CN107948249A - Big data plateau elastic telescopic method based on service discovery and container technique - Google Patents
Big data plateau elastic telescopic method based on service discovery and container technique Download PDFInfo
- Publication number
- CN107948249A CN107948249A CN201711062730.4A CN201711062730A CN107948249A CN 107948249 A CN107948249 A CN 107948249A CN 201711062730 A CN201711062730 A CN 201711062730A CN 107948249 A CN107948249 A CN 107948249A
- Authority
- CN
- China
- Prior art keywords
- node
- cluster
- big data
- service
- container
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/06—Generation of reports
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- 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
-
- 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
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- 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
- H04L67/56—Provisioning of proxy services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of big data plateau elastic telescopic method based on service discovery and container technique, comprise the following steps:(1) container technique modularization big data platform is used;(2) start big data cluster, register cluster metadata information;(3) report heartbeat data to service broker and update relevant information;(4) the agency service cycle reads big data cluster management information to service broker, judges whether node failure or demand alteration, if it is present performing the 5th step;Otherwise, the 6th step is performed;(5) if there are node failure situation, it tries recover the node container of failure;If there are demand alteration, metadata is changed according to demand, for cluster addition or deletion of node container;(6) the 3rd to the 5th step of the above is repeated, until cluster service terminates operation.The present invention can perceive big data platform interior state and stretch and improve cluster resource utilization rate so as to carry out effective elasticity.
Description
Technical field
It is more particularly to a kind of to be based on service discovery and container technique the present invention relates to cloud computing big data elastic telescopic field
Big data plateau elastic telescopic method.
Background technology
In cloud computing association area, elastic telescopic contributes to data center to keep the robustness of resource management, can reduce
Energy consumption alleviates system resource waste.The either show business such as the huge electric business of flow, game, or request amount fluctuation pole at present
The new media industry such as big video, live, is required for doing between " inadequate resource " and " wasting of resources " weighing.Deng Zifan is directed to
Horizontal extension and vertical telescopic each the shortcomings that, propose a kind of elasticity for being combined horizontal extension and vertical telescopic two ways
Stretch mode, but still remain the shortcomings that virtual machine technique is brought.Traditional solution is indicated in the research of Gandhi et al.
The defects of scheme:AlwaysOn can cause the serious wasting of resources by the way of full redundancy;Reactive uses delay start
Strategy, but when virtual machine or application environment start, setup time delays are too long, generally all can be more than 200 seconds;Predictive
Attempt to be fitted load module using strategies such as linear regressions, pre-cooling virtual machine shortens the setup times;Elastic telescopic side
Method according to request amount dynamic adjustresources dispensing, but due to virtual machine start delay the defects of, and employ with
The mode that Predictive is combined.
With the development of container technique, elastic telescopic method has obtained wider utilization.Such as YW Chen's et al.
Using the big data operation in the elastic telescopic acceleration isomerous environment of container in research, but need extension big in its solution
The correlation module of data platform, lacks versatility.Toffetti G et al. propose one kind using the elastic telescopic of container can
The micro services framework of self-management, can be with real-time response to cluster using etcd as state persistence center in its realization
The node failure of state, so as to fulfill self-recovery.HE Yu et al. propose a kind of High Performance Computing Cluster bullet based on container
Property stretch framework, but safeguard service state with single node in its realization, Single Point of Faliure easily occur, lack availability, Kan C etc.
People realizes a kind of elastic telescopic cloud platform based on container, which employs the mode being combined with Predictive methods
Carry out predicted flow rate change, it is impossible to tackle flow mutation.
Although recent years has carried out many research work on the elastic telescopic direction towards big data platform, so
And from traditional framework, elastic telescopic needs the change with reference to Predictive method predicted flow rates, this is because empty
Plan machine has the shortcomings that higher start delay, and such method can not tackle flow mutation in real time.In addition, it is currently based on
The elastic telescopic method of container technique however be exactly to need extra extension, otherwise be exactly in the presence of functionally the defects of, to current
Popular big data platform does not have general applicability.
The content of the invention
In view of above-mentioned the shortcomings of the prior art, it is an object of the present invention to provide one kind to be based on service discovery and container technique
Big data plateau elastic telescopic method, can according to service broker provide big data service life cycle information, so as to
Perceive the state change of cluster internal, for big data cluster provide on demand, flexible elastic telescopic service, and effectively improve
Cluster resource utilization rate.
In order to achieve the above object, the present invention adopts the following technical scheme that:
A kind of big data plateau elastic telescopic method based on service discovery and container technique of the present invention, including following step
Suddenly:
First step:Groupware encapsulation processing is carried out to major data platform using container technique;
Second step:The metadata catalog of big data cluster management is initialized, when big data cluster starts, pulls and opens
Corresponding big data platform assembly is moved, and cluster metadata information is registered to service broker;
Third step:The status monitor cycle of each mainframe cluster node reports heartbeat data to service broker, and more
New relevant information, realizes the state aware to cluster internal;
Four steps:The agency service cycle of mainframe cluster reads big data cluster management information to service broker, judges
With the presence or absence of node failure or demand alteration, if service broker does not receive the status number of container node in heart beat cycle
According to the node then is considered as node failure, the node operating status is labeled as failure by service broker from metadata at this time, instead
Node operating status labeled as effective, if there is node failure or demand alteration, then perform the 5th step;Otherwise,
Perform the 6th step;
5th step:If there are node failure situation, it tries recovers the node container of failure;If there are demand to change feelings
Condition, then change metadata according to demand, and corresponding agency service is added for cluster or deletion of node container;
6th step:The the 3rd to the 5th step of the above is repeated, until cluster service terminates operation.
As preferable technical solution, in the first step, at the carry out Groupware encapsulation to major data platform
Reason, specifically used Docker containers virtualization technology carry out mirror image encapsulation process to big data platform, form big data component
Storehouse, including Hadoop mirror images, Spark mirror images, Kafka mirror images and Storm mirror images.
As preferable technical solution, in the second step, the metadata catalog, specifically includes root as each note
128 GUID, the mark as each independent big data cluster individual, the subdirectory that the big data cluster of volume separately maintains
Relevant information and cluster demand the change metadata information of each node of storage cluster, wherein, the first number of cluster demand change
It is believed that breath, no change is with 0 mark, and increase node is with " 1 "+host ip character string identifications, and deletion of node is with " 2 "+host ip characters
String mark;The relevant information of each node of subdirectory storage cluster, specifically includes affiliated cluster ID, own IP address, node
Operating status, CPU usage, memory usage and I/O load situation, and stored using JSON forms, the node
Operating status, effectively with 0 mark, fails with 1 mark.
As preferable technical solution, in third step, the status monitor cycle of each mainframe cluster node
Heartbeat data is reported to service broker, and the method for updating relevant information is:
Status monitor obtains current hosts and obtains all containers operated on current hosts by container A PI
Relevant information, reports to service broker and heartbeat data and is updated, wherein, the relevant information specifically include current hosts with
And IP address, operating status and each resource information of each container on current hosts are operated in, each resource information includes CPU
Utilization rate, memory usage and I/O load situation;It is 5s to set the heartbeat packet response timeout cycle at the same time.
As preferable technical solution, in four steps, bridge of the service broker as service communication with the outside world,
All relevant informations for being stored in server-side are provided, are provided simultaneously with the function of renewal relevant information, the relevant information includes clothes
The program file of business operation, rely on storehouse, configuration and data;The agency service realizes asynchronous lead to using issue design pattern is subscribed to
Letter, all component information being responsible in periodic poll access subscription list, is handled each according to the service status information of acquisition
The node failure or demand alteration of node, carry out reset node or additions and deletions nodal operation on demand;It is described to judge whether to deposit
It is in the specific method that node failure or demand change:
According to the resource information of each node periodic feedback, the resource utilization information of 10 nearest heart beat cycles is obtained,
If a big data cluster container node has N number of, C is usedi、Mi、IiRepresent that the CPU usage of i-th of node, memory use respectively
Rate and I/O load, then each resource average service rate be WithTotal resources are comprehensive
Conjunction utilization rate is T=w1×Cavg+w2×Mavg+w3×Iavg, i.e.,Wherein ω1、ω2、
ω3The weight of CPU usage, memory usage and I/O load is represented respectively, and has ω1+ω2+ω3=1, ω1=ω2=
ω3=1/3, when having T in continuous 10 heart beat cycles>When 80%, then it represents that need in the minimum host node of load
One big data container node of middle increase, equally using T evaluation loads, change demand change metadata is character string " 1 "+host
ip;When having T in continuous 10 heart beat cycles<When 20%, then it represents that need to delete in the maximum host node of load
One big data container node, same demand change metadata of changing is character string " 2 "+host ip;Above-mentioned condition is not met,
It is then that need not change state by demand change metadata token.
As preferable technical solution, described to change metadata according to demand in the 5th step, corresponding agency service is
Cluster adds or the method for deletion of node container is:
If the initial of character string is " 1 ", when one of agency service is read representated by character string remainder
When ip is identical with itself institute generic ip, then increase container node operation is carried out;If the initial of character string is " 2 ", when it
In an agency service read ip representated by character string remainder it is identical with itself institute generic ip when, then carry out deletion appearance
Device nodal operation.
The present invention is had the following advantages relative to the prior art and effect:
1st, the present invention uses containerization solution, and changes in flow rate can obtain in real time from service broker, not only greatly
Reduction elastic telescopic response time, can with real-time perception to load change, so as to directly adjust number of containers, no longer
Need to be combined with Predictive methods.
2nd, the present invention can be enclosed in platform interior reality relative to the life cycle and service state of traditional big data platform
Existing, platform exterior is that stateless perceives, and the big data plateau elastic based on service discovery and container technique provided stretches
Method need not change the particular module of big data platform, check service state by the way of outside monitors poll, be suitable for
Most big data platform, specific general applicability.
Brief description of the drawings
Fig. 1 is the flow chart of the method for the present invention;
Fig. 2 is the implementation schematic diagram of the big data plateau elastic telescopic method based on service discovery and container technique.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings, but the implementation of the present invention and protection domain are not limited to
This.
Embodiment
As shown in Figure 1, being the flow chart of the method for the present invention, the big data of the invention based on service discovery and container technique is put down
Platform elastic telescopic method, specifically includes the description below:
1st, mirror image encapsulation process is carried out to big data platform using Docker containers virtualization technology, forms big data group
Part storehouse;
2nd, the metadata catalog of big data cluster management is initialized, when big data cluster starts, pulls and starts corresponding
Big data platform assembly, and cluster metadata information is registered to service broker, wherein, metadata catalog is every including root
128 GUID that the big data cluster of a registration separately maintains, as the mark of each independent big data cluster individual, son
Status information and cluster demand the change metadata information of each node of catalogue storage cluster, and the status information of each node is specific
Including affiliated cluster ID, IP address, node operating status, CPU usage, memory usage, I/O load situation, and use JSON
Form is stored;
3rd, the status monitor cycle of each mainframe cluster node reports heartbeat data to service broker, and updates all phases
Close information, including the IP address of current hosts, operating status and each resource information (including CPU usage, memory usage and
I/O load situation), and operate in the IP address, operating status and each resource information of each container on host (including CPU is used
Rate, memory usage and I/O load situation), while it is 5s to set the heartbeat packet response timeout cycle, is realized to cluster internal
State aware;
4th, the agency service cycle of mainframe cluster reads big data cluster management information to service broker, judges whether
Node failure or demand alteration, if it is present being transferred to step 5;Otherwise, it is transferred to step 6;
The method specifically judged is:
If in heart beat cycle service broker do not receive the status data of container node if by the node be considered as node lose
Effect, the node operating status is labeled as failure by service broker from metadata at this time, otherwise node operating status is labeled as having
Effect;According to the resource information of each node periodic feedback, the resource utilization information of 10 nearest heart beat cycles is obtained, if one
Big data cluster container node has N number of, uses Ci、Mi、IiRepresent the CPU usage of i-th of node respectively, memory usage and
I/O load, then each resource average service rate beWithTotal resources integrate
Utilization rate is T=w1×Cavg+w2×Mavg+w3×Iavg, i.e.,Wherein ω1,ω2,ω3
The weight of CPU usage, memory usage and I/O load is represented respectively, and has ω1+ω2+ω3=1 (acquiescence ω1=ω2=ω3
=1/3), when having T in continuous 10 heart beat cycles>When 80%, then it represents that need (same in the minimum host node of load
Sample uses T evaluations load) one big data container node of middle increase, change demand change metadata is corresponding information;When even
There is T in 10 continuous heart beat cycles<When 20%, then it represents that need to delete a big data in the maximum host node of load
Container node, same demand change metadata of changing is corresponding information;Do not meet above-mentioned condition and demand is then changed into metadata mark
State need not be changed by being denoted as.
The 5th, if there are node failure situation, it tries recovers the node container of failure;If there are demand alteration, root
Metadata is changed according to demand, corresponding agency service is added for cluster or deletion of node container.
6th, repeat above step 3 and arrive step 5, until cluster service terminates operation.
As shown in Fig. 2, give one kind of the big data plateau elastic telescopic method based on service discovery and container technique
Embodiment, the state aware elastic telescopic model are made of 3 service broker, agency service and status monitor parts, always
Body structure is designed using master-slave architecture, wherein bridge of the service broker as service communication with the outside world, there is provided all are stored in
The relevant information of server-side, including the program file of service operation, dependence storehouse, configuration and data etc., it is related to be provided simultaneously with renewal
The function of information;Agency service realizes asynchronous communication using issue design pattern is subscribed to, and is responsible for periodic poll access and subscribes to
All component information in list, handles the node failure of each node according to the service status information of acquisition or demand changes feelings
Condition, desirably carries out reset node or additions and deletions nodal operation;Status monitor is protected with registration center during service operation
The core of held state connection, main task are the state letters of real-time monitoring service accessibility, configuration information and each node component
Breath, i.e., periodically report heartbeat data to service broker, service broker is updated related status information.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention and from above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (6)
1. a kind of big data plateau elastic telescopic method based on service discovery and container technique, it is characterised in that including following
Step:
First step:Groupware encapsulation processing is carried out to major data platform using container technique;
Second step:The metadata catalog of big data cluster management is initialized, when big data cluster starts, pulls and starts phase
Big data platform assembly is answered, and cluster metadata information is registered to service broker;
Third step:The status monitor cycle of each mainframe cluster node reports heartbeat data, and more cenotype to service broker
Information is closed, realizes the state aware to cluster internal;
Four steps:The agency service cycle of mainframe cluster reads big data cluster management information to service broker, judges whether
There are node failure or demand alteration, if service broker does not receive the status data of container node in heart beat cycle
The node is considered as node failure, the node operating status is labeled as failure by service broker from metadata at this time, otherwise is saved
Point operating status if there is node failure or demand alteration, then performs the 5th step labeled as effectively;Otherwise, perform
6th step;
5th step:If there are node failure situation, it tries recovers the node container of failure;If there are demand alteration,
Metadata is then changed according to demand, and corresponding agency service is added for cluster or deletion of node container;
6th step:The the 3rd to the 5th step of the above is repeated, until cluster service terminates operation.
2. the big data plateau elastic telescopic method according to claim 1 based on service discovery and container technique, it is special
Sign is, in the first step, the carry out Groupware encapsulation processing to major data platform, specifically used Docker containers
Virtualization technology to big data platform carry out mirror image encapsulation process, formed big data Component Gallery, including Hadoop mirror images,
Spark mirror images, Kafka mirror images and Storm mirror images.
3. the big data plateau elastic telescopic method according to claim 1 based on service discovery and container technique, it is special
Sign is that in the second step, the metadata catalog, it is that the big data cluster each registered individually is tieed up to specifically include root
128 GUID of shield, the mark as each independent big data cluster individual, the correlation of each node of subdirectory storage cluster
Information and cluster demand change metadata information, wherein, the cluster demand changes metadata information, and no change is with 0 mark
Know, increase node is with " 1 "+host ip character string identifications, and deletion of node is with " 2 "+host ip character string identifications;The specific item is recorded
The relevant information of each node of accumulation, specifically include belonging to cluster ID, own IP address, node operating status, CPU usage,
Memory usage and I/O load situation, and stored using JSON forms, the node operating status, effectively with 0 mark
Note, fails with 1 mark.
4. the big data plateau elastic telescopic method according to claim 1 based on service discovery and container technique, it is special
Sign is, in third step, the status monitor cycle of each mainframe cluster node reports beats to service broker
According to, and the method for updating relevant information is:
Status monitor obtains current hosts and the correlation of all containers operated on current hosts is obtained by container A PI
Information, reports heartbeat data to service broker and is updated, wherein, the relevant information specifically includes current hosts and fortune
IP address, operating status and each resource information of each container of the row on current hosts, each resource information are used including CPU
Rate, memory usage and I/O load situation;It is 5s to set the heartbeat packet response timeout cycle at the same time.
5. the big data plateau elastic telescopic method according to claim 1 based on service discovery and container technique, it is special
Sign is, in four steps, bridge of the service broker as service communication with the outside world, there is provided all are stored in server-side
Relevant information, be provided simultaneously with the function of renewal relevant information, the program file of the relevant information including service operation, rely on
Storehouse, configuration and data;The agency service realizes asynchronous communication using issue design pattern is subscribed to, and is responsible for periodic poll and visits
Ask all component information in subscription list, the node failure of each node is handled according to the service status information of acquisition or demand becomes
More situation, carries out reset node or additions and deletions nodal operation on demand;It is described judge whether node failure or demand change
Specific method is:
According to the resource information of each node periodic feedback, the resource utilization information of 10 nearest heart beat cycles is obtained, if one
A big data cluster container node has N number of, uses Ci、Mi、IiRepresent respectively the CPU usage of i-th of node, memory usage, with
And I/O load, then each resource average service rate be WithTotal resources synthesis uses
Rate is T=w1×Cavg+w2×Mavg+w3×Iavg, i.e.,Wherein ω1、ω2、ω3Respectively
Represent the weight of CPU usage, memory usage and I/O load, and have ω1+ω2+ω3=1, ω1=ω2=ω3=1/
3, when having T in continuous 10 heart beat cycles>When 80%, then it represents that need to increase by one in the minimum host node of load
A big data container node, equally using T evaluation loads, change demand change metadata is character string " 1 "+host ip;When
There is T in continuous 10 heart beat cycles<When 20%, then it represents that need to delete one big number in the maximum host node of load
According to container node, same demand change metadata of changing is character string " 2 "+host ip;Above-mentioned condition is not met, then by demand
Change metadata token is that need not change state.
6. the big data plateau elastic telescopic method according to claim 1 based on service discovery and container technique, it is special
Sign is, in the 5th step, described to change metadata according to demand, corresponding agency service is added for cluster or deletion of node holds
The method of device is:
If the initial of character string is " 1 ", when one of agency service read ip representated by character string remainder with
When itself institute generic ip is identical, then increase container node operation is carried out;If the initial of character string is " 2 ", when wherein one
A agency service read ip representated by character string remainder it is identical with itself institute generic ip when, then carry out delete container section
Point operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711062730.4A CN107948249B (en) | 2017-11-02 | 2017-11-02 | large data platform elastic expansion method based on service discovery and container technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711062730.4A CN107948249B (en) | 2017-11-02 | 2017-11-02 | large data platform elastic expansion method based on service discovery and container technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107948249A true CN107948249A (en) | 2018-04-20 |
CN107948249B CN107948249B (en) | 2019-12-10 |
Family
ID=61934142
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711062730.4A Active CN107948249B (en) | 2017-11-02 | 2017-11-02 | large data platform elastic expansion method based on service discovery and container technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107948249B (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108897839A (en) * | 2018-06-26 | 2018-11-27 | 中国联合网络通信集团有限公司 | Data receiver method and system |
CN108958882A (en) * | 2018-06-06 | 2018-12-07 | 麒麟合盛网络技术股份有限公司 | A kind of container method of adjustment, device and system |
CN110034979A (en) * | 2019-04-23 | 2019-07-19 | 恒安嘉新(北京)科技股份公司 | A kind of proxy resources monitoring method, device, electronic equipment and storage medium |
CN110830289A (en) * | 2019-10-21 | 2020-02-21 | 华中科技大学 | Container abnormity monitoring method and monitoring system |
CN111432042A (en) * | 2020-03-02 | 2020-07-17 | 平安科技(深圳)有限公司 | Network address processing method, computer device and storage medium |
CN111708880A (en) * | 2020-05-12 | 2020-09-25 | 北京明略软件系统有限公司 | System and method for identifying class cluster |
CN112217885A (en) * | 2020-09-27 | 2021-01-12 | 普联国际有限公司 | Dynamic management method, device, equipment and storage medium for components |
CN112486513A (en) * | 2020-11-25 | 2021-03-12 | 湖南麒麟信安科技股份有限公司 | Container-based cluster management method and system |
CN112988329A (en) * | 2021-03-22 | 2021-06-18 | 北京思特奇信息技术股份有限公司 | Container configuration management method and system |
CN113377702A (en) * | 2021-07-06 | 2021-09-10 | 安超云软件有限公司 | Method and device for starting two-node cluster, electronic equipment and storage medium |
CN114762305A (en) * | 2019-11-28 | 2022-07-15 | 西门子股份公司 | Method for grabbing packets from containers in cluster context |
CN112217885B (en) * | 2020-09-27 | 2024-06-04 | 普联国际有限公司 | Dynamic management method, device, equipment and storage medium for components |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101594254A (en) * | 2009-06-30 | 2009-12-02 | 中国运载火箭技术研究院 | A kind of grid computing tolerance system and method based on agent skill group |
CN105119913A (en) * | 2015-08-13 | 2015-12-02 | 东南大学 | Web server architecture based on Docker and interactive method between modules |
CN106603594A (en) * | 2015-10-15 | 2017-04-26 | 中国电信股份有限公司 | Distributed service management method and system |
-
2017
- 2017-11-02 CN CN201711062730.4A patent/CN107948249B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101594254A (en) * | 2009-06-30 | 2009-12-02 | 中国运载火箭技术研究院 | A kind of grid computing tolerance system and method based on agent skill group |
CN105119913A (en) * | 2015-08-13 | 2015-12-02 | 东南大学 | Web server architecture based on Docker and interactive method between modules |
CN106603594A (en) * | 2015-10-15 | 2017-04-26 | 中国电信股份有限公司 | Distributed service management method and system |
Non-Patent Citations (3)
Title |
---|
CHUANQI KAN: ""DoCloud: An elastic cloud platform for Web applications based on Docker"", 《18TH INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY》 * |
WU, ZIMING,LIN, WEIWEI,ZHANG, ZILONG,WEN,: ""An Ensemble Random Forest Algorithm for Insurance Big Data Analysis"", 《 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING》 * |
YI-WEI CHEN, SHIH-HAO HUNG, CHIA-HENG TU, CHIH WEI YEH: ""Virtual Hadoop: MapReduce over Docker Containers with an Auto-Scaling Mechanism for Heterogeneous Environments"", 《PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON RESEARCH IN ADAPTIVE AND CONVERGENT SYSTEMS》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108958882A (en) * | 2018-06-06 | 2018-12-07 | 麒麟合盛网络技术股份有限公司 | A kind of container method of adjustment, device and system |
CN108897839B (en) * | 2018-06-26 | 2020-10-27 | 中国联合网络通信集团有限公司 | Data receiving method and system |
CN108897839A (en) * | 2018-06-26 | 2018-11-27 | 中国联合网络通信集团有限公司 | Data receiver method and system |
CN110034979A (en) * | 2019-04-23 | 2019-07-19 | 恒安嘉新(北京)科技股份公司 | A kind of proxy resources monitoring method, device, electronic equipment and storage medium |
CN110830289A (en) * | 2019-10-21 | 2020-02-21 | 华中科技大学 | Container abnormity monitoring method and monitoring system |
CN114762305A (en) * | 2019-11-28 | 2022-07-15 | 西门子股份公司 | Method for grabbing packets from containers in cluster context |
CN111432042A (en) * | 2020-03-02 | 2020-07-17 | 平安科技(深圳)有限公司 | Network address processing method, computer device and storage medium |
WO2021174730A1 (en) * | 2020-03-02 | 2021-09-10 | 平安科技(深圳)有限公司 | Network address processing method, computer device, and storage medium |
CN111708880A (en) * | 2020-05-12 | 2020-09-25 | 北京明略软件系统有限公司 | System and method for identifying class cluster |
CN112217885A (en) * | 2020-09-27 | 2021-01-12 | 普联国际有限公司 | Dynamic management method, device, equipment and storage medium for components |
CN112217885B (en) * | 2020-09-27 | 2024-06-04 | 普联国际有限公司 | Dynamic management method, device, equipment and storage medium for components |
CN112486513A (en) * | 2020-11-25 | 2021-03-12 | 湖南麒麟信安科技股份有限公司 | Container-based cluster management method and system |
CN112486513B (en) * | 2020-11-25 | 2022-08-12 | 湖南麒麟信安科技股份有限公司 | Container-based cluster management method and system |
CN112988329A (en) * | 2021-03-22 | 2021-06-18 | 北京思特奇信息技术股份有限公司 | Container configuration management method and system |
CN113377702A (en) * | 2021-07-06 | 2021-09-10 | 安超云软件有限公司 | Method and device for starting two-node cluster, electronic equipment and storage medium |
CN113377702B (en) * | 2021-07-06 | 2024-03-22 | 安超云软件有限公司 | Method and device for starting two-node cluster, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107948249B (en) | 2019-12-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107948249A (en) | Big data plateau elastic telescopic method based on service discovery and container technique | |
Zhou et al. | On cloud service reliability enhancement with optimal resource usage | |
CN103561055B (en) | Web application automatic elastic extended method under conversation-based cloud computing environment | |
CN103281366A (en) | Embedded agency monitoring device and method supporting real-time operating state acquiring | |
CN108196935A (en) | A kind of energy saving moving method of virtual machine towards cloud computing | |
CN104102543A (en) | Load regulation method and load regulation device in cloud computing environment | |
CN105515837B (en) | One kind being based on event driven high concurrent WEB flow generator | |
CN103716397B (en) | A kind of service-oriented simulation clock propulsion method | |
CN107122229A (en) | A kind of virtual machine restoration methods and device | |
CN107105049A (en) | Data migration method and device | |
Zhou et al. | Cost-effective hardware accelerator recommendation for edge computing | |
CN109005126A (en) | The processing method and equipment of data flow | |
CN102420850B (en) | Resource scheduling method and system thereof | |
Wan | Cloud Computing infrastructure for latency sensitive applications | |
CN110489203A (en) | A kind of container Scheduling Framework system | |
CN109634752A (en) | A kind of client request processing method and system based on page gateway | |
Zhang et al. | Cluster-aware virtual machine collaborative migration in media cloud | |
CN112044061A (en) | Game picture processing method and device, electronic equipment and storage medium | |
CN106959885A (en) | A kind of virtual machine High Availabitity realizes system and its implementation | |
Wang et al. | An efficient hybrid P2P MMOG cloud architecture for dynamic load management | |
CN109617960A (en) | A kind of web AR data presentation method based on attributed separation | |
CN116069460A (en) | Kubernetes container resource dynamic scheduling method based on monitoring system | |
Wang et al. | C3Meta: A Context-Aware Cloud-Edge-End Collaboration Framework Toward Green Metaverse | |
CN109634719A (en) | A kind of dispatching method of virtual machine, device and electronic equipment | |
CN110519101B (en) | Method and system for dynamic virtualization of performance management function of entity OLT (optical line terminal) |
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 |