CN109144672A - A kind of method, system and associated component for distributing PCIe device - Google Patents
A kind of method, system and associated component for distributing PCIe device Download PDFInfo
- Publication number
- CN109144672A CN109144672A CN201811044877.5A CN201811044877A CN109144672A CN 109144672 A CN109144672 A CN 109144672A CN 201811044877 A CN201811044877 A CN 201811044877A CN 109144672 A CN109144672 A CN 109144672A
- Authority
- CN
- China
- Prior art keywords
- pcie device
- virtual machine
- pcie
- physical internet
- internet ports
- 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
- G06F9/44—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/42—Bus transfer protocol, e.g. handshake; Synchronisation
- G06F13/4204—Bus transfer protocol, e.g. handshake; Synchronisation on a parallel bus
- G06F13/4221—Bus transfer protocol, e.g. handshake; Synchronisation on a parallel bus being an input/output bus, e.g. ISA bus, EISA bus, PCI bus, SCSI bus
-
- 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
- G06F9/4401—Bootstrapping
- G06F9/4411—Configuring for operating with peripheral devices; Loading of device drivers
-
- 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
- G06F2009/45591—Monitoring or debugging support
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Computer And Data Communications (AREA)
Abstract
This application discloses a kind of methods for distributing PCIe device, and the method includes when detecting that PCIe device is installed to PCIe slot, server platform starting VT, VT-D and SR-IOV simultaneously loads IOMMU, to construct virtual environment；The Bus number of the PCIe device is obtained by the driver being adapted to the PCIe device；Virtual machine is created in the virtual environment, and the Bus number is added to the control catalogue of the virtual machine, to distribute the physical internet ports of the PCIe device to the virtual machine.This method can reduce the demand that driver is run in VMM, improve the allocative efficiency of PCIe device.Disclosed herein as well is a kind of system, a kind of computer readable storage medium and a kind of server platforms for distributing PCIe device, have the above beneficial effect.
Description
Technical field
The present invention relates to technical field of virtualization, in particular to a kind of method, system, a kind of calculating for distributing PCIe device
Machine readable storage medium storing program for executing and a kind of server platform.
Background technique
It is a kind of that PCIe, which is also known as PCI-Express (peripheral component interconnect express),
High speed serialization computer expansion bus standard, PCIe device are the equipment using PCIe standard.
In order to achieve the purpose that virtual machine control PCIe device, need physics PCIe device distributing to virtual machine, it is existing
Technology is mainly to be realized by traditional equipment simulating/extras interface mode, but the prior art needs VMM
(Virtual Machine Monitor, monitor of virtual machine) participates in PCIe device distribution.But PCIe is carried out using VMM
The distribution of equipment needs to occupy the performance resource of VMM, there is a problem of that allocative efficiency is low, resource occupation is larger.
Therefore, the demand that driver is run in VMM how is reduced, the allocative efficiency for improving PCIe device is this field
The current technical issues that need to address of technical staff.
Summary of the invention
The purpose of the application is to provide a kind of method, system, a kind of computer readable storage medium for distributing PCIe device
And a kind of server platform, the demand for running driver in VMM can be reduced, the allocative efficiency of PCIe device is improved.
In order to solve the above technical problems, the application provides a kind of method for distributing PCIe device, this method comprises:
When detecting that PCIe device is installed to PCIe slot, server platform starts VT, VT-D and SR-IOV and adds
IOMMU is carried, to construct virtual environment；
The Bus number of the PCIe device is obtained by the driver being adapted to the PCIe device；
Virtual machine is created in the virtual environment, and the Bus number is added to the control catalogue of the virtual machine,
To distribute the physical internet ports of the PCIe device to the virtual machine.
Optionally, the server platform is specially the server platform for being equipped with Linux rhel7.2 system.
Optionally, virtual machine is created in the virtual environment includes:
It is created in the virtual environment by the virt-manager of the Linux rhel7.2 system described virtual
Machine.
Optionally, the PCIe device includes network interface card or HBA card.
Optionally, it when the PCIe device is the network interface card, distributes by the physical internet ports of the PCIe device to institute
After stating virtual machine, further includes:
IP address is distributed for the physical internet ports of the network interface card, is connected to establish the network of the virtual machine and the network interface card
It connects；Wherein, the physical internet ports of the virtual machine are connect with the physical internet ports of the network interface card by interchanger；
The handling capacity of the network interface card is tested using iperf network bandwidth testing tool.
Optionally, the interchanger is separately connected the physical internet ports and the network interface card of the virtual machine by 10,000,000,000 optical fiber cables
Physical internet ports.
Optionally, it when the PCIe device is the HBA card, distributes by the physical internet ports of the PCIe device to institute
After stating virtual machine, further includes:
Fio test is carried out to the HBA card by the virtual machine, and HBA card performance is determined according to fio test result.
Present invention also provides a kind of system for distributing PCIe device, which includes:
Environment construction module, for starting VT, VT-D and SR- when detecting that PCIe device is installed to PCIe slot
IOV simultaneously loads IOMMU, to construct virtual environment；
Bus number obtains module, obtains the PCIe device for the driver by being adapted to the PCIe device
Bus number；
Distribution module for creating virtual machine in the virtual environment, and the Bus number is added to described virtual
The control catalogue of machine, to distribute the physical internet ports of the PCIe device to the virtual machine.
Present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, the computer
The step of program realizes above-mentioned distribution PCIe device method when executing executes.
Present invention also provides a kind of server platform, including memory and processor, meter is stored in the memory
Calculation machine program, the processor realizes above-mentioned distribution PCIe device method when calling the computer program in the memory are held
Capable step.
The present invention provides a kind of methods for distributing PCIe device, including work as and detect that PCIe device is installed to PCIe slot
When upper, server platform starting VT, VT-D and SR-IOV simultaneously loads IOMMU, to construct virtual environment；By with the PCIe
The driver of equipment adaptation obtains the Bus number of the PCIe device；Create virtual machine in the virtual environment, and by institute
The control catalogue that Bus number is added to the virtual machine is stated, to distribute the physical internet ports of the PCIe device to described virtual
Machine.
The application is by when PCIe device is installed to PCIe slot, starting VT, VT-D and SR-IOV and loading IOMMU
Module constructs virtual environment, and under the virtual environment driver of virtual machine internal can directly carried out with PCIe device
Communication only need to reduce by management a small amount of or without VMM and need to run driver in VMM in the prior art
It relies on.Therefore, the need of the operation driver in VMM can be reduced by PCIe device being distributed to virtual machine under the virtual environment
It asks, improves the allocative efficiency of PCIe device.The application additionally provides a kind of system of distribution PCIe device, a kind of computer simultaneously
Readable storage medium storing program for executing and a kind of server platform have above-mentioned beneficial effect, and details are not described herein.
Detailed description of the invention
In ord to more clearly illustrate embodiments of the present application, attached drawing needed in the embodiment will be done simply below
It introduces, it should be apparent that, the drawings in the following description are only some examples of the present application, for ordinary skill people
For member, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart for the method for distributing PCIe device provided by the embodiment of the present application；
Fig. 2 is a kind of structural schematic diagram for the system for distributing PCIe device provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
In attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is
Some embodiments of the present application, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall in the protection scope of this application.
Below referring to Figure 1, Fig. 1 is a kind of process for the method for distributing PCIe device provided by the embodiment of the present application
Figure.
Specific steps may include:
S101: when detecting that PCIe device is installed to PCIe slot, server platform starts VT, VT-D and SR-IOV
And IOMMU is loaded, to construct virtual environment；
Wherein, the purpose of this step is to construct one for creating the virtual environment of virtual machine, and wooden man has detection
Whether PCIe device is installed to the operation on PCIe slot, and the specific PCIe slot can be the machine being connected with server platform
Slot on platform.The specific name model of PCIe device is not limited in the present embodiment, as long as the equipment is using PCIe standard
Equipment, specifically can be 10,000,000,000 network interface of intel x722 or HBA card.
When PCIe device is installed to PCIe slot, the detailed process for starting VT, VT-D and SR-IOV can be with are as follows: is taking
Del key is pressed during business device platform starting up and enters the interface BIOS, must confirm that " VT ", " VT-D " and " SR-IOV " is all
Characteristic is opened, and is saved and is exited.VT is the abbreviation of English virtualizationtechnology, means that CPU is virtual
Change technology.(Intel Virtualization Technology for Directed I/O, it is empty that Intel orients I/O to VT-D
Quasi-ization technology) technology be it is a kind of based on North Bridge north bridge chips hardware auxiliary virtualization technology, by north bridge
Built-in offer DMA virtualization and IRQ virtualization hardware realize novel I/O virtualization mode, and Intel VT-d can be in void
Reliability, flexibility and the performance of I/O are greatly improved in near-ring border.
When distributing virtual network port, it is necessary to which IOMMU (deposit by I/O Memory Management Unit, input and output
Reservoir administrative unit) module support, therefore need to load IOMMU in this step, the step with starting VT, VT-D and SR-IOV
Suddenly virtual environment is constructed together.SR-IOV (Single-root I/O virtualization, single I/O virtualization).As
A kind of special case, when the system of server platform is Linux rhel7.2, due to I/O Memory Management Unit
(IOMMU) module rhel7.2 default is not turned on, and is loaded IOMMU and needed to add a line parameter in kernel start-up parameter:
Intel_iommu=on, specifically: linux16/vmlinuz-3.10.0-327.ali2010.alios7.x86_64 root
=UUID=6988cc44-f2b9-4d88-9265-1d338a77b847 re crashkernel=auto rhgb quiet
LANG=en_US.UTF-8intel iommu=on.
After loading IOMMU module, in order to make IOMMU module come into force, can restart server platform keeps iommu raw
Effect, can be used and check IOMMU state: #dmesg as issued orders | grep-iiommu.
With VT-d technology, virtual machine is able to come using the direct PCIe device method of salary distribution or PCIe device sharing mode
Instead of traditional equipment simulating/extras interface mode, to greatly improve the PCIe performance of virtualization.
S102: the Bus number of the PCIe device is obtained by the driver being adapted to the PCIe device；
Wherein, there is the driver for being installed on PCIe device adaptation in this step default, install corresponding driving journey
After sequence, the Bus number of the PCIe device can be obtained by the driver being adapted to the PCIe device, it specifically can be with
The bus number (Bus number) of PCIe device is obtained by #lspci order.
S103: creating virtual machine in the virtual environment, and the Bus number is added to the control of the virtual machine
Catalogue, to distribute the physical internet ports of the PCIe device to the virtual machine.
Wherein, the virtual machine created under the virtual environment that S101 has been put up can make the driving journey of virtual machine internal
Sequence is directly communicated with PCIe device, only need to be reduced and be needed in the prior art by management a small amount of or without VMM
The dependence of driver is run in VMM.The Bus number of PCIe device is added in the control catalogue of virtual machine, it can realize
The physical internet ports of the PCIe device are distributed to the virtual machine, so that virtual machine carries out PCIe device by physical internet ports
Control.
As a preferred embodiment, when server platform is specially the clothes for being equipped with Linux rhel7.2 system
When business device platform, institute can be created in the virtual environment by the virt-manager of the Linux rhel7.2 system
State virtual machine.
The present embodiment is by when PCIe device is installed to PCIe slot, starting VT, VT-D and SR-IOV and loading
IOMMU module constructs virtual environment, and under the virtual environment driver of virtual machine internal can directly set with PCIe
It is standby to be communicated, only it need to reduce by management a small amount of or without VMM and need to run driving in VMM in the prior art
The dependence of program.Therefore, the operation driving journey in VMM can be reduced by PCIe device being distributed to virtual machine under the virtual environment
The demand of sequence improves the allocative efficiency of PCIe device.
As preferred embodiment, the Bus number is added to the control catalogue of the virtual machine, so as to will be described
The physical internet ports of PCIe device are distributed to the virtual machine, can also include being controlled by virtual machine PCIe device
The step of, specific operation can be determined according to being specially which kind of equipment of PCIe device.
When the PCIe device is the network interface card, distribute by the physical internet ports of the PCIe device to the virtual machine
Later, further includes: IP address is distributed for the physical internet ports of the network interface card, to establish the network of the virtual machine Yu the network interface card
Connection；Wherein, the physical internet ports of the virtual machine are connect with the physical internet ports of the network interface card by interchanger；Utilize iperf net
Network bandwidth test tool tests the handling capacity of the network interface card.Preferably, the interchanger is separately connected institute by 10,000,000,000 optical fiber cables
State the physical internet ports of virtual machine and the physical internet ports of the network interface card.
When the PCIe device is the HBA card, distribute by the physical internet ports of the PCIe device to described virtual
After machine, further includes: carry out fio test to the HBA card by the virtual machine, and determine HBA card according to fio test result
Performance.
Illustrate the stream of above-described embodiment description below by the embodiment of distribution network interface card and HBA card in practical applications
Journey,
Hardware device requirement:
1. a supportVirtualization Technology for Directed (VT-D) and SR-IOV
The server platform of characteristic；
2. one has the board of PCI Express*x8 8.0Gb/s (Gen3) slot；
3. PCIe device must be adhered on board
Software environment requirement:
1. the platform of Intel VT-d/SR-IOV is supported, herein by taking linux rhel7.2 as an example；
2. the newest firmware of network interface card；
3. supporting the trawl performance of physics functional module and virtual functions module；
Network interface card testing procedure:
1. installing on network interface card to PCIe slot to be measured, then by booting；
2. start-up course, which presses del key, enters the interface BIOS, it must confirm that " VT ", " VT-D " and " SR-IOV " all characteristics are equal
It opens, saves and exit.
3. installing RHEL7.2 system into server system disk；
4. being logged on in rhel7.2 system using root user；
5. empty in distribution since I/O Memory Management Unit (IOMMU) module rhel7.2 default is not turned on
When quasi- network interface, it is necessary to the support of IOMMU, and load IOMMU and need to add a line parameter in kernel start-up parameter:
Intel_iommu=on, such as:
6. restarting server makes IOMMU come into force, it can be used and check IOMMU state as issued orders,
#dmesg|grep–i iommu.
7. the driving being adapted to the network interface card is installed, by taking ten thousand Broadcom x722 of Intel as an example (driving can be obtained from official website),
After driving is installed, check whether driving loads success；
The Bus number bus number of 8.#lspci order acquisition network interface card；
9. creating a virtual machine using the virt-manager that RHEL7.2 is carried；
10. installing RHEL7.2 for newly created virtual machine, after being installed, virtual machine is closed；
11. clicking " Open → View → Detail " to edit virtual machine in virtual machine window interface；
12. clicking " Add Hardwar → PCI Host Device ", all pci equipment all will appear in the right control group
In；
13. one or more of selection physical internet ports are added
14. a pair virtual machine boots up, then the i40e physical drives of network interface card are installed, check being assigned to using lspci
The address bus of virtual network port will appear in lspci list；
15. ensure that the driving of network interface added is successfully loaded using lsmod, using ifconfig it can be seen that addition
The equipment of physical internet ports；
16. the physical internet ports of server and the physical internet ports of client are connected by interchanger using 10,000,000,000 optical fiber cables；
17. for the physical internet ports configure an address ip, all physical internet ports for then ensuring to add in virtual machine and
The physical internet ports of client can Ping it is logical.
18. whether can achieve 9.0Gb/s or more using iperf network broadband testing tool test handling capacity
HBA card testing procedure:
1. the platform of Intel VT-d/SR-IOV is supported, herein by taking linux rhel7.2 as an example；
The newest firmware of 2.HBA card；
3. supporting the trawl performance of physics functional module and virtual functions module；
Network interface card testing procedure:
1. installing HBA to be measured to snap on PCIe slot, then by booting；
2. start-up course, which presses del key, enters the interface BIOS, it must confirm that " VT ", " VT-D " and " SR-IOV " all characteristics are equal
It opens, saves and exit.
3. installing RHEL7.2 system into server system disk；
4. being logged on in rhel7.2 system using root user；
5. empty in distribution since I/O Memory Management Unit (IOMMU) module rhel7.2 default is not turned on
When quasi- network interface, it is necessary to the support of IOMMU, and load IOMMU and need to add a line parameter in kernel start-up parameter:
Intel_iommu=on；
6. restarting server makes IOMMU come into force, it can be used and check IOMMU state as issued orders,
#dmesg|grep–i iommu.
7. the driving being adapted to HBA card is installed, by taking the card of HBA 3216 as an example (driving can be obtained from official website), driving installation
After the completion, check whether driving loads success；
The Bus number bus number of 8.#lspci order acquisition HBA card；
9. creating a virtual machine using the virt-manager that RHEL7.2 is carried；
10. installing RHEL7.2 for newly created virtual machine, after being installed, virtual machine is closed；
11. clicking " Open → View → Detail " to edit virtual machine in virtual machine window interface；
12. clicking " Add Hardwar → PCI Host Device ", all pci equipment all will appear in the right control group
In (be equivalent to the control catalogue that Bus number is added to virtual machine)；
13. the address PCIe of HBA3216 is selected then to click completion, restarts virtual machine, check the storage card using lspci
Whether success is added.
14. installing the driving that HBA 3216 blocks in virtual machine, it is ensured that driving can be successfully loaded.
The hard disk that 15.#cat/proc/partitions is attached on the HBA card all can detecte to.
16.. it runs fio 2 hours or so, checks whether hard disk performance reaches the index of spec requirement, check log log
Whether there is hard disc apparatus is relevant to report an error.
Above-described embodiment interests Intel VT-d has not only speeded up number by the demand of reduction VMM participative management I/O flow
According to transmission, and eliminate most performance cost.This is by making VMM that specific I/O equipment safety is distributed to specific visitor
Family operating system is realized.VT-d needs the operation system example or hypervisor run in BIOS and on hardware
Middle offer support.
Above-described embodiment describes how to realize that direct PCIe device is allocated by vt-d technology, direct allotment
I/O equipment is managed to virtual machine, under this model, the driver of virtual machine internal directly and hardware device direct communication, only need
To pass through on a small quantity, or without the management of VMM.This model almost completely eliminates the need that driver is run in VMM
It asks.The present embodiment mainly provides a kind of test method of Intel VT-d, and tester can be made to be understood quickly and use this
Characteristic functions, while reducing the testing time, to improve testing efficiency.
Fig. 2 is referred to, Fig. 2 is a kind of structural representation for the system for distributing PCIe device provided by the embodiment of the present application
Figure；
The system may include:
Environment construction module 100, for when detecting that PCIe device is installed to PCIe slot, start VT, VT-D and
SR-IOV simultaneously loads IOMMU, to construct virtual environment；
Bus number obtains module 200, obtains the PCIe for the driver by being adapted to the PCIe device and sets
Standby Bus number；
Distribution module 300 is added to the void for creating virtual machine in the virtual environment, and by the Bus number
The control catalogue of quasi- machine, to distribute the physical internet ports of the PCIe device to the virtual machine.
Further, the server platform is specially the server platform for being equipped with Linux rhel7.2 system.
Further, distribution module 300 includes:
Virtual machine creating unit, for the virt-manager by the Linux rhel7.2 system described virtual
The virtual machine is created in environment；
Allocation unit, for the Bus number to be added to the control catalogue of the virtual machine, to set the PCIe
Standby physical internet ports are distributed to the virtual machine.
Further, the PCIe device includes network interface card or HBA card.
Further, when the PCIe device is the network interface card, further includes:
Network interface card test module, for for the network interface card physical internet ports distribute IP address, so as to establish the virtual machine with
The network connection of the network interface card；Wherein, the physical internet ports of the physical internet ports of the virtual machine and the network interface card are connected by interchanger
It connects；The handling capacity of the network interface card is tested using iperf network bandwidth testing tool.
Further, the interchanger is separately connected the physical internet ports and the net of the virtual machine by 10,000,000,000 optical fiber cables
The physical internet ports of card.
Further, when the PCIe device is the HBA card, further includes:
HBA card test module for carrying out fio test to the HBA card by the virtual machine, and is tested according to fio
As a result HBA card performance is determined.
Since the embodiment of components of system as directed is corresponded to each other with the embodiment of method part, the embodiment of components of system as directed is asked
Referring to the description of the embodiment of method part, wouldn't repeat here.
The present embodiment is by when PCIe device is installed to PCIe slot, starting VT, VT-D and SR-IOV and loading
IOMMU module constructs virtual environment, and under the virtual environment driver of virtual machine internal can directly set with PCIe
It is standby to be communicated, only it need to reduce by management a small amount of or without VMM and need to run driving in VMM in the prior art
The dependence of program.Therefore, the operation driving journey in VMM can be reduced by PCIe device being distributed to virtual machine under the virtual environment
The demand of sequence improves the allocative efficiency of PCIe device.
Present invention also provides a kind of computer readable storage mediums, have computer program thereon, the computer program
It is performed and step provided by above-described embodiment may be implemented.The storage medium may include: USB flash disk, mobile hard disk, read-only deposit
Reservoir (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or
The various media that can store program code such as CD.
Present invention also provides a kind of server platforms, may include memory and processor, have in the memory
Computer program when the processor calls the computer program in the memory, may be implemented above-described embodiment and be provided
The step of.Certain server platform can also include various network interfaces, the components such as power supply.
Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.It should be pointed out that for those skilled in the art, under the premise of not departing from the application principle, also
Can to the application, some improvement and modification can also be carried out, these improvement and modification also fall into the protection scope of the claim of this application
It is interior.
It should also be noted that, in the present specification, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.Under the situation not limited more, the element limited by sentence "including a ..." is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Claims (10)
1. a kind of method for distributing PCIe device characterized by comprising
When detecting that PCIe device is installed to PCIe slot, server platform starting VT, VT-D and SR-IOV is simultaneously loaded
IOMMU, to construct virtual environment；
The Bus number of the PCIe device is obtained by the driver being adapted to the PCIe device；
Virtual machine is created in the virtual environment, and the Bus number is added to the control catalogue of the virtual machine, so as to
The physical internet ports of the PCIe device are distributed to the virtual machine.
2. method according to claim 1, which is characterized in that the server platform is specially to be equipped with Linux
The server platform of rhel7.2 system.
3. method according to claim 2, which is characterized in that creating virtual machine in the virtual environment includes:
The virtual machine is created in the virtual environment by the virt-manager of the Linux rhel7.2 system.
4. method according to claim 1, which is characterized in that the PCIe device includes network interface card or HBA card.
5. method according to claim 4, which is characterized in that when the PCIe device is the network interface card, will be described
The physical internet ports of PCIe device are distributed to the virtual machine, further includes:
IP address is distributed for the physical internet ports of the network interface card, to establish the network connection of the virtual machine Yu the network interface card；Its
In, the physical internet ports of the virtual machine are connect with the physical internet ports of the network interface card by interchanger；
The handling capacity of the network interface card is tested using iperf network bandwidth testing tool.
6. method according to claim 5, which is characterized in that the interchanger is separately connected the void by 10,000,000,000 optical fiber cables
The physical internet ports of quasi- machine and the physical internet ports of the network interface card.
7. method according to claim 4, which is characterized in that when the PCIe device be the HBA card when, will described in
The physical internet ports of PCIe device are distributed to the virtual machine, further includes:
Fio test is carried out to the HBA card by the virtual machine, and HBA card performance is determined according to fio test result.
8. a kind of system for distributing PCIe device characterized by comprising
Environment construction module, for when detecting that PCIe device is installed to PCIe slot, starting VT, VT-D and SR-IOV to be simultaneously
IOMMU is loaded, to construct virtual environment；
Bus number obtains module, and the bus of the PCIe device is obtained for the driver by being adapted to the PCIe device
Number；
Distribution module is added to the virtual machine for creating virtual machine in the virtual environment, and by the Bus number
Catalogue is controlled, to distribute the physical internet ports of the PCIe device to the virtual machine.
9. a kind of server platform characterized by comprising
Memory, for storing computer program；
Processor is realized when for executing the computer program distributing PCIe device as described in any one of claim 1 to 7
The step of method.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes the side that PCIe device is distributed as described in any one of claim 1 to 7 when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811044877.5A CN109144672A (en) | 2018-09-07 | 2018-09-07 | A kind of method, system and associated component for distributing PCIe device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811044877.5A CN109144672A (en) | 2018-09-07 | 2018-09-07 | A kind of method, system and associated component for distributing PCIe device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109144672A true CN109144672A (en) | 2019-01-04 |
Family
ID=64823927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811044877.5A Pending CN109144672A (en) | 2018-09-07 | 2018-09-07 | A kind of method, system and associated component for distributing PCIe device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109144672A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111063387A (en) * | 2019-12-29 | 2020-04-24 | 苏州浪潮智能科技有限公司 | Method, device and equipment for testing performance of solid state disk and storage medium |
| CN111625318A (en) * | 2020-05-22 | 2020-09-04 | 苏州浪潮智能科技有限公司 | Communication test method, device and equipment |
| CN113485756A (en) * | 2021-06-30 | 2021-10-08 | 深圳市科力锐科技有限公司 | Hardware equipment configuration method, device, equipment and storage medium |
| CN113886153A (en) * | 2021-08-20 | 2022-01-04 | 苏州浪潮智能科技有限公司 | Container-based network card pressure testing method and device |
| CN116303148A (en) * | 2023-05-17 | 2023-06-23 | 北京中科网威信息技术有限公司 | Multi-slot device network card detection method and device, electronic device and storage medium |
| CN116909639A (en) * | 2023-09-13 | 2023-10-20 | 珠海星云智联科技有限公司 | Mounting system, method, cluster and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120102491A1 (en) * | 2010-10-26 | 2012-04-26 | Lsi Corporation | Virtual function boot in single-root and multi-root i/o virtualization environments |
| CN103984591A (en) * | 2014-05-15 | 2014-08-13 | 中国人民解放军国防科学技术大学 | PCI (Peripheral Component Interconnect) device INTx interruption delivery method for computer virtualization system |
| CN104049912A (en) * | 2014-05-23 | 2014-09-17 | 上海爱数软件有限公司 | Distributed storage management method based on virtualization platform |
| CN104468311A (en) * | 2014-11-18 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Method and system for virtualizing physical network card into multiple virtual network cards |
| CN105320628A (en) * | 2015-11-06 | 2016-02-10 | 中国科学院计算技术研究所 | Adaptation device, system and method for enabling single I/O device to be shared by multiple root nodes |
| CN106250211A (en) * | 2016-08-05 | 2016-12-21 | 浪潮(北京)电子信息产业有限公司 | A kind of virtualization implementation method based on SR_IOV |
| CN106330779A (en) * | 2015-06-23 | 2017-01-11 | 联想企业解决方案(新加坡)有限公司 | Server, physical switch, and communication system |
| CN106789337A (en) * | 2017-01-18 | 2017-05-31 | 郑州云海信息技术有限公司 | A kind of network performance optimizing method of KVM |
| CN106909443A (en) * | 2017-02-28 | 2017-06-30 | 郑州云海信息技术有限公司 | The collocation method and device of a kind of virtual machine |
-
2018
- 2018-09-07 CN CN201811044877.5A patent/CN109144672A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120102491A1 (en) * | 2010-10-26 | 2012-04-26 | Lsi Corporation | Virtual function boot in single-root and multi-root i/o virtualization environments |
| CN103984591A (en) * | 2014-05-15 | 2014-08-13 | 中国人民解放军国防科学技术大学 | PCI (Peripheral Component Interconnect) device INTx interruption delivery method for computer virtualization system |
| CN104049912A (en) * | 2014-05-23 | 2014-09-17 | 上海爱数软件有限公司 | Distributed storage management method based on virtualization platform |
| CN104468311A (en) * | 2014-11-18 | 2015-03-25 | 浪潮(北京)电子信息产业有限公司 | Method and system for virtualizing physical network card into multiple virtual network cards |
| CN106330779A (en) * | 2015-06-23 | 2017-01-11 | 联想企业解决方案(新加坡)有限公司 | Server, physical switch, and communication system |
| CN105320628A (en) * | 2015-11-06 | 2016-02-10 | 中国科学院计算技术研究所 | Adaptation device, system and method for enabling single I/O device to be shared by multiple root nodes |
| CN106250211A (en) * | 2016-08-05 | 2016-12-21 | 浪潮(北京)电子信息产业有限公司 | A kind of virtualization implementation method based on SR_IOV |
| CN106789337A (en) * | 2017-01-18 | 2017-05-31 | 郑州云海信息技术有限公司 | A kind of network performance optimizing method of KVM |
| CN106909443A (en) * | 2017-02-28 | 2017-06-30 | 郑州云海信息技术有限公司 | The collocation method and device of a kind of virtual machine |
Non-Patent Citations (3)
| Title |
|---|
| GREG SCHULZ著，李洪涛等译: "《云和虚拟数据存储网络》", 31 May 2017 * |
| ZANG, DW；CAO, Z；WANG, Z；LIU, XL；WANG, L ；SUN, NH；: "Decentralized NIC-Switching Architecture Using SR-IOV PCI Express Network Device", 《IEEE MICRO》 * |
| 王展，曹政，刘小丽，苏勇，***，安学军，孙凝晖: "基于单根I/O虚拟化的多根I/O资源池化方法", 《计算机研究与发展》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111063387A (en) * | 2019-12-29 | 2020-04-24 | 苏州浪潮智能科技有限公司 | Method, device and equipment for testing performance of solid state disk and storage medium |
| CN111625318A (en) * | 2020-05-22 | 2020-09-04 | 苏州浪潮智能科技有限公司 | Communication test method, device and equipment |
| CN111625318B (en) * | 2020-05-22 | 2023-01-10 | 苏州浪潮智能科技有限公司 | Communication test method, device and equipment |
| CN113485756A (en) * | 2021-06-30 | 2021-10-08 | 深圳市科力锐科技有限公司 | Hardware equipment configuration method, device, equipment and storage medium |
| CN113886153A (en) * | 2021-08-20 | 2022-01-04 | 苏州浪潮智能科技有限公司 | Container-based network card pressure testing method and device |
| CN113886153B (en) * | 2021-08-20 | 2023-06-09 | 苏州浪潮智能科技有限公司 | Network card pressure testing method and device based on container |
| CN116303148A (en) * | 2023-05-17 | 2023-06-23 | 北京中科网威信息技术有限公司 | Multi-slot device network card detection method and device, electronic device and storage medium |
| CN116303148B (en) * | 2023-05-17 | 2023-08-22 | 北京中科网威信息技术有限公司 | Multi-slot device network card detection method and device, electronic device and storage medium |
| CN116909639A (en) * | 2023-09-13 | 2023-10-20 | 珠海星云智联科技有限公司 | Mounting system, method, cluster and storage medium |
| CN116909639B (en) * | 2023-09-13 | 2023-12-12 | 珠海星云智联科技有限公司 | Mounting system, method, cluster and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109144672A (en) | A kind of method, system and associated component for distributing PCIe device | |
| US11061712B2 (en) | Hot-plugging of virtual functions in a virtualized environment | |
| US11640363B2 (en) | Managing a smart network interface controller (NIC) of an information handling system | |
| US8260841B1 (en) | Executing an out-of-band agent in an in-band process of a host system | |
| US7721080B2 (en) | Management of option ROM | |
| US9542201B2 (en) | Network bios management | |
| US9184991B2 (en) | Method and apparatus for developing service processor solutions | |
| EP3398066A1 (en) | Fpga-enabled compute instances | |
| US10353713B2 (en) | Method to facilitate rapid deployment and rapid redeployment of an information handling system | |
| EP2575041A1 (en) | Method and computer for controlling virtual machine | |
| US9417886B2 (en) | System and method for dynamically changing system behavior by modifying boot configuration data and registry entries | |
| US10606677B2 (en) | Method of retrieving debugging data in UEFI and computer system thereof | |
| CN111857840B (en) | BIOS (basic input output system) starting method and device | |
| US10303487B2 (en) | System and method for booting an information handling system | |
| US20180246840A1 (en) | Intelligent Certificate Discovery in Physical and Virtualized Networks | |
| CN108989145A (en) | A kind of test method and device of network interface card virtualized nature | |
| WO2012138046A1 (en) | Terminal device and method for executing an android application on a general-purpose operating system, and computer-readable recording medium for same | |
| US8793478B2 (en) | Grid computing resources and a method of use thereof | |
| CN107766084A (en) | Bootload and installation method and its computing system | |
| US11321077B1 (en) | Live updating of firmware behavior | |
| US11144326B2 (en) | System and method of initiating multiple adaptors in parallel | |
| US20170344448A1 (en) | Comprehensive testing of computer hardware configurations | |
| CN107741868B (en) | Setting method and device for Basic Input Output System (BIOS) | |
| US9778936B1 (en) | Booting a computing system into a manufacturing mode | |
| CN116627472A (en) | Firmware program upgrading method and server of high-speed peripheral component equipment |
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: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |