CN113672344A - Method for creating flexible distribution of multi-specification vGPU virtual machines based on OpenStack platform - Google Patents
Method for creating flexible distribution of multi-specification vGPU virtual machines based on OpenStack platform Download PDFInfo
- Publication number
- CN113672344A CN113672344A CN202110894718.XA CN202110894718A CN113672344A CN 113672344 A CN113672344 A CN 113672344A CN 202110894718 A CN202110894718 A CN 202110894718A CN 113672344 A CN113672344 A CN 113672344A
- Authority
- CN
- China
- Prior art keywords
- vgpu
- type
- trail
- provider
- creating
- 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
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- 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
- 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
- H04L41/0876—Aspects of the degree of configuration automation
- H04L41/0886—Fully automatic configuration
-
- 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
- H04L41/0893—Assignment of logical groups to network elements
-
- 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
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
-
- 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
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
-
- 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
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45562—Creating, deleting, cloning virtual machine instances
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method for creating flexible distribution of multi-specification vGPU virtual machines based on an OpenStack platform, belonging to the technical field of OpenStack cloud computing and comprising the following steps: enabling the vGPU type by the vGPU computing node and binding corresponding GPU equipment; setting the trail attribute of the vGPU provider through an openstack cli command; one or a group of trail attributes uniquely identify one vGPU type; a shader used by the vGPU virtual machine is created. The video memory is automatically distributed, and the use of the video card in different scenes is met.
Description
Technical Field
The invention relates to the technical field of OpenStack cloud computing, in particular to a method for creating a multi-specification vGPU virtual machine based on an OpenStack platform, flexibly distributing the size of a video memory, simplifying manual processes and improving reasonable creation of the virtual machine.
Background
OpenStack originates from cloud computing, develops in the future and is very rapid. IaaS (infrastructure as a service) is currently the most cloud service provided by cloud service providers, and OpenStack is the most typical representative thereof. The OpenStack is used as a large cloud operating system, controls three resources of computation, network and storage, provides a visual interface of a web end for facilitating control of an administrator, adopts an identity authentication mechanism to give user rights and resources, has a standard infrastructure and service functions, but also has other components for providing other services, and ensures high availability of user application programs.
Before the openstack T version, even if a plurality of physical machine devices are equipped, the type of the nova component configuration vGPU video card can only take effect in one type, so that the flexibility of the physical machine video card is greatly reduced.
Under the public cloud background, different users have different requirements on the performance of the display card, and only one video memory type is configured, so that the multi-scene requirement cannot be met, and therefore, the scheduling strategy for supporting the multi-type vgpu display card is to be solved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method for creating flexible allocation of multi-specification vGPU virtual machines based on an OpenStack platform.
The technical scheme of the invention is as follows:
a method for creating flexible distribution of multi-specification vGPU virtual machines based on an OpenStack platform,
the method comprises the following steps:
enabling a vGPU type by a vGPU computing node and binding corresponding GPU equipment;
setting the trail attributes of the vGPU provider through an openstack cli command, wherein one or a group of trail attributes uniquely identify one vGPU type;
a shader used by the vGPU virtual machine is created, and the like.
Further, in the above-mentioned case,
and creating a section of the vGPU type bound with the specified GPU equipment, and specifying the pci address of the corresponding GPU card.
And checking the list of the sub provider corresponding to each vGPU type, and confirming that the VGPU resource types and the total amount are supported.
And setting a trail attribute for the resource provider supporting the vGPU type so as to perform scheduling management through the trail.
And creating a custom navigator, adding a trail attribute and creating a virtual machine at the node.
In a still further aspect of the present invention,
the method comprises the following specific steps:
(1) enabling the vGPU type by the vGPU computing node and binding corresponding GPU equipment;
(2) the nova-computer service creates a sub provider supporting vGPU type resources;
(3) setting the trail attributes of the vGPU provider through an openstack cli command, wherein one or a group of trail attributes uniquely identify one vGPU type;
(4) and creating a navigator used by the vGPU virtual machine, and setting a trail attribute. And scheduling and matching the provider corresponding to the vGPU type through the trail attribute.
In a still further aspect of the present invention,
the method comprises the following concrete steps:
(1) modifying a configuration file
The vGPU function relates to nova-computer service, the used configuration file is nova-computer.
Adding an enabled _ vgpu _ types configuration in the devices section, specifying the vgpu type of the current node, enabling more than one node, and separating by commas;
creating a section for binding the vGPU type and the designated GPU equipment; the naming rule of the section is: and (2) adding a device _ addresses configuration item in the section of (vgpu _ $ (vgpu type)), and specifying the pci address of the corresponding GPU card.
(2) Checking node provider
When a 'vGPU type/PCI binding configuration section' is defined in a nova-computer. conf configuration file, a nova-computer service can create a sub provider on a provider tree;
(3) creating and configuring a trail
Each vGPU type creates one or a group of uniquely identified trait, and the create trait command is as follows:
setting a trail attribute for the resource provider supporting the vGPU type, and carrying out scheduling management through the trail; the command to associate a trail with a corresponding provider is as follows:
(4) using and creating virtual machine authentication
Creating a custom navigator and adding a trail attribute
And using the browser to create a virtual machine at the node:
verifying the created virtual machine:
(5) display card capable of realizing flexible distribution
The using condition of the display card is obtained by calling the openstack interface, when the virtual machine is established for the first time and one of the cards fails to be scheduled, the value of the display card is recorded, when the virtual machine is established for the next time and is scheduled, whether the value is smaller than the value of the display card recorded last time is judged, if the result is larger, an abnormal prompt of the establishment failure is directly returned, and task scheduling on the openstack level is not required to be continuously performed; if the result is smaller, continuing to execute, and so on;
(6) adding or replacing host machines, and solving the problem of file configuration immobility:
and (3) by adopting a mode of ignoring the intermediate model part and judging according to the display model and the display card name part, after a new GPU model is set up or the GPU rack position is changed, the code content of the upper application operation does not need to be upgraded or changed.
The invention has the advantages that
The virtual GPU functionality in Nova allows deployment to provide a specific GPU type for an instance using a physical GPU that can provide a virtual device. This functionality is highly dependent on the version of libvirt and the physical devices present on the host. Furthermore, the vendor's vGPU driver software must be installed and configured on the host at the same time.
Enabling GPU types if multiple GPU types are to be supported, a separate configuration section needs to be provided for each device. If the same PCI address is provided for both different types, nova-computer will refuse to boot and issue a specific error in the log. The virtual GPU is considered an intermediary device. Physical PCI devices that support virtual GPUs propose an intermediary device (mdev) type. The instance is created using a virtual GPU device that selects the VGPU device target master with a placement API for the particular VGPU resource class available through the compute node.
Drawings
FIG. 1 is a flow diagram for creating a multi-specification vGPU virtual machine;
fig. 2 is a configuration diagram of the Nova service yaml file.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
The NVIDIA vGPU software is a graphic virtualization platform, can enable a virtual machine to use NVIDIA GPU technology, and supports multiple virtual machines to simultaneously access NVIDIA single physical GPU deployed on a host system. By doing so, the vGPU provides graphics performance and application compatibility for the VM, as well as cost effectiveness and scalability by sharing the GPU among multiple workloads.
The method comprises the steps that a plurality of types of video cards are prepared, complex scenes such as video memory allocation and automatic creation must be considered, the performance of the vGPU video card is mainly divided by the allocated types of the video memory and the video card, and the video memory of the vGPU is allocated from a physical GPU when being created. In order to achieve the purpose that a user creates a virtual machine without perception, the scheme finishes automatic allocation of the video memory so as to meet the use requirements of video cards in different scenes.
The following technical scheme is provided:
the first part, the overall scheme:
the multi-specification vGPU support function integrally comprises the following steps:
(1) the vGPU compute node enables the vGPU type and binds corresponding GPU equipment.
(2) The nova-computer service creates a child provider that supports vGPU type resources.
(3) And the operation and maintenance personnel set the trail attributes of the vGPU provider through an openstack cli command, wherein one or a group of trail attributes uniquely identify one vGPU type.
(4) And creating a navigator used by the vGPU virtual machine, and setting a trail attribute. And scheduling and matching the provider corresponding to the vGPU type through the trail attribute.
Please refer to fig. 1 for a specific process of creating.
The second part comprises the following concrete implementation steps:
(1) modifying a configuration file
The vGPU function relates to nova-computer service, the used configuration file is nova-computer.
Adding an enabled _ vGPU _ types configuration in the devices section, specifying the vGPU type of the current node enable, multiple vGPU types can be enabled, and the vGPU types are separated by commas, for example, enabling nvidia-196 and nvidia-197 two vGPU types:
sections are created that bind the vGPU type with the specified GPU device. The naming rule of the section is: and (2) adding a device _ addresses configuration item in the section of (vgpu _ $ (vgpu type)), and specifying the pci address of the corresponding GPU card.
Multiple vGPU type/PCI binding configuration sections may be created, for example:
the yaml file configuration format of the actual configuration Nova service is shown in fig. 2.
(2) Checking node provider
Conf profile defines a "vGPU type/PCI binding configuration section" in the nova-computer, the nova-computer service creates a child provider on the provider tree.
And viewing a resource provider list on the gpu computing node:
the resource provider list is as follows:
checking a list of the child provider corresponding to each vGPU type, and confirming that the VGPU resource types and the total amount are supported:
wherein: the total column is the upper limit of the number of GPU types supported by the GPU equipment.
The manifest resource table is as follows:
checking the resource list of the main provider:
the inventory total resources table is as follows:
(3) creating and configuring a trail
Each vGPU type creates one or a set of uniquely identified trait, which is suggested to be named using a "type name", the create trait command is as follows:
remarking: specify an os-place version to be 1.6
And setting a trail attribute for the resource provider supporting the vGPU type so as to perform scheduling management through the trail. The command to associate a trail with a corresponding provider is as follows:
the GPU type corresponds to a custom feature, as follows:
GPU type corresponds to a detailed list of custom features, as shown below
(4) Using and creating virtual machine authentication
Creating a custom navigator and adding a trail attribute
The create specification detail command is shown in the following table:
and using the browser to create a virtual machine at the node:
verifying the created virtual machine:
as follows:
(5) display card capable of realizing flexible distribution
Because the simulation experiment is realized under the condition of not using a database, the use condition of the display card is obtained by calling an openstack interface. The situation that a plurality of virtual machines are actually created is considered, when the capacity of one video card is used up, the problem of video memory use-up is found out only by creating the virtual machine to report error and lack of resources, obviously, the defects are many, and time and resources are consumed.
Adopting a minimum value algorithm, recording the card display value after the virtual machine is scheduled to one card for the first time and then judging whether the value is smaller than the last recorded card display value when the virtual machine is scheduled for the next time, and directly returning an abnormal prompt of the failure of the establishment if the result is larger without continuing the task scheduling on the openstack level; if the result is smaller, the execution is continued, and so on.
(6) Adding or replacing host machines, and solving the problem of file configuration immobility:
the trap has no requirement on naming in principle, but needs to specify names in consideration of problems such as later maintenance, and the like, and a mode of ignoring an intermediate machine type part and judging according to a specific mark and a display machine type and display card name part is adopted, for example, the cusom _ NVIDIA _1EB8_ T4_2B, cusom is a prefix mark, T4_2B is a machine type and a display memory size, and the intermediate part is changed by random type change. The purpose of doing so is that after a new GPU model is set up or the GPU framework position is changed, the code content of the upper-layer application operation does not need to be upgraded or changed.
The above description is only a preferred embodiment of the present invention, and is only used to illustrate the technical solutions of the present invention, and not to limit the protection scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (8)
1. A method for creating flexible distribution of multi-specification vGPU virtual machines based on an OpenStack platform is characterized in that,
the method comprises the following steps:
enabling the vGPU type by the vGPU computing node and binding corresponding GPU equipment;
setting the trail attribute of the vGPU provider through an openstack cli command;
one or a group of trail attributes uniquely identify one vGPU type;
a shader used by the vGPU virtual machine is created.
2. The method of claim 1,
and creating a section of the vGPU type bound with the specified GPU equipment, and specifying the pci address of the corresponding GPU card.
3. The method of claim 2,
and checking the list of the sub provider corresponding to each vGPU type, and confirming that the VGPU resource types and the total amount are supported.
4. The method of claim 3,
and setting a trail attribute for the resource provider supporting the vGPU type so as to perform scheduling management through the trail.
5. The method of claim 4,
and creating a custom navigator, adding a trail attribute and creating a virtual machine at the node.
6. The method of claim 5,
the method comprises the following specific steps:
(1) enabling the vGPU type by the vGPU computing node and binding corresponding GPU equipment;
(2) the nova-computer service creates a sub provider supporting vGPU type resources;
(3) setting the trail attributes of the vGPU provider through an openstack cli command, wherein one or a group of trail attributes uniquely identify one vGPU type;
(4) creating a navigator used by the vGPU virtual machine, and setting a trail attribute; and scheduling and matching the provider corresponding to the vGPU type through the trail attribute.
7. The method of claim 6,
the method comprises the following concrete steps:
(1) modifying a configuration file
The vGPU function involves nova-computer services, the configuration file used is nova-computer.
(2) Checking node provider
When a 'vGPU type/PCI binding configuration section' is defined in a nova-computer. conf configuration file, a nova-computer service can create a sub provider on a provider tree;
(3) creating and configuring a trail
Each vGPU type creates one or a group of uniquely identified trait, and the create trait command is as follows:
setting a trail attribute for the resource provider supporting the vGPU type, and carrying out scheduling management through the trail; the command to associate a trail with a corresponding provider is as follows:
(4) using and creating virtual machine authentication
Creating a custom navigator and adding a trail attribute
And using the browser to create a virtual machine at the node:
verifying the created virtual machine:
(5) display card capable of realizing flexible distribution
The using condition of the display card is obtained by calling the openstack interface, when the virtual machine is established for the first time and one of the cards fails to be scheduled, the value of the display card is recorded, when the virtual machine is established for the next time and is scheduled, whether the value is smaller than the value of the display card recorded last time is judged, if the result is larger, an abnormal prompt of the establishment failure is directly returned, and task scheduling on the openstack level is not required to be continuously performed; if the result is smaller, continuing to execute, and so on;
(6) adding or replacing hosts, problem of file configuration immobility
And (3) by adopting a mode of ignoring the intermediate model part and judging according to the display model and the display card name part, after a new GPU model is set up or the GPU rack position is changed, the code content of the upper application operation does not need to be upgraded or changed.
8. The method of claim 7,
the configuration in step 1) is referred to as follows:
adding an enabled _ vgpu _ types configuration in the devices section, specifying the vgpu type of the current node, enabling more than one node, and separating by commas;
creating a section for binding the vGPU type and the designated GPU equipment; the naming rule of the section is: and (2) adding a device _ addresses configuration item in the section of (vgpu _ $ (vgpu type)), and specifying the pci address of the corresponding GPU card.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110894718.XA CN113672344A (en) | 2021-08-05 | 2021-08-05 | Method for creating flexible distribution of multi-specification vGPU virtual machines based on OpenStack platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110894718.XA CN113672344A (en) | 2021-08-05 | 2021-08-05 | Method for creating flexible distribution of multi-specification vGPU virtual machines based on OpenStack platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113672344A true CN113672344A (en) | 2021-11-19 |
Family
ID=78541466
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110894718.XA Pending CN113672344A (en) | 2021-08-05 | 2021-08-05 | Method for creating flexible distribution of multi-specification vGPU virtual machines based on OpenStack platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113672344A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114090186A (en) * | 2021-11-26 | 2022-02-25 | 中国科学院自动化研究所 | System for managing PCIE (peripheral component interface express) equipment based on Openstack platform |
| CN116755843A (en) * | 2023-08-17 | 2023-09-15 | 摩尔线程智能科技(北京)有限责任公司 | Virtual resource creation method and device, electronic equipment, chip and storage medium |
-
2021
- 2021-08-05 CN CN202110894718.XA patent/CN113672344A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114090186A (en) * | 2021-11-26 | 2022-02-25 | 中国科学院自动化研究所 | System for managing PCIE (peripheral component interface express) equipment based on Openstack platform |
| CN116755843A (en) * | 2023-08-17 | 2023-09-15 | 摩尔线程智能科技(北京)有限责任公司 | Virtual resource creation method and device, electronic equipment, chip and storage medium |
| CN116755843B (en) * | 2023-08-17 | 2023-12-19 | 摩尔线程智能科技(北京)有限责任公司 | Virtual resource creation method and device, electronic equipment, chip and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11405274B2 (en) | Managing virtual network functions | |
| CN102932408B (en) | A kind of management method of server cluster and platform | |
| US8104038B1 (en) | Matching descriptions of resources with workload requirements | |
| EP3554010A1 (en) | Method and system for use in constructing content delivery network platform on heterogeneous resources | |
| US9116874B2 (en) | Virtual machine test system, virtual machine test method | |
| CN103795759B (en) | The dispatching method and system of a kind of virtual machine image file | |
| JP5352890B2 (en) | Computer system operation management method, computer system, and computer-readable medium storing program | |
| CN110098946B (en) | Method and device for deploying virtualized network element equipment | |
| CN103873534B (en) | A kind of application cluster moving method and device | |
| WO2019060228A1 (en) | Systems and methods for instantiating services on top of services | |
| CN113672344A (en) | Method for creating flexible distribution of multi-specification vGPU virtual machines based on OpenStack platform | |
| CN108089913A (en) | A kind of virtual machine deployment method of super emerging system | |
| US11556369B2 (en) | Virtual machine deployment method and OMM virtual machine | |
| CN101276271A (en) | Method and interceptor system facing to tangent plane programming | |
| US10025630B2 (en) | Operating programs on a computer cluster | |
| CN114244717B (en) | Configuration method and device of virtual network card resources, computer equipment and medium | |
| JP7493053B2 (en) | Image file generating method, device and computer program | |
| EP3442201B1 (en) | Cloud platform construction method and cloud platform | |
| WO2022041507A1 (en) | 3d rendering method and system | |
| CN108073423A (en) | A kind of accelerator loading method, system and accelerator loading device | |
| CN109347716B (en) | Instantiation method and device of consumer VNF | |
| CN111884855A (en) | Cloud service system, method and server | |
| US9047248B2 (en) | Logical domain recovery | |
| US20210026672A1 (en) | Avoiding power-on failures in virtualized gpus | |
| CN104657216B (en) | The resource allocation methods and device of a kind of resource pool |
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 |