CN107783731B - Big data real-time processing method and system - Google Patents
Big data real-time processing method and system Download PDFInfo
- Publication number
- CN107783731B CN107783731B CN201710664834.6A CN201710664834A CN107783731B CN 107783731 B CN107783731 B CN 107783731B CN 201710664834 A CN201710664834 A CN 201710664834A CN 107783731 B CN107783731 B CN 107783731B
- Authority
- CN
- China
- Prior art keywords
- data
- main control
- processing
- nodes
- real
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
- G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0643—Management of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application discloses a big data real-time processing method and a processing system, wherein the real-time processing method comprises the following steps: receiving real-time data; creating N main control nodes according to the data receiving speed and the receiving total amount; distributing data to N main control nodes; acquiring real-time processing capacity data of a cluster server; selecting N working nodes according to the processing capacity of the cluster server; the N master nodes send data to the N working nodes. The big data processing method and the big data processing device can provide the data processing speed matched with the big data processing method and the big data processing device according to the data acquisition speed, save network resources, shorten response time and provide real-time data service for users.
Description
Technical Field
The application belongs to the technical field of computers, and particularly relates to a big data real-time processing method and a big data real-time processing system.
Background
With the rapid spread of networks, there is an increasing demand for data, such as patient vital sign data collected from monitoring equipment gateways and test result data generated from test workstations, in ICU intensive care units, which require rapid and accurate processing. The existing big data processing method is limited to the network transmission capacity, and a single-thread single-server processing mode is used, so that the data operation period is long, the customer experience is reduced, and even if a plurality of processors are used, the processor cluster cannot exert the maximum working capacity of the processor cluster due to the coordination problem among the processors.
Disclosure of Invention
In view of this, the present application provides a method and a system for real-time processing of big data, which are used to solve the technical problems of insufficient processing capability and poor real-time performance of big data in the prior art.
In order to solve the technical problem, the following technical scheme is adopted in the application:
the application protects a big data real-time processing method, which comprises the following steps:
receiving real-time data;
creating N main control nodes according to the data receiving speed and the receiving total amount;
distributing data to N main control nodes;
acquiring real-time processing capacity data of a cluster server;
selecting N working nodes according to the processing capacity of the cluster server;
the N master nodes send data to the N working nodes.
The method for creating the N main control nodes according to the data receiving speed and the receiving total amount comprises the following substeps:
calculating the data receiving speed;
calculating a reception total amount according to a predetermined time interval;
evaluating the minimum and maximum processing capacity of the master control node;
selecting the optimal number N of master control nodes;
n master nodes are created.
Wherein distributing the data to the N master nodes comprises:
dividing the data into N parts;
configuring a label for each data;
storing the label in a data distribution list;
and distributing each piece of data to a corresponding main control node, and processing the data by the main control node.
The step of acquiring the real-time processing capacity data of the cluster server comprises the step of judging the real-time processing capacity of the cluster according to the CPU processing capacity of the idle server in the cluster server and the storage capacity of the storage.
Selecting N working nodes according to the processing capacity of the cluster servers comprises sequencing the processing capacity of each server in the cluster servers and selecting the first N working nodes.
The application also protects a task controller, which comprises the following components:
a receiver for receiving real-time data;
the processor is used for creating N main control nodes according to the data receiving speed and the receiving total amount; distributing data to N main control nodes; acquiring real-time processing capacity data of a cluster server; selecting N working nodes according to the processing capacity of the cluster server; the N master nodes send data to the N working nodes.
The processor comprises a creation module used for creating N main control nodes according to the data receiving speed and the receiving total amount, and the creation module comprises the following sub-modules:
a speed calculation unit that calculates a data reception speed;
a reception total amount calculation unit calculating a reception total amount at predetermined time intervals;
the processing capacity calculation module is used for evaluating the minimum and maximum processing capacities of the main control node;
the selection unit is used for selecting the optimal number N of the main control nodes and the processing capacity of the main control nodes;
and the creating unit is used for creating N main control nodes.
The processor comprises a distribution module, wherein the distribution module is used for distributing data to the N main control nodes, and the distribution module comprises the following subcomponents:
a dividing unit that divides the data into N parts;
a label unit for configuring a label for each data;
the list unit stores the labels into a data distribution list;
and the distribution unit distributes each part of data to the corresponding main control node, and the main control node processes the data.
The step of acquiring the real-time processing capacity data of the cluster server comprises the step of judging the real-time processing capacity of the cluster according to the CPU processing capacity of the idle server in the cluster and the storage capacity of the storage.
The present application also claims a big data processing system, comprising:
the client sides are used for acquiring real-time data;
a task controller as described above;
and the cluster server is used for processing the task data issued by the task controller.
The beneficial effect of this application lies in: the big data processing method and the big data processing device can provide the data processing speed matched with the big data processing method and the big data processing device according to the data acquisition speed, save network resources, shorten response time and provide real-time data service for users.
Drawings
FIG. 1 is a schematic diagram of the composition of a big data real-time processing system according to the present application;
FIG. 2 is a flow chart of a big data real-time processing method according to the present application;
FIG. 3 is a flowchart of the work of creating N master nodes according to the present application;
FIG. 4 is a block diagram of a task controller according to the present application;
FIG. 5 is a block diagram of a processor in a task controller according to the present application;
FIG. 6 is a block diagram of a creation module of the present application;
fig. 7 is a block diagram of a distribution module according to the present application.
Detailed Description
According to the big data real-time processing method and the big data real-time processing system, the transmission speed and the acquisition amount of the real-time acquired data are evaluated, so that the master control node is dynamically generated, the working node matched with the dynamically generated master control node is created according to the evaluation of the processing capacity of the connected cluster server, and therefore the big data real-time processing method and the big data real-time processing system with optimized performance are provided for users on the basis of considering the network condition, the processing capacity and the data acquisition capacity through comprehensive evaluation of the speed of the big data and the working capacity of the cluster server.
The structure of the system is shown in fig. 1, and includes a plurality of clients, a client 1 to a client N, a task controller 101, and a cluster server 102, where the cluster server 102 includes M servers, where N, M is only a rough number and indicates a plurality. The client is responsible for acquiring real-time data, taking an ICU (intensive care unit) as an example, and the data generation source mainly comprises bedside monitoring equipment and in-hospital clinical data storage. As long as the equipment capable of collecting data can be used as a client, N clients in the system are connected to the system and are responsible for providing real-time data; and the task controller dynamically creates a master control node according to the data transmission speed and the total data amount of the client, and selects a suitable working node according to the real-time processing capacity of the cluster server so as to process the data sent by the master control node. The big data processing system realizes real-time, accurate and rapid processing of big data.
The work flow chart of the system is shown in fig. 2, and the big data processing method comprises the following steps:
s201, receiving real-time data;
the task controller 101 receives real-time task data sent by a plurality of clients, for example, various medical data of patients, including vital signs, examination and test indexes, monitoring data during treatment, and the like, and the data has characteristics of real-time performance, urgency and large quantity, and is called big data. The client collates the collected data and sends the data to the task controller 101 in a wired or wireless manner.
S202, creating N main control nodes according to the data receiving speed and the receiving total amount.
After the task controller 101 receives the task data, it performs the following sub-steps as shown in fig. 3:
s301, calculating data receiving speed;
the data receiving speed can be measured by using known means such as network speed, download speed, etc.
S302, calculating the total receiving amount according to a preset time interval;
the predetermined time interval is preset or designated by the user each time, and the total amount of the received data is calculated according to the downloading speed and the time interval.
S303, evaluating the minimum and maximum processing capacity of the main control node;
the minimum and maximum processing capacities of the master node are calculated according to the capacity and read/write speed of the memory and the processing capacity of the task controller 101, and further, the minimum and maximum processing capacities of the master node can be evaluated according to the number of threads allocated to the master node by the task controller and the capacity of the memory.
S304, selecting the optimal number N of the main control nodes and the processing capacity of the main control nodes.
And selecting the number N of the main control nodes and the processing capacity of the main control nodes according to the receiving speed and the receiving total amount of the data and the maximum and minimum processing capacities of the main control nodes, so that the data processing can be finished and the thread number of the task controller is not wasted. Wherein the processing power of the master node may be measured in terms of the number of threads assigned to it by the task controller 101 and the memory capacity.
S305, creating N main control nodes.
The task controller 101 creates N master nodes according to the number N of the master nodes and the processing capacity of the master nodes, and runs a background program called Nimbus on each master node.
S203, distributing the data to the N main control nodes;
and distributing the obtained data to N main control nodes, wherein in the distribution process, the data from one client is distributed to one main control node as much as possible in consideration of the continuity of the content contained in the data and the response speed returned to the client.
The method comprises the following substeps:
s2031, dividing the data into N parts;
the task controller 101 divides the received data into N parts, and divides the data from one client into one part as much as possible when dividing the data.
S2032, configuring a label for each data;
the label can be distributed to each data according to the sequence, and the label can also be configured to each data according to other rules, wherein the label of each data is unique in the whole network.
S2033, storing the label into a data distribution list;
the label is stored in a data distribution list, and the label is required to be used in subsequent sending and response.
S2034, distributing each data to a corresponding master control node, and processing the data by the master control node;
the task controller 101 distributes each piece of data to the master control node, and the Nimbus background program on the task controller is responsible for receiving data, unifying data formats, sending data and the like. Data from the same client, especially in one packet, is sent to the same master node as much as possible for processing. This is because there is often continuity between data from the same client, facilitating continuous processing by the master node.
After step S203 is executed, with continued reference to fig. 2, other steps are executed:
s204, acquiring real-time processing capacity data of the cluster server;
the step of acquiring the real-time processing capacity data of the cluster server comprises the step of judging the real-time processing capacity of the cluster according to the CPU processing capacity of the idle server in the cluster server and the storage capacity of the storage.
S205, selecting N working nodes according to the processing capacity of the cluster server;
and sequencing the processing capacity of each server in the cluster servers, and selecting the top N servers as working nodes. Each work node runs a background program called hypervisor, which is responsible for listening to the tasks assigned to it from Nimbus and starting or stopping the work process executing the tasks accordingly. Each worker process executes a subset of Topology; a running Topology consists of multiple work processes distributed over different work nodes.
S206, the N main control nodes send data to the N working nodes
The method comprises the steps that the Nimbus of the master control node establishes communication with the Supervisors of the corresponding working nodes, data are sent to the Supervisors of the corresponding working nodes, the Supervisors establish working processes for executing corresponding data tasks, and the data are processed. After the processing is finished, a kill command is called by the Supervisor to kill the work process, and after the whole processing is finished, the task controller calls the kill command to kill the Nimbus and the Supervisor and releases the master control node and the work node.
The work flow of the present application is briefly described above with reference to fig. 1 to 3, and the detailed configuration of the task controller 101 of the present application is described below with reference to fig. 4 to 7.
As shown in fig. 4, the task controller 101 includes the following components:
a receiver 401 for receiving real-time data;
the receiver 401 receives various data sent by the client.
A processor 402, configured to create N master control nodes according to a data receiving speed and a total receiving amount; distributing data to N main control nodes; acquiring real-time processing capacity data of a cluster server; selecting N working nodes according to the processing capacity of the cluster server; the N master nodes send data to the N working nodes.
The structure of the processor 402 is shown in fig. 5, and includes the following components:
a creating module 501, configured to create N master control nodes according to a data receiving speed and a total receiving amount;
as shown in fig. 6, the creation module 501 includes the following sub-modules:
speed calculation unit 601: calculating the data receiving speed;
the data receiving speed can be measured by using known means such as network speed, download speed, etc.
Reception total amount calculation unit 602: calculating a reception total amount according to a predetermined time interval;
the predetermined time interval is preset or designated by the user each time, and the total amount of the received data is calculated according to the downloading speed and the time interval.
The processing power calculation module 603: evaluating the minimum and maximum processing capacity of the master control node;
the minimum and maximum processing capacities of the master node are calculated according to the capacity and read-write speed of the memory and the processing capacity of the task controller 101, and further, the minimum and maximum processing capacities of the master node can be evaluated according to the number of threads allocated to the master node by the task controller 101 and the capacity of the memory.
The selecting unit 604 selects the optimal number N of the master nodes and the processing capability of the master nodes.
And selecting the number N of the main control nodes and the processing capacity of the main control nodes according to the receiving speed and the receiving total amount of the data and the maximum and minimum processing capacities of the main control nodes, so that the data processing can be finished and the thread number of the task controller is not wasted. Wherein the processing power of the master node may be measured in terms of the number of threads assigned to it by the task controller 101 and the memory capacity.
The creating unit 605 creates N master nodes.
The creating unit 605 creates N master nodes according to the number N of the master nodes and the processing capability of the master nodes, and runs a background program called Nimbus on each master node.
With continued reference to fig. 5, further comprising:
a distribution module 502, configured to distribute data to the N master control nodes;
as shown in FIG. 7, the distribution module 502 includes the following subcomponents:
a dividing unit 701 that divides data into N parts;
the dividing unit 701 divides the received data into N parts.
A label unit 702 configured to configure a label for each piece of data;
the label can be distributed to each data according to the sequence, and the label can also be configured to each data according to other rules, wherein the label of each data is unique in the whole network.
A list unit 703 that stores the tag in a data distribution list;
the label is stored in a data distribution list, and the label is required to be used in subsequent sending and response.
The distribution unit 704 distributes each piece of data to a corresponding main control node, and the main control node processes the data;
the distribution unit 704 distributes each piece of data to the master control node, and the Nimbus background program on the distribution unit is responsible for receiving data, unifying data formats, sending data and the like.
A judging module 503, configured to obtain real-time processing capability data of the cluster server;
the step of acquiring the real-time processing capacity data of the cluster server comprises the step of judging the real-time processing capacity of the cluster according to the CPU processing capacity of the idle server in the cluster server and the storage capacity of the storage.
A selecting module 504, configured to select N working nodes according to processing capabilities of the cluster servers;
and sequencing the processing capacity of each server in the cluster servers, and selecting the top N servers as working nodes. Each work node runs a background program called hypervisor, which is responsible for listening to the tasks assigned to it from Nimbus and starting or stopping the work process executing the tasks accordingly. Each worker process executes a subset of Topology; a running Topology consists of multiple work processes distributed over different work nodes.
A sending module 505, configured to enable the N master nodes to send data to the N working nodes.
The method comprises the steps that the Nimbus of the master control node establishes communication with the Supervisors of the corresponding working nodes, data are sent to the Supervisors of the corresponding working nodes, the Supervisors establish working processes for executing corresponding data tasks, and the data are processed. After the processing is finished, a kill command is called by the Supervisor to kill the work process, and after the whole processing is finished, the task controller calls the kill command to kill the Nimbus and the Supervisor and releases the master control node and the work node.
The description and applications of the invention herein are illustrative and are not intended to limit the scope of the invention to the embodiments described above. Variations and modifications of the embodiments disclosed herein are possible, and alternative and equivalent various components of the embodiments will be apparent to those skilled in the art. It will be clear to those skilled in the art that the present invention may be embodied in other forms, structures, arrangements, proportions, and with other components, materials, and parts, without departing from the spirit or essential characteristics thereof. Other variations and modifications of the embodiments disclosed herein may be made without departing from the scope and spirit of the invention.
Claims (8)
1. A big data real-time processing method comprises the following steps:
receiving real-time data;
creating N main control nodes according to the data receiving speed and the receiving total amount;
distributing data to N main control nodes;
acquiring real-time processing capacity data of a cluster server;
selecting N working nodes according to the processing capacity of the cluster server;
the N main control nodes send data to the N working nodes;
wherein, the step of creating N main control nodes according to the data receiving speed and the receiving total amount comprises the following substeps:
calculating the data receiving speed;
calculating a reception total amount according to a predetermined time interval;
evaluating the minimum and maximum processing capacity of the main control node according to the thread number of the main control node and the capacity of a memory;
selecting the optimal number N of the main control nodes according to the receiving speed and the receiving total amount of the data and the minimum and maximum processing capacity of the main control nodes;
n master nodes are created.
2. The processing method of claim 1, wherein distributing the data to the N master nodes comprises:
dividing the data into N parts;
configuring a label for each data;
storing the label in a data distribution list;
and distributing each piece of data to a corresponding main control node, and processing the data by the main control node.
3. The processing method of claim 1, wherein obtaining real-time processing capability data of cluster servers comprises determining real-time processing capability of a cluster according to CPU processing capability of idle servers in the cluster servers and storage capacity of a memory.
4. The process of claim 1 wherein selecting N worker nodes based on the processing capabilities of the cluster servers comprises sorting the processing capabilities of each of the cluster servers and selecting the top N worker nodes.
5. A task controller comprising the following components:
a receiver for receiving real-time data;
the processor is used for creating N main control nodes according to the data receiving speed and the receiving total amount; distributing data to N main control nodes; acquiring real-time processing capacity data of a cluster server; selecting N working nodes according to the processing capacity of the cluster server; the N main control nodes send data to the N working nodes;
the processor comprises a creation module for creating N main control nodes according to the data receiving speed and the receiving total amount, wherein the creation module comprises the following sub-modules:
a speed calculation unit that calculates a data reception speed;
a reception total amount calculation unit calculating a reception total amount at predetermined time intervals;
the processing capacity calculation module is used for evaluating the minimum and maximum processing capacities of the main control node according to the number of threads distributed to the main control node by the task controller and the capacity of the memory;
the selection unit selects the optimal number N of the main control nodes and the processing capacity of the main control nodes according to the receiving speed and the receiving total amount of the data and the minimum and maximum processing capacities of the main control nodes;
and the creating unit is used for creating N main control nodes.
6. The task controller of claim 5 wherein the processor includes a distribution module for distributing data among the N master nodes, the distribution module including the following subcomponents:
a dividing unit that divides the data into N parts;
a label unit for configuring a label for each data;
the list unit stores the labels into a data distribution list;
and the distribution unit distributes each part of data to the corresponding main control node, and the main control node processes the data.
7. The task controller of claim 5 wherein obtaining real-time processing capability data for the cluster servers comprises determining the real-time processing capability of the cluster based on the CPU processing capability of the idle servers in the cluster and the storage capacity of the memory.
8. A big data processing system, comprising:
the client sides are used for acquiring real-time data;
the task controller of one of claims 5 to 7;
and the cluster server is used for processing the task data issued by the task controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710664834.6A CN107783731B (en) | 2017-08-07 | 2017-08-07 | Big data real-time processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710664834.6A CN107783731B (en) | 2017-08-07 | 2017-08-07 | Big data real-time processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107783731A CN107783731A (en) | 2018-03-09 |
| CN107783731B true CN107783731B (en) | 2020-12-01 |
Family
ID=61437738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710664834.6A Active CN107783731B (en) | 2017-08-07 | 2017-08-07 | Big data real-time processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107783731B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110442508B (en) * | 2018-05-03 | 2023-05-23 | 阿里巴巴集团控股有限公司 | Test task processing method, device, equipment and medium |
| CN109597746B (en) * | 2018-12-26 | 2022-05-13 | 荣科科技股份有限公司 | Fault analysis method and device |
| CN113254220A (en) * | 2021-07-01 | 2021-08-13 | 国汽智控(北京)科技有限公司 | Networked automobile load cooperative control method, device, equipment and storage medium |
| CN113965587B (en) * | 2021-09-18 | 2022-04-22 | 苏州浪潮智能科技有限公司 | Data acquisition method, device, equipment and medium of artificial intelligence platform |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033889B (en) * | 2009-09-29 | 2012-08-22 | 熊凡凡 | Distributed database parallel processing system |
| CN103716381B (en) * | 2013-12-12 | 2017-04-12 | 华为技术有限公司 | Control method and management node of distributed system |
| US10177994B2 (en) * | 2014-08-13 | 2019-01-08 | Microsoft Technology Licensing, Llc | Fault tolerant federation of computing clusters |
| CN106874109A (en) * | 2016-12-29 | 2017-06-20 | 朗新科技股份有限公司 | A kind of distributed job distribution processing method and system |
-
2017
- 2017-08-07 CN CN201710664834.6A patent/CN107783731B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107783731A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107783731B (en) | Big data real-time processing method and system | |
| US10956424B2 (en) | Application recommending method and system, and server | |
| CN107291546B (en) | Resource scheduling method and device | |
| US7631034B1 (en) | Optimizing node selection when handling client requests for a distributed file system (DFS) based on a dynamically determined performance index | |
| US8024737B2 (en) | Method and a system that enables the calculation of resource requirements for a composite application | |
| US20100153482A1 (en) | Cloud-Based Automation of Resources | |
| CN105183299B (en) | A kind of man-machine interface service processing system and method | |
| CN105656962A (en) | Service calling method and device | |
| US11190431B2 (en) | Prioritized client-server communications based on server health | |
| CN106209482A (en) | A kind of data center monitoring method and system | |
| RU2016103796A (en) | SYSTEM AND METHOD OF MANAGING THE DATA BAR | |
| US20180006903A1 (en) | Performance assurance using workload phase detection | |
| CN103019853A (en) | Method and device for dispatching job task | |
| CN106557369A (en) | A kind of management method and system of multithreading | |
| US10419305B2 (en) | Visualization of workload distribution on server resources | |
| JP2014032674A (en) | Virtual machine resource arrangement system and method for the same | |
| CN103139104A (en) | Network transmission service class adjustment method, data terminal and network server | |
| CN109257399B (en) | Cloud platform application program management method, management platform and storage medium | |
| CN108509256B (en) | Method and device for scheduling running device and running device | |
| CN105049509A (en) | Cluster scheduling method, load balancer and clustering system | |
| CN108259568B (en) | Task allocation method and device, computer readable storage medium and electronic equipment | |
| CN113672500A (en) | Deep learning algorithm testing method and device, electronic device and storage medium | |
| CN114465915B (en) | CDN bandwidth prediction method, device and system and electronic equipment | |
| CN108733545B (en) | Pressure testing method and device | |
| CN109144846B (en) | Test method and device for testing server |
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 |