CN104636076A - Distributed block device driving method and system for cloud storage - Google Patents
Distributed block device driving method and system for cloud storage Download PDFInfo
- Publication number
- CN104636076A CN104636076A CN201310574012.0A CN201310574012A CN104636076A CN 104636076 A CN104636076 A CN 104636076A CN 201310574012 A CN201310574012 A CN 201310574012A CN 104636076 A CN104636076 A CN 104636076A
- Authority
- CN
- China
- Prior art keywords
- virtual
- virtual disk
- vsp
- vbus
- psp
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
- G06F3/0664—Virtualisation aspects at device level, e.g. emulation of a storage device or system
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a distributed block device driving method and system for cloud storage. The method comprises the steps that an I/O request transmitted from an upper-layer file system is converted into an access message of a virtual block device, a network card drive is called to send a data packet to a server, and therefore a true physical storage device on the server can be accessed. According to the distributed block device driving method and system, remote loading and running of various operating systems and instruction interfaces of various storage devices can be supported, and data requesting and processing can be efficiently finished.
Description
Technical field
The present invention relates to field of cloud calculation, particularly relate to a kind of distributed block device drives method and system stored for cloud.
Background technology
Along with the development of network technology, important personal data are synchronized in the network storage equipment by terminal device and carry out preserving and managing by user.Cloud computing is as a kind of novel Network Computing Mode, and operating system user be familiar with and application program are supplied to user as the content of the network storage.Cloud computing terminal, by network remote load operation system, adopts block stream mode Dynamic Execution, for user provides cross-platform various application and service.Due to cloud computing terminal not predetermined physical memory device itself, therefore its needs to drive by a kind of virtual memory facilities to carry out alternately with the physical memory resources on cloud computing server, thus provides the view of a virtual disk for user.This driving method needs remote loading and the operation that can support several operation systems, supports the instruction interface of multiple memory device, and can complete request of data and process efficiently.
There is following problem in traditional driving method:
The first, traditional driving method such as Windows driving model and Linux driving model are all the device Driver Models towards certain specific operating system, and be only applicable to stand-alone environment, can not meet that cloud computing virtual storage system is cross-platform, the demand of networking.
The second, the device model based on virtual machine coordinates the mode of network storage protocol can realize remote activation and the operation of operating system, and famous achievement has Collective, ISR and OSCircular.Wherein, Collective and ISR is the system based on the exploitation of VMWare device model, and OS Circular then uses Xen-HVM device model.But virtual machine takies more internal memory when running, and extends I/O access path, thus has considerable influence to data access performance.
Summary of the invention
In view of more than, the present invention propose a kind of for cloud store distributed block device drives method and system.
The present invention proposes a kind of distributed block device drives method stored for cloud, comprising:
The I/O that the VBD of terminal receives from OS asks and sends VSP to;
VSP extracts the virtual disk parameter in I/O request and sends VHBA to;
This virtual disk parameter is encapsulated as network data message and sends to server by VHBA;
The VIOP of server resolves the network data message received, and sends PSP to;
This virtual disk Parameter Switch, according to the mapping relations between virtual disk and physical disk, is physical disk parameter, accesses real memory device by PSP;
Result is returned to corresponding virtual disk device object by VHBA, activates VSP;
The data copy returned in the internal memory of specifying, is completed I/O request by VBD.
Further, also comprise:
PSP arranges the oracle listener to VBus, after detecting that VSP enters init state, PSP is by detection Physics disk, distribute and INIT block equipment interface, make respective field wherein point to the device number of physical equipment, carry out registering to VBus and write physical disk information, wait for that VBus writes virtual disk information, VBus is a kind of bus abstract between VSP and PSP, mutual in order to what complete between virtual disk interface and physical store interface;
VSP enters init state, registers to VBus, and write virtual disk request report, distributes and initialization interface structure, enters initialization completion status after making the device number of the sensing of respective field wherein virtual disk equipment;
After PSP detects in VBus and have registered new virtual unit, obtain virtual unit request report in VBus, according to the virtual disk information creating virtual disk in report;
After establishment completes, when PSP monitor VSP enter initialization completion status time, the physical disk information of updating the equipment in VBus, enters connection status, prepares the I/O request that process passes over from VSP;
VSP detects that PSP enters connection status, sets up the connection with PSP, and from VBus, reads in physical disk information, complete the mapping between virtual disk and physical disk.
Further, also comprise:
All drivers that operating system traversal pci bus exists, load VSP and drive;
The Virtual Block Device object that VSP initialization is concrete, registration interrupt handling routine, Virtual Block Device object will call VHBA as a PCI equipment and drive;
VHBA initialization of virtual bus adapter controller object, by the information distribution hardware resource of pci configuration space, registration break in service, expands next stage virtual interface bus structure VBus;
VHBA calls network sweep interface, sends link order confirm whether memory device prepares to receive virtual i/o request to server;
After acquisition one confirms successfully reply, VHBA sends virtual disk scan instruction and obtains device name, device number and virtual disk information;
According to the said equipment configuration information, VHBA registers new virtual disk device object to VBus, enters the establishing stage of Virtual Block Device.
The present invention proposes a kind of distributed block device driver system stored for cloud, and comprise terminal, this terminal comprises: VBD, VSP and VHBA, wherein:
VBD, the I/O received from OS ask and send VSP to, by the data copy returned in the internal memory of specifying, complete I/O request;
VSP, extracts the virtual disk parameter in I/O request and sends VHBA to;
VHBA, is encapsulated as network data message by this virtual disk parameter and sends to server, server process result is returned to corresponding virtual disk device object, activates VSP;
Wherein, the network data message that server parses receives, according to the mapping relations between virtual disk and physical disk, is physical disk parameter by this virtual disk Parameter Switch, accesses real memory device.
Further, VSP enters init state, registers to VBus, and write virtual disk request report, distributes and initialization interface structure, enters initialization completion status after making the device number of the sensing of respective field wherein virtual disk equipment; VSP detects that PSP enters connection status, sets up the connection with PSP, and from VBus, reads in physical disk information, complete the mapping between virtual disk and physical disk.
Further, the Virtual Block Device object that VSP initialization is concrete, registration interrupt handling routine, Virtual Block Device object will call VHBA as a PCI equipment and drive;
VHBA initialization of virtual bus adapter controller object, by the information distribution hardware resource of pci configuration space, registration break in service, expands next stage virtual interface bus structure VBus; VHBA calls network sweep interface, sends link order confirm whether memory device prepares to receive virtual i/o request to server; After acquisition one confirms successfully reply, VHBA sends virtual disk scan instruction and obtains device name, device number and virtual disk information; According to the said equipment configuration information, VHBA registers new virtual disk device object to VBus, enters the establishing stage of Virtual Block Device.
The present invention proposes a kind of distributed block device driver system stored for cloud, and comprise server, this server comprises VIOP and PSP, wherein:
VIOP, resolves the network data message received from terminal, sends PSP to;
PSP, according to the mapping relations between virtual disk and physical disk, is physical disk parameter by the virtual disk Parameter Switch carried in network data message, accesses real memory device;
Wherein, the I/O that terminal receives from OS asks, and extracts the virtual disk parameter in I/O request, this virtual disk parameter is encapsulated as network data message and sends to server, and server results is returned to corresponding virtual disk device object, complete I/O request.
Further, PSP arranges the oracle listener to VBus, after detecting that VSP enters init state, PSP, by detection Physics disk, distributes and INIT block equipment interface, makes respective field wherein point to the device number of physical equipment, carry out registering to VBus and write physical disk information, wait for that VBus writes virtual disk information, VBus is a kind of bus abstract between VSP and PSP, mutual in order to what complete between virtual disk interface and physical store interface; After PSP detects in VBus and have registered new virtual unit, obtain virtual unit request report in VBus, according to the virtual disk information creating virtual disk in report; After establishment completes, when PSP monitor VSP enter initialization completion status time, the physical disk information of updating the equipment in VBus, enters connection status, prepares the I/O request that process passes over from VSP.
The present invention proposes a kind of distributed block device driver system stored for cloud, comprises above-mentioned arbitrary described terminal and above-mentioned arbitrary described server.
Further, the communication transport protocols by standard between terminal and server sets up data exchange channels.
The present invention is the framework that memory device driver under cloud computing environment describes an opening.This framework, independent of specific operating system, hardware platform and system I/O bus, can meet that cloud computing virtual storage system is cross-platform, the demand of networking.
The present invention can support remote loading and the operation of several operation systems, supports the instruction interface of multiple memory device, and can complete request of data and process efficiently.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, forms a part of the present invention, and schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
What Figure 1 shows that device drives method under cloud computing environment of the present invention and legacy equipment driving method compares schematic diagram.
Figure 2 shows that the configuration diagram of the distributed block device driver system in one embodiment of the invention.
Figure 3 shows that the schematic flow sheet of the distributed block device drives method in one embodiment of the invention.
Embodiment
Various exemplary embodiment of the present invention is described in detail now with reference to accompanying drawing.It should be noted that: unless specifically stated otherwise, otherwise the positioned opposite and numerical value of the parts of setting forth in these embodiments and step does not limit the scope of the invention.
Meanwhile, it should be understood that for convenience of description, the size of the various piece shown in accompanying drawing is not draw according to the proportionate relationship of reality.
Illustrative to the description only actually of at least one exemplary embodiment below, never as any restriction to the present invention and application or use.
May not discuss in detail for the known technology of person of ordinary skill in the relevant, method and apparatus, but in the appropriate case, described technology, method and apparatus should be regarded as a part of authorizing instructions.
In all examples with discussing shown here, any occurrence should be construed as merely exemplary, instead of as restriction.Therefore, other example of exemplary embodiment can have different values.
It should be noted that: represent similar terms in similar label and letter accompanying drawing below, therefore, once be defined in an a certain Xiang Yi accompanying drawing, then do not need to be further discussed it in accompanying drawing subsequently.
The present invention is the framework that memory device driver under cloud computing environment describes an opening.This framework is independent of specific operating system, hardware platform and system I/O bus, and what be illustrated in figure 1 device drives method under cloud computing environment of the present invention and legacy equipment driving method compares schematic diagram.
Be traditional device drives method on the left of arrow in Fig. 1, traditional driving method does not need server, only drives local disk.Classic method towards specific operation system, and based on one-of-a-kind system.Memory device drives and is loaded in executive operating system kernel initialization process, and after this, the I/O request produced when application program is run all goes access local disk by this driving.Driving method of the present invention on the right side of arrow in Fig. 1.Wherein, left side is terminal, and right side is server.The present invention is independent of specific operating system, hardware platform and system bus, and driving is extended to network environment by the present invention.
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
Figure 2 shows that the configuration diagram of the distributed block device driver system in one embodiment of the invention.This system comprises terminal and server.Wherein, terminal comprises front-end module, and server comprises rear module.
Front-end module and rear module are all loaded into the driver of kernel state in the operating system of terminal and server respectively, and both have different 26S Proteasome Structure and Functions.According to the difference of functional hierarchy, front-end module and rear module establish respective driving storehouse respectively.Below in conjunction with accompanying drawing, front-end module and rear module are described respectively.
1. front-end module drives stack
Front-end module is responsible for the I/O request that acquisition topmost paper system transmits, and will ask the access message converting Virtual Block Device to, then call trawl performance by Packet Generation to server end.Front-end module drives protocol stack to run at the kernel state of terminal, is divided into 3 parts by functional structure.
(1) Virtual Block Device drives layer (virtual block device, VBD).
The main task of VBD obtains the request from operating system I/O subsystem outside, and convert thereof into feasible Virtual Block Device request of access, send middle level downwards to and drive, namely send VSP to, and the data copy to be returned by VSP is in the internal memory of specifying, complete I/O request.VBD driving upwards provides a virtual block device interface, has all attributes of block device, specifically can show as virtual disk kind equipment, virtual tape kind equipment, virtual drive kind equipment etc.For meeting the open requirement of system, VBD assembly is also for operating system provides PnP interface, device power supply (DPS) management interface and the I/O data access interface meeting relevant criterion.PnP interface provides the function such as startup, configuration, stopping, deletion of virtual memory facilities entity.The power supply signal of virtual memory facilities is passed to server by device power supply (DPS) management interface, provides power management policy by server, and the result that terminal returns according to server again arranges corresponding power supply status.In I/O data-interface, VBD provides comprehensive support to general data interaction interface ATA and SCSI.
(2) virtual store interface driver layer (virtual storage port, VSP).
VSP mainly realizes the various functions of front-end module, comprise scan bus, Fault recovery, command queuing, with kernel communication and other various function of initializing.It receives I/O request from VBD, extracts the virtual disk parameter in I/O request and sends lower floor and VHBA to.Until I/O asks process to complete, result is returned to VBD by VSP again.VSP also error process as time-out or instruction errors etc.Therefore, VSP be virtual device interface bus layer drive, for levels drive provide unified interface go forward side by side row bus scanning, finishing equipment is enumerated, data are transmitted and error handle.
(3) virtual bus adapter drives layer (virtual host bus adaptor, VHBA).
VHBA adopts the network transmission protocol be applicable to realize virtual interface bus structure VBus, and by with server interaction, complete the transmission of state between front-end module and rear module, data, order and message.VHBA is the driving of Virtual Controller, relevant to concrete hardware adapter downwards.Such as, it can call trawl performance and send I/O request message to server end.That is, virtual disk parameter is encapsulated as network data message and sends to server by VHBA, server process result is returned to corresponding virtual disk device object, activates VSP.
2. rear module drives stack
The process of rear module primary responsibility is from the virtual i/o request of the front-end module of multiple terminal, resolve visit information wherein, rank respectively according to request type, dispatch, construct true block device access instruction, and pass to physical equipment and process, finally the data organized are sent it back corresponding front-end module.Rear module drives the kernel state being positioned at service end, is divided into 2 levels by functional structure.
(1) virtual i/o process drives layer (virtual I/O processor, VIOP).
VIOP resolves the virtual i/o request from front-end module, classify, queues up and dispatches, and sends physical equipment access instruction wherein to PSP layer and processes.VIOP encapsulates from contents such as the data of PSP layer or responses, and sends corresponding front-end module to by network.The function of server end host-host protocol completes in VIOP.
(2) physical store interface drives layer (physical storage port, PSP).
PSP and Internet Transmission have nothing to do, and main process is from the physical equipment access instruction of VIOP device drive layer.This virtual disk Parameter Switch, according to the mapping relations between virtual disk and physical disk, is physical disk parameter, accesses real memory device by PSP.The block interface accessing instruction received can be carried out classifying according to interface class by it, be polymerized after, the physical storage device driver calling interface type with it corresponding processes.PSP is also responsible for false command process and command status is safeguarded.
The present invention can support remote loading and the operation of several operation systems, supports the instruction interface of multiple memory device, and can complete request of data and process efficiently.In the present invention, Virtual Block Device drives and carries out alternately with the physical memory resources on cloud computing server, thus provides the view of a virtual disk for user.
The present invention adopts the Intel Virtualization Technology based on block level, provides corresponding Virtual Block Device interface to process I/O request.Driving method adopts client terminal/server structure, according to code function, driver is divided into front-end module and rear module two parts.Front-end module operates in cloud computing terminal, for terminal OS provides virtual device interface, and does not need the code of particular hardware.Rear module operates in cloud computing server, provides the interface of I/O adapter and its physical equipment, and does not need terminal OS correlative code.Two intermodules use the communication transport protocols of a standard as iSCSI or NBD, for physically separated 2 intermodules set up data exchange channels.Below in conjunction with accompanying drawing, the workflow of front-end module and rear module is described in detail.
Cloud computing terminal this locality not resident operating system, the remote loading of operating system nucleus is carried out in the service that therefore needing BIOS to call PXE agreement after starting up provides.After OS kernel is loaded, in execution kernel initialization process, load front-end module protocol stack.The I/O request that after the loading of OS system program and OS start, the operation of application program produces, is all processed by front-end module and work rear module collaborative work in the server.Workflow mainly comprises scan bus, Virtual Block Device creates and I/O asks process 3 processes.
Scan bus, Virtual Block Device create, I/O request process is the flow process that order performs, namely, scan bus is that dummy block will establishment is prepared, Virtual Block Device creates to set up the mapping between virtual disk and physical disk, when then carrying out I/O request process, the mapping relations based on setting up are needed to change.To be described in detail respectively to above-mentioned three processes below.
(1) scan bus
Step one: in computer system starting process, the PCI(Peripheral Component Interconnect of operating system scanning acquiescence, peripheral component interconnect bus) root node, all drivers that traversal pci bus exists, load VSP and drive.
Step 2: the Virtual Block Device object that VSP initialization is concrete, registration interrupt handling routine.Virtual Block Device object will call VHBA as a PCI equipment and drive.
Step 3: VHBA initialization of virtual bus adapter controller object, by the information distribution hardware resource of pci configuration space, registration break in service, expands next stage virtual interface bus structure VBus.VBus is a kind of bus abstract between VSP and PSP, mutual in order to what complete between virtual disk interface and physical store interface.
Step 4: VHBA calls network sweep interface, and module end sends link order confirmation memory device and whether prepares the request of reception virtual i/o to the back-end.
Step 5: after acquisition one confirms successfully reply, VHBA sends the configuration information (comprising the information such as the number of virtual disk and the size of each disk) that virtual disk scan instruction obtains device name, device number and virtual disk.
Step 6: according to the said equipment configuration information, VHBA registers new virtual disk device object to VBus.Start the establishing stage entering Virtual Block Device.
(2) Virtual Block Device creates
VSP with PSP is undertaken communicating and consulting by the VBus bus abstract that bottom provides, and both collaborative works create Virtual Block Device, and flow process is as follows:
First step one: PSP arranges the oracle listener to VBus, after detecting that VSP enters init state, PSP is by detection Physics disk, distribute and the structures such as INIT block equipment interface, respective field is wherein made to point to the device number of physical equipment, carry out registering to VBus and write physical disk information, waiting for that VBus writes virtual disk information.
Step 2: VSP enters init state, registers to VBus, and write virtual disk request report, distributes and initialization interface structure, enters initialization completion status after making the device number of the sensing of respective field wherein virtual disk equipment.
Step 3: PSP obtains virtual unit request report in VBus after monitoring and have registered new virtual unit in function check to VBus, starts to create virtual disk according to the virtual disk configuration information in report.
Step 4: after having created, when PSP monitor VSP enter initialization completion status time, the information such as the physical sector number of updating the equipment in VBus, sector-size, then enter connection status, prepare the I/O request that process passes over from VSP.
Step 5: VSP detects that PSP enters connection status, sets up the connection with PSP immediately, and from VBus, reads in the information such as physical sector number, sector-size, and then complete the mapping relations table between virtual disk and physical disk.According to mapping relations table, VBD starts to register, distribute and the object disk of configure generic, and notice OS has new block device to be created.After this, OS can use virtual disk as use local disk.
(3) I/O request process
Figure 3 shows that the schematic flow sheet of the distributed block device drives method in one embodiment of the invention.The flow show I/O request processing flow.Comprise the following steps:
After step one: VSP receives the I/O request from OS from VBD, first this request is added request of access queue, and adopt the algorithm (as First Input First Output and Weighted Fair Queuing etc.) of suitable queue management, from queue, select suitable I/O request to be further processed.
Step 2: VSP takes out an I/O request at every turn from queue, and after previous I/O request process that is and if only if completes, the next I/O request in queue just can be processed.
Step 3: VSP extracts the correlation parameter (comprising the start address of requested disk block, block size and buffer pointer) in I/O request data structure, call the read/write interface of VHBA, correlation parameter is encapsulated into disk access read/write instruction, then will be encapsulated as network data message and sends to service end VIOP.
Step 4: VIOP resolves the request message received, and classifies to virtual i/o request according to classifying rules (by users classification or I/O classification of type).Scheduling strategy gives different priority for different classes of I/O queue, IOQ, and limit priority is given in the I/O request that such as can be system class.
Step 5: PSP calls the real memory device of physical disk interface accessing after polymerization process is carried out in the I/O received request.After server returns to result, result is returned to corresponding virtual disk device object by VHBA, activates VSP.
Step 6: VBD is by the data copy returned in the internal memory of specifying, and notice OS, completes an I/O request.
The present invention is not only confined to the computing terminal under cloud computing environment, also can be applicable on various computing equipment, as various application server.
So far, the present invention is described in detail.In order to avoid covering design of the present invention, details more known in the field are not described.Those skilled in the art, according to description above, can understand how to implement technical scheme disclosed herein completely.
Method of the present invention and device may be realized in many ways.Such as, any combination by software, hardware, firmware or software, hardware, firmware realizes method of the present invention and device.Said sequence for the step of described method is only to be described, and the step of method of the present invention is not limited to above specifically described order, unless specifically stated otherwise.In addition, in certain embodiments, can be also record program in the recording medium by the invention process, these programs comprise the machine readable instructions for realizing according to method of the present invention.Thus, the present invention also covers the recording medium stored for performing the program according to method of the present invention.
Although be described in detail specific embodiments more of the present invention by example, it should be appreciated by those skilled in the art, above example is only to be described, instead of in order to limit the scope of the invention.It should be appreciated by those skilled in the art, can without departing from the scope and spirit of the present invention, above embodiment be modified.Scope of the present invention is limited by claims.
Claims (10)
1., for the distributed block device drives method that cloud stores, it is characterized in that:
The I/O that the VBD of terminal receives from OS asks and sends VSP to;
VSP extracts the virtual disk parameter in I/O request and sends VHBA to;
This virtual disk parameter is encapsulated as network data message and sends to server by VHBA;
The VIOP of server resolves the network data message received, and sends PSP to;
This virtual disk Parameter Switch, according to the mapping relations between virtual disk and physical disk, is physical disk parameter, accesses real memory device by PSP;
Result is returned to corresponding virtual disk device object by VHBA, activates VSP;
The data copy returned in the internal memory of specifying, is completed I/O request by VBD.
2., according to claim 1 for the distributed block device drives method that cloud stores, it is characterized in that, also comprise:
PSP arranges the oracle listener to VBus, after detecting that VSP enters init state, PSP is by detection Physics disk, distribute and INIT block equipment interface, make respective field wherein point to the device number of physical equipment, carry out registering to VBus and write physical disk information, wait for that VBus writes virtual disk information, VBus is a kind of bus abstract between VSP and PSP, mutual in order to what complete between virtual disk interface and physical store interface;
VSP enters init state, registers to VBus, and write virtual disk request report, distributes and initialization interface structure, enters initialization completion status after making the device number of the sensing of respective field wherein virtual disk equipment;
After PSP detects in VBus and have registered new virtual unit, obtain virtual unit request report in VBus, according to the virtual disk information creating virtual disk in report;
After establishment completes, when PSP monitor VSP enter initialization completion status time, the physical disk information of updating the equipment in VBus, enters connection status, prepares the I/O request that process passes over from VSP;
VSP detects that PSP enters connection status, sets up the connection with PSP, and from VBus, reads in physical disk information, complete the mapping between virtual disk and physical disk.
3. according to claim 1 or 2 for cloud store distributed block device drives method, it is characterized in that, also comprise:
All drivers that operating system traversal pci bus exists, load VSP and drive;
The Virtual Block Device object that VSP initialization is concrete, registration interrupt handling routine, Virtual Block Device object will call VHBA as a PCI equipment and drive;
VHBA initialization of virtual bus adapter controller object, by the information distribution hardware resource of pci configuration space, registration break in service, expands next stage virtual interface bus structure VBus;
VHBA calls network sweep interface, sends link order confirm whether memory device prepares to receive virtual i/o request to server;
After acquisition one confirms successfully reply, VHBA sends virtual disk scan instruction and obtains device name, device number and virtual disk information;
According to the said equipment configuration information, VHBA registers new virtual disk device object to VBus, enters the establishing stage of Virtual Block Device.
4., for the distributed block device driver system that cloud stores, comprise terminal, this terminal comprises: VBD, VSP and VHBA, it is characterized in that:
VBD, the I/O received from OS ask and send VSP to, by the data copy returned in the internal memory of specifying, complete I/O request;
VSP, extracts the virtual disk parameter in I/O request and sends VHBA to;
VHBA, is encapsulated as network data message by this virtual disk parameter and sends to server, server process result is returned to corresponding virtual disk device object, activates VSP;
Wherein, the network data message that server parses receives, according to the mapping relations between virtual disk and physical disk, is physical disk parameter by this virtual disk Parameter Switch, accesses real memory device.
5., according to claim 4 for the distributed block device driver system that cloud stores, it is characterized in that:
VSP enters init state, registers to VBus, and write virtual disk request report, distributes and initialization interface structure, enters initialization completion status after making the device number of the sensing of respective field wherein virtual disk equipment; VSP detects that PSP enters connection status, sets up the connection with PSP, and from VBus, reads in physical disk information, complete the mapping between virtual disk and physical disk.
6., according to claim 5 for the distributed block device driver system that cloud stores, it is characterized in that:
The Virtual Block Device object that VSP initialization is concrete, registration interrupt handling routine, Virtual Block Device object will call VHBA as a PCI equipment and drive;
VHBA initialization of virtual bus adapter controller object, by the information distribution hardware resource of pci configuration space, registration break in service, expands next stage virtual interface bus structure VBus; VHBA calls network sweep interface, sends link order confirm whether memory device prepares to receive virtual i/o request to server; After acquisition one confirms successfully reply, VHBA sends virtual disk scan instruction and obtains device name, device number and virtual disk information; According to the said equipment configuration information, VHBA registers new virtual disk device object to VBus, enters the establishing stage of Virtual Block Device.
7., for the distributed block device driver system that cloud stores, comprise server, this server comprises VIOP and PSP, it is characterized in that:
VIOP, resolves the network data message received from terminal, sends PSP to;
PSP, according to the mapping relations between virtual disk and physical disk, is physical disk parameter by the virtual disk Parameter Switch carried in network data message, accesses real memory device;
Wherein, the I/O that terminal receives from OS asks, and extracts the virtual disk parameter in I/O request, this virtual disk parameter is encapsulated as network data message and sends to server, and server results is returned to corresponding virtual disk device object, complete I/O request.
8., according to claim 7 for the distributed block device driver system that cloud stores, it is characterized in that:
PSP arranges the oracle listener to VBus, after detecting that VSP enters init state, PSP is by detection Physics disk, distribute and INIT block equipment interface, make respective field wherein point to the device number of physical equipment, carry out registering to VBus and write physical disk information, wait for that VBus writes virtual disk information, VBus is a kind of bus abstract between VSP and PSP, mutual in order to what complete between virtual disk interface and physical store interface; After PSP detects in VBus and have registered new virtual unit, obtain virtual unit request report in VBus, according to the virtual disk information creating virtual disk in report; After establishment completes, when PSP monitor VSP enter initialization completion status time, the physical disk information of updating the equipment in VBus, enters connection status, prepares the I/O request that process passes over from VSP.
9., for the distributed block device driver system that cloud stores, it is characterized in that: comprise the arbitrary described terminal of claim 4 to 6 and the arbitrary described server of claim 7 or 8.
10., according to claim 9 for the distributed block device driver system that cloud stores, it is characterized in that: the communication transport protocols by standard between terminal and server sets up data exchange channels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310574012.0A CN104636076B (en) | 2013-11-15 | 2013-11-15 | A kind of distributed block device drives method and system for cloud storage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310574012.0A CN104636076B (en) | 2013-11-15 | 2013-11-15 | A kind of distributed block device drives method and system for cloud storage |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104636076A true CN104636076A (en) | 2015-05-20 |
| CN104636076B CN104636076B (en) | 2017-12-05 |
Family
ID=53214890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310574012.0A Active CN104636076B (en) | 2013-11-15 | 2013-11-15 | A kind of distributed block device drives method and system for cloud storage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104636076B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881254A (en) * | 2015-05-27 | 2015-09-02 | 北京百度网讯科技有限公司 | Data storage method and device |
| CN105404471A (en) * | 2015-11-03 | 2016-03-16 | 国云科技股份有限公司 | Distributed cloud storage cache layer realization method |
| CN106534328A (en) * | 2016-11-28 | 2017-03-22 | 网宿科技股份有限公司 | Node connection method and distributed computing system |
| CN106557280A (en) * | 2016-10-31 | 2017-04-05 | 北京华为数字技术有限公司 | Date storage method, storage array and host server |
| CN106610789A (en) * | 2015-10-26 | 2017-05-03 | 华为技术有限公司 | Data processing method, device and system |
| CN107015889A (en) * | 2017-04-12 | 2017-08-04 | 广州市品高软件股份有限公司 | A kind of implementation method of the multi-user virtual tape library based on cloud computing |
| CN107025146A (en) * | 2016-01-30 | 2017-08-08 | 华为技术有限公司 | A kind of document generating method, device and system |
| CN109656675A (en) * | 2017-10-11 | 2019-04-19 | 阿里巴巴集团控股有限公司 | Bus apparatus, computer equipment and the method for realizing physical host cloud storage |
| CN109933278A (en) * | 2017-12-19 | 2019-06-25 | 中国电信股份有限公司 | For realizing the method and apparatus of block device carry access |
| CN110568996A (en) * | 2019-09-05 | 2019-12-13 | 蒋昊坤 | Local storage capacity expansion system based on device driver |
| CN112860601A (en) * | 2019-11-12 | 2021-05-28 | 深圳怡化电脑股份有限公司 | Method and device for calling device driving function, computer device and system |
| CN113672411A (en) * | 2021-08-25 | 2021-11-19 | 烽火通信科技股份有限公司 | Method and device for realizing virtualization drive adaptation layer of network equipment |
| TWI769696B (en) * | 2020-02-14 | 2022-07-01 | 日商三菱電機股份有限公司 | Drive control device and drive control system |
| CN114844957A (en) * | 2022-04-27 | 2022-08-02 | 工银科技有限公司 | Link message conversion method, device, equipment, storage medium and program product |
| CN114860321A (en) * | 2022-04-06 | 2022-08-05 | 网易（杭州）网络有限公司 | External device control method, device, equipment and medium based on raspberry pi |
| CN115190044A (en) * | 2022-06-28 | 2022-10-14 | 平安银行股份有限公司 | Equipment connection state checking method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1623136A (en) * | 2002-01-09 | 2005-06-01 | 思科技术公司 | Methods and apparatus for implementing virtualization of storage within a storage area network through a virtual enclosure |
| CN1945537A (en) * | 2006-07-27 | 2007-04-11 | 清华大学 | Method for realizing high speed solid storage device based on storage region network |
| CN101419535A (en) * | 2008-11-19 | 2009-04-29 | 北京航空航天大学 | Distributed virtual magnetic disc system of virtual machine |
| CN102999400A (en) * | 2012-11-22 | 2013-03-27 | 中国电信股份有限公司云计算分公司 | Data backup method and device of cloud storage system |
| US20130083693A1 (en) * | 2011-10-04 | 2013-04-04 | Hitachi, Ltd. | Configuration management method of logical topology in virtual network and management server |
-
2013
- 2013-11-15 CN CN201310574012.0A patent/CN104636076B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1623136A (en) * | 2002-01-09 | 2005-06-01 | 思科技术公司 | Methods and apparatus for implementing virtualization of storage within a storage area network through a virtual enclosure |
| CN1945537A (en) * | 2006-07-27 | 2007-04-11 | 清华大学 | Method for realizing high speed solid storage device based on storage region network |
| CN101419535A (en) * | 2008-11-19 | 2009-04-29 | 北京航空航天大学 | Distributed virtual magnetic disc system of virtual machine |
| US20130083693A1 (en) * | 2011-10-04 | 2013-04-04 | Hitachi, Ltd. | Configuration management method of logical topology in virtual network and management server |
| CN102999400A (en) * | 2012-11-22 | 2013-03-27 | 中国电信股份有限公司云计算分公司 | Data backup method and device of cloud storage system |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881254B (en) * | 2015-05-27 | 2018-09-07 | 北京百度网讯科技有限公司 | Date storage method and device |
| WO2016188014A1 (en) * | 2015-05-27 | 2016-12-01 | 北京百度网讯科技有限公司 | Data storage method and device |
| US10469583B2 (en) | 2015-05-27 | 2019-11-05 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Data storage method and device |
| CN104881254A (en) * | 2015-05-27 | 2015-09-02 | 北京百度网讯科技有限公司 | Data storage method and device |
| CN106610789A (en) * | 2015-10-26 | 2017-05-03 | 华为技术有限公司 | Data processing method, device and system |
| CN106610789B (en) * | 2015-10-26 | 2019-08-16 | 华为技术有限公司 | A kind of data processing method, apparatus and system |
| CN105404471A (en) * | 2015-11-03 | 2016-03-16 | 国云科技股份有限公司 | Distributed cloud storage cache layer realization method |
| CN105404471B (en) * | 2015-11-03 | 2018-06-12 | 国云科技股份有限公司 | A kind of distribution cloud storage cache layer implementation method |
| CN107025146B (en) * | 2016-01-30 | 2019-10-18 | 华为技术有限公司 | A kind of document generating method, device and system |
| CN107025146A (en) * | 2016-01-30 | 2017-08-08 | 华为技术有限公司 | A kind of document generating method, device and system |
| CN106557280B (en) * | 2016-10-31 | 2019-10-15 | 北京华为数字技术有限公司 | Date storage method, storage array and host server |
| CN106557280A (en) * | 2016-10-31 | 2017-04-05 | 北京华为数字技术有限公司 | Date storage method, storage array and host server |
| CN106534328B (en) * | 2016-11-28 | 2020-01-31 | 网宿科技股份有限公司 | Node connection method and distributed computing system |
| CN106534328A (en) * | 2016-11-28 | 2017-03-22 | 网宿科技股份有限公司 | Node connection method and distributed computing system |
| WO2018094909A1 (en) * | 2016-11-28 | 2018-05-31 | 网宿科技股份有限公司 | Node connection method and distributed computing system |
| CN107015889A (en) * | 2017-04-12 | 2017-08-04 | 广州市品高软件股份有限公司 | A kind of implementation method of the multi-user virtual tape library based on cloud computing |
| CN107015889B (en) * | 2017-04-12 | 2019-11-22 | 广州市品高软件股份有限公司 | A kind of implementation method of the multi-user virtual tape library based on cloud computing |
| CN109656675A (en) * | 2017-10-11 | 2019-04-19 | 阿里巴巴集团控股有限公司 | Bus apparatus, computer equipment and the method for realizing physical host cloud storage |
| CN109933278A (en) * | 2017-12-19 | 2019-06-25 | 中国电信股份有限公司 | For realizing the method and apparatus of block device carry access |
| CN110568996A (en) * | 2019-09-05 | 2019-12-13 | 蒋昊坤 | Local storage capacity expansion system based on device driver |
| CN112860601A (en) * | 2019-11-12 | 2021-05-28 | 深圳怡化电脑股份有限公司 | Method and device for calling device driving function, computer device and system |
| TWI769696B (en) * | 2020-02-14 | 2022-07-01 | 日商三菱電機股份有限公司 | Drive control device and drive control system |
| CN113672411A (en) * | 2021-08-25 | 2021-11-19 | 烽火通信科技股份有限公司 | Method and device for realizing virtualization drive adaptation layer of network equipment |
| CN113672411B (en) * | 2021-08-25 | 2023-08-11 | 烽火通信科技股份有限公司 | Method and device for realizing network equipment virtualization driving adaptation layer |
| CN114860321A (en) * | 2022-04-06 | 2022-08-05 | 网易（杭州）网络有限公司 | External device control method, device, equipment and medium based on raspberry pi |
| CN114860321B (en) * | 2022-04-06 | 2023-07-18 | 网易（杭州）网络有限公司 | External device control method, device, equipment and medium based on raspberry pie |
| CN114844957B (en) * | 2022-04-27 | 2024-03-08 | 工银科技有限公司 | Link message conversion method, device, equipment, storage medium and program product |
| CN114844957A (en) * | 2022-04-27 | 2022-08-02 | 工银科技有限公司 | Link message conversion method, device, equipment, storage medium and program product |
| CN115190044A (en) * | 2022-06-28 | 2022-10-14 | 平安银行股份有限公司 | Equipment connection state checking method, device, equipment and storage medium |
| CN115190044B (en) * | 2022-06-28 | 2023-08-08 | 平安银行股份有限公司 | Device connection state checking method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104636076B (en) | 2017-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104636076A (en) | Distributed block device driving method and system for cloud storage | |
| US10862982B2 (en) | Cloud-scale heterogeneous datacenter management infrastructure | |
| CN102567052B (en) | Techniques for enabling remote management of servers configured with graphics processors | |
| CN105993009B (en) | The method and apparatus that MSI-X is interrupted are transmitted by computing resource of the non-transparent bridge into PCIe cluster | |
| US9798682B2 (en) | Completion notification for a storage device | |
| US8122109B2 (en) | Method and system for dynamic virtual environment migration | |
| US10498645B2 (en) | Live migration of virtual machines using virtual bridges in a multi-root input-output virtualization blade chassis | |
| WO2017066944A1 (en) | Method, apparatus and system for accessing storage device | |
| US10656877B2 (en) | Virtual storage controller | |
| US20170031694A1 (en) | System and method for remote system configuration managment | |
| TW201629783A (en) | Emulated endpoint configuration | |
| US10346065B2 (en) | Method for performing hot-swap of a storage device in a virtualization environment | |
| CN111679911B (en) | Management method, device, equipment and medium of GPU card in cloud environment | |
| CN109951553B (en) | Data processing method, system, electronic device and computer readable storage medium | |
| US20190332409A1 (en) | Identification and storage of logical to physical address associations for components in virtualized systems | |
| CN114417373A (en) | Data access method and device for NVMe-oF user mode client | |
| US20220050701A1 (en) | Open-channel storage device management with ftl on virtual machine | |
| US11113088B2 (en) | Generating and managing groups of physical hosts associated with virtual machine managers in an information handling system | |
| US11178216B2 (en) | Generating client applications from service model descriptions | |
| US20240086299A1 (en) | Development platform validation with simulation | |
| US11983182B2 (en) | System and method to enable a data analytics in a smart data accelerator interface device | |
| KR102532099B1 (en) | Storage virtualization device supporting a virtual machine, operation method thereof, and operation method of system having the same | |
| WO2024051231A1 (en) | Processor and processor error detection method | |
| US20230342190A1 (en) | Context-driven framework to migrate the applications and its dependencies by analyzing the relationships | |
| US20240028362A1 (en) | Object validation in software-defined data center scripts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220127 Address after: 100007 room 205-32, floor 2, building 2, No. 1 and No. 3, qinglonghutong a, Dongcheng District, Beijing Patentee after: Tianyiyun Technology Co.,Ltd. Address before: No.31, Financial Street, Xicheng District, Beijing, 100033 Patentee before: CHINA TELECOM Corp.,Ltd. |
|
| TR01 | Transfer of patent right |