CN110381159B - Task processing method and system - Google Patents

Task processing method and system Download PDF

Info

Publication number
CN110381159B
CN110381159B CN201910684012.3A CN201910684012A CN110381159B CN 110381159 B CN110381159 B CN 110381159B CN 201910684012 A CN201910684012 A CN 201910684012A CN 110381159 B CN110381159 B CN 110381159B
Authority
CN
China
Prior art keywords
available
standby
list
standby device
resource
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.)
Active
Application number
CN201910684012.3A
Other languages
Chinese (zh)
Other versions
CN110381159A (en
Inventor
程筱彪
徐雷
贾宝军
杨双仕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN201910684012.3A priority Critical patent/CN110381159B/en
Publication of CN110381159A publication Critical patent/CN110381159A/en
Application granted granted Critical
Publication of CN110381159B publication Critical patent/CN110381159B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
    • H04L67/63—Routing a service request depending on the request content or context

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Hardware Redundancy (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present disclosure provides a task processing method, including: for each edge node, when the load of the specific resource of the edge node is judged to reach a preset threshold value and a new task with specific resource requirements sent to the edge node is received, acquiring the specific resource requirements of the new task and a standby equipment list corresponding to the edge node, wherein the standby equipment list at least comprises equipment numbers of each standby equipment in a plurality of standby equipment corresponding to the edge node and available resource data of each standby equipment; determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list; sending the new task to the determined standby equipment; and receiving the task processing result returned by the determined standby equipment, and sending the task processing result to the edge node. The disclosure also provides a task processing system.

Description

Task processing method and system
Technical Field
The disclosed embodiments relate to the field of communications technologies, and in particular, to a task processing method and system.
Background
Edge computing refers to an open platform integrating network, computing, storage and application core capabilities at one side close to an object or a data source to provide nearest-end services nearby.
In the edge calculation, aiming at the problem of insufficient resources of the edge node, the prior art generally simply solves the problem of capacity expansion of hardware resources, but is often limited by various conditions of the edge calculation, and cannot realize large-scale increase of the hardware resources.
Disclosure of Invention
The embodiments of the present disclosure are directed to at least one of the technical problems in the prior art, and provide a task processing method and system.
In a first aspect, an embodiment of the present disclosure provides a task processing method, where the task processing method includes:
for each edge node, when the load of the specific resource of the edge node is judged to reach a preset threshold value and a new task with specific resource requirements sent to the edge node is received, acquiring the specific resource requirements of the new task and a standby equipment list corresponding to the edge node, wherein the standby equipment list at least comprises equipment numbers of each standby equipment in a plurality of standby equipment corresponding to the edge node and available resource data of each standby equipment;
determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list;
sending the new task to the determined standby equipment;
and receiving a task processing result returned by the determined standby equipment, and sending the task processing result to the edge node.
In some embodiments, the determining, from the standby device list, a standby device for processing the new task according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list includes:
according to the specific resource requirement of the new task and the available resource data of each standby device, determining the standby devices of which the available resource data can meet the specific resource requirement of the new task from the standby device list, and generating an available standby device list;
a standby device for processing the new task is determined from the list of available standby devices.
In some embodiments, the available resource data includes available computing resource data, available storage resource data, and available network resource data;
if the specific resource is a computing resource and the specific resource requirement of the new task includes a computing resource requirement, determining, from the standby device list, a standby device whose available resource data can satisfy the specific resource requirement of the new task according to the specific resource requirement of the new task and available resource data of each standby device, and generating an available standby device list, including:
according to the computing resource requirements of the new task and the available resource data of each standby device, extracting the available computing resource data and the available network resource data of each standby device from the standby device list to generate a first available resource list, wherein the first available resource list comprises the device number of each standby device, the corresponding available computing resource data and the corresponding available network resource data;
removing the standby equipment of which the available computing resource data do not meet the computing resource requirement of the new task in the first available resource list to obtain a new first available resource list;
and generating the available standby equipment list according to the new first available resource list, wherein the available standby equipment list is the new first available resource list.
In some embodiments, said determining a standby device from said list of available standby devices for processing said new task comprises:
for each standby equipment in the available standby equipment list, carrying out normalization processing on the available computing resource data of the standby equipment according to the available computing resource data of each standby equipment in the available standby equipment list to obtain a computing resource normalization value corresponding to the available computing resource data of the standby equipment;
for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device;
generating a first score value corresponding to each standby device in the available standby device list according to a preset first score model, a computing resource normalization value corresponding to available computing resource data of the standby device and a network resource normalization value corresponding to available network resource data of the standby device;
and determining the standby equipment with the highest first score value as the standby equipment for processing the new task according to the first score value corresponding to each standby equipment in the available standby equipment list.
In some embodiments, the preset first scoring model comprises: first scoring value formula: pi＝k1*Ai+k2*Bi；
Wherein, PiA first score value A corresponding to the ith standby device in the available standby device listiA computing resource normalization value corresponding to available computing resource data representing an ith standby device in the list of available standby devices, BiA network resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list1Representing the weight value, k, corresponding to the normalized value of the computing resource2Representing the weight value, k, corresponding to the normalized value of the network resource1+k21, and k1Greater than k2。
In some embodiments, the available resource data includes available computing resource data, available storage resource data, and available network resource data;
if the specific resource is a storage resource and the specific resource requirement of the new task includes a storage resource requirement, determining, from the standby device list, a standby device whose available resource data can satisfy the specific resource requirement of the new task according to the specific resource requirement of the new task and available resource data of each standby device, and generating an available standby device list, including:
according to the storage resource requirement of the new task and the available resource data of each standby device, extracting the available storage resource data and the available network resource data of each standby device from the standby device list to generate a second available resource list, wherein the second available resource list comprises the device number of each standby device, the corresponding available storage resource data and the corresponding available network resource data;
removing the standby equipment of which the available storage resource data in the second available resource list does not meet the storage resource requirement of the new task to obtain a new second available resource list;
and generating the available standby equipment list according to the new second available resource list, wherein the available standby equipment list is the new second available resource list.
In some embodiments, said determining a standby device from said list of available standby devices for processing said new task comprises:
for each standby device in the available standby device list, performing normalization processing on the available storage resource data of the standby device according to the available storage resource data of each standby device in the available standby device list to obtain a storage resource normalization value corresponding to the available storage resource data of the standby device;
for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device;
generating a second score value corresponding to the standby equipment according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby equipment and a network resource normalization value corresponding to the available network resource data of the standby equipment for each standby equipment in the available standby equipment list;
and determining the standby equipment with the highest second score value as the standby equipment for processing the new task according to the second score value corresponding to each standby equipment in the available standby equipment list.
In some embodiments, the preset second scoring model comprises: second scoring value formula: qi＝k3*Ci+k2*Bi；
Wherein Q isiA second score value, C, representing the corresponding ith standby device in the list of available standby devicesiA storage resource normalization value, B, corresponding to available storage resource data representing the ith standby device in the available standby device listiA network resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list3Representing the weight value, k, corresponding to the normalized value of the storage resource2Representing the weight value, k, corresponding to the normalized value of the network resource3+k21, and k3Greater than k2。
In a second aspect, an embodiment of the present disclosure provides a task processing system, including:
the edge cloud management platform is used for judging whether the load of the specific resource of each edge node reaches a preset threshold value or not and judging whether a new task with specific resource requirements is received or not, wherein the new task is sent to the edge node;
the device screening module is used for acquiring a standby device list corresponding to each edge node when the edge cloud management platform judges that the load of the specific resource of the edge node reaches a preset threshold value and a new task with specific resource requirements is received, wherein the standby device list comprises the device number of each standby device in a plurality of standby devices corresponding to the edge node and available resource data of each standby device; determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list;
the network control module is used for sending the new task to the determined standby equipment; and receiving a task processing result returned by the determined standby equipment, and sending the task processing result to the edge node.
In some embodiments, the device screening module is specifically configured to determine, according to the specific resource requirement of the new task and available resource data of each standby device, a standby device whose available resource data can meet the specific resource requirement of the new task from the standby device list, and generate an available standby device list; a standby device for processing the new task is determined from the list of available standby devices.
In some embodiments, the available resource data includes available computing resource data, available storage resource data, and available network resource data;
if the specific resource is a computing resource and the specific resource requirement of the new task includes a computing resource requirement, the device screening module is specifically configured to extract available computing resource data and available network resource data of each standby device from the standby device list according to the computing resource requirement of the new task and the available resource data of each standby device, and generate a first available resource list, where the first available resource list includes a device number of each standby device, corresponding available computing resource data, and corresponding available network resource data; removing the standby equipment of which the available computing resource data do not meet the computing resource requirement of the new task in the first available resource list to obtain a new first available resource list; and generating the available standby equipment list according to the new first available resource list, wherein the available standby equipment list is the new first available resource list.
In some embodiments, the device screening module is specifically configured to, for each standby device in the available standby device list, perform normalization processing on available computing resource data of the standby device according to the available computing resource data of each standby device in the available standby device list, to obtain a computing resource normalization value corresponding to the available computing resource data of the standby device; for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device; generating a first score value corresponding to each standby device in the available standby device list according to a preset first score model, a computing resource normalization value corresponding to available computing resource data of the standby device and a network resource normalization value corresponding to available network resource data of the standby device; and determining the standby equipment with the highest first score value as the standby equipment for processing the new task according to the first score value corresponding to each standby equipment in the available standby equipment list.
In some embodiments, the available resource data includes available computing resource data, available storage resource data, and available network resource data;
if the specific resource is a storage resource and the specific resource requirement of the new task includes a storage resource requirement, the device screening module is specifically configured to extract available storage resource data and available network resource data of each standby device from the standby device list according to the storage resource requirement of the new task and the available resource data of each standby device, and generate a second available resource list, where the second available resource list includes a device number of each standby device, corresponding available storage resource data, and corresponding available network resource data; removing the standby equipment of which the available storage resource data in the second available resource list does not meet the storage resource requirement of the new task to obtain a new second available resource list; and generating the available standby equipment list according to the new second available resource list, wherein the available standby equipment list is the new second available resource list.
In some embodiments, the device screening module is specifically configured to, for each standby device in the available standby device list, perform normalization processing on available storage resource data of the standby device according to the available storage resource data of each standby device in the available standby device list, to obtain a storage resource normalization value corresponding to the available storage resource data of the standby device; for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device; generating a second score value corresponding to the standby equipment according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby equipment and a network resource normalization value corresponding to the available network resource data of the standby equipment for each standby equipment in the available standby equipment list; and determining the standby equipment with the highest second score value as the standby equipment for processing the new task according to the second score value corresponding to each standby equipment in the available standby equipment list.
According to the task processing method and system provided by the embodiment of the disclosure, for each edge node, when the load of the specific resource of the edge node is judged to reach the preset threshold value and a new task with a specific resource requirement is received, the new task is forwarded to a standby device which is corresponding to the edge node and can be used for processing the new task, on one hand, the resource utilization rate of the standby device can be effectively improved, the resource waste of the standby device is avoided, and on the other hand, the load of the edge node in busy hours can be effectively reduced.
Drawings
Fig. 1 is a flowchart of a task processing method provided in an embodiment of the present disclosure;
FIG. 2 is a flow chart of one embodiment of step 12 in an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating an embodiment of step 121 in an embodiment of the present disclosure;
FIG. 4 is a flow chart of another embodiment of step 121 in an embodiment of the present disclosure;
FIG. 5 is a flowchart illustrating one embodiment of step 122 in an embodiment of the present disclosure;
FIG. 6 is a flow chart illustrating another embodiment of step 122 in an embodiment of the present disclosure;
FIG. 7 is a flowchart of another task processing method provided by an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a task processing system according to an embodiment of the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present disclosure, the following describes the task processing method and system provided by the present disclosure in detail with reference to the accompanying drawings.
Fig. 1 is a flowchart of a task processing method according to an embodiment of the present disclosure, and as shown in fig. 1, the task processing method includes:
step 11, for each edge node, when it is determined that the load of the specific resource of the edge node reaches a preset threshold and a new task with a specific resource requirement sent to the edge node is received, acquiring the specific resource requirement of the new task and a standby device list corresponding to the edge node.
The standby device list at least includes the device number of each standby device in the plurality of standby devices corresponding to the edge node and the available resource data of each standby device.
In embodiments of the present disclosure, resources may include, but are not limited to: computing resources (e.g., CPU, memory), storage resources (e.g., disk), and network resources (e.g., network bandwidth). In an embodiment of the present disclosure, the available resource data for each standby device includes available computing resource data, available storage resource data, and available network resource data.
In the embodiment of the present disclosure, the task processing method provided by the embodiment of the present disclosure may be performed by a task processing system, the system may be implemented by software and/or hardware, and the system may be integrated in a server. The embodiment of the present disclosure does not specifically limit the specific implementation form of the task processing system.
In the embodiment of the disclosure, the task processing system comprises an edge cloud management platform, an equipment screening module and a network control module.
In the embodiment of the present disclosure, the standby device may be an intelligent hardware device, for example, the intelligent hardware device is an intelligent gateway, an intelligent sound, an intelligent Wifi, or the like. Enterprises or operators and the like can provide a certain resource sharing reward mechanism to encourage individual users to share partial resources (such as computing resources, storage resources and network resources) of intelligent hardware equipment meeting the requirements of the individual users, and the enterprises or operators can use the intelligent hardware equipment as standby equipment of edge nodes deployed by the enterprises or operators and give the individual users certain benefits in the ordering of edge services according to the factors such as the capacity of the resources shared by the individual users and the sharing time length.
After determining the intelligent hardware devices (standby devices) shared by the individual users, the edge cloud management platform may number all the deployed edge nodes and all the intelligent hardware devices (standby devices) shared by the users respectively to obtain the node numbers of the edge nodes and the device numbers of the standby devices, and simultaneously match the edge nodes with the intelligent hardware devices (standby devices) that can be scheduled, and establish a one-to-many resource database, where the resource database includes a correspondence relationship between the node numbers of the edge nodes and the device numbers of the intelligent hardware devices, and where the device number of each intelligent hardware device (standby device) is correspondingly provided with a plurality of attribute fields for recording device information such as available resource data, IP addresses, and ports of the intelligent hardware devices (standby devices).
Table 1 shows a correspondence relationship between a node number of one edge node and device numbers of multiple backup devices, taking an edge node with a node number ID11 as an example, as shown in table 1, in a resource database, multiple backup devices corresponding to the edge node are provided, the device numbers of the multiple backup devices are ID21, ID22, …, and ID2n, an attribute field 1 is used to record available computing resource data of the backup device, an attribute field 2 is used to record available storage resource data of the backup device, an attribute field 3 is used to record available network resource data of the backup device, an attribute field 4 is used to record an IP address of the backup device, and an attribute field 5 is used to record a port of the backup device.
TABLE 1
Figure BDA0002145714280000091
Figure BDA0002145714280000101
In the embodiment of the present disclosure, the edge cloud management platform may monitor the load of the specific resource of each edge node, and monitor the new task sent to each edge node. In step 11, for each edge node, when the edge cloud management platform determines that the load of the specific resource of the edge node reaches the preset threshold and receives a new task with a specific resource requirement sent to the edge node, the edge cloud management platform calculates the specific resource requirement of the new task and calls a device number list corresponding to the edge node from a preset resource database, where the device number list includes device numbers of a plurality of standby devices corresponding to the edge node, and sends the device number list corresponding to the edge node and the specific resource requirement of the new task to the device screening module.
And after receiving the equipment number list corresponding to the edge node and the specific resource requirement of the new task, the equipment screening module acquires the standby equipment list corresponding to the edge node from a preset resource database according to the equipment numbers of the standby equipment in the equipment number list.
In the embodiment of the present disclosure, the specific resource may be a computing resource or a storage resource, and the specific resource requirement of the new task includes a computing resource requirement or a storage resource requirement.
In this disclosure, if the specific resource is a computing resource, the load of the specific resource may be a utilization rate of the computing resource (e.g., a CPU utilization rate, a memory utilization rate), and the available computing resource data of the standby device may be a remaining amount of the computing resource shared by the standby device, where the remaining amount of the computing resource may be calculated according to a total amount of the computing resource and the utilization rate; if the load of the specific resource is a storage resource, the load of the specific resource may be a utilization rate of the storage resource (e.g., a disk utilization rate), and the available storage resource data of the standby device may be a remaining amount of the storage resource shared by the standby device, where the remaining amount of the storage resource may be calculated according to the total amount of the storage resource and the utilization rate. In embodiments of the present disclosure, the available network resource data of the standby device may be a rate of the network bandwidth shared by the standby device.
In the embodiment of the present disclosure, the preset threshold may be set to 80%, and specifically, the preset threshold may be set according to actual needs, which is not limited in the embodiment of the present disclosure.
Table 2 shows a list of the standby devices corresponding to the edge node, and as shown in table 2, the device numbers of the standby devices corresponding to the edge node are ID21, ID22, …, and ID2n, respectively, and the available computing resource data of the standby devices corresponding to the edge node are a1、a2、…、anThe available storage resource data of each standby device corresponding to the edge node is c1、c2、…、cnThe available network resource data of each standby device corresponding to the edge node is b1、b2、…、bnAnd so on.
TABLE 2
Figure BDA0002145714280000111
And step 12, determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list.
In step 12, after acquiring the list of standby devices corresponding to the edge node and the specific resource requirement of the new task, the device screening module determines a standby device for processing the new task from the list of standby devices according to the specific resource requirement of the new task and the available resource data of each standby device in the list of standby devices.
Fig. 2 is a flow chart of a specific implementation of step 12 in an embodiment of the present disclosure, as shown in fig. 2, in some embodiments, step 12 includes:
and step 121, according to the specific resource requirement of the new task and the available resource data of each standby device, determining the standby device of which the available resource data can meet the specific resource requirement of the new task from the standby device list, and generating an available standby device list.
In step 121, the device screening module determines the standby devices whose available resource data can satisfy the specific resource requirement of the new task according to the specific resource requirement of the new task and the available resource data of each standby device, and generates an available standby device list. The available standby device list includes the device number of the standby device whose available resource data can satisfy the specific resource requirement of the new task and the corresponding available resource data.
Fig. 3 is a flowchart of a specific implementation manner of step 121 in an embodiment of the present disclosure, as shown in fig. 3, in some embodiments, the specific resource is a computing resource, the specific resource requirement of the new task includes a computing resource requirement, and step 121 includes:
step 1211a, extracting the available computing resource data and the available network resource data of each standby device from the standby device list according to the computing resource requirement of the new task and the available resource data of each standby device, and generating a first available resource list.
In step 1211a, the device screening module extracts the available computing resource data and the available network resource data of each standby device from the standby device list according to the computing resource requirements of the new task and the available resource data of each standby device, and generates a first available resource list.
The first available resource list includes a device number of each standby device, corresponding available computing resource data, and corresponding available network resource data.
Table 3 shows a first available resource list, which includes the device number (ID21, ID22, …, ID2n) of each spare device, the available computing resource data (a) of each spare device, as shown in Table 31、a2、…、an) And available network resource data of each standby device (b)1、b2、…、bn)。
TABLE 3
Figure BDA0002145714280000121
Step 1211b, removing the standby devices in the first available resource list, of which the available computing resource data does not meet the computing resource requirement of the new task, to obtain a new first available resource list.
In step 1211b, for each standby device in the first available resource list, if the device screening module determines that the available computing resource data of the standby device cannot meet the computing resource requirement of the new task, the device screening module removes the standby device from the first available resource list, that is, removes the device number of the standby device, the corresponding available computing resource data, and the corresponding available network resource data in the first available resource list, so that a new first available resource list can be obtained.
It is to be understood that if the available computing resource data of each standby device in the first available resource list can satisfy the computing resource requirement of the new task, the data in the first available resource list is not changed, and the new first available resource list in this step is still the first available resource list generated in step 1211 a.
For example, as shown in Table 3, in step 1211b, it is assumed that the available computing resource data a of the backup device corresponding to ID211If the computing resource requirement of the new task cannot be met, the device number ID21 of the standby device corresponding to the ID21 and the available computing resource data a are set1Available network resource data b1And removing the first available resource list to form a new first available resource list.
In this disclosure, the computing resource requirement may be a required amount of a new task for computing resources, and the available computing resource data of the standby device may be a remaining amount of computing resources shared by the standby device, and when it is determined that the available computing resource data of the standby device is smaller than the computing resource requirement of the new task, it is considered that the available computing resource data of the standby device cannot satisfy the computing resource requirement of the new task, otherwise, it is considered that the available computing resource data of the standby device can satisfy the computing resource requirement of the new task.
Step 1211c, generating a list of available standby devices according to the new first list of available resources, wherein the list of available standby devices is the new first list of available resources.
In step 1211c, the device filter module generates a list of available standby devices based on the new first list of available resources. The available standby device list is the new first available resource list, that is, the available standby device list is the first available resource list after the standby devices whose available computing resource data cannot meet the computing resource requirement of the new task are removed. It will be appreciated that the list of available standby devices includes the device numbers of the standby devices for which the available computing resource data meets the computing resource requirements of the new task, the corresponding available computing resource data, and the corresponding available network resource data.
Fig. 4 is a flowchart of another specific implementation of step 121 in this disclosure embodiment, as shown in fig. 4, in some embodiments, the specific resource is a storage resource, the specific resource requirement of the new task includes a storage resource requirement, and step 121 includes:
step 1212a, according to the storage resource requirement of the new task and the available resource data of each standby device, extracting the available storage resource data and the available network resource data of each standby device from the standby device list, and generating a second available resource list.
In step 1212a, the device screening module extracts, according to the storage resource requirement of the new task and the available resource data of each standby device, the available storage resource data and the available network resource data of each standby device from the standby device list, and generates a second available resource list.
The second available resource list includes the device number of each standby device, the corresponding available storage resource data, and the corresponding available network resource data.
Table 4 shows a second available resource list, which includes the device numbers (ID21, ID22, …, ID2n) of the respective standby devices, and the respective standby devices, as shown in Table 3Available storage resource data (c)1、c2、…、cn) And available network resource data of each standby device (b)1、b2、…、bn)。
TABLE 4
Figure BDA0002145714280000141
And 1212b, removing the standby equipment in the second available resource list, of which the available storage resource data does not meet the storage resource requirement of the new task, to obtain a new second available resource list.
In step 1212b, for each standby device in the second available resource list, if the device screening module determines that the available storage resource data of the standby device cannot meet the storage resource requirement of the new task, the device screening module removes the standby device from the second available resource list, that is, removes the device number of the standby device, the corresponding available storage resource data, and the corresponding available network resource data in the second available resource list, so that a new second available resource list can be obtained.
It can be understood that, if the available storage resource data of each standby device in the second available resource list can satisfy the storage resource requirement of the new task, the data in the second available resource list is not changed, and the new second available resource list in this step is still the second available resource list generated in step 1212 a.
For example, as shown in Table 4, in step 1212b, it is assumed that the available storage resource data c of the backup device corresponding to ID211If the storage resource requirement of the new task cannot be met, the device number ID21 of the standby device corresponding to the ID21 and the available storage resource data c are set1Available network resource data b1And removing the second available resource list to form a new second available resource list.
In this disclosure, the storage resource requirement may be a required amount of a new task for a storage resource, the available storage resource data of the standby device may be a remaining amount of the storage resource shared by the standby device, when it is determined that the available storage resource data of the standby device is smaller than the storage resource requirement of the new task, it is considered that the available storage resource data of the standby device cannot satisfy the storage resource requirement of the new task, otherwise, it is considered that the available storage resource data of the standby device can satisfy the storage resource requirement of the new task.
Step 1212c, generating an available standby device list according to the new second available resource list, where the available standby device list is the new second available resource list.
In step 1212c, the device screening module generates a list of available standby devices according to the new second list of available resources. The available standby device list is the new second available resource list, that is, the available standby device list is the second available resource list after the standby devices whose available storage resource data cannot meet the storage resource requirement of the new task are removed. It will be appreciated that the list of available standby devices includes the device numbers of the standby devices whose available storage resource data meets the storage resource requirements of the new task, the corresponding available storage resource data, and the corresponding available network resource data.
A standby device for processing the new task is determined from the list of available standby devices, step 122.
In step 122, the device screening module determines a standby device for processing the new task from the available standby device list, determines the standby device as a standby device for processing the new task when only one standby device is included in the available standby device list, and determines a standby device for processing the new task from the available standby device list when a plurality of standby devices are included in the available standby device list.
According to the description of step 121, if the specific resource is a computing resource and the specific resource requirement of the new task includes a computing resource requirement, the available standby device list in step 121 includes a device number of a standby device whose available computing resource data can satisfy the computing resource requirement of the new task, corresponding available computing resource data, and corresponding available network resource data; if the specific resource is a storage resource and the specific resource requirement of the new task includes a storage resource requirement, the available standby device list in step 121 includes a device number of a standby device whose available storage resource data can satisfy the storage resource requirement of the new task, corresponding available storage resource data, and corresponding available network resource data.
Fig. 5 is a flowchart of a specific implementation manner of step 122 in an embodiment of the present disclosure, as shown in fig. 5, in some embodiments, the specific resource is a computing resource, the specific resource requirement of the new task includes a computing resource requirement, the available standby device list includes a device number of a standby device whose available computing resource data can meet the computing resource requirement of the new task, corresponding available computing resource data, and corresponding available network resource data, and step 122 includes:
step 1221a, for each standby device in the available standby device list, performing normalization processing on the available computing resource data of the standby device according to the available computing resource data of each standby device in the available standby device list, to obtain a computing resource normalization value corresponding to the available computing resource data of the standby device.
In step 1221a, the device screening module performs, for each standby device in the available standby device list, a normalization process on the available computing resource data of the standby device according to the available computing resource data of each standby device in the available standby device list, so as to obtain a computing resource normalization value corresponding to the available computing resource data of the standby device. Therefore, the calculation resource normalization value corresponding to the available calculation resource data of each standby device in the available standby device list is obtained.
Specifically, assuming that the available standby device list is the first available resource list shown in table 3, in step 1221a, the device screening module, for an ith standby device in the available standby device list, according to the available computing resource data of the ith standby device, the available computing resource data of each standby device in the available standby device list, and the computing resource normalization value formula:
Figure BDA0002145714280000171
and calculating to obtain a calculation resource normalization value corresponding to the available calculation resource data of the standby equipment. Wherein, aiData representing the available computing resources of the ith standby device,
Figure BDA0002145714280000172
sum of available computing resource data, A, representing the standby devices in the list of available standby devicesiAnd computing resource normalization values corresponding to the available computing resource data of the ith standby device. Therefore, the calculation resource normalization values corresponding to the available calculation resource data of each standby device in the available standby device list can be calculated, and the calculation resource normalization values corresponding to the available calculation resource data of each standby device in the available standby device list are respectively A1、A2、…、Ai、…、An。
Step 1221b, for each standby device in the available standby device list, according to the available network resource data of each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device, so as to obtain a network resource normalization value corresponding to the available network resource data of the standby device.
In step 1221b, the device screening module performs, for each standby device in the available standby device list, a normalization process on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list, so as to obtain a network resource normalization value corresponding to the available network resource data of the standby device. Therefore, the network resource normalization value corresponding to the available network resource data of each standby device in the available standby device list is obtained.
Specifically, assuming that the available standby device list is the first available resource list shown in table 3, in step 1221b, the device screening module targets the ith standby device in the available standby device list, and according to the available network resource data of the ith standby device and the available network resource data of each standby device in the available standby device listAvailable network resource data and a network resource normalization value formula:
Figure BDA0002145714280000173
and calculating to obtain a calculation resource normalization value corresponding to the available network resource data of the standby equipment. Wherein, biAvailable network resource data representing the ith standby device,
Figure BDA0002145714280000174
the sum of the available network resource data representing the standby devices in the available standby device list, BiAnd indicating the network resource normalization value corresponding to the available network resource data of the ith standby device. Therefore, the network resource normalization values corresponding to the available network resource data of each standby device in the available standby device list can be calculated, and the network resource normalization values corresponding to the available network resource data of each standby device in the available standby device list are respectively B1、B2、…、Bi、…、Bn。
Step 1221c, for each standby device in the available standby device list, generating a first score value corresponding to the standby device according to a preset first score model, a computing resource normalization value corresponding to the available computing resource data of the standby device, and a network resource normalization value corresponding to the available network resource data of the standby device.
In step 1221c, the device screening module generates, for each standby device in the available standby device list, a first score value corresponding to the standby device according to a preset first score model, a computing resource normalization value corresponding to available computing resource data of the standby device, and a network resource normalization value corresponding to available network resource data of the standby device. Therefore, a first scoring value corresponding to each standby device in the available standby device list is obtained.
In an embodiment of the present disclosure, the preset first scoring model includes: first scoring value formula: pi＝k1*Ai+k2*Bi. Wherein, PiTo representA first score value, A, corresponding to the ith standby device in the list of available standby devicesiA normalized value of computing resource corresponding to the available computing resource data representing the ith standby device in the list of available standby devices, BiNetwork resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list1Representing the weight value, k, corresponding to the normalized value of the computing resource2Representing the weight value, k, corresponding to the normalized value of the network resource1+k21, and k1Greater than k2E.g. k1＝0.8，k20.2. Therefore, the first scoring values corresponding to the standby equipment in the available standby equipment list can be calculated, and the first scoring values corresponding to the standby equipment in the available standby equipment list are respectively P1、P2、…、Pi、…、Pn。
And 1221d, according to the first score values corresponding to the standby devices in the available standby device list, determining the standby device with the highest first score value as the standby device for processing the new task.
In step 1221d, the device screening module determines, according to the first score value corresponding to each standby device in the available standby device list, the standby device with the highest first score value as the standby device for processing the new task.
In some embodiments, the number of the standby devices with the highest first scoring values is multiple, that is, there are two or more standby devices with the same and the highest first scoring values, and then any one of the multiple standby devices with the highest first scoring values is determined as the standby device for processing the new task.
Fig. 6 is a flowchart of another specific implementation of step 122 in this disclosure embodiment, as shown in fig. 6, in some embodiments, the specific resource is a storage resource, the specific resource requirement of the new task includes a storage resource requirement, the available standby device list includes a device number of a standby device whose available storage resource data can satisfy the storage resource requirement of the new task, corresponding available storage resource data, and corresponding available network resource data, and step 122 includes:
step 1222a, for each standby device in the available standby device list, according to the available storage resource data of each standby device in the available standby device list, performing normalization processing on the available storage resource data of the standby device, to obtain a storage resource normalization value corresponding to the available storage resource data of the standby device.
In step 1222a, the device screening module normalizes, for each standby device in the available standby device list, the available storage resource data of the standby device according to the available storage resource data of each standby device in the available standby device list, so as to obtain a storage resource normalized value corresponding to the available storage resource data of the standby device. Therefore, a storage resource normalization value corresponding to the available storage resource data of each standby device in the available standby device list is obtained.
Specifically, assuming that the available standby device list is the second available resource list shown in table 4, in step 1222a, the device screening module, for the ith standby device in the available standby device list, according to the available storage resource data of the ith standby device, the available storage resource data of each standby device in the available standby device list, and the storage resource normalization value formula:
Figure BDA0002145714280000191
and calculating to obtain a storage resource normalization value corresponding to the available storage resource data of the standby equipment. Wherein, ciData representing the available storage resources of the ith standby device,
Figure BDA0002145714280000192
representing the sum of the available storage resource data of the individual spare devices in the list of available spare devices, CiAnd indicating the storage resource normalization value corresponding to the available storage resource data of the ith standby device. Therefore, the storage resource normalization value corresponding to the available storage resource data of each standby device in the available standby device list can be calculated and obtained, and the storage resource normalization value of each standby device in the available standby device listThe normalized values of the storage resources corresponding to the available storage resource data are respectively C1、C2、…、Ci、…、Cn。
Step 1222b, for each standby device in the available standby device list, according to the available network resource data of each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device, so as to obtain a network resource normalization value corresponding to the available network resource data of the standby device.
In the embodiment of the present disclosure, for a detailed description of step 1222b, reference may be made to the description of step 1221b, which is not described herein again.
Step 1222c, for each standby device in the available standby device list, generating a second score value corresponding to the standby device according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby device, and a network resource normalization value corresponding to the available network resource data of the standby device.
In step 1222c, the device screening module generates, for each standby device in the list of available standby devices, a second score value corresponding to the standby device according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby device, and a network resource normalization value corresponding to the available network resource data of the standby device. Therefore, a second scoring value corresponding to each standby device in the available standby device list is obtained.
In an embodiment of the present disclosure, the preset second scoring model includes: second scoring value formula: qi＝k3*Ci+k2*Bi(ii) a Wherein Q isiA second score value, C, representing the value of the ith standby device in the list of available standby devicesiA storage resource normalization value corresponding to available storage resource data representing the ith backup device in the available backup device list, BiNetwork resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list3Representing storage resource normalization valuesCorresponding weight value, k2Representing the weight value, k, corresponding to the normalized value of the network resource3+k21, and k3Greater than k2E.g. k3＝0.8，k20.2. Therefore, the second scoring values corresponding to the standby equipment in the available standby equipment list can be calculated, and the second scoring values corresponding to the standby equipment in the available standby equipment list are Q1、Q2、…、Qi、…、Qn。
Step 1222d, according to the second scoring value corresponding to each spare device in the available spare device list, determining the spare device with the highest second scoring value as the spare device for processing the new task.
In step 1222d, the device screening module determines the standby device with the highest second score value as the standby device for processing the new task according to the second score value corresponding to each standby device in the available standby device list.
In some embodiments, the number of the standby devices with the highest second score values is multiple, that is, there are two or more standby devices with the same and the highest second score values, and then any one of the multiple standby devices with the highest second score values is determined as the standby device for processing the new task.
And step 13, sending the new task to the determined standby equipment.
In the embodiment of the present disclosure, the network control module sends the new task to the determined standby device through the switch.
Specifically, before the network control module sends the new task to the determined standby device through the switch, after the device screening module determines a standby device for processing the new task, the device screening module feeds back the device number of the determined standby device to the edge cloud management platform.
Then, the edge cloud management platform queries the IP address and the port of the standby device corresponding to the device number according to the determined device number of the standby device, and sends the determined device number of the standby device, the task number of the new task, the node number of the edge node, the determined IP address of the standby device, and the determined port of the standby device to the network control module.
In the embodiment of the present disclosure, the Network control module is a Software Defined Network (SDN) control module, the SDN control module includes an SDN controller, and the switch is an SDN switch.
After the network control module receives the determined device number of the standby device, the task number of the new task, the node number of the edge node, the determined IP address of the standby device and the determined port of the standby device, which are sent by the edge cloud management platform, an SDN controller in the network control module issues a corresponding flow table to an SDN switch, so that the SDN switch forwards the new task corresponding to the task number to the standby device corresponding to the device number according to the flow table, the determined IP address of the standby device and the determined port of the standby device.
And 14, receiving the task processing result returned by the determined standby equipment, and sending the task processing result to the edge node.
In this embodiment of the present disclosure, after the determined standby device completes processing the new task, a task processing result of the new task is returned to the network control module through the SDN switch.
And after the network control module receives the task processing result returned by the determined standby equipment, the SDN controller in the network control module sends the task processing result to the edge node corresponding to the node number of the edge connection node.
In the embodiment of the present disclosure, the purpose of capacity expansion of edge nodes is achieved by using resources shared by various intelligent hardware devices (standby devices), and for each edge node, when it is determined that the load of a specific resource of the edge node reaches a preset threshold and a new task with a specific resource requirement is received and sent to the edge node, the new task is forwarded to a standby device corresponding to the edge node, where the standby device can be used to process the new task, so that the load of the edge node during busy hours is reduced as much as possible without performing large-scale resource capacity expansion.
According to the task processing method provided by the embodiment of the disclosure, for each edge node, when the load of the specific resource of the edge node reaches the preset threshold value and a new task with a specific resource requirement sent to the edge node is received, the new task is forwarded to a standby device corresponding to the edge node and capable of processing the new task, on one hand, the resource utilization rate of intelligent hardware devices (standby devices) can be effectively improved, the resource waste of the intelligent hardware devices (standby devices) is avoided, and on the other hand, the load of the edge node in busy hours can be effectively reduced.
Fig. 7 is a flowchart of another task processing method provided in the embodiment of the present disclosure, and as shown in fig. 7, the task processing method includes:
step 21, for each edge node, when the edge cloud management platform determines that the load of the specific resource of the edge node reaches a preset threshold and receives a new task with a specific resource requirement sent to the edge node, the edge cloud management platform acquires an equipment number list corresponding to the edge node and the specific resource requirement of the new task.
The device number list includes device numbers of a plurality of standby devices corresponding to the edge node.
And step 22, the edge cloud management platform sends the equipment number list corresponding to the edge node and the specific resource requirement of the new task to the equipment screening module.
And step 23, the device screening module acquires the standby device list corresponding to the edge node according to the device number of each standby device in the device number list.
The standby device list at least includes the device number of each standby device in the plurality of standby devices corresponding to the edge node and the available resource data of each standby device.
Step 24, the device screening module determines a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list.
And 25, feeding back the determined equipment number of the standby equipment to the edge cloud management platform by the equipment screening module.
And step 26, the edge cloud management platform sends the determined equipment number of the standby equipment, the task number of the new task, the node number of the edge node, the determined IP address of the standby equipment and the determined port of the standby equipment to the network control module.
And 27, the network control module issues a corresponding flow table to the switch according to the information received from the edge cloud management platform.
Step 28, the switch forwards the new task to the determined standby device according to the flow table.
And step 29, after the determined standby equipment finishes processing the new task, returning a task processing result to the network control module through the switch.
And step 30, the network control module returns the task processing result to the edge node corresponding to the node number.
In addition, for other specific descriptions of the embodiments of the present disclosure, reference may be made to the specific description of the task processing method in the foregoing embodiments, and details are not repeated here.
Fig. 8 is a schematic structural diagram of a task processing system according to an embodiment of the present disclosure, and as shown in fig. 8, the task processing system includes: the system comprises an edge cloud management platform 301, a device screening module 302 and a network control module 303.
The edge cloud management platform 301 is configured to determine, for each edge node, whether a load of a specific resource of the edge node reaches a preset threshold, and determine whether a new task with a specific resource requirement is received and sent to the edge node.
The device screening module 302 is configured to, for each edge node, obtain a standby device list corresponding to the edge node when the edge cloud management platform 301 determines that the load of the specific resource of the edge node reaches a preset threshold and determines that a new task with a specific resource requirement is received, where the standby device list includes a device number of each standby device in a plurality of standby devices corresponding to the edge node and available resource data of each standby device; and determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list.
The network control module 303 is configured to send the new task to the determined standby device; and receiving a task processing result returned by the determined standby equipment, and sending the task processing result to the edge node.
In some embodiments, the device screening module 302 is specifically configured to determine, according to the specific resource requirement of the new task and the available resource data of each standby device, a standby device whose available resource data can meet the specific resource requirement of the new task from the standby device list, and generate an available standby device list; a standby device for processing the new task is determined from the list of available standby devices.
In an embodiment of the present disclosure, the available resource data includes available computing resource data, available storage resource data, and available network resource data.
In some embodiments, if the specific resource is a computing resource and the specific resource requirement of the new task includes a computing resource requirement, the device screening module 302 is specifically configured to extract available computing resource data and available network resource data of each standby device from the standby device list according to the computing resource requirement of the new task and the available resource data of each standby device, and generate a first available resource list, where the first available resource list includes a device number of each standby device, corresponding available computing resource data, and corresponding available network resource data; removing the standby equipment of which the available computing resource data do not meet the computing resource requirement of the new task in the first available resource list to obtain a new first available resource list; and generating the available standby equipment list according to the new first available resource list, wherein the available standby equipment list is the new first available resource list.
In some embodiments, the device screening module 302 is specifically configured to, for each standby device in the available standby device list, perform normalization processing on available computing resource data of the standby device according to the available computing resource data of each standby device in the available standby device list, so as to obtain a computing resource normalization value corresponding to the available computing resource data of the standby device; for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device; generating a first score value corresponding to each standby device in the available standby device list according to a preset first score model, a computing resource normalization value corresponding to available computing resource data of the standby device and a network resource normalization value corresponding to available network resource data of the standby device; and determining the standby equipment with the highest first score value as the standby equipment for processing the new task according to the first score value corresponding to each standby equipment in the available standby equipment list.
In some embodiments, the preset first scoring model comprises: first scoring value formula: pi＝k1*Ai+k2*Bi(ii) a Wherein, PiA first score value A corresponding to the ith standby device in the available standby device listiA computing resource normalization value corresponding to available computing resource data representing an ith standby device in the list of available standby devices, BiA network resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list1Representing the weight value, k, corresponding to the normalized value of the computing resource2Representing the weight value, k, corresponding to the normalized value of the network resource1+k21, and k1Greater than k2。
In some embodiments, if the specific resource is a storage resource and the specific resource requirement of the new task includes a storage resource requirement, the device screening module 302 is specifically configured to extract available storage resource data and available network resource data of each standby device from the standby device list according to the storage resource requirement of the new task and the available resource data of each standby device, and generate a second available resource list, where the second available resource list includes a device number of each standby device, corresponding available storage resource data, and corresponding available network resource data; removing the standby equipment of which the available storage resource data in the second available resource list does not meet the storage resource requirement of the new task to obtain a new second available resource list; and generating the available standby equipment list according to the new second available resource list, wherein the available standby equipment list is the new second available resource list.
In some embodiments, the device screening module 302 is specifically configured to, for each standby device in the available standby device list, perform normalization processing on the available storage resource data of the standby device according to the available storage resource data of each standby device in the available standby device list, so as to obtain a storage resource normalization value corresponding to the available storage resource data of the standby device; for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device; generating a second score value corresponding to the standby equipment according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby equipment and a network resource normalization value corresponding to the available network resource data of the standby equipment for each standby equipment in the available standby equipment list; and determining the standby equipment with the highest second score value as the standby equipment for processing the new task according to the second score value corresponding to each standby equipment in the available standby equipment list.
In some embodiments, the preset second scoring model comprises: second score value is publicFormula (II): qi＝k3*Ci+k2*Bi(ii) a Wherein Q isiA second score value, C, representing the corresponding ith standby device in the list of available standby devicesiA storage resource normalization value, B, corresponding to available storage resource data representing the ith standby device in the available standby device listiA network resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list3Representing the weight value, k, corresponding to the normalized value of the storage resource2Representing the weight value, k, corresponding to the normalized value of the network resource3+k21, and k3Greater than k2。
In addition, the task processing system provided in the embodiment of the present disclosure is configured to implement the task processing method provided in any one of the foregoing embodiments, and specific descriptions may refer to descriptions of any one of the foregoing embodiments, which are not repeated herein.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.

Claims (14)

1. A task processing method, comprising:
for each edge node, when the load of the specific resource of the edge node is judged to reach a preset threshold value and a new task with specific resource requirements sent to the edge node is received, acquiring the specific resource requirements of the new task and a standby equipment list corresponding to the edge node, wherein the standby equipment list at least comprises equipment numbers of each standby equipment in a plurality of standby equipment corresponding to the edge node and available resource data of each standby equipment; wherein the standby device comprises an intelligent hardware device;
determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list;
sending the new task to the determined standby equipment;
and receiving a task processing result returned by the determined standby equipment, and sending the task processing result to the edge node.
2. The method according to claim 1, wherein the determining a standby device from the standby device list for processing the new task according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list comprises:
according to the specific resource requirement of the new task and the available resource data of each standby device, determining the standby devices of which the available resource data can meet the specific resource requirement of the new task from the standby device list, and generating an available standby device list;
a standby device for processing the new task is determined from the list of available standby devices.
3. The task processing method according to claim 2, wherein the available resource data includes available computing resource data, available storage resource data, and available network resource data;
if the specific resource is a computing resource and the specific resource requirement of the new task includes a computing resource requirement, determining, from the standby device list, a standby device whose available resource data can satisfy the specific resource requirement of the new task according to the specific resource requirement of the new task and available resource data of each standby device, and generating an available standby device list, including:
according to the computing resource requirements of the new task and the available resource data of each standby device, extracting the available computing resource data and the available network resource data of each standby device from the standby device list to generate a first available resource list, wherein the first available resource list comprises the device number of each standby device, the corresponding available computing resource data and the corresponding available network resource data;
removing the standby equipment of which the available computing resource data do not meet the computing resource requirement of the new task in the first available resource list to obtain a new first available resource list;
and generating the available standby equipment list according to the new first available resource list, wherein the available standby equipment list is the new first available resource list.
4. A task processing method according to claim 3, wherein said determining a standby device for processing the new task from the list of available standby devices comprises:
for each standby equipment in the available standby equipment list, carrying out normalization processing on the available computing resource data of the standby equipment according to the available computing resource data of each standby equipment in the available standby equipment list to obtain a computing resource normalization value corresponding to the available computing resource data of the standby equipment;
for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device;
generating a first score value corresponding to each standby device in the available standby device list according to a preset first score model, a computing resource normalization value corresponding to available computing resource data of the standby device and a network resource normalization value corresponding to available network resource data of the standby device;
and determining the standby equipment with the highest first score value as the standby equipment for processing the new task according to the first score value corresponding to each standby equipment in the available standby equipment list.
5. The task processing method according to claim 4, wherein the preset first scoring model includes: first scoring value formula: pi＝k1*Ai+k2*Bi；
Wherein, PiA first score value A corresponding to the ith standby device in the available standby device listiA computing resource normalization value corresponding to available computing resource data representing an ith standby device in the list of available standby devices, BiA network resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list1Representing the weight value, k, corresponding to the normalized value of the computing resource2Representing the weight value, k, corresponding to the normalized value of the network resource1+k21, and k1Greater than k2。
6. The task processing method according to claim 2, wherein the available resource data includes available computing resource data, available storage resource data, and available network resource data;
if the specific resource is a storage resource and the specific resource requirement of the new task includes a storage resource requirement, determining, from the standby device list, a standby device whose available resource data can satisfy the specific resource requirement of the new task according to the specific resource requirement of the new task and available resource data of each standby device, and generating an available standby device list, including:
according to the storage resource requirement of the new task and the available resource data of each standby device, extracting the available storage resource data and the available network resource data of each standby device from the standby device list to generate a second available resource list, wherein the second available resource list comprises the device number of each standby device, the corresponding available storage resource data and the corresponding available network resource data;
removing the standby equipment of which the available storage resource data in the second available resource list does not meet the storage resource requirement of the new task to obtain a new second available resource list;
and generating the available standby equipment list according to the new second available resource list, wherein the available standby equipment list is the new second available resource list.
7. The task processing method of claim 6, wherein said determining a standby device from the list of available standby devices for processing the new task comprises:
for each standby device in the available standby device list, performing normalization processing on the available storage resource data of the standby device according to the available storage resource data of each standby device in the available standby device list to obtain a storage resource normalization value corresponding to the available storage resource data of the standby device;
for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device;
generating a second score value corresponding to the standby equipment according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby equipment and a network resource normalization value corresponding to the available network resource data of the standby equipment for each standby equipment in the available standby equipment list;
and determining the standby equipment with the highest second score value as the standby equipment for processing the new task according to the second score value corresponding to each standby equipment in the available standby equipment list.
8. The task processing method according to claim 7, wherein the preset second scoring model includes: second scoring value formula: qi＝k3*Ci+k2*Bi；
Wherein Q isiA second score value, C, representing the corresponding ith standby device in the list of available standby devicesiA storage resource normalization value, B, corresponding to available storage resource data representing the ith standby device in the available standby device listiA network resource normalization value k corresponding to available network resource data representing the ith standby device in the available standby device list3Representing the weight value, k, corresponding to the normalized value of the storage resource2Representing the weight value, k, corresponding to the normalized value of the network resource3+k21, and k3Greater than k2。
9. A task processing system, comprising:
the edge cloud management platform is used for judging whether the load of the specific resource of each edge node reaches a preset threshold value or not and judging whether a new task with specific resource requirements is received or not, wherein the new task is sent to the edge node;
the device screening module is used for acquiring a standby device list corresponding to each edge node when the edge cloud management platform judges that the load of the specific resource of the edge node reaches a preset threshold value and a new task with specific resource requirements is received, wherein the standby device list comprises the device number of each standby device in a plurality of standby devices corresponding to the edge node and available resource data of each standby device; determining a standby device for processing the new task from the standby device list according to the specific resource requirement of the new task and the available resource data of each standby device in the standby device list; wherein the standby device comprises an intelligent hardware device;
the network control module is used for sending the new task to the determined standby equipment; and receiving a task processing result returned by the determined standby equipment, and sending the task processing result to the edge node.
10. The task processing system according to claim 9, wherein the device screening module is specifically configured to determine, from the standby device list, a standby device whose available resource data can meet a specific resource requirement of the new task according to the specific resource requirement of the new task and available resource data of each standby device, and generate an available standby device list; a standby device for processing the new task is determined from the list of available standby devices.
11. A task processing system according to claim 10, wherein the available resource data comprises available computing resource data, available storage resource data and available network resource data;
if the specific resource is a computing resource and the specific resource requirement of the new task includes a computing resource requirement, the device screening module is specifically configured to extract available computing resource data and available network resource data of each standby device from the standby device list according to the computing resource requirement of the new task and the available resource data of each standby device, and generate a first available resource list, where the first available resource list includes a device number of each standby device, corresponding available computing resource data, and corresponding available network resource data; removing the standby equipment of which the available computing resource data do not meet the computing resource requirement of the new task in the first available resource list to obtain a new first available resource list; and generating the available standby equipment list according to the new first available resource list, wherein the available standby equipment list is the new first available resource list.
12. The task processing system according to claim 11, wherein the device screening module is specifically configured to, for each standby device in the available standby device list, perform normalization processing on the available computing resource data of the standby device according to the available computing resource data of each standby device in the available standby device list, to obtain a computing resource normalization value corresponding to the available computing resource data of the standby device; for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device; generating a first score value corresponding to each standby device in the available standby device list according to a preset first score model, a computing resource normalization value corresponding to available computing resource data of the standby device and a network resource normalization value corresponding to available network resource data of the standby device; and determining the standby equipment with the highest first score value as the standby equipment for processing the new task according to the first score value corresponding to each standby equipment in the available standby equipment list.
13. A task processing system according to claim 10, wherein the available resource data comprises available computing resource data, available storage resource data and available network resource data;
if the specific resource is a storage resource and the specific resource requirement of the new task includes a storage resource requirement, the device screening module is specifically configured to extract available storage resource data and available network resource data of each standby device from the standby device list according to the storage resource requirement of the new task and the available resource data of each standby device, and generate a second available resource list, where the second available resource list includes a device number of each standby device, corresponding available storage resource data, and corresponding available network resource data; removing the standby equipment of which the available storage resource data in the second available resource list does not meet the storage resource requirement of the new task to obtain a new second available resource list; and generating the available standby equipment list according to the new second available resource list, wherein the available standby equipment list is the new second available resource list.
14. The task processing system according to claim 13, wherein the device screening module is specifically configured to, for each standby device in the available standby device list, perform normalization processing on the available storage resource data of the standby device according to the available storage resource data of each standby device in the available standby device list, to obtain a storage resource normalization value corresponding to the available storage resource data of the standby device; for each standby device in the available standby device list, performing normalization processing on the available network resource data of the standby device according to the available network resource data of each standby device in the available standby device list to obtain a network resource normalization value corresponding to the available network resource data of the standby device; generating a second score value corresponding to the standby equipment according to a preset second score model, a storage resource normalization value corresponding to the available storage resource data of the standby equipment and a network resource normalization value corresponding to the available network resource data of the standby equipment for each standby equipment in the available standby equipment list; and determining the standby equipment with the highest second score value as the standby equipment for processing the new task according to the second score value corresponding to each standby equipment in the available standby equipment list.
CN201910684012.3A 2019-07-26 2019-07-26 Task processing method and system Active CN110381159B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910684012.3A CN110381159B (en) 2019-07-26 2019-07-26 Task processing method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910684012.3A CN110381159B (en) 2019-07-26 2019-07-26 Task processing method and system

Publications (2)

Publication Number Publication Date
CN110381159A CN110381159A (en) 2019-10-25
CN110381159B true CN110381159B (en) 2022-02-01

Family

ID=68256429

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910684012.3A Active CN110381159B (en) 2019-07-26 2019-07-26 Task processing method and system

Country Status (1)

Country Link
CN (1) CN110381159B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112988346B (en) * 2021-02-07 2024-02-23 中国联合网络通信集团有限公司 Task processing method, device, equipment and storage medium
CN115562870B (en) * 2022-10-25 2023-07-21 北京京航计算通讯研究所 Task node resource construction method of cluster

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101640231B1 (en) * 2015-02-12 2016-07-18 소프트온넷(주) Cloud Driving Method for supporting auto-scaled Hadoop Distributed Parallel Processing System
CN108243246A (en) * 2017-12-25 2018-07-03 北京市天元网络技术股份有限公司 A kind of edge calculations resource regulating method, edge device and system
CN109167835A (en) * 2018-09-13 2019-01-08 重庆邮电大学 A kind of physics resource scheduling method and system based on kubernetes
CN109688222A (en) * 2018-12-26 2019-04-26 深圳市网心科技有限公司 The dispatching method of shared computing resource, shared computing system, server and storage medium
CN109714797A (en) * 2019-02-18 2019-05-03 南京邮电大学 A kind of mobile edge network resource allocation methods based on Game Theory

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9015708B2 (en) * 2011-07-28 2015-04-21 International Business Machines Corporation System for improving the performance of high performance computing applications on cloud using integrated load balancing
US9047129B2 (en) * 2012-07-23 2015-06-02 Adobe Systems Incorporated Systems and methods for load balancing of time-based tasks in a distributed computing system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101640231B1 (en) * 2015-02-12 2016-07-18 소프트온넷(주) Cloud Driving Method for supporting auto-scaled Hadoop Distributed Parallel Processing System
CN108243246A (en) * 2017-12-25 2018-07-03 北京市天元网络技术股份有限公司 A kind of edge calculations resource regulating method, edge device and system
CN109167835A (en) * 2018-09-13 2019-01-08 重庆邮电大学 A kind of physics resource scheduling method and system based on kubernetes
CN109688222A (en) * 2018-12-26 2019-04-26 深圳市网心科技有限公司 The dispatching method of shared computing resource, shared computing system, server and storage medium
CN109714797A (en) * 2019-02-18 2019-05-03 南京邮电大学 A kind of mobile edge network resource allocation methods based on Game Theory

Also Published As

Publication number Publication date
CN110381159A (en) 2019-10-25

Similar Documents

Publication Publication Date Title
US10237238B2 (en) Regional firewall clustering in a networked computing environment
US9742667B2 (en) Packet processing method, device and system
CN105940377B (en) Methods, systems, and computer readable media for cloud-based virtualization orchestrators
EP3745678B1 (en) Storage system, and method and apparatus for allocating storage resources
EP4092992A1 (en) Data processing method, apparatus, and system
CN110365748A (en) Treating method and apparatus, storage medium and the electronic device of business datum
CN101690132A (en) Dynamically configuring a router to find the best dhcp server
US20230042747A1 (en) Message Processing Method and Device, Storage Medium, and Electronic Device
CN110381159B (en) Task processing method and system
US10476746B2 (en) Network management method, device, and system
WO2016048390A1 (en) Link aggregation configuration for a node in a software-defined network
US20160019090A1 (en) Data processing control method, computer-readable recording medium, and data processing control device
CN103795622A (en) Message forwarding method and device using same
CN108989101B (en) Log output system and method and electronic equipment
Wang et al. On the fairness-efficiency tradeoff for packet processing with multiple resources
CN117149445A (en) Cross-cluster load balancing method and device, equipment and storage medium
CN113904951A (en) Data monitoring method and device of gateway equipment and related equipment
CN113448729A (en) Load balancing method, device, equipment and storage medium
CN110086727B (en) Load sharing method and device between CGN boards
Lakshmanan et al. Placement of replicated tasks for distributed stream processing systems
CN105335376A (en) Stream processing method, device and system
Chang et al. Unreliable retrial queue with loss and feedback under threshold-based policy
US10129147B2 (en) Network-on-chip flit transmission method and apparatus
US9819571B2 (en) Control apparatus and method for supplying switch with entry
CN114257545A (en) Message forwarding method and device

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