CN111625356A - PCIe device resource pooling method, device, equipment and medium - Google Patents

PCIe device resource pooling method, device, equipment and medium Download PDF

Info

Publication number
CN111625356A
CN111625356A CN202010442565.0A CN202010442565A CN111625356A CN 111625356 A CN111625356 A CN 111625356A CN 202010442565 A CN202010442565 A CN 202010442565A CN 111625356 A CN111625356 A CN 111625356A
Authority
CN
China
Prior art keywords
pcie
interconnected
resource
devices
resource pool
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.)
Withdrawn
Application number
CN202010442565.0A
Other languages
Chinese (zh)
Inventor
林楷智
黄冠潣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Inspur Intelligent Technology Co Ltd
Original Assignee
Suzhou Inspur Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Inspur Intelligent Technology Co Ltd filed Critical Suzhou Inspur Intelligent Technology Co Ltd
Priority to CN202010442565.0A priority Critical patent/CN111625356A/en
Publication of CN111625356A publication Critical patent/CN111625356A/en
Withdrawn legal-status Critical Current

Links

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
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • 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
    • G06F13/10—Program control for peripheral devices
    • G06F13/102—Program control for peripheral devices where the programme performs an interfacing function, e.g. device driver
    • 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
    • G06F13/4282—Bus transfer protocol, e.g. handshake; Synchronisation on a serial bus, e.g. I2C bus, SPI 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
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The application discloses a resource pooling method of PCIe equipment, which comprises the following steps: interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain an interconnected PCIe; and performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool. Obviously, in the application, because the PCIe Switch may interconnect a plurality of different PCIe devices, and perform resource allocation on the interconnected PCIe by using the routing table of the interconnected PCIe, the limitation that different storage media cannot span a rack and a machine is broken, so that different storage media can be pooled in resources, and the purpose of performing resource integration on different storage media is achieved. Correspondingly, the resource pooling device, the equipment and the medium for the PCIe equipment also have the beneficial effects.

Description

PCIe device resource pooling method, device, equipment and medium
Technical Field
The present invention relates to the field of server technologies, and in particular, to a resource pooling method, device, apparatus, and medium for PCIe devices.
Background
With the rapid development of computer technology, the demand of people for storage resources is also increasing. In the prior art, although a design architecture for performing software management and control on storage resources has appeared, no research related to resource pooling for different storage media has appeared at present, that is, different types of storage media cannot perform resource integration across cabinets and machines. At present, no effective solution exists for the technical problem.
Therefore, it is an urgent technical problem to be solved by those skilled in the art how to pool resources for different storage media to realize resource integration of different storage media.
Disclosure of Invention
In view of this, an object of the present invention is to provide a method, an apparatus, a device and a medium for pooling resources of PCIe devices, so as to pool resources of different storage media and implement resource integration of different storage media. The specific scheme is as follows:
a method of resource pooling for PCIe devices, comprising:
interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain an interconnected PCIe;
and performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool.
Preferably, the process of interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain an interconnected PCIe includes:
and interconnecting a plurality of EDSFFs and/or Rulers and/or VNME SSDs and/or GPUs by utilizing the PCIe Switch to obtain the interconnected PCIe.
Preferably, the process of interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain an interconnected PCIe includes:
and interconnecting a plurality of PCIe devices by utilizing the Fabric and/or optical port and/or electrical port and/or Multi-Host and/or SR-IOV and/or MR-IOV and/or Shared I/O of the PCIe Switch to obtain the interconnected PCIe.
Preferably, the process of allocating resources to the interconnected PCIe according to the routing table of the interconnected PCIe includes:
and switching the uplink port and/or the downlink port of the PCIe Switch, and modifying the routing table of the interconnected PCIe to perform resource allocation on the interconnected PCIe.
Preferably, after the process of performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool, the method further includes:
and mounting the PCIe resource pool to the NVME.
Preferably, after the process of performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool, the method further includes:
and mounting the PCIe resource pool to an RSD architecture server.
Preferably, after the mounting the PCIe resource pool to the RSD architecture server, the method further includes:
and utilizing the API of the RSD architecture server to perform resource management on the RSD architecture server mounted with the PCIe resource pool.
Correspondingly, the invention also discloses a resource pooling device of PCIe equipment, which comprises:
the equipment interconnection module is used for interconnecting a plurality of different PCIe equipment by utilizing PCIe Switch to obtain interconnected PCIe;
and the resource allocation module is used for allocating resources to the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool.
Correspondingly, the invention also discloses a resource pooling device of PCIe device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of a method for pooling resources of a PCIe device as disclosed in the foregoing when executing said computer program.
Accordingly, the present invention also discloses a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method for resource pooling for PCIe devices as disclosed above.
Therefore, in the resource pooling method provided by the invention, the PCIe Switch can be used for interconnecting a plurality of different PCIe devices, and the routing table of the interconnected PCIe is used for carrying out resource allocation on the interconnected PCIe, so that the limitation that different storage media cannot carry out cross-cabinet and cross-machine integration is broken, the resource pooling of different storage media can be realized, and the purpose of carrying out resource integration on different storage media is achieved. Correspondingly, the resource pooling device, the equipment and the medium for the PCIe equipment also have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a resource pooling method of PCIe devices according to an embodiment of the present invention;
fig. 2 is a topology diagram of a whole architecture according to an embodiment of the present invention;
fig. 3 is a block diagram of a resource pooling apparatus of a PCIe device according to an embodiment of the present invention;
fig. 4 is a block diagram of a resource pooling device of a PCIe device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a resource pooling method of a PCIe device according to an embodiment of the present invention, where the resource pooling method includes:
step S11: interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain an interconnected PCIe;
step S12: and performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool.
In this embodiment, a resource pooling method for PCIe devices is provided, through which resources can be pooled for different storage media, and a purpose of resource integration for different storage media is achieved.
Specifically, in the resource pooling method provided in this embodiment, a plurality of PCIe devices are interconnected by using a PCIe Switch to obtain an interconnected PCIe, and because a communication protocol used by the PCIe devices is PCIe, different PCIe devices can be interconnected and communicated by using some advanced application functions in the PCIe Switch to obtain an interconnected PCIe with a larger storage space. Wherein, the high-level application functions in the PCIe Switch include: Multi-Host, SR-IOV, MR-IOV, and Shared I/O, among others.
It can be understood that, because the routing table of the interconnected PCIe stores the storage location and the attribute feature of each PCIe device, in this embodiment, in order to enable the CPU in the upper layer architecture to manage and use the storage resource of any PCIe device in the interconnected PCIe, after obtaining the interconnected PCIe, the routing table of the interconnected PCIe is used to allocate the resource to the interconnected PCIe, and thus, the purpose of integrating the storage resource in the interconnected PCIe is achieved. It can be thought that, after resource allocation is performed on the internet PCIe, sharing of storage resources in the PCIe resource pool can be achieved, and thus the problem that different storage media cannot perform resource integration across the cabinet and the machine is solved.
In addition, the PCIe resource pool obtained by the method does not need to be added with other devices to use the Physical Frame in the PCIe resource pool as in the traditional storage architecture, and the Physical Frame in the PCIe resource pool can be correspondingly mapped and managed by using the PCIe Switch, so that the convenience of different users in using the PCIe resource pool can be further improved.
As can be seen, in the resource pooling method provided in this embodiment, since the PCIe Switch may be used to interconnect a plurality of different PCIe devices, and the PCIe routing table for interconnecting PCIe is used to perform resource allocation on the interconnected PCIe, the limitation that different storage media cannot perform cross-cabinet and cross-machine integration is broken, so that different storage media can be resource pooled, and the purpose of performing resource integration on different storage media is achieved.
Based on the above embodiments, this embodiment further describes and optimizes the technical solution, and as a preferred implementation, the above steps: the process of interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain the interconnected PCIe comprises the following steps:
and interconnecting a plurality of EDSFFs and/or Rulers and/or VNME SSDs and/or GPUs by using PCIe Switch to obtain the interconnected PCIe.
It will be appreciated that in practical applications, there may be many different types of PCIe devices, such as: EDSFF, miller, VNME SSD (Non-Volatile Memory Express Solid State Disk, NMVE Solid State Disk), GPU (Graphics Processing Unit), and the like, and these PCIe devices are common storage media in real life, so in this embodiment, a PCIe Switch is used to interconnect a plurality of EDSFFs and/or runners and/or VNME SSDs and/or GPUs, and thus the limitation that different storage resources cannot be integrated across machines and racks is eliminated.
Therefore, the technical scheme provided by the embodiment can further improve the universality of the method provided by the application in practical application.
Based on the above embodiments, this embodiment further describes and optimizes the technical solution, and as a preferred implementation, the above steps: the process of interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain the interconnected PCIe comprises the following steps:
and the PCIe devices are interconnected by utilizing the Fabric and/or optical port and/or electrical port and/or Multi-Host and/or SR-IOV and/or MR-IOV and/or Shared I/O of the PCIe Switch to obtain the interconnected PCIe.
With the continuous upgrade of the application functions of the PCIe Switch, there may be a plurality of connection interfaces of different application functions in the PCIe Switch, such as: and the storage resources in a plurality of PCIe devices can be virtualized by using the advanced application functions Multi-Host, SR-IOV, MR-IOV or Shared I/O in PCIe Switch, and are correspondingly isolated and Shared. Therefore, in the embodiment, the PCIe devices are interconnected by using the Fabric and/or optical port and/or electrical port and/or Multi-Host and/or SR-IOV and/or MR-IOV and/or Shared I/O of the PCIe Switch, so as to obtain the interconnected PCIe.
Obviously, the technical scheme provided by the embodiment can make the interconnection process of the PCIe devices more flexible and diversified.
Based on the above embodiments, this embodiment further describes and optimizes the technical solution, and as a preferred implementation, the above steps: the process of resource allocation for the interconnected PCIe according to the routing table of the interconnected PCIe comprises the following steps:
and switching the uplink port and/or the downlink port of the PCIe Switch, and modifying a routing table of the interconnected PCIe to allocate resources to the interconnected PCIe.
Specifically, in this embodiment, in the process of resource allocation for the interconnected PCIe, resource allocation is performed for the interconnected PCIe by switching the uplink port and/or the downlink port of the PCIe switch and modifying the routing table of the interconnected PCIe, because the interconnected PCIe routing table determines the communication link of each PCIe device, in this embodiment, resource allocation is performed for the interconnected PCIe by using the setting manner.
Obviously, the technical scheme provided by the embodiment can further ensure the accuracy and reliability in the resource allocation process of the interconnected PCIe.
Based on the above embodiments, this embodiment further describes and optimizes the technical solution, and as a preferred implementation, the above steps: after the process of performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe and obtaining the PCIe resource pool, the method further comprises the following steps:
and mounting the PCIe resource pool to the NVME.
It can be understood that, because the Non-Volatile Memory Express (NVME) can not only greatly reduce the time delay of data in the storage process, but also has a low power consumption amount in the use process, the NVME is widely applied in the actual operation process.
In view of the above considerations, in the embodiment, in order to further improve the user experience of the user when using the NVME, the PCIe resource pool is mounted on the NVME after the PCIe resource pool is obtained. It can be thought that when the PCIe resource pool is mounted to the NVME, the storage space of the NVME is equivalently expanded, and in this case, the NVME can be applied to more practical application scenarios.
Based on the above embodiments, this embodiment further describes and optimizes the technical solution, and as a preferred implementation, the above steps: after the process of performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe and obtaining the PCIe resource pool, the method further comprises the following steps:
and mounting the PCIe resource pool to the RSD architecture server.
It can be understood that, because the RSD architecture server can perform cabinet combination scheduling on resources such as CPU, memory, PCIe, storage, etc., the RSD architecture server is more commonly applied in enterprises. Therefore, in the actual operation process, the storage space of the RSD architecture server can be further expanded by mounting the PCIe resource pool on the RSD architecture server.
Obviously, after the PCIe resource pool is mounted on the RSD architecture server, the RSD architecture server may perform more flexible configuration and adjustment on the storage resources in the PCIe resource pool, so as to achieve the purpose of more appropriate allocation and management of the storage resources.
As a preferred embodiment, after the process of mounting the PCIe resource pool to the RSD architecture server, the method further includes:
and performing resource management on the RSD architecture server mounted with the PCIe resource pool by using an API of the RSD architecture server.
It can be understood that, after the PCIe resource pool is mounted to the RSD architecture server, the PCIe resource pool is equivalent to a storage resource of the RSD architecture server itself, and the API in the RSD architecture server can manage and allocate the storage resource in the RSD architecture server, so in this embodiment, the API can also be used to perform resource management on the RSD architecture server after the PCIe resource pool is mounted, which avoids a tedious step of performing resource management on the RSD architecture server after the PCIe resource pool is mounted by using an additional CPU.
Therefore, by the technical scheme provided by the embodiment, the usability of the user in the process of managing the PCIe resource pool can be further improved.
Based on the technical content disclosed in the foregoing embodiments, this embodiment is specifically described by an application scenario embodiment. In the prior art, under a 1U standard machine height, the whole machine can accommodate 32 EDSFF Short and LongRuler, 32 NF1, and 128 m.2 flash memory devices, under this machine architecture, by using the PCIe device resource pooling method disclosed in the foregoing embodiments, it is possible to design a whole machine architecture that can be compatible with both Short EDSFF Long Ruler, 4 m.2, NF1, or m.2, and then, PIN Define is used to implement a multi-type and flexibly configurable whole machine system.
Referring to fig. 2, fig. 2 is a topology diagram of a whole architecture according to an embodiment of the present invention, in the topology architecture, PCIe Switch is used to connect different flash media NF1 or M.3, Long Ruler, Short Ruler and m.2 together under a HOST. Or, in practical applications, a highly available and versatile software and hardware architecture can be formed based on the PCIe device resource pooling method disclosed in the foregoing and by using Flash media of different forms. Specifically, Flash memory media of different forms and different quantities can be mixed and inserted to form a complete machine architecture meeting application requirements of different clients, so that the complete machine architecture is more flexible and activated, wherein the Flash memory media of different forms comprise: samsung NF1/M.3, EDSFF, Long Ruler/Short Ruler, U2, U3, M2, and the like. When the storage architecture can support 128 m.2 flash memory devices, PCIe Switch can be used to further expand the storage space of the storage architecture, that is, PCIe Switch is used to extend 4 m.2, in this case, 4 m.2 with small capacity can be used to achieve a large-capacity EDSFF miller flash memory, so that the manufacturing cost required by the large-capacity storage medium can be relatively reduced.
It can be understood that, in the prior art, because NF1, EDSFF miller and m.2 have different overall hardware architectures and structural topologies, different flash media cannot implement resource integration across enclosures and machines, and with the technical solution provided in this embodiment, a pooling design oF storage resources is achieved by matching PCIe Switch and NVMe-af protocol or NVMe protocol, and the limitation oF the traditional machines or enclosures on the storage resources is eliminated. Obviously, by the technical scheme provided by the embodiment, a set of storage system can be used to meet the architecture requirements of different types of flash memory media, so that the consumption of human resources in the design and development process of the storage architecture can be greatly reduced.
Referring to fig. 3, fig. 3 is a structural diagram of a resource pooling apparatus for PCIe devices according to an embodiment of the present invention, where the resource pooling apparatus includes:
the device interconnection module 21 is configured to interconnect multiple different PCIe devices by using a PCIe Switch, so as to obtain an interconnected PCIe;
and the resource allocation module 22 is configured to perform resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe, so as to obtain a PCIe resource pool.
Preferably, the device interconnection module 21 includes:
and the first equipment interconnection unit is used for interconnecting a plurality of EDSFFs and/or Rulers and/or VNME SSDs and/or GPUs by utilizing the PCIe Switch to obtain the interconnection PCIe.
Preferably, the device interconnection module 21 includes:
and the second equipment interconnection unit is used for interconnecting a plurality of PCIe equipment by utilizing the Fabric and/or the optical port and/or the electrical port and/or the Multi-Host and/or the SR-IOV and/or the MR-IOV and/or the Shared I/O of the PCIe Switch to obtain the interconnected PCIe.
Preferably, the resource allocation module 22 includes:
and the resource allocation unit is used for switching the uplink port and/or the downlink port of the PCIe Switch and modifying the routing table of the interconnected PCIe so as to allocate resources to the interconnected PCIe.
Preferably, the method further comprises the following steps:
the first mounting module is configured to perform resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe, and after a process of obtaining a PCIe resource pool, the first mounting module further includes: and mounting the PCIe resource pool to the NVME.
Preferably, the method further comprises the following steps:
the second mounting module is configured to perform resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe, and after a process of obtaining a PCIe resource pool, the second mounting module further includes: and mounting the PCIe resource pool to an RSD architecture server.
Preferably, the method further comprises the following steps:
the API management module, after the process of mounting the PCIe resource pool to the RSD architecture server, further includes: and utilizing the API of the RSD architecture server to perform resource management on the RSD architecture server mounted with the PCIe resource pool.
The resource pooling device of the PCIe device provided by the embodiment of the invention has the beneficial effects of the resource pooling method of the PCIe device disclosed in the foregoing.
Referring to fig. 4, fig. 4 is a structural diagram of a resource pooling device of a PCIe device according to an embodiment of the present invention, where the resource pooling device includes:
a memory 31 for storing a computer program;
a processor 32 for implementing the steps of a method for pooling resources of a PCIe device as disclosed above when executing a computer program.
The resource pooling device of the PCIe device provided in the embodiment of the present invention has the beneficial effects of the foregoing disclosed resource pooling method of the PCIe device.
Accordingly, an embodiment of the present invention further discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the resource pooling method for PCIe devices as disclosed in the foregoing are implemented.
The computer-readable storage medium provided by the embodiment of the invention has the beneficial effects of the above-disclosed resource pooling method for PCIe devices.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing describes in detail a method, an apparatus, a device, and a medium for pooling resources of a PCIe device provided in the present invention, and a specific example is applied in the present disclosure to illustrate the principle and the implementation of the present invention, and the description of the foregoing embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (10)

1. A method for resource pooling of PCIe devices, comprising:
interconnecting a plurality of PCIe devices by using a PCIe Switch to obtain an interconnected PCIe;
and performing resource allocation on the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool.
2. The method of claim 1, wherein the process of interconnecting multiple PCIe devices using a PCIe Switch to obtain an interconnected PCIe comprises:
and interconnecting a plurality of EDSFFs and/or Rulers and/or VNME SSDs and/or GPUs by utilizing the PCIe Switch to obtain the interconnected PCIe.
3. The method of claim 1, wherein the process of interconnecting multiple PCIe devices using a PCIe Switch to obtain an interconnected PCIe comprises:
and interconnecting a plurality of PCIe devices by utilizing the Fabric and/or optical port and/or electrical port and/or Multi-Host and/or SR-IOV and/or MR-IOV and/or Shared I/O of the PCIe Switch to obtain the interconnected PCIe.
4. The method of claim 1, wherein the process of resource allocation for the interconnected PCIe according to the routing table of the interconnected PCIe comprises:
and switching the uplink port and/or the downlink port of the PCIe Switch, and modifying the routing table of the interconnected PCIe to perform resource allocation on the interconnected PCIe.
5. The method of any of claims 1 to 4, wherein the resource allocation for the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool further comprises:
and mounting the PCIe resource pool to the NVME.
6. The method of any of claims 1 to 4, wherein the resource allocation for the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool further comprises:
and mounting the PCIe resource pool to an RSD architecture server.
7. The method of claim 6, wherein the mounting the PCIe resource pool to an RSD fabric server is followed by:
and utilizing the API of the RSD architecture server to perform resource management on the RSD architecture server mounted with the PCIe resource pool.
8. An apparatus for resource pooling of PCIe devices, comprising:
the equipment interconnection module is used for interconnecting a plurality of different PCIe equipment by utilizing PCIe Switch to obtain interconnected PCIe;
and the resource allocation module is used for allocating resources to the interconnected PCIe according to the routing table of the interconnected PCIe to obtain a PCIe resource pool.
9. A resource pooling device for PCIe devices, comprising:
a memory for storing a computer program;
a processor for implementing the steps of a resource pooling method of a PCIe device of any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of a method of resource pooling for PCIe devices as recited in any one of claims 1 to 7.
CN202010442565.0A 2020-05-22 2020-05-22 PCIe device resource pooling method, device, equipment and medium Withdrawn CN111625356A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010442565.0A CN111625356A (en) 2020-05-22 2020-05-22 PCIe device resource pooling method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010442565.0A CN111625356A (en) 2020-05-22 2020-05-22 PCIe device resource pooling method, device, equipment and medium

Publications (1)

Publication Number Publication Date
CN111625356A true CN111625356A (en) 2020-09-04

Family

ID=72272043

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010442565.0A Withdrawn CN111625356A (en) 2020-05-22 2020-05-22 PCIe device resource pooling method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN111625356A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115442239A (en) * 2022-08-01 2022-12-06 超聚变数字技术有限公司 Bandwidth resource allocation method, PCIe channel switcher and electronic equipment
CN115774620A (en) * 2022-12-23 2023-03-10 摩尔线程智能科技(北京)有限责任公司 Method and device for realizing mutual access of storage spaces in GPU (graphics processing Unit) interconnection architecture and computing equipment
WO2024179298A1 (en) * 2023-02-27 2024-09-06 浪潮电子信息产业股份有限公司 Cross-cabinet server memory pooling method, apparatus and device, server, and medium

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115442239A (en) * 2022-08-01 2022-12-06 超聚变数字技术有限公司 Bandwidth resource allocation method, PCIe channel switcher and electronic equipment
CN115442239B (en) * 2022-08-01 2024-02-09 河南昆仑技术有限公司 Bandwidth resource allocation method, PCIe channel switcher and electronic device
CN115774620A (en) * 2022-12-23 2023-03-10 摩尔线程智能科技(北京)有限责任公司 Method and device for realizing mutual access of storage spaces in GPU (graphics processing Unit) interconnection architecture and computing equipment
CN115774620B (en) * 2022-12-23 2023-09-05 摩尔线程智能科技(北京)有限责任公司 Method, device and computing equipment for realizing memory space mutual access in GPU interconnection architecture
WO2024131989A1 (en) * 2022-12-23 2024-06-27 摩尔线程智能科技(北京)有限责任公司 Method and apparatus for realizing mutual access of storage spaces in gpu interconnect architecture, computing device, computer readable storage medium, and computer program product
WO2024179298A1 (en) * 2023-02-27 2024-09-06 浪潮电子信息产业股份有限公司 Cross-cabinet server memory pooling method, apparatus and device, server, and medium

Similar Documents

Publication Publication Date Title
US9342376B2 (en) Method, system, and device for dynamic energy efficient job scheduling in a cloud computing environment
CN111625356A (en) PCIe device resource pooling method, device, equipment and medium
US10481804B2 (en) Cluster system with calculation and storage converged
CN109768871B (en) Method for configuring multiple virtual network cards, host machine and storage medium
US10091295B1 (en) Converged infrastructure implemented with distributed compute elements
US11157457B2 (en) File management in thin provisioning storage environments
US9898338B2 (en) Network computer system and method for dynamically changing execution sequence of application programs
US9432484B1 (en) CIM-based data storage management system having a restful front-end
CN110908609B (en) Method, system and equipment for processing disk and readable storage medium
CN109634720B (en) Method, system and device for sharing FPGA (field programmable Gate array) board card by multiple virtual machines
CN107580011B (en) Data sharing method and desktop cloud server
US10776173B1 (en) Local placement of resource instances in a distributed system
CN110809030B (en) Network flow control method and device, coder-decoder and storage device
CN103152394A (en) Data access system, internal memory share device and data reading method
KR101559541B1 (en) Multi-pc system based on virtual desktop technology
US9575881B2 (en) Systems and methods for providing improved latency in a non-uniform memory architecture
US10084785B2 (en) Connecting and retrieving security tokens based on context
CN103607429A (en) Cloud computing service realization method and system thereof
CN106354428B (en) Storage sharing system of multi-physical layer partition computer system structure
CN113535087B (en) Data processing method, server and storage system in data migration process
EP3076306B1 (en) Method and apparatus for achieving device sharing
CN110383254B (en) Optimizing memory mapping associated with network nodes
CN110704334A (en) Method, system and equipment for important product data management
CN111831451A (en) Cloud host memory allocation method, cloud host, cloud device and storage medium
CN103108046A (en) Cloud terminal virtual machine login method and cloud terminal virtual machine login device and cloud terminal virtual machine login system

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20200904