CN107391236A - A kind of cluster block Realization of Storing and device - Google Patents

A kind of cluster block Realization of Storing and device Download PDF

Info

Publication number
CN107391236A
CN107391236A CN201710830214.5A CN201710830214A CN107391236A CN 107391236 A CN107391236 A CN 107391236A CN 201710830214 A CN201710830214 A CN 201710830214A CN 107391236 A CN107391236 A CN 107391236A
Authority
CN
China
Prior art keywords
cluster
corosync
lvm
management
virtual machine
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
Application number
CN201710830214.5A
Other languages
Chinese (zh)
Other versions
CN107391236B (en
Inventor
马怀旭
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.)
Zhengzhou Yunhai Information Technology Co Ltd
Original Assignee
Zhengzhou Yunhai Information 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 Zhengzhou Yunhai Information Technology Co Ltd filed Critical Zhengzhou Yunhai Information Technology Co Ltd
Priority to CN201710830214.5A priority Critical patent/CN107391236B/en
Publication of CN107391236A publication Critical patent/CN107391236A/en
Application granted granted Critical
Publication of CN107391236B publication Critical patent/CN107391236B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • 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
    • G06F3/0614—Improving the reliability of storage systems
    • 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
    • G06F3/0638—Organizing or formatting or addressing of data
    • G06F3/0644—Management of space entities, e.g. partitions, extents, pools
    • 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
    • G06F3/0665—Virtualisation aspects at area level, e.g. provisioning of virtual or logical volumes
    • 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
    • G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • 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
    • G06F9/54—Interprogram communication
    • G06F9/542—Event management; Broadcasting; Multicasting; Notifications
    • 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
    • G06F9/54—Interprogram communication
    • G06F9/546—Message passing systems or structures, e.g. queues
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/45579—I/O management, e.g. providing access to device drivers or storage

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the invention discloses a kind of cluster block Realization of Storing and device, methods described to include：Block device is provided to virtual machine by logical volume management LVM, so that the file system that the virtual machine creating oneself needs；Cluster management is carried out using corosync cluster management systems so that for the resource operation of LVM storage pools, the main frame master chosen by corosync clusters is performed.The embodiment of the present invention reduces the flow of each I/O operation, it is possible to increase the efficiency of cluster file system, while the IO speed of the virtual machine of cluster is improved, optimize cluster-based storage performance.

Description

A kind of cluster block Realization of Storing and device
Technical field
The present invention relates to cloud computing technology, espespecially a kind of cluster block Realization of Storing and device.
Background technology
With the fast development of computer technology and network technology, group system is with its powerful operational capability and stalwartness Fault tolerant mechanism allows it progressively to turn into the focus of computer industry.But the development as supporting cluster file system is distributed The influence of formula, slower development, most cluster file system are to be re-created on the basis of original file system virtually The file system format of machine demand.Such file system has deepened the flow of input and output I/O operation each time, reduces text The access rate of part system.
The content of the invention
In order to solve the above-mentioned technical problem, the embodiments of the invention provide a kind of cluster block Realization of Storing and device, The flow of each I/O operation can be reduced, it is possible to increase the efficiency of cluster file system, while improve the virtual machine of cluster IO speed.
In order to reach the object of the invention, on the one hand, the embodiments of the invention provide a kind of cluster block Realization of Storing, bag Include：
Block device is provided to virtual machine by logical volume management LVM, so that the file system that the virtual machine creating oneself needs System；
Cluster management is carried out using corosync cluster management systems so that for the resource operation of LVM storage pools, by Main frame master that corosync clusters choose is performed.
Further, the main frame master is selected to include by corosync clusters：
When Corosync selects master nodes, the IO of physical hard disk time delay is chosen according to current hosts.
Further, methods described also includes：
Logical volume LV is provided by LVM, and all I/O operations for LV are mapped on corresponding physical hard disk and carried out.
Further, methods described also includes：
When every virtual machine carries out I/O operation, physical hard disk corresponding to oneself logical volume LV is only operated.
Further, the resource operation for LVM storage pools includes：
When creating the LVM storage pools that block device is provided, the storage that All hosts are able to access that in cluster is selected, one Platform is able to access that on the main frame of the storage that performing LVM creates operation；
Described in carry during LVM storage pools, LVM described in carry is managed by the cluster management add-on module of carry node and stored The main frame in pond, wherein, cluster management add-on module is the module for all operations of management corosync clusters write.
Further, methods described also includes：
When issue operation is deleted to the wound of the volume of storage pool when, the operation is taken over by the cluster management add-on module write, The operation is dealt on master nodes by corosync, master nodes perform the operation, are returned after having performed The operating result.
Further, methods described also includes：
Corosync provides looped network redundancy agreement RRP patterns, and corosync clusters are formed by redundant network.
Further, methods described also includes：
Corosync provides redundancy message pass through mechanism, and each corosync clustered node receives message afterwards by wide Broadcast and send other all nodes to, message is issued by each cluster member by corosync loop network.
On the other hand, the embodiment of the present invention additionally provides a kind of cluster block storage realization device, including：
Module is provided, for providing block device to virtual machine by logical volume management LVM, so that the virtual machine creating oneself The file system needed；
Management module, for carrying out cluster management using corosync cluster management systems so that for LVM storage pools Resource operation, the main frame master that is chosen by corosync clusters are performed.
Further, the management module is additionally operable to：
When Corosync selects master nodes, the IO of physical hard disk time delay is chosen according to current hosts.
Logical volume LV is provided by LVM, and all I/O operations for LV are mapped on corresponding physical hard disk and carried out.
Further, described device also includes：
When every virtual machine carries out I/O operation, physical hard disk corresponding to oneself logical volume LV is only operated.
Further, the management module is additionally operable to：
When creating the LVM storage pools that block device is provided, the storage that All hosts are able to access that in cluster is selected, one Platform is able to access that on the main frame of the storage that performing LVM creates operation；
Described in carry during LVM storage pools, LVM described in carry is managed by the cluster management add-on module of carry node and stored The main frame in pond, wherein, cluster management add-on module is the module for all operations of management corosync clusters write.
Further, described device also includes：
When issue operation is deleted to the wound of the volume of storage pool when, the operation is taken over by the cluster management add-on module write, The operation is dealt on master nodes by corosync, master nodes perform the operation, are returned after having performed The operating result.
Further, described device also includes：
Corosync provides looped network redundancy agreement RRP patterns, and corosync clusters are formed by redundant network.
Further, described device also includes：
Corosync provides redundancy message pass through mechanism, and each corosync clustered node receives message afterwards by wide Broadcast and send other all nodes to, message is issued by each cluster member by corosync loop network.
Compared with prior art, the embodiment of the present invention by by logical volume management LVM provide block device to virtual machine so that The file system that the virtual machine creating oneself needs；Cluster management is carried out using corosync cluster management systems so that right In the resource operation of LVM storage pools, the main frame master chosen by corosync clusters is performed.The embodiment of the present invention drops The low flow of each I/O operation, it is possible to increase the efficiency of cluster file system, while improve the IO speed of the virtual machine of cluster Degree, optimizes cluster-based storage performance.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by specification, rights Specifically noted structure is realized and obtained in claim and accompanying drawing.
Brief description of the drawings
Accompanying drawing is used for providing further understanding technical solution of the present invention, and a part for constitution instruction, with this The embodiment of application is used to explain technical scheme together, does not form the limitation to technical solution of the present invention.
Fig. 1 is the flow chart of cluster block Realization of Storing of the embodiment of the present invention；
Fig. 2 is the structure chart that cluster of embodiment of the present invention block stores realization device.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with accompanying drawing to the present invention Embodiment be described in detail.It should be noted that in the case where not conflicting, in the embodiment and embodiment in the application Feature can mutually be combined.
Can be in the computer system of such as one group computer executable instructions the flow of accompanying drawing illustrates the step of Perform.Also, although logical order is shown in flow charts, in some cases, can be with suitable different from herein Sequence performs shown or described step.
Fig. 1 is the flow chart of cluster block Realization of Storing of the embodiment of the present invention, as shown in figure 1, the embodiment of the present invention Method comprises the following steps：
Step 100：Block device is provided to virtual machine by logical volume management LVM, so that the virtual machine creating oneself needs File system；
In the embodiment of the present invention, block device is provided to virtual machine, the file system of virtual machine creating oneself needs by LVM System, it is possible to increase the speed of virtual machine I/O operation, improve virtual machine storage performance.
Step 101：Cluster management is carried out using corosync cluster management systems so that for the resource of LVM storage pools Operation, the main frame master that is chosen by corosync clusters are performed.
Cluster management system is provided by corosync, while a master agent functionality is provided by corosync, File system operation is carried out by master, using master operation document systems, avoids, because multi-machine operation, causing data not One is qualitative.
Further, the main frame master is selected to include by corosync clusters：
When Corosync selects master nodes, the IO of physical hard disk time delay is chosen according to current hosts.
Specifically, the value of the IO speed of an acquiescence is set, when the IO speed of master main frames is less than this current value Wait, the minimum main frame of IO speed is reselected by corosync to carry out metadata operation.
Further, methods described also includes：
Logical volume LV is provided by LVM, and all I/O operations for LV are mapped on corresponding physical hard disk and carried out.
Further, methods described also includes：
When every virtual machine carries out I/O operation, physical hard disk corresponding to oneself logical volume LV is only operated.
Further, the resource operation for LVM storage pools includes：
When creating the LVM storage pools that block device is provided, the storage that All hosts are able to access that in cluster is selected, one Platform is able to access that on the main frame of the storage that performing LVM creates operation；
Described in carry during LVM storage pools, LVM described in carry is managed by the cluster management add-on module of carry node and stored The main frame in pond, wherein, cluster management add-on module is the module for all operations of management corosync clusters write.
Further, methods described also includes：
When issue operation is deleted to the wound of the volume of storage pool when, the operation is taken over by the cluster management add-on module write, The operation is dealt on master nodes by corosync, master nodes perform the operation, are returned after having performed The operating result.
Further, methods described also includes：
Corosync provides looped network redundancy agreement RRP patterns, and corosync clusters are formed by redundant network.
Further, methods described also includes：
Corosync provides redundancy message pass through mechanism, and each corosync clustered node receives message afterwards by wide Broadcast and send other all nodes to, message is issued by each cluster member by corosync loop network.
The embodiment of the present invention by logical volume management LVM by providing block device to virtual machine, so that the virtual machine creating The file system that oneself needs；Cluster management is carried out using corosync cluster management systems so that for the money of LVM storage pools Source is operated, and the main frame master that is chosen by corosync clusters is performed.The embodiment of the present invention reduces each I/O operation Flow, it is possible to increase the efficiency of cluster file system, while improve the IO speed of the virtual machine of cluster, optimize cluster and deposit Store up performance.
The method of the embodiment of the present invention is described in detail from principle below：
The present invention proposes a kind of cluster block storage implementation.Block device file system based on cluster is referred to as collection now The research center of group's file system, there is provided to virtual machine with specific block device, virtual machine then according to required file format, The block device is formatted as to the file system of oneself demand, when virtual machine uses the block device, virtual machine directly passes through lattice The file system of formula is transparent to block device business, reduces the flow of each I/O operation.The IO behaviour of fair speed is provided simultaneously Make, improve the efficiency of cluster file system, while improve the IO speed of the virtual machine of cluster.
The implementation of the embodiment of the present invention ensures cluster member by using corosync cluster management systems, simultaneously Ensure the uniformity of cluster internal message by corosync, by logical volume management (Logical Volume Manager, LVM) specific block device is provided, ensure the uniqueness of LVM operations by corosync, is coordinated by both, realizes cluster Block storage scheme.For cluster file system, ensure that multiple nodes access jointly, while it is also cluster file system to operate Demand.
The embodiment of the present invention provides block device by LVM, is supplied to virtual machine by providing block device, virtual machine creating is certainly The file system that oneself needs, the speed of virtual machine I/O operation is improved, improve virtual machine storage performance.Collection is provided by corosync Cluster management system, while a master agent functionality is provided by corosync, file system operation is carried out by master, Using master operation document systems, avoid, because multi-machine operation, causing data to differ qualitative, every virtual machine carries out I/O operation When, only operate oneself logical volume LV corresponding to disk, data collision will not be caused.LVM operations are metadata operations, multimachine Metadata inconsistence problems are easily caused when operation.Cluster communication is provided by corosync.
The embodiment of the present invention carries out cluster communication by corosync, carries out cluster management, and block device is provided by LVM, The IO performances of virtual disk are improved, while are used by cluster communication to reach this plot storage cluster, are stored every time for LVM The resource operation in pond, the master only chosen by corosync clusters perform operation, and other main frames only carry out I/O operation, without metadata operation.
Corosync selects to need to choose the IO of disk time delay according to current hosts when master nodes, sets The value of the IO speed of one acquiescence, when the IO speed of master main frames be less than it is current this when, selected again by corosync The minimum main frame of IO speed is selected to carry out metadata operation.
Technical scheme specific implementation process of the embodiment of the present invention is as follows：
Host deployments corosync all first, corosync clusters are formed, cluster management add-on module is write, passes through Corosync transmits message, while the situation of other nodes is obtained from corosync.
Create cluster block storage pool when firstly the need of selection cluster in All hosts it can be seen that storage, create storage One is needed when pond it can be seen that the main frame of the storage, LVM is performed on the host and creates operation, is led to when carry storage pool Cross the main frame of the cluster management add-on module management carry of the carry node storage pool；
When storage pool is issued operation is deleted to the wound of the volume of storage pool when, cluster management add-on module takes over these behaviour Make, by corosync, operation is dealt on master nodes, master nodes perform the operation, and being returned after having performed should Operating result, operation are completed.
The present invention uses corosync clusters and LVM logical volume managements, additional cluster add-on module, can pass through Corosync carries out cluster management with redundant network, while by the property of corosync clusters, all nodes can keep disappearing The uniformity of breath reaches the effect of a main prepare more, can keep the stability of cluster and the stabilization of storage pool to the full extent Property, LVM provides logical volume management, and by the management to logical volume, the storage provided upper strata is mapped directly on bottom hardware, The IO efficiency of the storage of the guarantee offer of maximum capacity is provided.
The embodiment of the present invention provides logical volume management by LVM, and redundant cluster management and redundancy are provided by corosync Message passing mechanism ensures the stability of cluster and the reliability of cluster operation；Logical volume management is externally provided by LVM, there is provided LV, all I/O operations for LV are mapped directly on physical hard disk, improve the IO speed of disk；Pass through cluster add-on module pair Cluster carries out selecting main operation, i.e. master nodes carry out operation processing, avoid more main frames while operate LVM metadata, avoid Metadata inconsistency.
Further, corosync provides looped network redundancy agreement (Redundant Ring Protocol, RRP) pattern, leads to Redundant network composition cluster is crossed, can farthest ensure the stability of cluster when Network Abnormal.
Further, corosync provides redundancy message pass through mechanism, and each corosync clustered node receives message All other all nodes can be sent to by broadcast afterwards, then be issued message by corosync loop network each Individual cluster member, it is easily restorative when the uniformity of all message of cluster and message transmission can be kept to fail.
Further, LVM provides logical volume management, including the LV that are provided of LVM are that the physics that region be directly facing in bottom is set Standby, each LV has logical volume corresponding to oneself, can only ensure every within the scope of oneself is divided for LV I/O operation One LV IO is independent of each other, simultaneously as LV directly maps the physical equipment of bottom, therefore can ensure to provide bottom storage Maximum performance.
Further, LVM provides logical volume management, in addition to：The division information of all physical equipments is all recorded in first number According to region, when All hosts all have mapped the physical disk of bottom, the physical equipment can be operated, when more main Machine easily causes the inconsistent situation of metadata data when operating, and storage pool easily occurs and is write bad situation, it is therefore desirable to one Platform main frame is responsible for metadata operation specially, ensures that all operations can only carry out one simultaneously, other main frames are after completing to operate Refresh Data is carried out, i.e., it can be seen that all data.
Further, there can only be a main frame to carry out metadata operation, master selections are carried out in corosync clusters Operation, i.e. cluster add-on module, all operations of management cluster, are carried out selecting main operation by cluster add-on module, monitored simultaneously The IO performances of current hosts, master is selected when performance reaches bottlenecks metadata operation again, is reached with optimal operability Can, complete metadata operation.
The embodiment of the present invention is ensured to the full extent by the management of corosync redundant networks and redundancy message pass through mechanism The stability of cluster and the reliability of operation.By LVM carry out logical volume management, all I/O operations not by file system this One layer, directly it is issued on disk, the IO performances of disk can be improved to the full extent, so as to improves the IO performances of storage pool.
Fig. 2 is the structure chart that cluster of embodiment of the present invention block stores realization device, as shown in Fig. 2 the embodiment of the present invention is another On the one hand a kind of cluster block storage realization device provided, including：
Module 201 is provided, for providing block device to virtual machine by logical volume management LVM, so that the virtual machine creating The file system that oneself needs；
Management module 202, for carrying out cluster management using corosync cluster management systems so that stored for LVM The resource operation in pond, the main frame master that is chosen by corosync clusters are performed.
Further, the management module 202 is additionally operable to：
When Corosync selects master nodes, the IO of physical hard disk time delay is chosen according to current hosts.
Further, described device also includes：
When every virtual machine carries out I/O operation, physical hard disk corresponding to oneself logical volume LV is only operated.
Further, the management module 202 is additionally operable to：
When creating the LVM storage pools that block device is provided, the storage that All hosts are able to access that in cluster is selected, one Platform is able to access that on the main frame of the storage that performing LVM creates operation；
Described in carry during LVM storage pools, LVM described in carry is managed by the cluster management add-on module of carry node and stored The main frame in pond, wherein, cluster management add-on module is the module for all operations of management corosync clusters write.
Further, described device also includes：
When issue operation is deleted to the wound of the volume of storage pool when, the operation is taken over by the cluster management add-on module write, The operation is dealt on master nodes by corosync, master nodes perform the operation, are returned after having performed The operating result.
Further, described device also includes：
Corosync provides looped network redundancy agreement RRP patterns, and corosync clusters are formed by redundant network.
Further, described device also includes：
Corosync provides redundancy message pass through mechanism, and each corosync clustered node receives message afterwards by wide Broadcast and send other all nodes to, message is issued by each cluster member by corosync loop network.
The embodiment of the present invention passes through cluster block storage scheme, it is possible to increase the performance of cluster-based storage and the stability of cluster, Wherein, cluster block storage implementation, by redundant network and redundancy message pass through mechanism, data consistency and cluster are ensured Stability, by logical volume management, improve the IO performances of cluster-based storage.It can be seen that the embodiment of the present invention is by improving cluster-based storage Performance, optimize cluster-based storage performance.
Although disclosed herein embodiment as above, described content be only readily appreciate the present invention and use Embodiment, it is not limited to the present invention.Technical staff in any art of the present invention, taken off not departing from the present invention On the premise of the spirit and scope of dew, any modification and change, but the present invention can be carried out in the form and details of implementation Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.

Claims (10)

  1. A kind of 1. cluster block Realization of Storing, it is characterised in that including：
    Block device is provided to virtual machine by logical volume management LVM, so that the file system that the virtual machine creating oneself needs；
    Cluster management is carried out using corosync cluster management systems so that for the resource operation of LVM storage pools, by Main frame master that corosync clusters choose is performed.
  2. 2. cluster block Realization of Storing according to claim 1, it is characterised in that as described in the selection of corosync clusters Main frame master includes：
    When Corosync selects master nodes, the IO of physical hard disk time delay is chosen according to current hosts.
  3. 3. cluster block Realization of Storing according to claim 1, it is characterised in that also include：
    Logical volume LV is provided by LVM, and all I/O operations for LV are mapped on corresponding physical hard disk and carried out.
  4. 4. cluster block Realization of Storing according to claim 3, it is characterised in that also include：
    When every virtual machine carries out I/O operation, physical hard disk corresponding to oneself logical volume LV is only operated.
  5. 5. cluster block Realization of Storing according to claim 1, it is characterised in that the money for LVM storage pools Source operation includes：
    When creating the LVM storage pools that block device is provided, the storage that All hosts are able to access that in cluster is selected, in an energy Enough access and LVM establishment operations are performed on the main frame of the storage；
    Described in carry during LVM storage pools, LVM storage pools described in carry are managed by the cluster management add-on module of carry node Main frame, wherein, cluster management add-on module is the module for all operations of management corosync clusters write.
  6. 6. cluster block Realization of Storing according to claim 5, it is characterised in that also include：
    When issue operation is deleted to the wound of the volume of storage pool when, the operation is taken over by the cluster management add-on module write, passed through The operation is dealt on master nodes by corosync, and master nodes perform the operation, after having performed described in return Operating result.
  7. 7. cluster block Realization of Storing according to claim 1, it is characterised in that also include：
    Corosync provides looped network redundancy agreement RRP patterns, and corosync clusters are formed by redundant network.
  8. 8. cluster block Realization of Storing according to claim 7, it is characterised in that also include：
    Corosync provides redundancy message pass through mechanism, and each corosync clustered node is passed after receiving message by broadcasting Other all nodes are given, message is issued by each cluster member by corosync loop network.
  9. 9. a kind of cluster block stores realization device, it is characterised in that including：
    Module is provided, for providing block device to virtual machine by logical volume management LVM, so that the virtual machine creating oneself needs File system；
    Management module, for carrying out cluster management using corosync cluster management systems so that for the resource of LVM storage pools Operation, the main frame master that is chosen by corosync clusters are performed.
  10. 10. cluster block according to claim 9 stores realization device, it is characterised in that the management module is additionally operable to：
    When Corosync selects master nodes, the IO of physical hard disk time delay is chosen according to current hosts.
CN201710830214.5A 2017-09-15 2017-09-15 Cluster block storage implementation method and device Active CN107391236B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710830214.5A CN107391236B (en) 2017-09-15 2017-09-15 Cluster block storage implementation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710830214.5A CN107391236B (en) 2017-09-15 2017-09-15 Cluster block storage implementation method and device

Publications (2)

Publication Number Publication Date
CN107391236A true CN107391236A (en) 2017-11-24
CN107391236B CN107391236B (en) 2020-03-06

Family

ID=60351788

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710830214.5A Active CN107391236B (en) 2017-09-15 2017-09-15 Cluster block storage implementation method and device

Country Status (1)

Country Link
CN (1) CN107391236B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9047018B1 (en) * 2012-03-20 2015-06-02 Emc Corporation Method and system for zero-copy disk IO using sector unaligned buffers
CN105407087A (en) * 2015-10-28 2016-03-16 杭州数梦工场科技有限公司 Message sending method and device
CN106777394A (en) * 2017-02-28 2017-05-31 郑州云海信息技术有限公司 A kind of cluster file system
CN106919346A (en) * 2017-02-21 2017-07-04 无锡华云数据技术服务有限公司 A kind of shared Storage Virtualization implementation method based on CLVM

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9047018B1 (en) * 2012-03-20 2015-06-02 Emc Corporation Method and system for zero-copy disk IO using sector unaligned buffers
CN105407087A (en) * 2015-10-28 2016-03-16 杭州数梦工场科技有限公司 Message sending method and device
CN106919346A (en) * 2017-02-21 2017-07-04 无锡华云数据技术服务有限公司 A kind of shared Storage Virtualization implementation method based on CLVM
CN106777394A (en) * 2017-02-28 2017-05-31 郑州云海信息技术有限公司 A kind of cluster file system

Also Published As

Publication number Publication date
CN107391236B (en) 2020-03-06

Similar Documents

Publication Publication Date Title
CN103503414B (en) A kind of group system calculating storage and merge
US9645756B2 (en) Optimization of in-memory data grid placement
CN108228086A (en) The method and apparatus that RAID is rebuild
CN111565113B (en) Flexible Ethernet network topology abstraction method and system for SDN controller
US10608951B2 (en) Live resegmenting of partitions in distributed stream-processing platforms
CN105049293B (en) The method and device of monitoring
TW201140450A (en) Continuous optimization of archive management scheduling by use of integrated content-resource analytic model
CN109828868A (en) Date storage method, device, management equipment and dual-active data-storage system
CN107769938A (en) The system and method that a kind of Openstack platforms support Multi net voting region
CN108280080A (en) A kind of method of data synchronization, device and electronic equipment
CN108319618B (en) Data distribution control method, system and device of distributed storage system
CN109343929A (en) A kind of multi-screen interaction method and system based on the shared video memory of virtualization
CN108089912A (en) A kind of virtual machine surpasses emerging system construction method and device with container
CN103701633A (en) Setup and maintenance system of visual cluster application for distributed search SolrCloud
CN103329105A (en) Application recovery in file system
CN105095103A (en) Storage device management method and device used for cloud environment
CN106528265A (en) Virtual machine management method and system based on distributed SAN (Storage Area Network) storage architecture
CN102929769A (en) Virtual machine internal-data acquisition method based on agency service
CN110456984A (en) The method that the block device of a kind of pair of Ceph storage carries out continuous data protection
CN105391651A (en) Virtual optical network multilayer resource convergence method and system
CN105657057A (en) Calculation and storage fused cluster system
CN109218086A (en) A kind of switching network construction method and system
CN108846053A (en) Data copy management method, device, equipment, system and readable storage medium storing program for executing
CN112929206B (en) Method and device for configuring cloud physical machine in cloud network environment
EP3806389A1 (en) Virtual subnet constructing method and device, and storage medium

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
GR01 Patent grant
GR01 Patent grant