CN109491773B

CN109491773B - Compensation task scheduling method, device and system based on time slicing

Info

Publication number: CN109491773B
Application number: CN201811142806.9A
Authority: CN
Inventors: 任卫东
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2018-09-28
Filing date: 2018-09-28
Publication date: 2021-07-27
Anticipated expiration: 2038-09-28
Also published as: CN109491773A

Abstract

One or more embodiments of the present specification disclose a compensation task scheduling method, apparatus, and system based on time slicing, where a first operation node receives a scheduling instruction sent by a scheduling node; determining one or more second operation nodes corresponding to a time slicing strategy according to the time slicing strategy in a scheduling instruction; distributing each time slice in the time slice strategy to the corresponding second operation node, so that each second operation node salvages the mark information of the service flow to be recovered in a corresponding quantity according to the salvage strategy of the time slice distributed by the second operation node, divides the mark information of the service flow to be recovered into N groups according to the distribution strategy of the time slice distributed by the second operation node, and distributes the mark information of each group of service flow to be recovered to the corresponding third operation node for recovery operation.

Description

Compensation task scheduling method, device and system based on time slicing

Technical Field

The present application relates to the field of internet technologies, and in particular, to a method, an apparatus, and a system for scheduling a compensation task based on time slicing.

Background

During the business processing, the generated pipeline data can be persisted in the database. The system can perform corresponding service flow processing operation based on the current flow data.

In the process of processing the service flow, if the processing interruption is caused by retriable exception due to system failure and the like, the application system can perform recovery processing on the current service flow at the interruption occurrence position.

The current recovery processing mode is generally to recover the service flow by using a compensation scheduling algorithm. The current compensation scheduling algorithm is based on time sequencing to recover in sequence, so that the recovery time is long and the efficiency is low.

Disclosure of Invention

The present specification provides a compensation task scheduling method, device and system based on time slicing, so as to solve or partially solve the technical problem that the existing recovery mode is low in efficiency.

To solve the above technical problem, the present specification provides a compensation task scheduling method based on time slicing

A method, the method comprising:

a first operation node receives a scheduling instruction sent by a scheduling node; the scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

determining one or more second operation nodes corresponding to the time slicing strategy according to the time slicing strategy;

distributing each time slice in the time slice strategy to the corresponding second operation node, so that each time slice is correspondingly distributed to one second operation node; each time slice carries a respective fishing strategy and a respective distribution strategy, so that each second operation node salvages the mark information of the service flow to be recovered in a corresponding quantity according to the fishing strategy of the time slice allocated to the second operation node, the mark information of the service flow to be recovered is divided into N groups according to the distribution strategy of the time slice allocated to the second operation node, and the mark information of each group of the service flow to be recovered is allocated to a corresponding third operation node for recovery operation, wherein N is a positive integer.

The present specification discloses a receiving module for receiving a scheduling instruction sent by a scheduling node; the scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

the determining module is used for determining one or more second operation nodes corresponding to the time slicing strategy according to the time slicing strategy;

the first distribution module is used for distributing each time slice in the time slice strategy to the corresponding second operation node, so that each time slice is correspondingly distributed to one second operation node; each time slice carries a respective fishing strategy and a respective distribution strategy, so that each second operation node salvages the mark information of the service flow to be recovered in a corresponding quantity according to the fishing strategy of the time slice allocated to the second operation node, the mark information of the service flow to be recovered is divided into N groups according to the distribution strategy of the time slice allocated to the second operation node, and the mark information of each group of the service flow to be recovered is allocated to a corresponding third operation node for recovery operation, wherein N is a positive integer.

The present specification discloses that a second operational node receives a time-slice allocated by a first operational node according to a time-slice policy; the number of the second operation nodes is determined by the time slicing strategy, the time slicing strategy is sent to the first operation node by a scheduling node, the time slicing strategy comprises one or more time slices, and each time slice corresponds to one second operation node by the time slicing strategy; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered; fishing out the mark information of the corresponding quantity of the service flow to be recovered according to the fishing strategy of the allocated time slices;

and dividing the mark information of the service flow to be recovered into N groups according to the distributed time slicing distribution strategy, and distributing the mark information of each group of service flow to be recovered to a corresponding third running node for recovery operation, wherein N is a positive integer.

This specification discloses a compensation task scheduling device based on time slicing, including:

a receiving unit, configured to receive a time slice allocated by a first operating node according to a time slice policy; the number of the second operation nodes is determined by the time slicing strategy, the time slicing strategy is sent to the first operation node by a scheduling node, the time slicing strategy comprises one or more time slices, and each time slice corresponds to one second operation node by the time slicing strategy; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

the fishing unit is used for fishing the mark information of the corresponding quantity of the service flow to be recovered according to the fishing strategy of the allocated time slices;

and the first allocation unit is used for dividing the mark information of the service flow to be recovered into N groups according to the distributed time-slicing distribution strategy, and allocating the mark information of each group of service flow to be recovered to a corresponding third running node for recovery operation, wherein N is a positive integer.

This specification discloses a compensation task scheduling system based on time slicing, including:

the scheduling node is used for sending a scheduling instruction; the scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

a first operation node for receiving a scheduling instruction sent by the scheduling node;

the first operation node is used for determining one or more second operation nodes corresponding to the time slicing strategy according to the time slicing strategy;

the first operation node is configured to allocate each time slice in the time slice policy to the corresponding second operation node, so that each time slice is allocated to one second operation node; each time slice carries a respective fishing strategy and a respective distribution strategy;

the second running node is used for fishing the mark information of the service flow to be recovered in a corresponding quantity according to the fishing strategy of the time slices allocated by the second running node, dividing the mark information of the service flow to be recovered into N groups according to the distribution strategy of the time slices allocated by the second running node, and allocating the mark information of each group of service flow to be recovered to a corresponding third running node, wherein N is a positive integer;

and the third running node is used for carrying out recovery operation on the corresponding service flow to be recovered.

The present specification discloses a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.

The present specification discloses a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the program.

Through one or more technical schemes of this description, this description has following beneficial effect or advantage:

one or more embodiments of the present specification disclose a compensation task scheduling method, apparatus, and system based on time slicing. The first operational node receives a scheduling instruction sent by the scheduling node. The scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices. The one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered, and one or more second operation nodes corresponding to the time slice strategy are determined according to the time slice strategy. And then distributing each time slice in the time slice strategy to the corresponding second operation node, so that each time slice is correspondingly distributed to one second operation node. That is to say, in this embodiment, the recovery time interval of the service flow to be recovered is sliced, and then each time slice is divided into different second operation nodes to perform parallel processing, so that the recovery time of the service flow can be shortened, and the recovery efficiency can be improved. Furthermore, each second operation node fetches the corresponding amount of the mark information of the service flow to be restored according to the self-allocated time slice fetching strategy, divides the mark information of the service flow to be restored into N groups according to the self-allocated time slice distribution strategy, and allocates the mark information of each group of the service flow to be restored to the corresponding third operation node for restoration operation, so that the fetching operation and the restoration operation are processed in parallel, thereby further shortening the restoration time of the service flow and improving the restoration efficiency.

The above description is only an outline of the technical solution of the present specification, and the embodiments of the present specification are described below in order to make the technical means of the present specification more clearly understood, and the present specification and other objects, features, and advantages of the present specification can be more clearly understood.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the specification. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 illustrates a relational construct diagram of a scheduling node and a run node according to one embodiment of the present description;

FIG. 2 is a diagram illustrating an implementation process of a time-slicing based compensation task scheduling method performed by a first running node according to one embodiment of the present specification;

FIG. 3 is a diagram illustrating an implementation process of a time-slicing based compensation task scheduling method performed by a second running node according to an embodiment of the present specification;

FIG. 4 is a schematic diagram of a device for time-slicing based compensation task scheduling executed by a running node according to an embodiment of the present specification;

FIG. 5 is another diagram illustrating an apparatus for time-slicing based compensatory task scheduling that is executed by a running node according to one embodiment of the present specification;

FIG. 6 shows a schematic diagram of a computer device according to one embodiment of the present description; .

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The embodiment of the specification provides a compensation task scheduling method, a compensation task scheduling device and a compensation task scheduling system based on time slicing, and the method, the compensation task scheduling device and the compensation task scheduling system are used for solving the technical problem that the recovery efficiency of service flow in the prior art is low.

As an alternative embodiment, the system for compensating task scheduling based on time slicing in this embodiment includes the following nodes: scheduling nodes and operating nodes.

The number of the scheduling nodes is one or more, each scheduling node has a respective scheduling period, the scheduling period of each scheduling node is configured by an operator, and the period length of each scheduling node can be dynamically adjusted by the operator according to actual conditions.

In addition, each scheduling node involves three parameters: time slicing strategy, fishing strategy and distributing strategy.

The time slicing strategy involves two parameters: one or more time slices, and a number of divisions of the time slices. The time slicing strategy comprises one or more time slices, and the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered.

The service flow to be recovered is the service flow which is abnormal in the execution process and needs to be recovered by the operation node, and is stored in the database.

Each service flow to be recovered has respective abnormal occurrence time. The exception occurrence time refers to a failure occurrence time of the traffic flow to be restored.

The recovery time interval of the service flow to be recovered refers to a time period specified by a system or an operator and used for recovering the service flow to be recovered, and can be adjusted according to actual conditions.

For example, the abnormal occurrence time of the to-be-recovered traffic flow a, the to-be-recovered traffic flow B, and the to-be-recovered traffic flow C is 17:00, 17:10, and 17:20 of the day, respectively. Assuming that the time period for recovering the to-be-recovered service flow specified by the system is 9:00-18:00 on the day, that is, the abnormal service flow occurs in the time period of 9:00-18:00 on the day, the to-be-recovered service flow a, the to-be-recovered service flow B, and the to-be-recovered service flow C are included therein.

The one or more time slices in this embodiment are obtained by slicing the recovery time interval of the service flow to be recovered, and the one or more time slices are used to represent the time interval for recovering the service flow to be recovered.

For example, slicing the recovery time interval 9:00-18:00 of the traffic pipeline to be recovered may be divided into one or more time slices.

Further, the resulting time slices may be sliced again.

Therefore, the time slice included in the time slice policy actually includes a first time slice, and the first time slice divides the recovery time interval of the to-be-recovered traffic flow into one of more than two time intervals.

Further, the time slice in the time slice policy further includes a second time slice, where the second time slice is a partial time interval extracted from the first time slice.

In this embodiment, the time slicing has at least the following two expressions:

the first way of representation is by the time difference with the current time. For example, if the system needs to recover the service flow in the last two days (the recovery time interval of the service flow to be recovered), the recovery time interval in the last two days may be divided into the following time slices:

time slice 1 is [ -2 days, -1 day), that is, the current time slice only recovers the service flow to be recovered from the last 1 to 2 days.

Time slice 2 is [ -1 day, -1 hour), that is, the current time slice only recovers the latest 1 hour to 1 day of the service flow to be recovered.

Time slice 3 is [ -1 hour, -5 minutes), i.e. the current time slice only recovers the last 5 minutes to 1 hour of the traffic flow to be recovered.

Time slice 4 is [ -5 minutes, -5 seconds), i.e. the current time slice only recovers the last 5 to 5 minutes of the traffic flow to be recovered.

The time slicing is to divide the recovery time interval of the to-be-recovered traffic stream [ -2 days, -5 seconds) into one of 4 time intervals. So these 4 time intervals can be considered as first time slices.

And since the range of time slice 1 is [ -2 days, -1 day), this range is actually relatively large. The process of recovering the to-be-recovered traffic flow may be recovered from-2 days in time sequence, or may be recovered from two ends to the middle, and so on, although there are other recovery manners. Therefore, the service flow to be recovered in a certain or several time segments in the time slice 1 needs to wait until the service flow to be recovered in other time segments is recovered, and the waiting time is very long. Therefore, a certain time segment or several time segments can be extracted from the time slice 1 and used as the second time slice. Time slice 5, e.g., extracted from time slice 1, assumed to be [ -1.7 days, -1.5 days); time slice 6, assumed to be [ -1.5 days, -1.4 days).

Time-slice 5 and time-slice 6 are both second time-slices.

By executing the implementation process of this embodiment with the second time slice and the first time slice, the service flow to be recovered in some time periods (the second time slice) waiting for too long recovery time in the first time slice and the service flow to be recovered in the first time slice can be recovered together.

Of course, in this embodiment, one or more second time slices may be divided from the first time slice according to system judgment, random, artificial regulation, actual situations, and the like, and the dividing number of the second time slices is not limited.

Of course, it can be known from the above description that the second time slice actually overlaps the first time slice, and therefore, the to-be-recovered traffic flow that needs to be recovered in the second time slice may also be the to-be-recovered traffic flow that needs to be recovered in the first time slice. In order to avoid the waste of system resources caused by recovering the same service flow to be recovered, after the service flow to be recovered in any time slice is recovered, marking operation is performed on the service flow to be recovered, which has performed recovery operation, so that if other operation nodes see the mark, the service flow to be recovered, which has performed recovery operation, cannot be recovered again, and system resources can be saved.

As can be seen from this example, the embodiment cuts the fishing time into 4 time slices according to the time difference value from the current time. The time periods represented by each time slice are different in scope.

The second way is to realize this by specifying the real time interval. For example, if the system needs to recover the traffic flow in the recovery time interval 2018.09.10.00:00:00-2018.09.11.10:49:05, the time can be divided into the following time slices:

the time slice 1 is [2018.09.10.00:00:00, 2018.09.11.00:00:00), that is, the current time slice only recovers the business flowing water to be recovered from 2018.09.10 00 min/night 00 o 'clock 00 s to 2018.09.11 00 min/night 00 o' clock 00 s.

Time slice 2 is [2018.09.11.0:0:0, 2018.09.11.09:44:00), i.e. the current time slice only recovers 2018.09.11 business flow to be recovered from 00 min/night 00 min/00 s to 2018.09.11 am 9 o' clock 44 min/00 s.

Time slice 3 is [2018.09.11.09:44:00, 2018.09.11.10:44:00), i.e. the current time slice only recovers the to-be-recovered traffic stream of 2018.09.11 am at 9 am 44 min 00 s to 2018.09.11 am at 10 am 44 min 00 s.

Time slice 4 is [2018.09.11.10:44:00, 2018.09.11.10:49:05), i.e. the current time slice only recovers the to-be-recovered traffic stream of 2018.09.11 am 44 min 00 s to 2018.09.11 am 10 pm 49 min 05 s.

As can be seen from this example, the present embodiment divides the fishing time into 4 time slices according to the real time interval, and each time slice has a different time division range.

The number of divisions of a time slice.

The division number of the time slices is related to the fishing time of the service flow to be recovered, and the existing recovery mode is to recover in sequence according to the time sequence. However, in this embodiment, a recovery time interval of the to-be-recovered service flow is defined, and then the recovery time interval is sliced, so that the number of divisions of a time slice is provided. For example, the system divides the recovery time interval of 2018.09.10.00:00:00-2018.09.11.10:49:05 into 4 time slices.

The above describes two parameters involved in the time slicing strategy.

Based on the two parameters, the time slicing strategy at least comprises the following strategies:

and determining the strategy of the second operation nodes with the corresponding number according to the division number of the time slices.

And allocating each time slice to a corresponding second operation node, so that each time slice is correspondingly allocated with one second operation node.

For each time slice, there is a respective fishing strategy and distribution strategy.

The fishing strategy of each time slice in the time slice strategies specifically comprises the following steps: and fishing the mark information of the service flow to be recovered according to the expected total number of the fishing flow in each time slice.

In each time slice, the total number of fishing streams is expected, such as time slice 4: total amount of fished water of [2018.09.11.10:44:00, 2018.09.11.10:49:05) is estimated to be 50. Time slicing 3: total amount of fished water of [2018.09.11.09:44:00, 2018.09.11.10:44:00) is expected to be 100, and so on.

The distribution policy of each time slice in the time slice policies is specifically: and grouping the mark information of the service flow to be recovered according to the expected grouping number corresponding to the total fishing flow in each time slice.

In each time slice, besides the total amount of the fishing flow, the number of packets corresponding to the total amount of the fishing flow is also set. For example, time slice 4: total number of fetched flow of [2018.09.11.10:44:00, 2018.09.11.10:49:05) is predicted to be 50, and the number of packets corresponding to the total number of fetched flow is 5, that is, after 50 pieces of flag information of the traffic flow to be recovered are fetched, the 50 pieces of flag information of the traffic flow to be recovered are divided into 5 groups. The grouping can be evenly distributed, randomly distributed or grouped according to a certain rule. If the distribution is even, the mark information of the service flow to be recovered in each group is 10.

The running node, which is an instance of the application system, is a real traffic pipeline handler that receives the relevant parameters of the scheduling node and then performs a specific recovery action based on the relevant parameters.

In this embodiment, the operation node includes three types of nodes: the system comprises a first operation node, a second operation node and a third operation node.

The first running node is mainly used for distributing the second running node according to the time slicing strategy. The second running node is mainly used for fishing the mark information of the service flow to be recovered, and the third running node is mainly used for executing specific recovery operation.

Referring to fig. 1, a relationship map of a scheduling node and a running node in the present embodiment is shown.

In this embodiment, taking 1 scheduling node, 1 first operating node, 2 operating nodes, and 5 third operating nodes in a cycle as an example, a structure formed by the nodes is a stub structure.

The above is an explanation of the system architecture and terms that need to be used in the present embodiment.

In one or more embodiments of the present specification, a time-slicing based compensation task scheduling method is disclosed, which is applied to a first application node side. Referring to fig. 2, the method comprises the steps of:

in step 21, the first operating node receives a scheduling instruction sent by the scheduling node.

Wherein the scheduling instruction is sent by the scheduling node. Each scheduling node has its own scheduling period, and when the scheduling node reaches the scheduling period, it randomly initiates a scheduling instruction to one running node, and in order to distinguish it from the following running nodes, this embodiment refers to the running node that the scheduling node randomly selects and sends the scheduling instruction as a first running node, so the step of this embodiment is that the first running node receives the scheduling instruction sent by the scheduling node.

The scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices and the division number of the time slices.

The one or more time slices are obtained by slicing a recovery time interval of the service flow to be recovered.

And each time slice has a respective corresponding fishing strategy and distribution strategy.

And step 22, determining one or more second operation nodes corresponding to the time slicing strategy according to the time slicing strategy.

In a specific implementation process, two parameters are involved in the time slicing strategy: one or more time slices, and a division number of the time slices.

Thus, the time slicing strategy comprises at least the following strategies:

and determining the strategy of the second operation nodes with the corresponding number according to the division number of the time slices. Furthermore, according to the time slicing policy, determining one or more second operation nodes corresponding to the time slicing policy includes: and determining the corresponding number of the second operation nodes according to the division number of the time slices in the time slicing strategy. If the number of divisions of the time slice is 5, the number of the determined second operation nodes is also 5. One time slice corresponds to one second operational node.

In addition, the time slicing policy may further include: and allocating each time slice to a corresponding second operation node, so that each time slice is correspondingly allocated with one second operation node.

The number of time slices divided may be one or more, and the processing manner of 1 time slice is different from the processing manner of more than two time slices.

If the time slicing policy includes one time slice, that is, the number of time slices divided is only 1, the time slices are processed by the first running node itself, and if there are more than two time slices, the time slices are allocated to the corresponding second running node for processing.

In a specific implementation process, if a time slice is included in the time slice policy, the first operation node is determined as the second operation node according to the time slice.

If the scheduling instruction only carries a plurality of time slices (more than two time slices), the first operating node determines a corresponding number of second operating nodes according to the dividing number of the time slices. For example, if the number of divisions of a time slice is 50, 50 second operation nodes are determined, so that one time slice corresponds to one second operation node.

Step 23, allocating each time slice in the time slice policy to the corresponding second operating node, so that each time slice is allocated to one second operating node correspondingly.

Each time slice carries a respective fishing strategy and a respective distribution strategy, so that each second operation node salvages the mark information of the service flow to be recovered in a corresponding quantity according to the fishing strategy of the time slice allocated to the second operation node, the mark information of the service flow to be recovered is divided into N groups according to the distribution strategy of the time slice allocated to the second operation node, and the mark information of each group of the service flow to be recovered is allocated to a corresponding third operation node for recovery operation, wherein N is a positive integer.

Wherein the number of second operational nodes is determined by the number of divisions of the time slice. If two time slices are provided, the two times are distributed to respective second operation nodes, and the related strategies (the fishing strategy and the distribution strategy) of each time slice are also sent to the respective corresponding second operation nodes.

In this embodiment, one of the second operation nodes a is taken as an example, and it is assumed that the time slice 2 allocated to the second operation node a is [ -1 day, -1 hour), that is, the current time slice only catches the latest traffic flow to be recovered from 1 hour to 1 day. The expected total number of fishing pipelines is 100, and the number of packets is 5. The second operational node would, according to time slicing 2: -1 day, -1 hour), and 100 pieces of mark information of the service flow to be restored with the planned processing time in the range are obtained. Assuming equal distribution, the flag information of the 100 to-be-recovered traffic streams is divided into 5 groups, and each group has 20 flag information of the to-be-recovered traffic streams. And then distributing the mark information of each group of service flow to be recovered to a corresponding third running node according to a distribution strategy, wherein the number of the third running nodes corresponds to the number of the groups. Assuming that the number of the third operating nodes is 5, the number of the third operating nodes is determined to be 5, and each group corresponds to one third operating node. Suppose that, for one of the third running nodes a1, after receiving the flag information of its corresponding 20 pieces of traffic to be restored, the corresponding restoration operation is performed. Specifically, the third running node a1 may drag for the corresponding service flow to be restored according to the flag information of the service flow to be restored.

The second running node and the third running node execute the specific fishing implementation process.

And one second operation node is correspondingly allocated to each time slice. And if only 1 time slice exists, determining the first running node as the second running node, and performing subsequent fishing work by the first running node. In this embodiment, the description is made in the perspective of the first operating node.

Obtaining the one time slice;

fishing out the mark information of the corresponding number of the service flow to be recovered based on the fishing-out strategy of the time slice;

and dividing the mark information of the service flow to be recovered into N groups according to the distribution strategy of the time slice, and distributing the mark information of each group of service flow to be recovered to a corresponding third running node for recovery operation.

Further, if the number of packets included in the distribution policy is one group. And determining the first running node as a third running node, and then executing the corresponding recovery operation by the first running node.

And dividing the mark information of the service flow to be recovered into a group according to the distribution strategy of the time slice.

And performing corresponding recovery operation based on the mark information of the group of service pipelines to be recovered.

The above is a compensation task scheduling method based on time slicing on the first operation node side.

Based on the same inventive concept, one or more embodiments of the present specification introduce a time-slicing based compensation task scheduling method from the perspective of the second operating node.

Referring to fig. 3, the method of the present embodiment includes the steps of:

step 31, the second operating node receives the time slice allocated by the first operating node according to the time slice policy.

The number of the second operation nodes is determined by the first operation node according to a time slicing strategy, and the time slicing strategy is sent to the first operation node by the scheduling node. In a specific implementation process, the time slicing policy includes the number of time slicing divisions, so that the number of the second running nodes is determined by the number of time slicing divisions in the time slicing policy.

The time slicing policy comprises one or more time slices, so that each time slice corresponds to one second operation node after the time slices are determined according to the number of the time slices.

The one or more time slices are obtained by slicing a recovery time interval of the service flow to be recovered. The specific division has already been described in the above embodiments, and therefore is not described herein again.

And step 32, fishing the corresponding amount of mark information of the service flow to be recovered according to the fishing strategy of the allocated time slices.

In a specific implementation process, the fishing strategy for each time slice in the time slice strategies specifically is as follows: and fishing the mark information of the service flow to be recovered according to the expected total number of the fishing flow in each time slice.

Therefore, in the process of fishing the mark information of the service flow to be recovered, the corresponding amount of the mark information of the service flow to be recovered is fished according to the estimated total fishing flow number in the allocated time slices, and the fished abnormal generation time of the service flow to be recovered is in the allocated time slices.

And step 33, dividing the mark information of the service flow to be recovered into N groups according to the distribution strategy of the allocated time slices, and allocating the mark information of each group of service flow to be recovered to a corresponding third running node for recovery operation.

Wherein N is a positive integer.

Wherein the distribution policy of each time slice in the time slice policies is specifically: and grouping the mark information of the service flow to be recovered according to the expected grouping number corresponding to the total fishing flow in each time slice.

In the grouping process, the flag information of the service flow to be recovered can be divided into one or more groups, and the processing modes of one group and the groups are different.

If the distribution strategy of the distributed time slices contains a group of groups, determining the group number of the groups; the second running node is determined to be the third running node. The recovery operation is actually performed directly by the second running node. The specific implementation process is as follows: dividing the mark information of the service flow to be recovered into a group according to the distributed time-slicing distribution strategy; and the second running node directly performs recovery operation based on the mark information of the group of service pipelines to be recovered.

And if the number of the mark information of the service flow to be recovered is divided into two or more groups, distributing each group to a third running node according to a distribution strategy, and performing recovery operation by the third running node.

As an alternative embodiment, a problem of service recovery interruption or delay caused by that one or more service pipelines to be recovered cannot be recovered for a long time may also occur. In order to solve the problem, in this embodiment, the service to be restored that cannot be restored for a long time is put into the next time slice for processing, and the specific implementation process is as follows: and if the recovery time of the recovery operation of M service running water to be recovered in the ith group of the N groups exceeds a preset time threshold, distributing the identification information of the M service running water to be recovered to a third running node corresponding to the (i + 1) th group, and enabling the third running node corresponding to the (i + 1) th group to perform the recovery operation, wherein i is a positive integer and i is less than N, and M is a positive integer.

As an optional embodiment, after the third running node performs the recovery operation on the to-be-recovered service flow, the marking operation is also performed on the to-be-recovered service flow that has performed the recovery operation, so that if other third running nodes see the mark, the recovery operation is not performed on the to-be-recovered service flow that has performed the recovery operation again, and thus system resources can be saved.

As an optional embodiment, after performing the fishing operation of the marker information of the service flow to be recovered, the second running node also performs a marking operation on the marker information of the service flow to be recovered that has been fished, and if other second running nodes see the marking, the second running node does not perform the fishing again. Of course, the mark of the retrieved mark information of the service flow to be restored is different from the mark of the service flow to be restored which is subjected to the restoration operation.

The above is an implementation process of a time-slicing based compensation task scheduling method disclosed in one or more embodiments in this specification.

One or more embodiments of the present specification introduce a time-slicing based compensatory task scheduling device based on the same inventive concept as the previous embodiments.

Referring to fig. 4, the apparatus includes:

a receiving module 41, configured to receive a scheduling instruction sent by a scheduling node; the scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

a determining module 42, configured to determine, according to the time slicing policy, one or more second operation nodes corresponding to the time slicing policy;

a first allocating module 43, configured to allocate each time slice in the time slice policy to the corresponding second running node, so that each time slice is allocated to one second running node; each time slice carries a respective fishing strategy and a respective distribution strategy, so that each second operation node salvages the mark information of the service flow to be recovered in a corresponding quantity according to the fishing strategy of the time slice allocated to the second operation node, the mark information of the service flow to be recovered is divided into N groups according to the distribution strategy of the time slice allocated to the second operation node, and the mark information of each group of the service flow to be recovered is allocated to a corresponding third operation node for recovery operation, wherein N is a positive integer.

As an alternative embodiment, the time-slicing policy contains the number of divisions of a time slice;

the determining module 42 is specifically configured to determine the corresponding number of second operation nodes according to the number of time slices divided in the time slicing policy.

As an optional embodiment, the fishing policy for each time slice in the time slice policies specifically is: a strategy of fishing the mark information of the service flow to be recovered according to the predicted total fishing flow in each time slice;

As an alternative embodiment, if the time slicing policy includes a time slice;

the determining module 42 is specifically configured to determine the first operating node as the second operating node according to the time slice.

As an alternative embodiment, the first distribution module 43 specifically includes:

an obtaining module for obtaining the one time slice;

the fishing module is used for fishing the mark information of the service flow to be recovered in a corresponding quantity based on the fishing strategy of the time slice;

and the second distribution module is used for dividing the mark information of the service flow to be recovered into N groups according to the distribution strategy of the time slice, and distributing the mark information of each group of service flow to be recovered to a corresponding third running node for recovery operation.

As an alternative embodiment, if the number of packets included in the distribution policy is one group;

the first distribution module 43 specifically includes:

a third allocation module, configured to divide the flag information of the service flow to be recovered into a group according to the distribution policy of the time slice;

and the recovery module is used for carrying out corresponding recovery operation based on the mark information of the group of service flow to be recovered.

As an optional embodiment, the time slicing in the time slicing policy includes a first time slicing, where the first time slicing divides a recovery time interval of the to-be-recovered traffic flow into one of more than two time intervals.

As an optional embodiment, the time slices in the time slice policy further include a second time slice, where the second time slice is a partial time interval extracted from the first time slice.

Based on the same inventive concept as in the foregoing embodiments, an embodiment of this specification further provides a time-slicing-based compensation task scheduling device, with reference to fig. 5, including:

a receiving unit 51, configured to receive a time slice allocated by a first operating node according to a time slice policy; the number of the second operation nodes is determined by the time slicing strategy, the time slicing strategy is sent to the first operation node by a scheduling node, the time slicing strategy comprises one or more time slices, and each time slice corresponds to one second operation node by the time slicing strategy; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

the fishing unit 52 is configured to fish the corresponding amount of flag information of the service flow to be recovered according to the fishing strategy of the allocated time slice;

the first allocating unit 53 is configured to divide the flag information of the service flow to be recovered into N groups according to the allocated distribution policy of the time slice, and allocate the flag information of each group of service flow to be recovered to a corresponding third running node to perform a recovery operation, where N is a positive integer.

As an alternative embodiment, the number of second running nodes is determined by the number of divisions of a time-slice in the time-slicing policy.

As an optional embodiment, the fishing unit 52 is specifically configured to fish the corresponding amount of flag information of the service flow to be recovered according to the expected total number of the fishing flow in the allocated time slice, and the abnormal occurrence time of the fished service flow to be recovered is in the allocated time slice.

As an alternative embodiment, if the distribution policy of the allocated time slice contains a group of packet numbers;

the first distributing unit 53 specifically includes:

a determining unit, configured to determine the second operation node as the third operation node;

the second distributing unit is used for dividing the mark information of the service flow to be recovered into a group according to the distributing strategy of the distributed time slices;

and the recovery unit is used for directly performing recovery operation based on the mark information of the group of service flow to be recovered.

As an alternative embodiment, the apparatus further comprises:

and a third allocating unit, configured to allocate, if recovery time of recovery operation of M service flows to be recovered in an ith group of the N groups exceeds a preset time threshold, identification information of the M service flows to be recovered to a third running node corresponding to an (i + 1) th group, so that the third running node corresponding to the (i + 1) th group performs recovery operation, where i is a positive integer and i < N, and M is a positive integer.

Based on the same inventive concept, the following embodiments disclose a compensated task scheduling system based on time slicing, comprising:

Since the flow of implementing each node has been described in detail in one or more embodiments, it is not described herein again.

Based on the same inventive concept as in the previous embodiments, the present specification further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of any of the methods described above.

Based on the same inventive concept as in the previous embodiments, the embodiments of the present specification further provide a computer apparatus, as shown in fig. 6, including a memory 604, a processor 602, and a computer program stored on the memory 604 and executable on the processor 602, wherein the processor 602 executes the computer program to implement the steps of any of the methods described above.

Where in fig. 3 a bus architecture (represented by bus 600) is shown, bus 600 may include any number of interconnected buses and bridges, and bus 600 links together various circuits including one or more processors, represented by processor 602, and memory, represented by memory 604. The bus 600 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 605 provides an interface between the bus 600 and the receiver 601 and transmitter 603. The receiver 601 and the transmitter 603 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 602 is responsible for managing the bus 600 and general processing, and the memory 604 may be used for storing data used by the processor 602 in performing operations.

Through one or more embodiments of the present description, the present description has the following advantages or advantages:

The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, this description is not intended for any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present specification and that specific languages are described above to disclose the best modes of the specification.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the present description may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the specification, various features of the specification are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the present specification as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this specification.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the description and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of this description may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components of a gateway, proxy server, system in accordance with embodiments of the present description. The present description may also be embodied as an apparatus or device program (e.g., computer program and computer program product) for performing a portion or all of the methods described herein. Such programs implementing the description may be stored on a computer-readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the specification, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The description may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A method for time-slicing based compensatory task scheduling, the method comprising:

2. The method of claim 1, wherein the time-slicing policy comprises a partition number of time slices;

the determining one or more second operation nodes corresponding to the time slicing policy according to the time slicing policy includes:

and determining the corresponding number of the second operation nodes according to the division number of the time slices in the time slicing strategy.

3. The method of claim 1, wherein the first and second light sources are selected from the group consisting of a red light source, a green light source, and a blue light source,

the fishing strategy of each time slice in the time slice strategies specifically comprises the following steps: a strategy of fishing the mark information of the service flow to be recovered according to the predicted total fishing flow in each time slice;

4. The method of claim 1, wherein if the time-slicing strategy comprises a time-slice;

the determining, according to the time slicing policy, one or more second operation nodes corresponding to the time slicing policy specifically includes:

and determining the first running node as the second running node according to the time slice.

5. The method of claim 4, wherein each time slice in the time-slicing policy is assigned to a respective corresponding second operational node such that each time slice is assigned to one of the second operational nodes; each time slice carries a respective fishing strategy and a respective distribution strategy; enabling each second operation node to salvage the mark information of the service flow to be recovered in a corresponding quantity according to the salvage strategy of the time slices allocated by the second operation node, dividing the mark information of the service flow to be recovered into N groups according to the distribution strategy of the time slices allocated by the second operation node, and allocating the mark information of each group of service flow to be recovered to a corresponding third operation node for recovery operation, wherein the recovery operation specifically comprises the following steps:

obtaining the one time slice;

6. The method of claim 5, wherein if the number of packets included in the distribution policy is one group;

the dividing the mark information of the service flow to be restored into N groups according to the distribution strategy of the time slice, and allocating the mark information of each group of service flow to be restored to a corresponding third running node to perform a corresponding restoration operation, specifically including:

dividing the mark information of the service flow to be recovered into a group according to the distribution strategy of the time slice;

7. The method of claim 1, wherein time-slicing in the time-slicing policy comprises first time-slicing that divides a recovery time interval of the to-be-recovered traffic flow into one of more than two time intervals.

8. The method of claim 7, wherein a time slice in the time-slicing policy further comprises a second time slice, the second time slice being a partial time interval extracted from the first time slice.

9. A time-slicing based compensatory task scheduler comprising:

a receiving module, configured to receive a scheduling instruction sent by a scheduling node; the scheduling instruction carries a time slicing strategy, and the time slicing strategy comprises one or more time slices; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

10. The apparatus of claim 9, the time-slicing policy contains a partition number of time slices;

the determining module is specifically configured to determine the corresponding number of second operation nodes according to the number of time slices divided in the time slicing policy.

11. The apparatus as set forth in claim 9, wherein,

12. The apparatus of claim 9, wherein if the time-slicing strategy comprises a time-slice;

the determining module is specifically configured to determine, according to the time slice, the first operating node as the second operating node.

13. The apparatus according to claim 12, wherein the first allocation module specifically includes:

an obtaining module for obtaining the one time slice;

14. The apparatus of claim 13, if the number of packets included in the distribution policy is one group;

the first allocation module specifically includes:

15. The apparatus of claim 9, wherein time-slicing in the time-slicing policy comprises first time-slicing that divides a recovery time interval of the to-be-recovered traffic flow into one of more than two time intervals.

16. The apparatus of claim 15, wherein a time slice in the time-slicing policy further comprises a second time slice, the second time slice being a partial time interval extracted from the first time slice.

17. A method for time-slicing based compensatory task scheduling, the method comprising:

the second operation node receives the time slices distributed by the first operation node according to the time slice strategy; the number of the second operation nodes is determined by the time slicing strategy, the time slicing strategy is sent to the first operation node by a scheduling node, the time slicing strategy comprises one or more time slices, and each time slice corresponds to one second operation node by the time slicing strategy; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered; fishing out the mark information of the corresponding quantity of the service flow to be recovered according to the fishing strategy of the allocated time slices;

18. The method of claim 17, the number of second operational nodes is determined by a number of divisions of a time-slice in the time-slicing policy.

19. The method of claim 18, wherein each time-slice fishing policy in the time-slice policies is specifically: a strategy of fishing the mark information of the service flow to be recovered according to the predicted total fishing flow in each time slice;

20. The method according to claim 19, wherein the fetching of the flag information of the corresponding number of the to-be-recovered traffic streams according to the allocated time slice fetching policy specifically includes:

and fishing out the mark information of the corresponding number of the service flow to be recovered according to the estimated total fishing flow number in the allocated time slices, wherein the abnormal generation time of the fished service flow to be recovered is in the allocated time slices.

21. The method of claim 17, wherein if the distribution policy for the allocated time slices contains a group number of packets;

the dividing the mark information of the service flow to be restored into N groups according to the distributed time-slicing distribution strategy, and distributing the mark information of each group of service flow to be restored to a corresponding third running node for restoration operation, specifically including:

determining the second operational node as the third operational node;

dividing the mark information of the service flow to be recovered into a group according to the distributed time-slicing distribution strategy;

and directly performing recovery operation based on the mark information of a group of service pipelines to be recovered.

22. The method according to claim 17, wherein after the flag information of the traffic flow to be restored is divided into N groups according to the distribution policy of the allocated time slices, and the flag information of each group of traffic flow to be restored is allocated to the corresponding third running node for performing the restoration operation, the method further comprises:

and if the recovery time of the recovery operation of M service running water to be recovered in the ith group of the N groups exceeds a preset time threshold, distributing the identification information of the M service running water to be recovered to a third running node corresponding to the (i + 1) th group, and enabling the third running node corresponding to the (i + 1) th group to perform the recovery operation, wherein i is a positive integer and i is less than N, and M is a positive integer.

23. A time-slicing based compensatory task scheduler comprising:

a receiving unit, configured to receive a time slice allocated by a first operating node according to a time slice policy; the number of the second operation nodes is determined by the time slicing strategy, the time slicing strategy is sent to the first operation node by the scheduling node, the time slicing strategy comprises one or more time slices, and each time slice corresponds to one second operation node by the time slicing strategy; the one or more time slices are obtained by slicing the recovery time interval of the service flow to be recovered;

24. The apparatus of claim 23, the number of second operational nodes determined by a number of divisions of a time-slice in the time-slicing policy.

25. The apparatus of claim 24, wherein each time-sliced fishing policy in the time-slicing policies is specifically: a strategy of fishing the mark information of the service flow to be recovered according to the predicted total fishing flow in each time slice;

26. The apparatus according to claim 25, wherein the fetching unit is specifically configured to fetch a corresponding amount of flag information of the to-be-recovered traffic flow according to an expected total number of the fetching traffic flows in the allocated time slice, and an exception generating time of the fetched to-be-recovered traffic flow is in the allocated time slice.

27. The apparatus of claim 23, if the distribution policy for the allocated time slices contains a set number of packets;

the first distribution unit specifically includes:

28. The apparatus of claim 23, the apparatus further comprising:

29. A time-slicing based compensatory task scheduling system, comprising:

30. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.

31. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 1 to 8 when executing the program.