CN110308989A - A kind of resource management apparatus and method for OpenStack across data center - Google Patents
A kind of resource management apparatus and method for OpenStack across data center Download PDFInfo
- Publication number
- CN110308989A CN110308989A CN201910470637.XA CN201910470637A CN110308989A CN 110308989 A CN110308989 A CN 110308989A CN 201910470637 A CN201910470637 A CN 201910470637A CN 110308989 A CN110308989 A CN 110308989A
- Authority
- CN
- China
- Prior art keywords
- resource
- data center
- data
- management apparatus
- environment configurations
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/069—Management of faults, events, alarms or notifications using logs of notifications; Post-processing of notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The resource management apparatus and method that the present invention relates to a kind of for OpenStack across data center, the device include: multiple data centers;Multiple probes respectively correspond each data center's setting, for monitoring data center's state in real time, and acquire the status information of the data center to send with hollow resource information;One database, for the status information and hollow resource information to be carried out data storage;One configuration synchronization module, synchronizes the environment configurations of the data center for being responsible for;One scheduling of resource module, for realizing the unified resource scheduling between the data center.The present invention is able to achieve resource United Dispatching of the openstack across data center, and realizes multiple data centers global monitoring, management resource and system configuration.
Description
Technical field
The present invention relates to field of cloud computer technology, more particularly to openstack cloud computing platform across data center resource
Managing device and method.
Background technique
OpenStack is the cloud computing service platform of an open source, for public cloud and private clound etc. provide one it is expansible,
Telescopic cloud computing service can control the resource pools such as large-scale calculating, storage, network by data center.
With the large scale deployment of OpenStack platform, cloud data center deploys thousands of physical node, these
Physical node belongs to different data centers, and data center is in different geographical locations again.Openstack version is supported at present
Multiple data centers Managed Solution be: in a set of openstack of each data center deployment, these data centers
Openstack shares a keystone module and horizon module, i.e., unified authentication and operation interface.But its
His serviced component is constant, and each openstack system is not interfere with each other, without Resource Dependence;Various resources all in local acquisition, guarantee
To storage, the access of computing resource is remained in local data.
The existing multiple data centers Managed Solution of Openstack, although providing unified authentication and operation interface,
But be also completely independent between each data center, there are several point defects in actual use:
1) resources such as their calculating, storage and mirror image are independent, cannot achieve the resource across data center and unifiedly and flexibly adjust
Degree;
Although 2) share keystone module and horizon module, system manager can only be same in operation interface
When monitor and operation one data center, for example, can only check current data center resource and configuration current data center, no
It can global monitoring and operation;
3) because sharing the same keystone module and horizon module, the keystone of any one data center
Module and horizon module error, then all data centers are all unavailable.
Therefore, the existing multiple data centers Managed Solution of Openstack is not met by the system administration of actual production environment
Demand.For Openstack across defect existing for data center, Research on Resource Management Technology of the invention mainly has two sides
Face: first is that the resource across data center unifies dynamic dispatching;Second is that being realized under conditions of each data center is completely independent operation
Multiple data centers global monitoring, management resource and system configuration.
Invention " a method of it is shared based on the more region mirror image resources of OpenStack ", this method comprises the following steps:
It disposes more region cloud systems and shares glance module;It is more that user under different tenants can specify different sharing policy realizations
Mirror image resources or snapshot under region it is shared.The present invention uses the setting mirror image resources in more region to share, and both may be used
To reduce the storage of disk, and the utilization rate of resource can be improved.Meanwhile flexible Resources Sharing, it can be convenient difference
The efficient utilization of resource between tenant between difference region, this also greatly improves the service efficiency of cloud system, ensure that
System high efficiency is smoothly run.The patent is mirror image resources sharing method, and sharing mode is shared glance module, this human hair
Resource management in bright includes many-sided resource such as user, calculating, storage, network, mirror image, and way to manage is also not over altogether
Enjoy opensack glance module.
Summary of the invention
In order to solve the above technical problem, the present invention provides a kind of resource managements for OpenStack across data center
Device characterized by comprising
Multiple data centers;
Multiple probes respectively correspond each data center's setting, for monitoring data center's state in real time, and acquire
The status information of the data center with hollow resource information to send;
One database, for the status information and hollow resource information to be carried out data storage;
One configuration synchronization module, synchronizes the environment configurations of the data center for being responsible for;
One scheduling of resource module, for realizing the unified resource scheduling between the data center.
Above-mentioned resource management apparatus, which is characterized in that the status information includes running state information and configuration status letter
Breath.
Above-mentioned resource management apparatus, which is characterized in that the environment configurations include: again
Environment configurations request execution module, described for requesting the relevant environment needed before resource configuration to be synchronized to user
Data center;
Fault-tolerant module executes Fault recovery for providing fault tolerant mechanism.
Above-mentioned resource management apparatus, which is characterized in that the scheduling of resource module is by the way that dispatching algorithm is arranged by user
Request dynamic it is dispatched to the data center.
Above-mentioned resource management apparatus, which is characterized in that the data-base recording content includes: heart time, calls
Whether Compute API is successful, whether environment configurations synchronize, CPU, memory, disk surplus and/or network IP quantity, wherein
The heart time is the time of the probe returned data.
Above-mentioned resource management apparatus, which is characterized in that the configuration synchronization module further includes whether an environment configurations synchronize
Judgment module, for judging the data center environment configuration whether in synchronous regime before implementing scheduling of resource.
Above-mentioned resource management apparatus, which is characterized in that the dispatching algorithm is worst adjustment procedure.
A method of for across the data center carry out resource management of OpenStack characterized by comprising
It monitors step in real time, by the way that the probe of multiple each data centers of correspondence is arranged, monitors the data center in real time
State, and acquire the status information of the data center with hollow resource information;
A database is arranged in information storing step, and the status information and hollow resource information are carried out data storage;
Configuration synchronization procedure synchronizes the environment configurations of the data center for being responsible for;
Scheduling of resource step, for realizing the unified resource scheduling between the data center.
Above-mentioned method for managing resource, which is characterized in that the status information includes running state information and configuration status letter
Breath.
Above-mentioned method for managing resource, which is characterized in that the environment configurations step includes: again
Environment configurations request step, for requesting the relevant environment needed before resource configuration to be synchronized to the data user
Center;
Fault-tolerant step executes Fault recovery for providing fault tolerant mechanism.
Above-mentioned method for managing resource, which is characterized in that the scheduling of resource step is by the way that dispatching algorithm is arranged by user
Request dynamic it is dispatched to the data center.
Above-mentioned resource management apparatus, which is characterized in that the data-base recording content includes: heart time, calls
Whether Compute API is successful, whether environment configurations synchronize, CPU, memory, disk surplus and/or network IP quantity, wherein
The heart time is the time of the probe returned data.
Above-mentioned resource management apparatus, which is characterized in that the configuration synchronization procedure further includes whether an environment configurations synchronize
Judgment step, for judging data center environment configuration whether in synchronous regime before implementing scheduling of resource.
Above-mentioned resource management apparatus, which is characterized in that the dispatching algorithm is worst adjustment procedure.
Above-mentioned method for managing resource, which is characterized in that the environment configurations request step further comprises:
User initiates environment configurations request step;
Ergodic data Center List judges whether it is empty, if it is not, then one new thread of starting goes to obtain in the data
Heart IP calls the data center API, executes request, if it is, terminating;
Judge whether implementing result succeeds, and log is written into result and function parameter, returns to implementing result.
Above-mentioned method for managing resource, which is characterized in that the fault-tolerant step further comprises:
The case where traversing log sheet, judging whether there is environment configurations request failure, if there is then executing Fault recovery step;
Judge to execute and whether succeed, then modify log sheet in this way, executes Fault recovery step until traversal if not being to continue with
It is fully completed;
Further judge whether the data center calls success, if still there is calling unsuccessful, continues to execute mistake
Recovering step.
Above-mentioned method for managing resource, which is characterized in that the scheduling of resource step further comprises:
User initiates resource bid request;
Traverse resource request number;
Calculate data center's idling-resource ranking;
Judge whether data center's idling-resource number is greater than zero, if it is, in the data that distribution ranks the first
The heart gives the user;If it is not, then the resource request of the user dispatches failure.
Detailed description of the invention
Fig. 1 is the resource unified management architecture diagram across data center.
Fig. 2 is data center's running state monitoring probe flow chart.
Fig. 3 environment configurations process execution request flow chart.
Fig. 4 error recovery procedure flow chart.
Fig. 5 data center resource United Dispatching program flow diagram.
Specific embodiment
Embodiment 1:
Method for managing resource for openstack across data center can guarantee each data center's independent operating, and can be full
The resource United Dispatching of Zu Ge data center and the demand of global monitoring management.
Key point 1, data center's running state monitoring;Whether dynamic realtime obtains each data center's state good, and unites
Ji Ge data center idling-resource;State includes operating status and configuration status.
Key point 2, data center environment configure management by synchronization;Data synchronization mechanism is provided, user needs before requesting resource
Relevant environment configuration be synchronized to each data center, and provide fault tolerant mechanism.
Key point 3, data center resource United Dispatching;Dispatching algorithm is provided, by being dispatched to for user resources request dynamic
Each data center.
The invention also discloses a kind of cloud computing platforms based on OpenStack system, fill including the resource management
It sets.
The invention also provides a kind of storage mediums, for storing the computer journey for executing a kind of method for managing resource
Sequence.
General technical effect: the present invention is able to achieve resource United Dispatching of the openstack across data center, and realizes majority
According to center global monitoring, management resource and system configuration.
It is more clearly understandable for features described above and effect of the invention can be illustrated, hereafter again for an embodiment, and cooperate
Figure of description is described in detail below.
Embodiment 2:
Resource unified management across data center realizes that framework is as shown in Figure 1.Each data center 151 disposes operating status
Probe 141 is monitored, probe 141 is responsible for the openstack system running state of acquisition data center 151 and the inanition of data center
Resource, and these information are stored in database;Configuration synchronization module 11 is responsible for synchronizing the environment configurations of each data center 151, main
It to include environment configurations process execution request and error recovery procedure;Resource United Dispatching module 12 executes each data center 151
Between scheduling of resource.
151 running state monitoring probe 141 of data center, whether the operating status for grasping each data center in real time is good,
Idling-resource is counted, as shown in Figure 2.Specific embodiment is as follows:
S01, the real-time condition that each data center is saved with a database table, field includes heart time, service_
Ok and data_ok, cpu, memory, disk, network ip quantity etc.;Heart time is the time of probe returned data, service_
Ok is openstack system mode, and data_ok is whether data center environment configuration synchronizes.
S02, probe were every 30 seconds calling data center openstack compute api, if calling successfully
Service_ok is true, and call result includes cpu, memory, disk surplus.These data are stored in database table by probe
In, when heart time is newest and service_ok and data_ok is true, then it represents that the data center is available.
Whether scheduling of resource successfully relies on some environment configurations, therefore before scheduling of resource, it is to be ensured that each data center
Environment configurations be synchronous, if the environment configurations of certain data center are asynchronous, its position data_ok is designated as false.
The module includes environment configurations process execution request and error recovery procedure.Error recovery procedure is that a backstage timing executes
Program, responsible traversal log sheet, those execution, which are failed, and reform the function execution record that field is true re-executes one
It is secondary, and will not reform data_ok position of the field for the data center of true after having traversed and be designated as true.Specific embodiment
It is as follows:
S01, as shown in figure 3, user initiates environment configurations request, environment configurations requestor is by ergodic data central series
Table, each data center will start a new thread, and thread is responsible for calling data center api, will knot if running succeeded
Log sheet is written in fruit and function parameter, returns to implementing result;If executing failure, if the request results will affect resource tune
Degree, then the position data_ok for modifying the data center in S0 table is false.
S02, as shown in figure 4, error recovery procedure is timing routine, log sheet can be constantly traversed, if the weight of record
Doing field is true, then executes Fault recovery function, the field of reforming that the record is modified if function runs succeeded is
false.After having traversed log sheet, data center is judged whether there is also there is the record for reforming field as true, if without if
The position data_ok for modifying the data center is true.
Data center resource United Dispatching module, as shown in figure 5, specific implementation method is as follows:
S01, regulation user resources request format are that { number: N number of, flavor:{ cpu:N is a, memory: N M, disk: N
G, IP:N }, data center: { } }, how many part resource request is number indicate, flavor indicates what a resource request required
Resource details, data center indicates that user can specify dispatches in which data center, indicates if it is sky in all data
It is dispatched in center.
S02, the idling-resource in order to balance each data center, dispatching algorithm use worst adjustment procedure, i.e., selection is empty every time
The not busy maximum data center's scheduling of resource.
S03, we provide data center's idling-resource number={ cpu: CPU number/flavor.cpu of data center's free time
Part, memory: data center's free memory size/flavor. memory part, disk: data center's free disk size/flavor.
Disk part, IP: IP number/flavor.IP parts of data center's free time }, we choose, and CPU, memory, disk, number is minimum in IP
The number as the data center, then to each data center resource number ranking, the more forward expression idling-resource of ranking is more
It is more.
S04, the data center for being suitble to scheduling for a resource request distribution every time, then update data center's idling-resource
Ranking is suitble to the data center of scheduling for lower a resource allocation, if the number of all data centers of current standings is less than
1, then the data center that do not dispatch properly terminates program.
Claims (19)
1. a kind of resource management apparatus for OpenStack across data center characterized by comprising
Multiple data centers;
Multiple probes respectively correspond each data center's setting, for monitoring data center's state in real time, and described in acquisition
The status information of data center and hollow resource information are to send;
One database, for the status information and hollow resource information to be carried out data storage;
One configuration synchronization module, synchronizes the environment configurations of the data center for being responsible for;
One scheduling of resource module, for realizing the unified resource scheduling between the data center.
2. resource management apparatus according to claim 1, which is characterized in that the status information includes running state information
With configuration status information.
3. resource management apparatus according to claim 1, which is characterized in that the environment configurations include: again
Environment configurations request execution module, for requesting the relevant environment needed before resource configuration to be synchronized to the data user
Center;
Fault-tolerant module executes Fault recovery for providing fault tolerant mechanism.
4. resource management apparatus according to claim 3, which is characterized in that the scheduling of resource module is adjusted by setting
User's request dynamic is dispatched to the data center by degree algorithm.
5. resource management apparatus according to claim 1, which is characterized in that the data-base recording content includes: heartbeat
Time calls whether Compute API is successful, whether environment configurations synchronize, CPU, memory, disk surplus and/or network IP
Quantity, wherein the heart time is the time of the probe returned data.
6. resource management apparatus according to claim 1 or 3, which is characterized in that the configuration synchronization module further includes one
Whether environment configurations synchronize judgment module, for judging whether the data center environment configuration is located before implementing scheduling of resource
In synchronous regime.
7. resource management apparatus according to claim 4, which is characterized in that the dispatching algorithm is worst adjustment procedure.
8. a kind of method for across the data center carry out resource management of OpenStack characterized by comprising
It monitors step in real time, by the probe of the multiple each data centers of correspondence of setting, monitors data center's state in real time,
And acquire the status information and hollow resource information of the data center;
A database is arranged in information storing step, and the status information and hollow resource information are carried out data storage;
Configuration synchronization procedure synchronizes the environment configurations of the data center for being responsible for;
Scheduling of resource step, for realizing the unified resource scheduling between the data center.
9. method for managing resource according to claim 8, which is characterized in that the status information includes running state information
With configuration status information.
10. method for managing resource according to claim 8, which is characterized in that the environment configurations step includes: again
Environment configurations request step, for requesting the relevant environment needed before resource configuration to be synchronized in the data user
The heart;
Fault-tolerant step executes Fault recovery for providing fault tolerant mechanism.
11. method for managing resource according to claim 8, which is characterized in that the scheduling of resource step is to pass through setting
User's request dynamic is dispatched to the data center by dispatching algorithm.
12. resource management apparatus according to claim 8, which is characterized in that the data-base recording content includes: heartbeat
Time calls whether Compute API is successful, whether environment configurations synchronize, CPU, memory, disk surplus and/or network IP
Quantity, wherein the heart time is the time of the probe returned data.
13. the resource management apparatus according to claim 8 or 10, which is characterized in that the configuration synchronization procedure further includes
The judgment step whether one environment configurations synchronize, for judging that data center environment configuration is before implementing scheduling of resource
It is no to be in synchronous regime.
14. resource management apparatus according to claim 11, which is characterized in that the dispatching algorithm is worst adjustment procedure.
15. method for managing resource according to claim 10, which is characterized in that the environment configurations request step is further
Include:
User initiates environment configurations request step;
Ergodic data Center List judges whether it is empty, if it is not, then one new thread of starting goes to obtain the data center IP,
The data center API is called, request is executed, if it is, terminating;
Judge whether implementing result succeeds, and log is written into result and function parameter, returns to implementing result.
16. method for managing resource according to claim 10, which is characterized in that the fault-tolerant step further comprises:
The case where traversing log sheet, judging whether there is environment configurations request failure, if there is then executing Fault recovery step;
Judge to execute and whether succeed, then modify log sheet in this way, executes Fault recovery step until traversal is whole if not being to continue with
It completes;
Further judge whether the data center calls success, if still there is calling unsuccessful, continues to execute Fault recovery
Step.
17. method for managing resource according to claim 8, which is characterized in that the scheduling of resource step further comprises:
User initiates resource bid request;
Traverse resource request number;
Calculate data center's idling-resource ranking;
Judge whether data center's idling-resource number is greater than zero, if it is, the data center that ranks the first of distribution to
The user;If it is not, then the resource request of the user dispatches failure.
18. a kind of cloud computing platform based on OpenStack system, including the resource such as claim 1 to 8 as described in any one
Managing device.
19. a kind of storage medium requires the calculating of any one method for managing resource in 8 to 17 for storing perform claim
Machine program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910470637.XA CN110308989A (en) | 2019-05-31 | 2019-05-31 | A kind of resource management apparatus and method for OpenStack across data center |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910470637.XA CN110308989A (en) | 2019-05-31 | 2019-05-31 | A kind of resource management apparatus and method for OpenStack across data center |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110308989A true CN110308989A (en) | 2019-10-08 |
Family
ID=68075240
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910470637.XA Pending CN110308989A (en) | 2019-05-31 | 2019-05-31 | A kind of resource management apparatus and method for OpenStack across data center |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110308989A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114024978A (en) * | 2020-07-15 | 2022-02-08 | 中移(苏州)软件技术有限公司 | Cloud resource synchronization method, device, node and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102916974A (en) * | 2012-11-07 | 2013-02-06 | 曙光信息产业股份有限公司 | Cluster configuration updating method |
CN103401938A (en) * | 2013-08-07 | 2013-11-20 | 西安电子科技大学 | Resource distribution system based on service features under distributed cloud architecture and method thereof |
CN103973815A (en) * | 2014-05-27 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Method for unified monitoring of storage environment across data centers |
CN104731912A (en) * | 2015-03-24 | 2015-06-24 | 浪潮集团有限公司 | Message transmission method and device for message middleware MQ |
US9363190B2 (en) * | 2013-07-31 | 2016-06-07 | Manjrasoft Pty. Ltd. | System, method and computer program product for energy-efficient and service level agreement (SLA)-based management of data centers for cloud computing |
CN106293872A (en) * | 2016-07-27 | 2017-01-04 | 云南电网有限责任公司信息中心 | A kind of SLA resources balance management-control method based on resource pool |
CN107612787A (en) * | 2017-11-06 | 2018-01-19 | 南京易捷思达软件科技有限公司 | A kind of cloud hostdown detection method for cloud platform of being increased income based on Openstack |
CN109450693A (en) * | 2018-11-23 | 2019-03-08 | 金色熊猫有限公司 | Mixed cloud monitoring system and the monitoring method for using it |
-
2019
- 2019-05-31 CN CN201910470637.XA patent/CN110308989A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102916974A (en) * | 2012-11-07 | 2013-02-06 | 曙光信息产业股份有限公司 | Cluster configuration updating method |
US9363190B2 (en) * | 2013-07-31 | 2016-06-07 | Manjrasoft Pty. Ltd. | System, method and computer program product for energy-efficient and service level agreement (SLA)-based management of data centers for cloud computing |
CN103401938A (en) * | 2013-08-07 | 2013-11-20 | 西安电子科技大学 | Resource distribution system based on service features under distributed cloud architecture and method thereof |
CN103973815A (en) * | 2014-05-27 | 2014-08-06 | 浪潮电子信息产业股份有限公司 | Method for unified monitoring of storage environment across data centers |
CN104731912A (en) * | 2015-03-24 | 2015-06-24 | 浪潮集团有限公司 | Message transmission method and device for message middleware MQ |
CN106293872A (en) * | 2016-07-27 | 2017-01-04 | 云南电网有限责任公司信息中心 | A kind of SLA resources balance management-control method based on resource pool |
CN107612787A (en) * | 2017-11-06 | 2018-01-19 | 南京易捷思达软件科技有限公司 | A kind of cloud hostdown detection method for cloud platform of being increased income based on Openstack |
CN109450693A (en) * | 2018-11-23 | 2019-03-08 | 金色熊猫有限公司 | Mixed cloud monitoring system and the monitoring method for using it |
Non-Patent Citations (1)
Title |
---|
王煜炜;程彤;卢兴;黄艳;: "面向多数据中心的统一资源调度机制研究", 《科技经济导刊 2018年第2期》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114024978A (en) * | 2020-07-15 | 2022-02-08 | 中移(苏州)软件技术有限公司 | Cloud resource synchronization method, device, node and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109885389B (en) | Parallel deep learning scheduling training method and system based on container | |
EP3819757A1 (en) | Edge application management method and system | |
US11307943B2 (en) | Disaster recovery deployment method, apparatus, and system | |
CN103778031B (en) | Distributed system multilevel fault tolerance method under cloud environment | |
WO2019154394A1 (en) | Distributed database cluster system, data synchronization method and storage medium | |
CN108337303A (en) | A kind of method of data synchronization and distributed system | |
CN108920153B (en) | Docker container dynamic scheduling method based on load prediction | |
CN111405055A (en) | Multi-cluster management method, system, server and storage medium | |
CN106850260A (en) | A kind of dispositions method and device of virtual resources management platform | |
US20210092188A1 (en) | Edge application management method and system | |
CN110990200B (en) | Flow switching method and device based on multiple active data centers | |
CN109151045A (en) | A kind of distribution cloud system and monitoring method | |
CN106302806A (en) | A kind of method of data synchronization, system, synchronous obtaining method and relevant apparatus | |
CN107357688A (en) | Distributed system and its fault recovery method and device | |
CN114466027B (en) | Cloud primary database service providing method, system, equipment and medium | |
CN113064744A (en) | Task processing method and device, computer readable medium and electronic equipment | |
CN110489225A (en) | A kind of service expansion method, device and equipment based on message queue | |
CN111880934A (en) | Resource management method, device, equipment and readable storage medium | |
CN113760513B (en) | Distributed task scheduling method, device, equipment and medium | |
CN104793981B (en) | A kind of online snapshot management method and device of cluster virtual machine | |
CN110099084A (en) | A kind of method, system and computer-readable medium guaranteeing storage service availability | |
CN113515316A (en) | Novel edge cloud operating system | |
CN109558239A (en) | A kind of method for scheduling task, device, system, computer equipment and storage medium | |
CN110308989A (en) | A kind of resource management apparatus and method for OpenStack across data center | |
CN113672336A (en) | K8S container cluster deployment method, device, equipment and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191008 |
|
RJ01 | Rejection of invention patent application after publication |