CN104363277A - Allocation management system and management method for bandwidth resources in cloud game distributed system - Google Patents
Allocation management system and management method for bandwidth resources in cloud game distributed system Download PDFInfo
- Publication number
- CN104363277A CN104363277A CN201410636059.XA CN201410636059A CN104363277A CN 104363277 A CN104363277 A CN 104363277A CN 201410636059 A CN201410636059 A CN 201410636059A CN 104363277 A CN104363277 A CN 104363277A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- user
- game
- bandwidth
- server
- 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
-
- 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
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- 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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- 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
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an allocation management system for bandwidth resources in a cloud game distributed system. The allocation management system comprises a management system and a managed system. The management system comprises a master control server, a log server and a material storage server, the managed system comprises a server cluster, and the server cluster comprises a plurality of slave physical machines. A management method includes maintaining a real-time monitor for monitoring running states of virtual machines; providing resource occupation bases for a scheduling module. The allocation management system and the management method have the advantages that the user experience can be effectively improved, and network bandwidth jitter can be reduced by 20%.
Description
Technical field
The present invention relates to bandwidth resource allocation technical field in distributed system, specifically network bandwidth resources distribution system and method thereof in a kind of cloud game distributed system.
Background technology
Along with developing rapidly of Intel Virtualization Technology, kinds of schemes is deployed and is applied in field of cloud calculation.Such as VMware, the leader in virtual market, for whole industry provides business virtual machine product, increase income in community in addition at non-commercialization, KVM and XEN is two free but powerful virtualization scheme.Although virtual basic solution is increasingly mature, in concrete application scenarios, still there is problem much to be solved, this one of them be exactly the scheduling problem of resource.A lot of ripe effective ways and strategy has been had for the scheduling problem of cpu resource in virtual field, but about the scheduling of resource of the GPU network bandwidth is still also in the starting stage.
For cloud game, cloud game pattern briefly refers to that client uses remote connection software, be connected when carrying out long with the virtual machine operating in high in the clouds, cloud virtual machine carries out logical calculated, the image rendering of playing, and finally view data is passed back client, such user just can play at the situation experience 3D only having the hardware such as display, keyboard, mouse, eliminates the high cost that brings of equipment such as frequent updating high end games video card.But wherein there is the game experiencing of some problems affect user in this, urgently to be resolved hurrily.
Some phenomenon following and rule are found through experiments: 1, taking of bandwidth resources becomes positively related with the quantity of user.2, the bandwidth that each virtual machine takies is shaken very large up and down.3, suitable Bandwidth Allocation Policy is the guarantee to game fluency.In a word, when number of users is larger, the network bandwidth has become the Main Bottleneck of whole system, and this problem is never well solved now.
Summary of the invention
The present invention is directed to the deficiency that in existing cloud platform, network bandwidth resources dispatching method exists, propose the System and method for of bandwidth resource allocation management in a kind of distributed system.By using Network Programming Technology, in some clusters, building distributed framework, be referred to as BAM (Bandwidth Allocation Management), be responsible for each distribution from machine (slave) bandwidth resources in whole network.Whole framework core operates on main frame (master), and it is multiplexed etc. that the technology that core is used relates to epoll under Linux and asynchronous IO.Except the Scheduling Framework that this is general, the present invention is also integrated with two kinds of new network bandwidth dispatching methods with framework, is used for doing between the fluency of playing in overall network bandwidth sum single virtual machine weighing.These two kinds of methods are based on the distribution method (Fairness-allocationscheduling) of justice with based on the distribution method (Sharing-allocation scheduling) shared respectively, the former is the self-adapting dispatching method based on fairness specifically, strictly distributes equal bandwidth resources for each virtual machine; The latter is based on shared model, and each moment takies the few virtual machine of network bandwidth resources can remaining bandwidth Resourse Distribute to the many virtual machine of demand, and achieve sharing of resource, efficiency is higher but network fluctuation can be larger.These two kinds of methods are applicable to different application scenarioss.
Technical solution of the present invention is as follows:
Bandwidth resource allocation management system in a kind of cloud game distributed system, its feature is, comprise the management system be made up of main control server, log server and material storage server, and the server cluster be made up of some subordinate physical machines be managed system;
Described main control server is connected with described log server and material storage server respectively;
Described main control server, for obtaining the request from user, and analysis request, make response to request, for user distributes suitable virtual machine, run and play accordingly, the broadband resource between scheduling virtual machine distributes;
Described log server, for recording the running status of virtual machine, the service condition of CPU, GPU, bandwidth resources, and player information;
Described material storage server, for storing Game Virtual Machine image file;
The described system that is managed is some server clusters from physical machine composition, eachly from physical machine, has run some virtual machines, has one to play and remote desktop software in each virtual machine.
Described main control server is made up of connection management module, extensible policy module;
Described connection manager, for receiving the game request sent from user, select the subordinate physical machine of follow-up access, and final sum virtual machine being wherein connected, thus user and virtual machine having been coupled together after judging process;
Described extensible policy module, for the interface of manual intervention.
Described connection management module comprises virtual machine heap and integrated network bandwidth scheduling method two minor structures;
Described virtual machine heap obtains all CPU from physical machine, GPU, network bandwidth resources behaviour in service from log server, and safeguard a most rickle from physical machine resources occupation situation according to general status, take resource minimum be positioned at heap top from physical machine;
Integrated network broadband dispatching method comprises based on the distribution method of justice with based on the distribution method shared.
Bandwidth resource allocation management method in a kind of cloud game distributed system, its feature is, the method comprises the steps:
When step 1, game start, main control server obtains user and starts game request, analysis request, and starts as user disposes corresponding virtual machine;
Step 2, main control server choose the virtual machine on the most abundant physical machine of resource from the virtual machine of self is piled, and start this virtual machine;
Game on step 3, main control server startup virtual machine and remote desktop software, user and virtual machine are connected by remote desktop software;
After step 4, connection establishment, virtual machine picture is sent to user by network, and virtual machine also by the operational feedback of Network Capture user, makes user be able to operate game;
In step 5, game, the network traffics of main control server Real-Time Monitoring virtual machine, ensure by integrated network bandwidth scheduling method the fluency that each user plays games;
After step 6, game over, the connection of connection manager active disconnect user and subordinate physics machinery compartment, and suspend the operation of virtual machine, upgrade the resource information of virtual machine heap.
In described step 5, integrated network bandwidth scheduling method is selected for connection manager, is divided into the method for allocating bandwidth resources based on justice and the method for allocating bandwidth resources based on justice:
The described method for allocating bandwidth resources based on justice: be the network bandwidth that each virtual machine run allots a quota, this broadband is enough to meet the smooth minimum requirements run of game, preset the size of this network bandwidth, when the broadband resource that user uses exceedes default, main control server is by reducing the mode of quality of play, and the broadband resource reducing user uses;
The described method for allocating bandwidth resources based on justice: namely all virtual machines share an overall network bandwidth, if some virtual machine occupied bandwidths resource of a certain moment declines, then the rapid virtual machine that need bandwidth resources many to those unnecessary allocated bandwidth of main control server meeting.
Compared with prior art, the invention has the beneficial effects as follows:
(1) effectively improve Consumer's Experience, reduce by the network bandwidth shake of 20%.
(2) while guarantee user quality of play, can economize on resources for service provider.
(3) for service provider provides extra charge method, namely press nominal bandwidth and pay.
(4) more user, when service provider's resource scarcity, its impact on QoS of customer can be alleviated.
Accompanying drawing explanation
The topological diagram of the distributed cloud game system of Fig. 1
Game bandwidth resources service condition under the existing network bandwidth resources dispatching method of Fig. 2
Fig. 3 is based on the method for allocating bandwidth resources of justice
Fig. 4 is based on the method for allocating bandwidth resources shared
Embodiment
Elaborate for embodiments of the invention below, the present embodiment premised on technical solution of the present invention under implement, give detailed execution mode and concrete operating process, the platform that is suitable for of the present invention is not limited to following embodiment.
The system being responsible for bandwidth resource allocation management in cloud game distributed system comprises main control server, log server, material storage server, and the system that is managed is the server cluster that some subordinate physical machines (slave) form.The topological diagram of this system as shown in Figure 1.Fig. 2 is the configuration diagram of middle distributed system network bandwidth scheduling System and method for of the present invention, the module major deployments of present system is on master control machine, comprise connection manager, extensible policy, material memory, log server, described connection manager is piled by virtual machine and integrated network bandwidth scheduling method forms.
Be made up of connection management module (connect manager), extensible policy module (scalable strategy) in described main control server.Connection management module in charge receives the game request sent from user (client), the subordinate physical machine (slave) of follow-up access is selected after judging process, and final sum virtual machine is wherein connected, thus user and virtual machine are coupled together; Extensible policy module refers to the ability supporting that manual control whole system is run, in general this distributed system is that adaptive system ensures process orderly function by program, if but run into accident, then need manual intervention, extensible policy module has been reserved in this invention.
Two important minor structures are had: virtual machine heap and integrated network bandwidth scheduling method in above-described connection management module (connect manager).Virtual machine heap obtains all CPU from machine, GPU, network bandwidth resources behaviour in service from log server, and safeguards that one is occupied the most rickle of situation from machine resources according to general status, take resource minimum be positioned at heap top from machine.Each connection manager receives the subordinate physical machine (the subordinate physical machine that namely resources occupation is minimum) from all selecting heap top after the request of user from virtual machine heap, and at this running game virtual machine from machine; Integrated network broadband dispatching method has two kinds: based on the distribution method of justice with based on the distribution method shared.
The service conditions such as the running status of described log server primary responsibility record virtual machine and CPU, GPU, bandwidth resources, and the player information that players accesses time, duration, end time etc. are detailed.This server is intended to the persistence doing data, for the data analysis in later stage and user behavior analysis provide mass data.In the present invention, log server adopts the combination of Mysql and Redis.Log server is connected with main control server.
The storage of Game Virtual Machine image file is responsible for by described material storage server.During virtual machine initialization, subordinate physical machine can from material storage server copy virtual machine image.From material services device copy original virtual machine image file to from physical machine, the recovery of virtual machine image file can be completed when damaging from the virtual machine image file in physical machine, being difficult to and recover.
The described system that is managed is some server clusters from physical machine composition, and some virtual machines have been run in the inside.Have one to play and remote desktop software Teamviewer in each virtual machine, logical calculated and the picture of being that is responsible for game in high in the clouds are played up, and Teamviewer is responsible for picture recording to get off, and packs by Internet Transmission to user.
Log server regularly carries out state sampling to the cluster be managed, and reads each GPU from physical machine, CPU, network bandwidth resources situation.Virtual machine heap in connection manager reads resource using information from log server, then calculates the resource free time degree of each machine, forms virtual machine heap according to heapsort.When there being user to initiate game request, connection manager receives this request and resolves it, then from virtual machine heap, read maximum the numbering from physical machine of resource space limit, at this from running game virtual machine physical machine, in virtual machine, mainly contain game and remote connection software.Thus this machine is set up long connection with user.Remote connection software is transferred to game recording on the display of user side continuously, continuously the keyboard of user and mouse instructions is sent back virtual machine again simultaneously, carries out game logic calculating and image rendering for virtual machine.
Bandwidth resource allocation management method in a kind of cloud game distributed system, comprises step:
When step 1, game start, main control server obtains user and starts game request, analysis request, and starts as user disposes corresponding virtual machine;
Step 2, main control server choose the virtual machine on the most abundant physical machine of resource from the virtual machine of self is piled, and start this virtual machine;
Game on step 3, main control server startup virtual machine and remote desktop software, user and virtual machine are connected by remote desktop software;
After step 4, connection establishment, virtual machine picture is sent to user by network, and virtual machine also by the operational feedback of Network Capture user, makes user be able to operate game;
In step 5, game, the network traffics of main control server Real-Time Monitoring virtual machine, ensure by integrated network bandwidth scheduling method the fluency that each user plays games;
After step 6, game over, the connection of connection manager active disconnect user and subordinate physics machinery compartment, and suspend the operation of virtual machine, upgrade the resource information of virtual machine heap.
Integrated network bandwidth scheduling method is selected for connection manager, is divided into based on justice with based on shared two kinds of modes, supports the later stage to add new strategy process again.The former facilitates cloud game operator in actual applications can according to network bandwidth cases charged; The latter can improve the utilance of resource, is applicable to multi-user, the situation that resource is critical.
The present invention maintains the running status that a real-time watch-dog is used for monitoring virtual machine, thus provides resource occupation foundation for scheduler module.Actual testing experiment shows that the present invention can improve Consumer's Experience, and reduces by the network bandwidth shake of 20%.
Claims (5)
1. bandwidth resource allocation management system in a cloud game distributed system, it is characterized in that, comprise the management system be made up of main control server, log server and material storage server, and the server cluster be made up of some subordinate physical machines be managed system;
Described main control server is connected with described log server and material storage server respectively;
Described main control server, for obtaining the request from user, and analysis request, make response to request, for user distributes suitable virtual machine, run and play accordingly, the broadband resource between scheduling virtual machine distributes;
Described log server, for recording the running status of virtual machine, the service condition of CPU, GPU, bandwidth resources, and player information;
Described material storage server, for storing Game Virtual Machine image file;
The described system that is managed is some server clusters from physical machine composition, eachly from physical machine, has run some virtual machines, has one to play and remote desktop software in each virtual machine.
2. bandwidth resource allocation management system in cloud game distributed system according to claim 1, is characterized in that, described main control server is made up of connection management module, extensible policy module;
Described connection manager, for receiving the game request sent from user, select the subordinate physical machine of follow-up access, and final sum virtual machine being wherein connected, thus user and virtual machine having been coupled together after judging process;
Described extensible policy module, for the interface of manual intervention.
3. bandwidth resource allocation management system in cloud game distributed system according to claim 2, is characterized in that, described connection management module comprises virtual machine heap and integrated network bandwidth scheduling method two minor structures;
Described virtual machine heap obtains all CPU from physical machine, GPU, network bandwidth resources behaviour in service from log server, and safeguard a most rickle from physical machine resources occupation situation according to general status, take resource minimum be positioned at heap top from physical machine;
Integrated network broadband dispatching method comprises based on the distribution method of justice with based on the distribution method shared.
4. a bandwidth resource allocation management method in cloud game distributed system, it is characterized in that, the method comprises the steps:
When step 1, game start, main control server obtains user and starts game request, analysis request, and starts as user disposes corresponding virtual machine;
Step 2, main control server choose the virtual machine on the most abundant physical machine of resource from the virtual machine of self is piled, and start this virtual machine;
Game on step 3, main control server startup virtual machine and remote desktop software, user and virtual machine are connected by remote desktop software;
After step 4, connection establishment, virtual machine picture is sent to user by network, and virtual machine also by the operational feedback of Network Capture user, makes user be able to operate game;
In step 5, game, the network traffics of main control server Real-Time Monitoring virtual machine, ensure by integrated network bandwidth scheduling method the fluency that each user plays games;
After step 6, game over, the connection of connection manager active disconnect user and subordinate physics machinery compartment, and suspend the operation of virtual machine, upgrade the resource information of virtual machine heap.
5. bandwidth resource allocation management method according to claim 1, it is characterized in that, in described step 5, integrated network bandwidth scheduling method is selected for connection manager, is divided into the method for allocating bandwidth resources based on justice and the method for allocating bandwidth resources based on justice:
The described method for allocating bandwidth resources based on justice: be the network bandwidth that each virtual machine run allots a quota, this broadband is enough to meet the smooth minimum requirements run of game, preset the size of this network bandwidth, when the broadband resource that user uses exceedes default, main control server is by reducing the mode of quality of play, and the broadband resource reducing user uses;
The described method for allocating bandwidth resources based on justice: namely all virtual machines share an overall network bandwidth, if some virtual machine occupied bandwidths resource of a certain moment declines, then the main control server virtual machine that can bandwidth resources be needed many to those unnecessary allocated bandwidth.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410636059.XA CN104363277A (en) | 2014-11-13 | 2014-11-13 | Allocation management system and management method for bandwidth resources in cloud game distributed system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410636059.XA CN104363277A (en) | 2014-11-13 | 2014-11-13 | Allocation management system and management method for bandwidth resources in cloud game distributed system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104363277A true CN104363277A (en) | 2015-02-18 |
Family
ID=52530503
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410636059.XA Pending CN104363277A (en) | 2014-11-13 | 2014-11-13 | Allocation management system and management method for bandwidth resources in cloud game distributed system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104363277A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104850618A (en) * | 2015-05-18 | 2015-08-19 | 北京京东尚科信息技术有限公司 | System and method for providing sorted data |
CN106331750A (en) * | 2016-10-08 | 2017-01-11 | 中山大学 | Self-adapting cloud game platform bandwidth optimization method based on regions of interest |
CN106534159A (en) * | 2016-12-01 | 2017-03-22 | 上海电机学院 | Virtual Internet bar realization method based on game |
CN108259268A (en) * | 2017-12-30 | 2018-07-06 | 上海陆家嘴国际金融资产交易市场股份有限公司 | Network monitoring data processing method, device, computer equipment and storage medium |
CN108256182A (en) * | 2018-01-02 | 2018-07-06 | 西安交通大学 | A kind of layout method of dynamic reconfigurable FPGA |
CN110933036A (en) * | 2019-10-29 | 2020-03-27 | 咪咕互动娱乐有限公司 | Cloud game service system and server |
CN111249724A (en) * | 2018-12-03 | 2020-06-09 | 索尼互动娱乐有限责任公司 | Machine learning driven resource allocation |
CN111432019A (en) * | 2020-03-31 | 2020-07-17 | 广州微算互联信息技术有限公司 | Cloud game equipment distribution method and system based on edge cloud cooperation mode |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060095917A1 (en) * | 2004-11-01 | 2006-05-04 | International Business Machines Corporation | On-demand application resource allocation through dynamic reconfiguration of application cluster size and placement |
CN103023872A (en) * | 2012-11-16 | 2013-04-03 | 杭州顺网科技股份有限公司 | Cloud game service platform |
CN103729234A (en) * | 2013-12-20 | 2014-04-16 | 中电长城网际系统应用有限公司 | Method and device for clustering management of virtual machines |
CN104133727A (en) * | 2014-08-08 | 2014-11-05 | 成都致云科技有限公司 | Load distribution method based on real-time resources |
-
2014
- 2014-11-13 CN CN201410636059.XA patent/CN104363277A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060095917A1 (en) * | 2004-11-01 | 2006-05-04 | International Business Machines Corporation | On-demand application resource allocation through dynamic reconfiguration of application cluster size and placement |
CN103023872A (en) * | 2012-11-16 | 2013-04-03 | 杭州顺网科技股份有限公司 | Cloud game service platform |
CN103729234A (en) * | 2013-12-20 | 2014-04-16 | 中电长城网际系统应用有限公司 | Method and device for clustering management of virtual machines |
CN104133727A (en) * | 2014-08-08 | 2014-11-05 | 成都致云科技有限公司 | Load distribution method based on real-time resources |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104850618A (en) * | 2015-05-18 | 2015-08-19 | 北京京东尚科信息技术有限公司 | System and method for providing sorted data |
CN104850618B (en) * | 2015-05-18 | 2018-06-01 | 北京京东尚科信息技术有限公司 | A kind of system and method that ordered data is provided |
CN106331750A (en) * | 2016-10-08 | 2017-01-11 | 中山大学 | Self-adapting cloud game platform bandwidth optimization method based on regions of interest |
CN106331750B (en) * | 2016-10-08 | 2019-04-30 | 中山大学 | A kind of cloud game platform adaptive bandwidth optimization method based on area-of-interest |
CN106534159A (en) * | 2016-12-01 | 2017-03-22 | 上海电机学院 | Virtual Internet bar realization method based on game |
CN108259268A (en) * | 2017-12-30 | 2018-07-06 | 上海陆家嘴国际金融资产交易市场股份有限公司 | Network monitoring data processing method, device, computer equipment and storage medium |
CN108256182A (en) * | 2018-01-02 | 2018-07-06 | 西安交通大学 | A kind of layout method of dynamic reconfigurable FPGA |
CN108256182B (en) * | 2018-01-02 | 2020-10-27 | 西安交通大学 | Layout method of dynamically reconfigurable FPGA |
CN111249724A (en) * | 2018-12-03 | 2020-06-09 | 索尼互动娱乐有限责任公司 | Machine learning driven resource allocation |
CN110933036A (en) * | 2019-10-29 | 2020-03-27 | 咪咕互动娱乐有限公司 | Cloud game service system and server |
CN110933036B (en) * | 2019-10-29 | 2022-03-22 | 咪咕互动娱乐有限公司 | Cloud game service system and server |
CN111432019A (en) * | 2020-03-31 | 2020-07-17 | 广州微算互联信息技术有限公司 | Cloud game equipment distribution method and system based on edge cloud cooperation mode |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104363277A (en) | Allocation management system and management method for bandwidth resources in cloud game distributed system | |
Hong et al. | Placing virtual machines to optimize cloud gaming experience | |
JP7259033B2 (en) | Resource allocation driven by machine learning | |
CA2814420C (en) | Load balancing between general purpose processors and graphics processors | |
US20130060837A1 (en) | Monitoring And Benchmarking Client Performance From The Server-Side | |
US20150371355A1 (en) | Host-Based Heterogeneous Multi-GPU Assignment | |
EP3161636B1 (en) | Data center management of multimode servers | |
US20210027401A1 (en) | Processes and systems that determine sustainability of a virtual infrastructure of a distributed computing system | |
CN110474966B (en) | Method for processing cloud platform resource fragments and related equipment | |
US20130339956A1 (en) | Computer system and optimal arrangement method of virtual machine in computer system | |
CN111966500A (en) | Resource scheduling method and device, electronic equipment and storage medium | |
CN111450524B (en) | Information processing method and device in cloud game, cloud game server and medium | |
US20150133216A1 (en) | View generation based on shared state | |
CN103561055B (en) | Web application automatic elastic extended method under conversation-based cloud computing environment | |
US20150130814A1 (en) | Data collection for multiple view generation | |
CN112988400B (en) | Video memory optimization method and device, electronic equipment and readable storage medium | |
Anwar et al. | Taming the cloud object storage with mos | |
CN109460297A (en) | A kind of edge cloud game caching and resource regulating method | |
CN111552550A (en) | Task scheduling method, device and medium based on GPU (graphics processing Unit) resources | |
US20150130815A1 (en) | Multiple parallel graphics processing units | |
WO2024066828A1 (en) | Data processing method and apparatus, and device, computer-readable storage medium and computer program product | |
Deng et al. | Server allocation for multiplayer cloud gaming | |
CN112286637A (en) | Method and device for adjusting computing resources | |
Mann | Modeling the virtual machine allocation problem | |
CN110493317B (en) | Method for processing cloud platform resource fragments and related equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150218 |