CN105162824A - Host multi-path disposition method in cloud storage system, and system - Google Patents
Host multi-path disposition method in cloud storage system, and system Download PDFInfo
- Publication number
- CN105162824A CN105162824A CN201510395218.6A CN201510395218A CN105162824A CN 105162824 A CN105162824 A CN 105162824A CN 201510395218 A CN201510395218 A CN 201510395218A CN 105162824 A CN105162824 A CN 105162824A
- Authority
- CN
- China
- Prior art keywords
- cloud
- multipath
- scsi
- memory node
- storage system
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0668—Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
-
- 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
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a host multi-path disposition method in cloud storage system. The host multi-path disposition method is applied to a multi-controller cloud storage system, the cloud storage system comprises a cloud storage client and a cloud storage service end. The method comprises steps that, multi-path disposition is carried out by the cloud storage client, and multi-path strategy is further set, SCSI initiation end disposition is carried out by the cloud storage client; SCSI target end disposition is carried out by each storage node of the cloud storage service end; a communication path of each storage node of the cloud storage client and the cloud storage service end is established. Through the method and the system, high reliability and high throughput of the cloud storage system can be realized.
Description
Technical field
The present invention relates to cloud technical field of memory, main frame multipath dispositions method and system in espespecially a kind of cloud storage system.
Background technology
Cloud storage provides stores service, and local data to be left in by network the on-line storage space that storage service provider (SSP) provides by stores service.Need the user of stores service no longer to need to set up the data center of oneself, only need apply for stores service to SSP, thus avoid the repeated construction of storage platform, save expensive hardware/software infrastructure investment.
In existing cloud storage system; very high requirement is had for reliability and throughput; and in the cloud storage system with a large amount of memory node; it is situation about often there will be that memory node breaks down; after failure, ensure that the continuity that cloud storage client host is read and write memory system data is vital.Store the application scenarios of client host at a large amount of cloud, have strict demand to the total bandwidth that whole cloud storage system can provide, the bandwidth availability ratio fully promoting each node in cloud storage system is also extremely important.
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides main frame multipath dispositions method and system in a kind of cloud storage system, high reliability and the high-throughput of cloud storage system can be realized.
In order to reach the object of the invention, the invention provides main frame multipath dispositions method in a kind of cloud storage system, be applied to multi-controller cloud storage system, this cloud storage system comprises cloud and stores client and cloud stores service end, the method comprises: cloud stores client deployment multipath, and arranges multipath strategy; Cloud stores client deployment SCSI originating end; Each memory node of cloud stores service end disposes scsi target end respectively; By SCSI originating end and scsi target end, set up the communication path that cloud stores each memory node of client and cloud stores service end.
Further, described cloud stores client deployment multipath, and arranges multipath strategy, is specially: cloud stores client host and disposes multipath by integrated Multipath I/O, and to arrange multipath strategy be failover policies or load balancing.
Further, described cloud stores client deployment SCSI originating end, is specially: cloud stores client host and disposes SCSI originating end, and in SCSI originating end, add the IP of each memory node of cloud stores service end.
Further, each memory node of described cloud stores service end disposes scsi target end respectively, be specially: each memory node of cloud stores service end creates scsi target end respectively, the storage resources of configuration scsi target end, and configure scsi target end and specify accessed cloud to store client, and configuration data is kept in configuration file.
Further, the configuration file of each memory node of described cloud stores service end is identical, and passes through the share directory of cluster file system maintain configuration file; If the configuration that there is memory node changes, the memory node do not changed again importing configuration files keeps the synchronous of configuration.
Present invention also offers a kind of cloud storage system, described cloud storage system comprises cloud and stores client and cloud stores service end, and described cloud stores client deployment multipath, and arranges multipath strategy; Dispose SCSI originating end; Each memory node of described cloud stores service end disposes scsi target end respectively, by SCSI originating end and scsi target end, sets up the communication path that cloud stores each memory node of client and cloud stores service end.
Compared with prior art, the present invention is in the cloud storage system with a large amount of memory node, after memory node breaks down, ensure the continuity that cloud storage client host is read and write memory system data, store the application scenarios of client host at a large amount of cloud, fully promote the bandwidth availability ratio of each node in cloud storage system; By the network topology structure proposed, all memory nodes and cloud are stored client host connect, the main frame multipath of client host deploy is stored by cloud, realize the object of cloud storage system high reliability and high-throughput, and the present invention has very strong versatility, can not impact existing cloud storage system framework.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from specification, or understand by implementing the present invention.Object of the present invention and other advantages realize by structure specifically noted in specification, claims and accompanying drawing and obtain.
Accompanying drawing explanation
Accompanying drawing is used to provide the further understanding to technical solution of the present invention, and forms a part for specification, is used from and explains technical scheme of the present invention, do not form the restriction to technical solution of the present invention with the embodiment one of the application.
Fig. 1 is the structural representation of network topology of the present invention.
Fig. 2 is the schematic flow sheet of main frame multipath dispositions method in cloud storage system in a kind of embodiment of the present invention.
Fig. 3 is the configuration diagram of cloud storage system in a kind of embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, hereinafter will be described in detail to embodiments of the invention by reference to the accompanying drawings.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combination in any mutually.
Can perform in the computer system of such as one group of computer executable instructions in the step shown in the flow chart of accompanying drawing.Further, although show logical order in flow charts, in some cases, can be different from the step shown or described by order execution herein.
Fig. 1 is the structural representation of network topology of the present invention.Connected mode as shown in the figure, cloud is stored client and is connected with the memory node in cloud storage system by router, and wherein, switching network uses two-router, i.e. router one and router two, thus single-router fault can be avoided to cause service disconnection; Cloud storage client host configure double netcard and binds, avoiding the service disconnection that net card failure causes; In addition, cloud stores client host and each memory node, i.e. memory node 1 ~ 4, has an access path, both can avoid the service disconnection that node failure causes, also can make full use of the bandwidth of each node to promote throughput.
Fig. 2 is the schematic flow sheet of main frame multipath dispositions method in cloud storage system in a kind of embodiment of the present invention.Based on the network topology structure of Fig. 1, method of the present invention comprises:
Step 201, cloud stores client deployment multipath, and arranges multipath strategy.
Existing multipath deployment scheme mainly for dual controller disk array centralised storage system, in the present invention for multi-controller (multinode) cloud storage system.
In this step, client is stored for WindowServer2008 cloud, cloud stores client host and disposes multipath by integrated Multipath I/O (MPIO), MPIO architecture is by being established to multiple session connection small computer system interface (SCSI of storage array, SmallComputerSystemInterface), optical-fibre channel and storage area network (SAN, StorageAreaNetwork) connected in series.
Multipath strategy comprises failover policies and load balancing, wherein, failover policies, for arranging main path and selected path, only has a main path usually as active path access services device, automatically switch to alternative path when main path breaks down, improve reliability with this; Load balancing is all paths is all active path, and cloud stores client can carry out improving performance by all path access server ends.
Step 202, cloud stores client deployment SCSI originating end (SCSIinitiator).
SCSI is a SCSI instruction set can run on the upper strata of IP agreement for hardware device, and this instruction set can be implemented in IP network and runs SCSI agreement, can carry out Route Selection on such as high speed gigabit Ethernet.SCSI technology is a kind of new storing technology, and this technology is by existing scsi interface and Ethernet combine with technique, makes server can intercourse data with using the stocking system of IP network.
In this step, cloud stores client host to be needed to dispose SCSI originating end (SCSIinitiator), by adding the IP of all memory nodes in SCSIinitiator, realizing cloud and storing client host and each memory node and have a communication path.
Step 203, each memory node of cloud stores service end disposes scsi target end (SCSITarget), by SCSI originating end and scsi target end, sets up the communication path that cloud stores each memory node of client and cloud stores service end.
In this step, each memory node of cloud stores service end needs to dispose SCSITarget, connects and processes cloud and store for storing client with cloud the SCSI request that client sends over.Each memory node of cloud stores service end has identical SCSITarget configuration file, and the unified cluster file system that adopts of SCSITarget configuration file is safeguarded.
For IPSAN, SCSITarget needs to provide iSCSITarget to support iSCSI agreement simultaneously, iSCSITarget be used for manage cloud store client to server connection and memory allocated resource stores client to cloud, concrete configuration comprises establishment iSCSITarget, to iSCSITarget memory allocated resource, specify the cloud can accessing it to store client etc. to iSCSITarget, all these configurations are all kept in the middle of configuration file.In order to ensure the consistency that all memory node iSCSITarget configure, all memory nodes are needed to have identical configuration file, Gluster cluster file system is adopted to safeguard a share directory, when the configuration of a memory node changes, other node again importing configuration files keeps the synchronous of configuration.
Fig. 3 is the configuration diagram of cloud storage system in a kind of embodiment of the present invention.Present invention also offers a kind of cloud storage system, this cloud storage system comprises cloud and stores client and cloud stores service end, wherein,
Cloud stores client deployment multipath, and arranges multipath strategy; Dispose SCSI originating end;
Each memory node of cloud stores service end disposes scsi target end respectively, by SCSI originating end and scsi target end, sets up the communication path that cloud stores each memory node of client and cloud stores service end.
Further, cloud stores client deployment multipath, and arranges multipath strategy, is specially: cloud stores client host and disposes multipath by integrated Multipath I/O, and to arrange multipath strategy be failover policies or load balancing.
Further, cloud stores client deployment SCSI originating end, is specially: cloud stores client host and disposes SCSI originating end, and in SCSI originating end, add the IP of each memory node of cloud stores service end.
Further, each memory node of cloud stores service end disposes scsi target end respectively, be specially: each memory node of cloud stores service end creates scsi target end respectively, the storage resources of configuration scsi target end, and configure scsi target end and specify accessed cloud to store client, and configuration data is kept in configuration file.
Further, the configuration file of each memory node of cloud stores service end is identical, and passes through the share directory of cluster file system maintain configuration file; If the configuration that there is memory node changes, the memory node do not changed again importing configuration files keeps the synchronous of configuration.
The present invention is in the cloud storage system with a large amount of memory node, after memory node breaks down, ensure the continuity that cloud storage client host is read and write memory system data, store the application scenarios of client host at a large amount of cloud, fully promote the bandwidth availability ratio of each node in cloud storage system; By the network topology structure proposed, all memory nodes and cloud are stored client host connect, the main frame multipath of client host deploy is stored by cloud, realize the object of cloud storage system high reliability and high-throughput, and the present invention has very strong versatility, can not impact existing cloud storage system framework.
Although the execution mode disclosed by the present invention is as above, the execution mode that described content only adopts for ease of understanding the present invention, and be not used to limit the present invention.Those of skill in the art belonging to any the present invention; under the prerequisite not departing from the spirit and scope disclosed by the present invention; any amendment and change can be carried out in the form implemented and details; but scope of patent protection of the present invention, the scope that still must define with appending claims is as the criterion.
Claims (10)
1. a main frame multipath dispositions method in cloud storage system, is characterized in that, be applied to multi-controller cloud storage system, and described cloud storage system comprises cloud and stores client and cloud stores service end, and the method comprises:
Cloud stores client deployment multipath, and arranges multipath strategy;
Cloud stores client deployment SCSI originating end;
Each memory node of cloud stores service end disposes scsi target end respectively;
By SCSI originating end and scsi target end, set up the communication path that cloud stores each memory node of client and cloud stores service end.
2. main frame multipath dispositions method in cloud storage system according to claim 1, is characterized in that, described cloud stores client deployment multipath, and arranges multipath strategy, is specially:
Cloud stores client host and disposes multipath by integrated Multipath I/O, and to arrange multipath strategy be failover policies or load balancing.
3. main frame multipath dispositions method in cloud storage system according to claim 1 and 2, is characterized in that, described cloud stores client deployment SCSI originating end, is specially:
Cloud stores client host and disposes SCSI originating end, and in SCSI originating end, add the IP of each memory node of cloud stores service end.
4. main frame multipath dispositions method in cloud storage system according to claim 3, is characterized in that, each memory node of described cloud stores service end disposes scsi target end respectively, is specially:
Each memory node of cloud stores service end creates scsi target end respectively, the storage resources of configuration scsi target end, and configures scsi target end and specify accessed cloud to store client, and is kept in configuration file by configuration data.
5. main frame multipath dispositions method in cloud storage system according to claim 4, is characterized in that, the configuration file of each memory node of described cloud stores service end is identical, and passes through the share directory of cluster file system maintain configuration file;
If the configuration that there is memory node changes, the memory node do not changed again importing configuration files keeps the synchronous of configuration.
6. a cloud storage system, described cloud storage system comprises cloud and stores client and cloud stores service end, it is characterized in that,
Described cloud stores client deployment multipath, and arranges multipath strategy; Dispose SCSI originating end;
Each memory node of described cloud stores service end disposes scsi target end respectively, by SCSI originating end and scsi target end, sets up the communication path that cloud stores each memory node of client and cloud stores service end.
7. cloud storage system according to claim 6, is characterized in that, described cloud stores client deployment multipath, and arranges multipath strategy, is specially:
Cloud stores client host and disposes multipath by integrated Multipath I/O, and to arrange multipath strategy be failover policies or load balancing.
8. the cloud storage system according to claim 6 or 7, is characterized in that, described cloud stores client deployment SCSI originating end, is specially:
Cloud stores client host and disposes SCSI originating end, and in SCSI originating end, add the IP of each memory node of cloud stores service end.
9. cloud storage system according to claim 8, is characterized in that, each memory node of described cloud stores service end disposes scsi target end respectively, is specially:
Each memory node of cloud stores service end creates scsi target end respectively, the storage resources of configuration scsi target end, and configures scsi target end and specify accessed cloud to store client, and is kept in configuration file by configuration data.
10. cloud storage system according to claim 9, is characterized in that, the configuration file of each memory node of described cloud stores service end is identical, and passes through the share directory of cluster file system maintain configuration file; If the configuration that there is memory node changes, the memory node do not changed again importing configuration files keeps the synchronous of configuration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510395218.6A CN105162824A (en) | 2015-07-07 | 2015-07-07 | Host multi-path disposition method in cloud storage system, and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510395218.6A CN105162824A (en) | 2015-07-07 | 2015-07-07 | Host multi-path disposition method in cloud storage system, and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105162824A true CN105162824A (en) | 2015-12-16 |
Family
ID=54803578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510395218.6A Pending CN105162824A (en) | 2015-07-07 | 2015-07-07 | Host multi-path disposition method in cloud storage system, and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105162824A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354436A (en) * | 2016-09-20 | 2017-01-25 | 郑州云海信息技术有限公司 | Storage system based on distributed IPSAN |
| CN107707665A (en) * | 2017-10-19 | 2018-02-16 | 郑州云海信息技术有限公司 | A kind of network storage method, device, system and computer-readable recording medium |
| CN110098960A (en) * | 2019-04-24 | 2019-08-06 | 苏州浪潮智能科技有限公司 | A kind of distributed block storage system exempts from close automatic configuration method and device |
| CN110825710A (en) * | 2019-11-22 | 2020-02-21 | 北京浪潮数据技术有限公司 | Configuration synchronization method, device, system and medium for cluster file system |
| CN111212123A (en) * | 2019-12-26 | 2020-05-29 | 天津中科曙光存储科技有限公司 | ZooKeeper-based Lunmap management method |
| CN112269533A (en) * | 2020-10-16 | 2021-01-26 | 苏州浪潮智能科技有限公司 | Command processing method, system, equipment and computer readable storage medium |
| WO2022007418A1 (en) * | 2020-07-08 | 2022-01-13 | 苏州浪潮智能科技有限公司 | Cloud platform block device abnormity auditing method, apparatus and device and storage medium |
| CN114115750A (en) * | 2022-01-24 | 2022-03-01 | 苏州浪潮智能科技有限公司 | Caching method and device applied to full flash memory storage |
| US11294782B1 (en) * | 2021-03-22 | 2022-04-05 | EMC IP Holding Company LLC | Failover affinity rule modification based on node health information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050281262A1 (en) * | 2004-06-17 | 2005-12-22 | Zur Uri E | Method and system for supporting read operations for iSCSI and iSCSI chimney |
| EP1786151A2 (en) * | 2005-11-14 | 2007-05-16 | Broadcom Corporation | Network nodes cooperatively routing traffic flow amongst wired and wireless networks |
| CN101471830A (en) * | 2007-12-25 | 2009-07-01 | 英业达股份有限公司 | Method for accessing remote logic equipment through multiple routes in Linux system |
-
2015
- 2015-07-07 CN CN201510395218.6A patent/CN105162824A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050281262A1 (en) * | 2004-06-17 | 2005-12-22 | Zur Uri E | Method and system for supporting read operations for iSCSI and iSCSI chimney |
| EP1786151A2 (en) * | 2005-11-14 | 2007-05-16 | Broadcom Corporation | Network nodes cooperatively routing traffic flow amongst wired and wireless networks |
| CN101471830A (en) * | 2007-12-25 | 2009-07-01 | 英业达股份有限公司 | Method for accessing remote logic equipment through multiple routes in Linux system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106354436A (en) * | 2016-09-20 | 2017-01-25 | 郑州云海信息技术有限公司 | Storage system based on distributed IPSAN |
| CN107707665A (en) * | 2017-10-19 | 2018-02-16 | 郑州云海信息技术有限公司 | A kind of network storage method, device, system and computer-readable recording medium |
| CN110098960A (en) * | 2019-04-24 | 2019-08-06 | 苏州浪潮智能科技有限公司 | A kind of distributed block storage system exempts from close automatic configuration method and device |
| CN110098960B (en) * | 2019-04-24 | 2022-07-08 | 苏州浪潮智能科技有限公司 | Secret-free automatic configuration method and device for distributed block storage system |
| CN110825710A (en) * | 2019-11-22 | 2020-02-21 | 北京浪潮数据技术有限公司 | Configuration synchronization method, device, system and medium for cluster file system |
| CN111212123A (en) * | 2019-12-26 | 2020-05-29 | 天津中科曙光存储科技有限公司 | ZooKeeper-based Lunmap management method |
| WO2022007418A1 (en) * | 2020-07-08 | 2022-01-13 | 苏州浪潮智能科技有限公司 | Cloud platform block device abnormity auditing method, apparatus and device and storage medium |
| US11782609B2 (en) | 2020-07-08 | 2023-10-10 | Inspur Suzhou Intelligent Technology Co., Ltd. | Method and apparatus for auditing abnormality of block device in cloud platform, device, and storage medium |
| CN112269533A (en) * | 2020-10-16 | 2021-01-26 | 苏州浪潮智能科技有限公司 | Command processing method, system, equipment and computer readable storage medium |
| US11294782B1 (en) * | 2021-03-22 | 2022-04-05 | EMC IP Holding Company LLC | Failover affinity rule modification based on node health information |
| CN114115750A (en) * | 2022-01-24 | 2022-03-01 | 苏州浪潮智能科技有限公司 | Caching method and device applied to full flash memory storage |
| CN114115750B (en) * | 2022-01-24 | 2022-05-13 | 苏州浪潮智能科技有限公司 | Caching method and device applied to full flash memory storage |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105162824A (en) | Host multi-path disposition method in cloud storage system, and system | |
| US9906407B1 (en) | Methods and apparatus for scalable resilient networks | |
| JP7014729B2 (en) | How and equipment to expand a high availability server cluster | |
| CN105095317B (en) | Distributed data base service management system | |
| EP2901308B1 (en) | Load distribution in data networks | |
| US9722867B2 (en) | Resource management method, resource management system and resource manager | |
| JP5876137B2 (en) | Incremental high radix network scaling | |
| JP5844373B2 (en) | System and method for facilitating protection from runaway subnet manager instances in a middleware machine environment | |
| Wood et al. | CloudNet: A platform for optimized WAN migration of virtual machines | |
| US10942759B2 (en) | Seamless virtual standard switch to virtual distributed switch migration for hyper-converged infrastructure | |
| CN113572831B (en) | Communication method, computer equipment and medium between Kubernetes clusters | |
| JP2012084129A (en) | Systems and methods for multi-tenant system providing virtual data centers in cloud configuration | |
| CN104679608A (en) | Infrastructure visualization platform building method and mirror management structure of infrastructure visualization platform building method | |
| US11281374B2 (en) | Automated storage network reconfiguration for heterogeneous storage clusters | |
| JP2016530604A (en) | Managing computing sessions | |
| Kokkinos et al. | Survey: Live migration and disaster recovery over long-distance networks | |
| US20170097941A1 (en) | Highly available network filer super cluster | |
| US9286170B2 (en) | Preventing extreme coresidency hazards in cloud computing | |
| US9712455B1 (en) | Determining availability of networking resources prior to migration of a server or domain | |
| CN111431980B (en) | Distributed storage system and path switching method thereof | |
| CN105262640A (en) | System and method for improving reliability of cloud platform server, and disposition framework of system | |
| CN109639488A (en) | A kind of more outer nets shunt accelerated method and system | |
| CN107734037A (en) | A kind of NAS clusters and data access method | |
| CN106921576B (en) | Virtualization system-based data network and management network flow separation method and device | |
| CN112655185B (en) | Apparatus, method and storage medium for service allocation in a software defined network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151216 |
|
| RJ01 | Rejection of invention patent application after publication |