loss based on the statistical parameter of the first health loss comprises:

and carrying out weighted summation based on the statistical parameters of the first health loss degree to obtain the target health loss degree, wherein the statistical parameters of the first health loss degree comprise at least one of the maximum value, the average value and the current value of the first health loss degree.

7. The method of any one of claims 1 to 6, wherein the first indicator comprises at least one of CPU utilization, memory utilization, disk utilization.

8. A server stability assessment apparatus, the apparatus comprising:

a first determining module configured to determine a first health loss according to a first number of the first indicators in the first period;

a second determining module, configured to determine a second health loss degree according to a second number of the average time delays of the first period and the second period;

9. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.

11. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-7.

12. A chip comprising one or more interface circuits and one or more processors; the interface circuit is configured to receive a signal from a memory of an electronic device and to send the signal to the processor, the signal comprising computer instructions stored in the memory, which when executed by the processor, cause the electronic device to perform the method of any of claims 1-7.