CN114443283A - Application instance scaling method and device - Google Patents
Application instance scaling method and device Download PDFInfo
- Publication number
- CN114443283A CN114443283A CN202111639021.4A CN202111639021A CN114443283A CN 114443283 A CN114443283 A CN 114443283A CN 202111639021 A CN202111639021 A CN 202111639021A CN 114443283 A CN114443283 A CN 114443283A
- Authority
- CN
- China
- Prior art keywords
- current
- adjustment time
- time
- application
- current adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000008859 change Effects 0.000 claims abstract description 94
- 230000003247 decreasing effect Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008602 contraction Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000007423 decrease Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a method and a device for stretching an application example, and relates to the technical field of cloud computing. The method comprises the following steps: acquiring a request load amount at the current adjusting moment; acquiring historical data in a preset time interval adjacent to the current adjusting moment; acquiring the number n of monotone changes of the number of application instances; judging whether the absolute value of the change rate of the request load amount at the current adjustment moment and the request load amount at the adjustment moment adjacent to the current adjustment moment in the historical data is smaller than a preset change rate threshold value or not; obtaining the target quantity of the current adjusting moment according to the change trend of the number of the application examples in the historical data; and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment. The target quantity can be adaptively adjusted according to historical data, so that the number of the current application examples is adjusted, and the automatic expansion efficiency is improved.
Description
Technical Field
The invention relates to the technical field of cloud computing, in particular to a method and a device for stretching and retracting an application example.
Background
The non-service computing (Serverless computing) is a model of cloud computing, which isolates a developer from a server, so that the developer does not excessively consider the configuration, management, operation and maintenance, logs and the like of the server and concentrates on the development of business logic, thereby realizing rapid development and iteration. Knative is a serverless computing platform, which provides functions of automatic expansion and contraction to zero, version control, flow control and the like in addition to the isolation server function of the serverless computing platform, and is a serverless computing platform with a large use amount in recent years. The Knative automatic scaling function is based on the user request quantity, and when the request quantity exceeds the value which can be processed by the current application example, the request is processed in time by expanding more examples; when the request volume decreases, the server resources are released by reducing the instances.
Firstly, managing personnel at a server side deploys a Knative at the server side, then a service deployment user at a client side deploys an application to the server side, and a target volume is set when the application is deployed. The setting of the target volume requires the service deployment user to test the request processing capability of the application in advance so as to make it more efficient when the Knative automatically scales. The request of a common user reaches a proxy container of Knative through a client and a gateway, and an automatic telescopic module of Knative is a circular standing program which can monitor the request load of an application at any time and judge that the existing instance can process the request load. Specifically, a subtraction operation is performed according to the request load R in the current proxy container and a target amount T preset for the application by the user, so as to obtain the number P of the application instances.
And finally, the automatic scaling module judges whether the number of the application examples needs to be adjusted according to the calculated number of the application examples, and adjusts the number of the application examples which actually run when the adjustment is needed.
Knative adopts a mode of requesting load/target quantity to stretch application examples, the target quantity is poor in user friendliness, and users often do not know how much the application examples should be set; and once the target quantity is set, the target quantity is fixed and cannot be adjusted according to the practical running close condition, and the automatic stretching and retracting needs to adjust the number of instances according to the target quantity, so that the automatic stretching and retracting efficiency is influenced.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present invention provide a method and an apparatus for stretching an application example, so as to overcome the problem in the prior art that the efficiency is low when Knative performs automatic stretching due to a set fixed target amount.
In order to solve one or more of the above technical problems, the technical solution adopted by the present invention is as follows:
in a first aspect, a scaling method for an application instance is provided, including:
acquiring a request load amount at the current adjusting moment;
acquiring historical data in a preset time interval adjacent to the current adjusting moment; wherein the historical data comprises at least: the method comprises the steps of historical adjustment time, request load capacity, target capacity and application instance number, wherein at least the request load capacity, the target capacity and the application instance number corresponding to the historical adjustment time exist at each historical adjustment time;
acquiring the number n of monotonous changes of the number of application instances; wherein n comprises: number n of monotonically increasing application instance numbers+And the number n of monotonically decreasing application instance numbers-(ii) a And, n+，n-Are all integers greater than 1;
judging whether the absolute value of the change rate of the request load amount at the current adjustment moment and the request load amount at the adjustment moment adjacent to the current adjustment moment in the historical data is smaller than a preset change rate threshold value or not;
if so, acquiring a target quantity of the current adjustment time according to the variation trend of the application example quantity respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time;
and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
Further, the scaling method of the application example further comprises the following steps:
and storing the current adjusting time, the requested load capacity of the current adjusting time, the target capacity of the current adjusting time and the number of the application instances actually operated at the current adjusting time into historical data for circularly executing the method.
Further, the scaling method of the application example further comprises the following steps:
and if the absolute value of the change rate of the request load amount at the current adjustment time and the request load amount at the adjustment time adjacent to the current adjustment time in the historical data is judged to be larger than a preset change rate threshold, taking the target amount of the adjustment time adjacent to the current adjustment time in the historical data as the target amount of the current adjustment time.
Further, obtaining the target quantity of the current adjustment time according to the variation trend of the number of the application instances respectively corresponding to the adjustment times adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time includes:
if from the front n+And if the change trend from the adjustment time to the adjustment time adjacent to the current adjustment time in the historical data respectively corresponds to the number of the application examples which is monotonically increased in sequence, reducing the target quantity of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target quantity of the current adjustment time, wherein the minimum value of the target quantity of the current adjustment time is 1.
Further, obtaining the target amount at the current adjustment time according to the trend of the number of the application instances respectively corresponding to the adjustment times adjacent to the current adjustment time in the history data from n adjustment times before the current adjustment time further includes:
if from the front n-And if the change trends of the application example numbers respectively corresponding to the adjustment time adjacent to the current adjustment time from the adjustment time to the historical data are in a monotone decreasing order, increasing the target quantity of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target quantity of the current adjustment time.
Further, obtaining the target amount of the current adjustment time according to the trend of the change of the number of the application instances respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time further includes:
and if the change trends of the number of the application examples respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from the previous n adjustment times are not unique, taking the target quantity of the adjustment time adjacent to the current adjustment time in the historical data as the target quantity of the current adjustment time.
Further, the scaling the number of the application instances actually running according to the requested load amount at the current adjustment time and the target amount at the current adjustment time includes:
obtaining an application instance calculation value at the current adjusting time by rounding the quotient of the requested load amount at the current adjusting time and the target amount at the current adjusting time;
limiting the application instance calculation value at the current adjusting time according to a preset instance upper limit and/or a preset instance lower limit to obtain an application instance limiting value at the current adjusting time; the application instance limit value at the current adjusting time is between an instance upper limit and an instance lower limit;
and executing expansion and adjustment according to the application instance limit value at the current adjustment moment, and adjusting the number of the actually-operated application instances.
Further, obtaining the number n of monotonically changing application instance numbers includes:
counting the number n of monotonically increasing applications of the number of application instances nearest to the current adjustment time in the history data+And the number n of monotonous reductions of the number of application instances nearest to the current adjustment instant-。
Further, the preset time interval is a statistical period.
In a second aspect, a telescopic device of an application example is provided, which includes: the device comprises a request load capacity acquisition module, a historical data acquisition module, a change frequency acquisition module, a change rate judgment module, a target quantity acquisition module and an application expansion adjustment module;
the request load capacity acquisition module is used for acquiring the request load capacity at the current adjustment moment;
the historical data acquisition module is used for acquiring historical data in a preset time interval adjacent to the current adjustment moment;
the change times acquisition module is used for acquiring the times n of monotonous change of the number of the application instances;
the change rate judging module is used for judging whether the absolute value of the change rate of the request load quantity at the current adjusting moment and the request load quantity at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not;
the target quantity obtaining module is used for obtaining the target quantity of the current adjusting time according to the change trend of the number of the application examples respectively corresponding to the adjusting time adjacent to the current adjusting time from n adjusting times before the current adjusting time to the historical data;
applying a telescopic adjusting module; and the method is used for telescopically adjusting the number of the application instances which actually run according to the request load amount at the current adjusting time and the target amount at the current adjusting time.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
1. the target quantity can be adaptively adjusted according to historical data, so that the number of current application examples is adjusted, and the automatic telescoping efficiency of Knative is improved;
2. when the target amount is set, the default value can be directly set without testing in advance, so that the user friendliness is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a scaling method of an application example according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a relationship between historical data and a time axis of a current adjustment time according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of n +, n-value determination provided by an embodiment of the present invention;
fig. 4 is a schematic diagram of an n + value taking method provided in the embodiment of the present invention;
FIG. 5 is a schematic diagram of a situation of reducing the target amount according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a situation of increasing the target amount according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a situation in which the target amount is kept constant according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a telescopic device according to an application example provided in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of examples of the present invention, and not all examples. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. Also, the use of the terms "a," "an," or "the" and similar referents do not denote a limitation of quantity, but rather denote the presence of at least one. The reference numerals in the drawings in the specification merely indicate the distinction between the respective functional components or modules, and do not indicate the logical relationship between the components or modules. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used only to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
Hereinafter, various embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It is to be noted that, in the drawings, the same reference numerals are given to constituent parts having substantially the same or similar structures and functions, and repeated description thereof will be omitted.
The Knative service-free computing platform has an automatic expansion function and can adjust the number of application instances according to the set target quantity. In the prior art, a user needs to deploy an application to a server side through a service while setting a target volume. On one hand, the target quantity is fixed once set, which is not beneficial to the efficient telescopic adjustment of the number of application examples; on the other hand, the setting of the target volume requires that the service deployment user pre-test the request processing capability of the application in advance, so as to make automatic scaling of the Knative more efficient, and under more conditions, the service deployment user even has difficulty in learning the accurate setting of the target volume, maintaining efficient automatic scaling, and having poor user friendliness. The embodiment of the invention discloses a method and a device for stretching an application example, and the specific technical scheme is as follows:
in one embodiment, as shown in fig. 1, a method for scaling an application instance includes:
step S1: acquiring a request load amount at the current adjusting moment;
step S2: acquiring historical data in a preset time interval adjacent to the current adjusting moment;
step S3: acquiring the number n of monotonous changes of the number of application instances;
step S4: judging whether the absolute value of the change rate of the request load quantity at the current adjusting moment and the request load quantity at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not;
step S5: if so, acquiring a target quantity of the current adjustment time according to the variation trend of the application example quantity respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time;
step S6: and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
Knative is a serverless computing platform used for providing user cloud computing. At least comprising at the client: service deployment users and normal users. The service deployment user deploys the application to the server side, and sets the target volume when deploying the application. The ordinary user can send a request to the server, the request of the ordinary user reaches a proxy container of Knative through a client and a gateway, and the request load quantity in the proxy container is represented by R. The Knative automatic expansion module is a circular stationing program, monitors the request load of the application and judges the request load which can be processed by the existing example. The period of this cycle monitoring can be preset, typically set to 60 minutes.
Step S1: and acquiring the requested load at the current adjusting moment.
And acquiring the request load amount of the current adjusting moment from the proxy container.
Step S2: and acquiring historical data in a preset time interval adjacent to the current adjusting moment.
The historical data includes at least: the historical adjustment time, the request load amount R, the target amount T and the application instance number P. Each historical adjustment time corresponds to a request load amount R, a target amount T and an application instance number P. The preset time interval is a statistical interval, and is usually preset to be one week or one month. The time range selected by the preset time interval is covered, which is close to the current adjusting moment, namely: the last adjustment time in the preset time interval is adjacent to the current adjustment time, and the relevant data of all historical adjustment times of the preset time interval before the last adjustment time are included. The number n of monotone changes of the number of application instances referred to below is obtained from the historical data statistics in the preset time interval. Fig. 2 shows a time axis relationship of the above-described history data with the current adjustment time. Wherein t is-NThe time in the history data which is farthest away from the current adjustment time. R-N，T-N，P-NIs given as-NIn response to each otherThe load amount of the requests, the target amount and the number of application examples.
Step S3: and acquiring the number n of monotonously changing application instance numbers.
Wherein n comprises n+And n-。n+And n-Are all integers greater than 1. n is+Representing the number of times of monotone increase of the number of application instances nearest to the current adjustment time in the historical data; n is-Indicating the number of monotonically decreasing application instance numbers in the historical data that are closest to the current adjustment time.
FIGS. 3 and 4 show n+，n-The statistical manner of (2). From t in FIG. 3-3～t-1The number of application examples is monotonously reduced twice, and n is obtained through statistics -2; from t-8 to t-5, the number of application examples is monotonically increased three times, and n is counted+3. The case of not being counted is shown in fig. 4, taking the number of application instances increased as an example: from t-9～t-6The time, the number of application instances is monotonically increased 3 times, but the 3 monotonic changes are not the closest to the current adjustment time, so n is not counted+Counting; from t-2～t-1Increased by 1 time, due to n+And n-Are all integers greater than 1, so this change is not counted in n+Counting; from t-5～t-3Is a monotonic change in the number of application instances that are closest to the current adjustment time, so in this schematic, n+＝2。
Step S4: and judging whether the absolute value of the change rate of the request load amount at the current adjusting moment and the request load amount at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not.
This step is for judging the requested load amount R at the current adjustment time0Relative to the adjacent adjustment time (previous adjustment time t)-1) Corresponding request load R-1Is within a preset rate-of-change threshold. Namely: judgment of
Whether it is true. Where a is a preset rate of change threshold, typically set at 1%. Here, only the amount of change is considered, and no increase or decrease is considered, so the absolute value of the equation is taken and compared with a preset change rate threshold. If the above formula is determined to be negative, step S41 is executed.
Step S41: and taking the target quantity of the adjustment time adjacent to the current adjustment time in the historical data as the target quantity of the current adjustment time. Namely T0＝T-1。
If the determination result of the above expression is true, the condition for adjusting the target value of the current adjustment time is satisfied, and the process continues to step S5.
Step S5: and obtaining the target quantity of the current adjusting time according to the change trend of the quantity of the application examples respectively corresponding to the adjusting time adjacent to the current adjusting time in the historical data from n adjusting times before the current adjusting time. The method specifically comprises the following steps:
step S51: if from the front n+And if the change trend from the adjustment time to the application instance number respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data is monotonically increased in sequence, decreasing the target amount of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target amount of the current adjustment time, wherein the minimum value of the target amount of the current adjustment time is 1.
Step S52: if from the front n-And if the change trend of the number of the application examples respectively corresponding to the adjustment time adjacent to the current adjustment time from the adjustment time to the historical data is in a monotone decreasing order, increasing the target quantity of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target quantity of the current adjustment time.
Step S53: and if the change trends of the number of the application examples respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from the previous n adjustment times are not unique, taking the target quantity of the adjustment time adjacent to the current adjustment time in the historical data as the target quantity of the current adjustment time.
FIG. 5 shows the situation set forth in step S51. In this figure, assume n +3. From t-1～t0And a step of executing target quantity adjustment when the absolute value of the change rate meeting the request load quantity is smaller than a preset change rate threshold value. At n+In the case of 3, from t-4～t-1The trend of the change of the application example is monotonous and is increased when the t is0Target amount of time T0Adjusted according to the following formula:
T0＝max(0.9T-1，1)
fig. 6 shows the case set forth in step S52. In this illustration, assume n -2. From t-1～t0And a step of executing target quantity adjustment when the absolute value of the change rate meeting the request load quantity is smaller than a preset change rate threshold value. In the case of n ═ 2, from t-3～t-1The application example changes in a monotonous decreasing trend, and the t is the time0Target amount of time T0Adjusted according to the following formula:
T0＝1.1T-1
fig. 7 shows the case set forth in step S53. In this illustration, assume that n+Is 3 and n-From t 2-1～t0And the absolute value of the change rate meeting the requirement of the load capacity is smaller than a preset change rate threshold value. However, from t-4～t-1The application instance variation trend is not monotonically increasing and is from t-3～t-1The application instance trend is not monotonically decreasing. Therefore, not for t0Target amount of time T0Make any adjustment, T0＝T-1。
Step S6: and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
Obtaining the target quantity T of the current adjusting moment0Then, according to the following formula:
obtaining the number of application instances at the current adjustment time specifically includes:
step S61: obtaining the application instance calculation value P at the current adjusting time by rounding the quotient of the requested load amount at the current adjusting time and the target amount at the current adjusting timec；
Step S62: limiting the application instance calculation value at the current adjusting time according to a preset instance upper limit and/or a preset instance lower limit to obtain an application instance limiting value P at the current adjusting timeL(ii) a Wherein the application instance limit value at the current adjustment time is between the instance upper limit and the instance lower limit;
step S63: executing expansion and adjustment on the number P of actually-operated application instances according to the application instance limit value at the current adjustment moment0。
In another embodiment, a method for scaling an application instance further comprises:
step S7: and storing the current adjusting time, the requested load capacity of the current adjusting time, the target capacity of the current adjusting time and the number of the application instances actually operated at the current adjusting time into the historical data for circularly executing the method.
Adjust the current time t0The requested load amount R at the current adjustment time0Target quantity T at the current adjustment time0The number of application instances P actually running at the current adjustment time0And storing the historical data for providing calculation basis when the method is circularly executed.
In another embodiment, as shown in fig. 8, a telescopic device of an application example includes: a request load amount acquisition module 10, a historical data acquisition module 20, a change frequency acquisition module 30, a change rate judgment module 40, a target amount acquisition module 50, and an application stretch adjustment module 60;
a request load amount obtaining module 10, configured to obtain a request load amount at a current adjustment time;
a historical data obtaining module 20, configured to obtain historical data in a preset time interval that is immediately adjacent to the current adjustment time;
a change number obtaining module 30, configured to obtain a number n of times that the number of application instances monotonically changes;
the change rate judging module 40 is configured to judge whether an absolute value of a change rate between a requested load amount at a current adjustment time and a requested load amount at an adjustment time adjacent to the current adjustment time in the historical data is smaller than a preset change rate threshold;
a target quantity obtaining module 50, configured to obtain a target quantity at the current adjustment time according to a variation trend of the number of application instances respectively corresponding to adjustment times adjacent to the current adjustment time in the historical data from n +1 adjustment times before the current adjustment time;
applying a telescoping adjustment module 60; and the method is used for telescopically adjusting the number of the application instances which actually run according to the request load amount at the current adjusting time and the target amount at the current adjusting time.
All the above-mentioned optional technical solutions can be combined arbitrarily to form the optional embodiments of the present invention, and are not described herein again.
Example one
One embodiment of the present application is described below in conjunction with fig. 1-4. A method of scaling an application instance, comprising:
knative is a serverless computing platform used for providing user cloud computing. At least comprising at the client: service deployment users and normal users. The service deployment user deploys the application to the server side, and sets the target volume when deploying the application. The ordinary user can send a request to the server, the request of the ordinary user reaches a proxy container of Knative through a client and a gateway, and the request load quantity in the proxy container is represented by R. The Knative automatic expansion module is a circular stationing program, monitors the request load of the application and judges the request load which can be processed by the existing example. The period of this cycle monitoring can be preset, typically set to 60 minutes.
Step S1: and acquiring the requested load at the current adjusting moment.
And acquiring the request load amount of the current adjusting moment from the proxy container.
Step S2: and acquiring historical data in a preset time interval adjacent to the current adjusting moment.
The historical data includes at least: the historical adjustment time, the request load amount R, the target amount T and the application instance number P. Each historical adjustment time corresponds to a request load amount R, a target amount T and an application instance number P. The preset time interval is a statistical interval, and is usually preset to be one week or one month. The time range selected by the preset time interval is covered, which is close to the current adjusting moment, namely: the last adjustment time in the preset time interval is adjacent to the current adjustment time, and the relevant data of all historical adjustment times of the preset time interval before the last adjustment time are included. The number n of monotone changes of the number of application instances referred to below is obtained from the historical data statistics in the preset time interval. Fig. 2 shows a time axis relationship of the above-described history data with the current adjustment time. Wherein t is-NThe time in the history data which is farthest away from the current adjustment time. R-N，T-N，P-NIs given as-NThe request load amount, the target amount and the application instance number at the corresponding moment.
Step S3: and acquiring the number n of monotonously changing application instance numbers.
Wherein n comprises n+And n-。n+And n-Are all integers greater than 1. n is+Representing the number of times of monotone increase of the number of application instances nearest to the current adjustment time in the historical data; n is-Indicating the number of monotonically decreasing numbers of application instances in the historical data that are closest to the current adjustment time.
FIGS. 3 and 4 show n+，n-The statistical manner of (2). From t in FIG. 3-3～t-1The number of application examples is monotonously reduced twice, and n is obtained through statistics -2; from t-8 to t-5, the number of application examples is monotonously increased three times, and n is counted+3. The case of not being counted is shown in fig. 4, taking the number of application instances increased as an example: from t-9～t-6At time, the number of application instances monotonically increases 3 times, but the 3 monotonic changes are not closest to the current adjustmentChange in time, so n is not counted+Counting; from t-2～t-1Increased by 1 time, due to n+And n-Are all integers greater than 1, so this change is not counted in n+Counting; from t-5～t-3Is a monotonic change in the number of application instances that are closest to the current adjustment time, so in this schematic, n+＝2。
Step S4: and judging whether the absolute value of the change rate of the request load amount at the current adjusting moment and the request load amount at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not.
This step is for judging the requested load amount R at the current adjustment time0Relative to the adjacent adjustment time (previous adjustment time t)-1) Corresponding request load amount R-1Is within a preset rate-of-change threshold. Namely: judgment of
Whether it is true. Where a is a preset rate of change threshold, typically set at 1%. Here, only the amount of change is considered, and no increase or decrease is considered, so the absolute value of the equation is taken and compared with a preset change rate threshold. If the above formula is determined to be negative, step S41 is executed.
Step S41: and taking the target quantity of the adjustment time adjacent to the current adjustment time in the historical data as the target quantity of the current adjustment time. Namely T0＝T-1。
Example two
Another embodiment of the present application is described below in conjunction with fig. 5. A method of scaling an application instance, comprising:
step S1: acquiring a request load amount at the current adjusting moment;
step S2: acquiring historical data in a preset time interval adjacent to the current adjusting moment;
step S3: acquiring the number n of monotone changes of the number of application instances;
step S4: judging whether the absolute value of the change rate of the request load quantity at the current adjusting moment and the request load quantity at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not;
the steps S1-S3 have been described in detail in the first embodiment, and are not described herein again.
Step S4: and judging whether the absolute value of the change rate of the request load amount at the current adjusting moment and the request load amount at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not.
This step is for judging the requested load amount R at the current adjustment time0Relative to the adjacent adjustment time (previous adjustment time t)-1) Corresponding request load R-1Is within a preset rate-of-change threshold. Namely: judgment of
Whether it is true. Where a is a preset rate of change threshold, typically set at 1%. Here, only the amount of change is considered, and no increase or decrease is considered, so the absolute value of the equation is taken and compared with a preset change rate threshold.
If the determination result of the above expression is true, the condition for adjusting the target value of the current adjustment time is satisfied, and the process continues to step S5.
Step S5: and obtaining the target quantity of the current adjusting time according to the change trend of the quantity of the application examples respectively corresponding to the adjusting time adjacent to the current adjusting time in the historical data from n adjusting times before the current adjusting time. The method specifically comprises the following steps:
step S51: if from the front n+And if the change trend from the adjustment time to the application instance number respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data is monotonically increased in sequence, decreasing the target amount of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target amount of the current adjustment time, wherein the minimum value of the target amount of the current adjustment time is 1.
FIG. 5 shows the result set forth in step S51The situation is. In this figure, assume n +3. From t-1～t0And a step of executing target quantity adjustment when the absolute value of the change rate meeting the request load quantity is smaller than a preset change rate threshold value. At n+In the case of 3, from t-4～t-1The application example changes in a monotonous increasing way, and the t is the time0Target amount of time T0Adjusted according to the following formula:
T0＝max(0.9T-1，1)
step S6: and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
Obtaining the target quantity T at the current adjustment time0Then, according to the following formula:
obtaining the number of application instances at the current adjustment time specifically includes:
step S61: obtaining the application instance calculation value P of the current adjusting time by rounding the quotient of the requested load amount of the current adjusting time and the target amount of the current adjusting timec；
Step S62: limiting the application instance calculation value at the current adjusting time according to a preset instance upper limit and/or a preset instance lower limit to obtain an application instance limiting value P at the current adjusting timeL(ii) a Wherein the application instance limit value at the current adjustment time is between the instance upper limit and the instance lower limit;
step S63: executing expansion and adjustment on the number P of actually-operated application instances according to the application instance limit value at the current adjustment moment0。
EXAMPLE III
Another embodiment of the present application is described below in conjunction with fig. 6. A method of scaling an application instance, comprising:
step S1: acquiring a request load amount at the current adjusting moment;
step S2: acquiring historical data in a preset time interval adjacent to the current adjusting moment;
step S3: acquiring the number n of monotonous changes of the number of application instances;
step S4: judging whether the absolute value of the change rate of the request load amount at the current adjustment moment and the request load amount at the adjustment moment adjacent to the current adjustment moment in the historical data is smaller than a preset change rate threshold value or not;
step S5: if so, acquiring a target quantity of the current adjustment time according to the variation trend of the application example quantity respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time;
step S6: and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
The steps S1-S4 and S6 are described in detail in the second embodiment, and are not described herein again.
Step S52: if from the front n-And if the change trend of the number of the application examples respectively corresponding to the adjustment time adjacent to the current adjustment time from the adjustment time to the historical data is in a monotone decreasing order, increasing the target quantity of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target quantity of the current adjustment time.
Fig. 6 shows the case set forth in step S52. In this illustration, assume n -2. From t-1～t0And a step of executing target quantity adjustment when the absolute value of the change rate meeting the request load quantity is smaller than a preset change rate threshold value. In the case where n-2 is selected from t-3～t-1The application example changes in a monotonous decreasing trend, and the t is the time0Target amount of time T0Adjusted according to the following formula:
T0＝1.1T-1
example four
Another embodiment of the present application is described below in conjunction with fig. 7. A method of scaling an application instance, comprising:
step S1: acquiring a request load amount at the current adjusting moment;
step S2: acquiring historical data in a preset time interval adjacent to the current adjusting moment;
step S3: acquiring the number n of monotone changes of the number of application instances;
step S4: judging whether the absolute value of the change rate of the request load amount at the current adjustment moment and the request load amount at the adjustment moment adjacent to the current adjustment moment in the historical data is smaller than a preset change rate threshold value or not;
step S5: if so, acquiring a target quantity of the current adjustment time according to the variation trend of the application example quantity respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time;
step S6: and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
The steps S1-S4 and S6 are described in detail in the second embodiment, and are not described herein again.
Fig. 7 shows the case set forth in step S53. In this illustration, assume n+Is 3 and n-From t 2-1～t0And the absolute value of the change rate meeting the requirement of the load capacity is smaller than a preset change rate threshold value. However, from t-4～t-1The application instance variation trend is not monotonically increasing and is from t-3～t-1The application instance variation trend is not monotonically decreasing. Therefore, not for t0Target amount of time T0Make any adjustment, T0＝T-1。
EXAMPLE five
In another embodiment of the present application, a method for scaling an application instance further comprises:
step S7: and storing the current adjusting time, the requested load capacity of the current adjusting time, the target capacity of the current adjusting time and the number of the application instances actually operated at the current adjusting time into the historical data for circularly executing the method.
Adjust the current time t0The requested load amount R at the current adjustment time0Target quantity T at the current adjustment time0The number of application instances P actually running at the current adjustment time0And storing the historical data for providing calculation basis when the method is circularly executed.
EXAMPLE six
Another embodiment of the present application is described below in conjunction with fig. 8. A retractor device according to an embodiment of the present invention comprises: a request load amount acquisition module 10, a historical data acquisition module 20, a change frequency acquisition module 30, a change rate judgment module 40, a target amount acquisition module 50, and an application stretch adjustment module 60;
a request load amount obtaining module 10, configured to obtain a request load amount at a current adjustment time;
a historical data obtaining module 20, configured to obtain historical data in a preset time interval that is immediately adjacent to the current adjustment time;
a change number obtaining module 30, configured to obtain a number n of times that the number of application instances monotonically changes;
the change rate judging module 40 is configured to judge whether an absolute value of a change rate between a requested load amount at a current adjustment time and a requested load amount at an adjustment time adjacent to the current adjustment time in the historical data is smaller than a preset change rate threshold;
a target quantity obtaining module 50, configured to obtain a target quantity at the current adjustment time according to a variation trend of the number of application instances respectively corresponding to adjustment times adjacent to the current adjustment time in the historical data from n adjustment times before the current adjustment time;
applying a telescoping adjustment module 60; and the method is used for telescopically adjusting the number of the application instances which actually run according to the request load amount at the current adjusting time and the target amount at the current adjusting time.
In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program loaded on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from the memory, or installed from the ROM. The computer program, when executed by an external processor, performs the above-described functions defined in the methods of embodiments of the present application.
It should be noted that the computer readable medium of the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the server; or may exist separately and not be assembled into the server. The computer readable medium carries one or more programs which, when executed by the server, cause the server to: when the peripheral mode of the terminal is detected to be not activated, acquiring a frame rate of an application on the terminal; when the frame rate meets the screen information condition, judging whether a user is acquiring the screen information of the terminal; and controlling the screen to enter an immediate dimming mode in response to the judgment result that the user does not acquire the screen information of the terminal.
Computer program code for carrying out operations for embodiments of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement without inventive effort.
The technical solutions provided by the present application are introduced in detail, and specific examples are applied in the description to explain the principles and embodiments of the present application, and the descriptions of the above examples are only used to help understanding the method and the core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific embodiments and the application range may be changed. In view of the above, the description should not be taken as limiting the application.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (10)
1. A method for scaling application instances, which is used for automatically scaling and adjusting the number of application instances actually running at a preset adjusting moment, and is characterized by comprising the following steps:
acquiring a request load amount at the current adjusting moment;
acquiring historical data in a preset time interval adjacent to the current adjusting moment; wherein the historical data includes at least: the method comprises the steps that at historical adjustment time, request load capacity, target capacity and application instance number are obtained, and at each historical adjustment time, at least the request load capacity, the target capacity and the application instance number corresponding to the historical adjustment time exist;
acquiring the number n of monotonous changes of the number of application instances; wherein n comprises: number n of monotonically increasing application instance numbers+And the number n of monotonically decreasing application instance numbers-(ii) a And the number of the first and second electrodes,n+，n-are all integers greater than 1;
judging whether the absolute value of the change rate of the request load amount at the current adjustment moment and the request load amount at the adjustment moment adjacent to the current adjustment moment in the historical data is smaller than a preset change rate threshold value or not;
if so, acquiring a target quantity of the current adjustment time according to the change trend of the quantity of the application examples respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from n +1 adjustment times before the current adjustment time;
and the number of the application examples which actually run is telescopically adjusted according to the requested load amount at the current adjusting moment and the target amount at the current adjusting moment.
2. The method of claim 1, further comprising:
and storing the current adjusting time, the requested load capacity of the current adjusting time, the target capacity of the current adjusting time and the number of the application instances actually operated at the current adjusting time into the historical data for circularly executing the method.
3. The method of claim 1, further comprising:
and if the absolute value of the change rate of the request load amount at the current adjustment time and the request load amount at the adjustment time adjacent to the current adjustment time in the historical data is judged to be larger than a preset change rate threshold, taking the target amount of the adjustment time adjacent to the current adjustment time in the historical data as the target amount of the current adjustment time.
4. The method according to claim 1, wherein the obtaining the target amount of the current adjustment time according to the trend of the number of the application instances respectively corresponding to the adjustment time adjacent to the current adjustment time in the history data from n +1 adjustment times before the current adjustment time comprises:
if from the front n+And if the change trends of the application instance numbers respectively corresponding to the adjustment time adjacent to the current adjustment time in the history data from +1 adjustment time to the adjustment time adjacent to the current adjustment time are in sequential monotonic increase, the target quantity of the adjustment time adjacent to the current adjustment time in the history data is monotonically decreased by ten percent to be used as the target quantity of the current adjustment time, and the minimum value of the target quantity of the current adjustment time is 1.
5. The method according to claim 4, wherein the obtaining the target amount of the current adjustment time according to the trend of the number of the application instances respectively corresponding to the adjustment time adjacent to the current adjustment time in the history data from n +1 adjustment times before the current adjustment time further comprises:
if from the front n-And if the change trends of the application instance numbers respectively corresponding to the adjustment time adjacent to the current adjustment time in the historical data from the +1 adjustment time to the adjustment time adjacent to the current adjustment time are in a monotone decreasing order, increasing the target quantity of the adjustment time adjacent to the current adjustment time in the historical data by ten percent to be used as the target quantity of the current adjustment time.
6. The method according to claim 4, wherein the obtaining the target amount of the current adjustment time according to the trend of the number of the application instances respectively corresponding to the adjustment time adjacent to the current adjustment time in the history data from n +1 adjustment times before the current adjustment time further comprises:
and if the change trends of the number of the application examples respectively corresponding to the adjustment time adjacent to the current adjustment time from the previous n +1 adjustment times to the historical data are not unique, taking the target quantity of the adjustment time adjacent to the current adjustment time in the historical data as the target quantity of the current adjustment time.
7. The method according to claim 1, wherein the scaling and adjusting the number of the application instances actually running according to the requested load amount at the current adjustment time and the target amount at the current adjustment time comprises:
rounding the quotient of the requested load amount at the current adjusting time and the target amount at the current adjusting time to obtain an application instance calculation value at the current adjusting time;
limiting the application instance calculation value at the current adjusting time according to a preset instance upper limit and/or a preset instance lower limit to obtain an application instance limiting value at the current adjusting time; wherein the application instance limit value at the current adjustment time is between the instance upper limit and the instance lower limit;
and executing expansion and adjustment on the number of the actually-operated application instances according to the application instance limit value at the current adjustment moment.
8. The method according to claim 1, wherein the obtaining the number n of times that the number of application instances changes monotonically comprises:
counting, in the history data, the number n of monotonically increasing times of the number of application instances nearest to the current adjustment time+And the number n of monotonous reductions of the number of application instances nearest to the current adjustment instant-。
9. The method according to claim 1, wherein the predetermined time interval is a statistical period.
10. A telescopic device for use in an application example, the device comprising: the device comprises a request load capacity acquisition module, a historical data acquisition module, a change frequency acquisition module, a change rate judgment module, a target quantity acquisition module and an application expansion adjustment module;
the request load quantity acquisition module is used for acquiring the request load quantity at the current adjustment moment;
the historical data acquisition module is used for acquiring historical data in a preset time interval adjacent to the current adjustment moment;
the change times obtaining module is used for obtaining the times n of monotonous change of the number of the application instances;
the change rate judging module is used for judging whether the absolute value of the change rate between the request load amount at the current adjusting moment and the request load amount at the adjusting moment adjacent to the current adjusting moment in the historical data is smaller than a preset change rate threshold value or not;
the target quantity obtaining module is used for obtaining the target quantity of the current adjusting time according to the change trend of the number of the application examples respectively corresponding to the adjusting time adjacent to the current adjusting time from n adjusting times before the current adjusting time to the historical data;
the application expansion and contraction adjusting module; and the method is used for telescopically adjusting the number of the application instances which actually run according to the request load amount at the current adjusting time and the target amount at the current adjusting time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111639021.4A CN114443283B (en) | 2021-12-29 | 2021-12-29 | Method and device for stretching application instance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111639021.4A CN114443283B (en) | 2021-12-29 | 2021-12-29 | Method and device for stretching application instance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114443283A true CN114443283A (en) | 2022-05-06 |
| CN114443283B CN114443283B (en) | 2023-11-17 |
Family
ID=81366206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111639021.4A Active CN114443283B (en) | 2021-12-29 | 2021-12-29 | Method and device for stretching application instance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114443283B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130055241A1 (en) * | 2011-08-22 | 2013-02-28 | International Business Machines Corporation | Rapid Provisioning of Virtual Machines Based on Multi-Dimensional User Request Patterns in a Cloud |
| CN103916396A (en) * | 2014-04-10 | 2014-07-09 | 电子科技大学 | Method for automatic expansion of application examples of cloud platform based on load self-adaption |
| CN109918194A (en) * | 2019-01-16 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Intelligent dilatation capacity reduction method, device, computer equipment and storage medium |
| CN112698908A (en) * | 2019-10-23 | 2021-04-23 | 阿里巴巴集团控股有限公司 | Cloud computing resource expansion processing method and device, storage medium and processor |
| CN112711506A (en) * | 2019-10-24 | 2021-04-27 | 阿里巴巴集团控股有限公司 | Method and device for adjusting application instances in resource group, storage medium and processor |
| CN113518000A (en) * | 2021-05-12 | 2021-10-19 | 北京奇艺世纪科技有限公司 | Method and device for adjusting number of instances of online service and electronic equipment |
-
2021
- 2021-12-29 CN CN202111639021.4A patent/CN114443283B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130055241A1 (en) * | 2011-08-22 | 2013-02-28 | International Business Machines Corporation | Rapid Provisioning of Virtual Machines Based on Multi-Dimensional User Request Patterns in a Cloud |
| CN103916396A (en) * | 2014-04-10 | 2014-07-09 | 电子科技大学 | Method for automatic expansion of application examples of cloud platform based on load self-adaption |
| CN109918194A (en) * | 2019-01-16 | 2019-06-21 | 深圳壹账通智能科技有限公司 | Intelligent dilatation capacity reduction method, device, computer equipment and storage medium |
| CN112698908A (en) * | 2019-10-23 | 2021-04-23 | 阿里巴巴集团控股有限公司 | Cloud computing resource expansion processing method and device, storage medium and processor |
| CN112711506A (en) * | 2019-10-24 | 2021-04-27 | 阿里巴巴集团控股有限公司 | Method and device for adjusting application instances in resource group, storage medium and processor |
| CN113518000A (en) * | 2021-05-12 | 2021-10-19 | 北京奇艺世纪科技有限公司 | Method and device for adjusting number of instances of online service and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114443283B (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444009B (en) | Resource allocation method and device based on deep reinforcement learning | |
| CN109542512B (en) | Data processing method, device and storage medium | |
| US20200218456A1 (en) | Application Management Method, Storage Medium, and Electronic Apparatus | |
| CN111176820A (en) | Deep neural network-based edge computing task allocation method and device | |
| CN113515382B (en) | Cloud resource allocation method and device, electronic equipment and storage medium | |
| CN107483292B (en) | Dynamic monitoring method for cloud platform | |
| WO2016184048A1 (en) | Method and device for frequency management for multi-core processor cpu | |
| CN112783614A (en) | Object processing method, device, equipment, storage medium and program product | |
| CN110276404B (en) | Model training method, device and storage medium | |
| CN112822044B (en) | Distributed cluster deployment method and device, electronic equipment and readable storage medium | |
| CN114443283A (en) | Application instance scaling method and device | |
| CN110347477B (en) | Service self-adaptive deployment method and device in cloud environment | |
| CN108399031B (en) | Method and device for determining interface layout mode | |
| CN116302477A (en) | Dynamic allocation method and system of performance resources and related components | |
| CN113791863B (en) | Virtual container-based power Internet of things proxy resource scheduling method and related equipment | |
| CN114884969A (en) | Cluster instance quantity regulation and control method, device, terminal and storage medium | |
| CN115205157A (en) | Image processing method and system, electronic device, and storage medium | |
| CN114168439A (en) | Pressure measurement control method and device for service in cluster, storage medium and terminal | |
| CN113918344A (en) | Resource demand allocation method, device, equipment and computer readable medium | |
| CN115329924A (en) | Neural network structure determination method and device and related products | |
| CN113408601B (en) | Model generation method, electronic device and storage medium | |
| CN112102821B (en) | Data processing method, device, system and medium applied to electronic equipment | |
| KR102676784B1 (en) | Method and system for evaluating service performance perceived by user | |
| US20230351144A1 (en) | Instruction Set Architecture for Implementing Linear Activation Functions in Neural Networks | |
| CN117917606A (en) | Offshore wind turbine grid-connected strategy control method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |