CN106302733A - A kind of distributed type assemblies merges implementation method and the device of NFS protocol - Google Patents
A kind of distributed type assemblies merges implementation method and the device of NFS protocol Download PDFInfo
- Publication number
- CN106302733A CN106302733A CN201610674991.0A CN201610674991A CN106302733A CN 106302733 A CN106302733 A CN 106302733A CN 201610674991 A CN201610674991 A CN 201610674991A CN 106302733 A CN106302733 A CN 106302733A
- Authority
- CN
- China
- Prior art keywords
- nfs
- client
- distributed type
- type assemblies
- implementation method
- 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
- H04L67/1097—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]
-
- 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
- H04L67/14—Session management
- H04L67/141—Setup of application sessions
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 kind of distributed type assemblies and merge implementation method and the device of NFS protocol, by receiving the enabled instruction of user's input;Call user's space data access interface API Access node object storage device data, by network delivery to storage cluster;Storage cluster loads NFS module, starts NFS service, monitors client connection request;When having listened to client connection request, the identity of client is identified, sets up with client after being identified by and be connected.Distributed type assemblies provided by the present invention merges implementation method and the device of NFS protocol, for merging multiple memory nodes in the distributed type assemblies of one, by horizontal extendible file system NFS module, realize NFS and share raising access efficiency, reduce I O access path, decrease performance consumption, thus improve the access efficiency of whole cluster.
Description
Technical field
The present invention relates to distributed type assemblies technical field, particularly relate to a kind of distributed type assemblies and merge the reality of NFS protocol
Existing method and device.
Background technology
Multiple memory nodes can be formed a whole by distributed cluster storage system, deposits with metadata and data are unified
The framework of storage, the transmission of user data only occurs between client and back end, it is ensured that the linear increasing of cluster overall performance
Long, system comprises monitoring service (Monitor, then write a Chinese character in simplified form Mon), Metadata Service (MDS), data, services (OSD:Object
Storage Device object storage device) and client, system external provides the POSIX interface data service of standard.
Monitoring service, Metadata Service and the data, services of system all use cluster mode, it is possible to be guaranteed in any node
When breaking down, do not affect host service, it is achieved that the High Availabitity of system.Under normal circumstances, three monitoring services are used, it is achieved
The functions such as the monitoring of system, log collection, system administration;Metadata cluster can use active and standby mould in the case of scale is less
Formula, larger or use cluster mode, linear expansion file cocurrent access ability time performance requirement is higher;System is supported
Data, services is the most extending transversely, and performance is with its linear increase.Design of hardware and software is accomplished without Single Point of Faliure, at arbitrary prison
Control service, data, services or applied host machine still can ensure in the case of breaking down that data access service is not interrupted.
The most commonly used access interface of distributed file system is Native protocol interface, i.e. realizes based on FUSE
POSIX compatibility interface.This interface is relative to NAS access interface, better performances, and has tradition application or Legacy System
The good suitability, application program need not make any amendment.NFS access protocal before, is the most all in FUSE interface basis
On realize corresponding function by increasing by one layer of NFS service, thus constitute the system configuration of cluster NFS.But owing to FUSE is
The file system interface of a kind of User space, needs repeatedly to carry out context swap (context at User space and kernel state
Switch), thus producing certain performance loss, especially for NAS accesses, performance loss is even more serious.
Summary of the invention
It is an object of the invention to provide a kind of distributed type assemblies and merge implementation method and the device of NFS protocol, existing to reduce
During having distributed type assemblies to merge the realization of NFS protocol, performance consumption is compared with problem big, that access efficiency is relatively low.
For solving above-mentioned technical problem, the present invention provides a kind of distributed type assemblies to merge the implementation method of NFS protocol, bag
Include:
Receive the enabled instruction of user's input;
Call user's space data access interface API Access node object storage device data, by network delivery to depositing
Accumulation;
Described storage cluster loads NFS module, starts NFS service, monitors client connection request;
When having listened to client connection request, the identity of described client is identified, is identified by rear and institute
State client and set up connection.
Alternatively, also included before described monitoring client connection request:
Described NFS module loading configuration file, reads config directory list and user right configuration information.
Alternatively, the described identity to described client is identified, and sets up with described client and be connected after being identified by
Including:
According to the configuration file described client of item identification;If described configuration file item judges the request being to allow, then know
Do not pass through.
Alternatively, also include after being connected with the foundation of described client:
Return connection response, so that described client is written and read operation.
Alternatively, also include after the described identity to described client is identified:
When identifying described client and there is no authority, generate warning information.
Alternatively, also include:
Subdirectory file in described config directory list is shown.
Alternatively, also include:
Receive the order of the amendment share directory of user's input, the share directory list in described configuration file is carried out more
Newly.
Alternatively, also include:
Receive the order of the inquiry share directory of user's input, show share directory list to described user.
Present invention also offers a kind of distributed type assemblies fusion NFS protocol realizes device, including:
Receiver module, for receiving the enabled instruction of user's input;
Calling module, is used for calling user's space data access interface API Access node object storage device data, passes through
Network delivery is to storage cluster;
Monitor module, load NFS module for described storage cluster, start NFS service, monitor client connection request;
Identification module, for when having listened to client connection request, is identified the identity of described client, knows
Do not set up by rear and described client and be connected.
Distributed type assemblies provided by the present invention merges implementation method and the device of NFS protocol, inputs by receiving user
Enabled instruction;Call user's space data access interface API Access node object storage device data, by network delivery extremely
Storage cluster;Storage cluster loads NFS module, starts NFS service, monitors client connection request;When having listened to client
During connection request, the identity of client is identified, sets up with client after being identified by and be connected.Provided by the present invention point
Cloth cluster merges implementation method and the device of NFS protocol, for the multiple memory nodes of fusion in the distributed type assemblies of one, logical
Cross horizontal extendible file system NFS module, it is achieved NFS shares and improves access efficiency, reduces I O access path, decreasing property
Can consume, thus improve the access efficiency of whole cluster.
Accompanying drawing explanation
For the clearer explanation embodiment of the present invention or the technical scheme of prior art, below will be to embodiment or existing
In technology description, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to root
Other accompanying drawing is obtained according to these accompanying drawings.
Fig. 1 is a kind of detailed description of the invention that distributed type assemblies provided by the present invention merges the implementation method of NFS protocol
Flow chart;
Fig. 2 is original topology schematic diagram in prior art;
Fig. 3 is to increase topology schematic diagram after API in embodiment provided by the present invention;
Fig. 4 is NFS Booting sequence figure in embodiment provided by the present invention;
Fig. 5 is that in embodiment provided by the present invention, configuration file loads flow chart;
Fig. 6 is read operation flow chart in embodiment provided by the present invention;
Fig. 7 is share directory operating process in embodiment provided by the present invention;
Fig. 8 merges the structured flowchart realizing device of NFS protocol for the distributed type assemblies that the embodiment of the present invention provides.
Detailed description of the invention
In order to make those skilled in the art be more fully understood that the present invention program, below in conjunction with the accompanying drawings and detailed description of the invention
The present invention is described in further detail.Obviously, described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, broadly falls into the scope of protection of the invention.
Distributed type assemblies provided by the present invention merges the flow process of a kind of detailed description of the invention of the implementation method of NFS protocol
Figure is as it is shown in figure 1, the method includes:
Step S101: receive the enabled instruction of user's input;
Step S102: call user's space data access interface API Access node object storage device data, pass through network
It is transferred to storage cluster;
Step S103: described storage cluster loads NFS module, starts NFS service, monitors client connection request;
Step S104: when having listened to client connection request, is identified the identity of described client, identifies logical
Later set up with described client and be connected.
Distributed type assemblies provided by the present invention merges the implementation method of NFS protocol, by receiving the startup of user's input
Instruction;Call user's space data access interface API Access node object storage device data, by network delivery to storing collection
Group;Storage cluster loads NFS module, starts NFS service, monitors client connection request;Please when having listened to client connection
When asking, the identity of client is identified, sets up with client after being identified by and be connected.Distributed collection provided by the present invention
Group merges the implementation method of NFS protocol, for the multiple memory nodes of fusion in the distributed type assemblies of one, by the most expansible
File system NFS module, it is achieved NFS share improve access efficiency, reduce I O access path, decrease performance consumption, thus
Improve the access efficiency of whole cluster.
On the basis of above-described embodiment, distributed type assemblies provided by the present invention merges in the implementation method of NFS protocol,
Can also include before described monitoring client connection request:
Described NFS module loading configuration file, reads config directory list and user right configuration information.
Further, the identity of described client is identified, is connected with the foundation of described client after being identified by
Process can particularly as follows:
According to the configuration file described client of item identification;If described configuration file item judges the request being to allow, then know
Do not pass through.
On the basis of any of the above-described embodiment, distributed type assemblies provided by the present invention merges the realization side of NFS protocol
In method, can also include after being connected with the foundation of described client:
Return connection response, so that described client is written and read operation.
Preferably, it is identified can further include afterwards in the described identity to described client:
When identifying described client and there is no authority, generate warning information.
Additionally, embodiment provided by the present invention can also include:
Subdirectory file in described config directory list is shown.
Distributed type assemblies merges the implementation method of NFS protocol and can also include: modifies share directory and inquires about
Process, be specifically as follows:
Receive the order of the amendment share directory of user's input, the share directory list in described configuration file is carried out more
Newly;
Receive the order of the inquiry share directory of user's input, show share directory list to described user.
Open up after original topology schematic diagram and Fig. 3 embodiment provided by the present invention in Fig. 2 prior art increases API
Flutterring shown in schematic diagram, the embodiment of the present application is called user's space data access interface api function storehouse by design and is got around FUSE extension
Loading point directly accesses osd.User directly can access osd data at application program by calling this API.It reduces FUSE
With the I/O access path of kernel VFS layer, accessing node osd by it, performance and latency all can be increased dramatically.This
Function library defines and achieves one group of POSIX compatibility API, with the API one_to_one corresponding in FUSE interface.
Refer to NFS Booting sequence figure in Fig. 4 embodiment provided by the present invention, Fig. 5 configuration file loads flow chart, figure
6 read operation flow charts and Fig. 7 share directory operating process, the process that realizes the embodiment of the present invention below is carried out the most in detail
Thin description.
System manager by application program assign startup order, Background scheduling API by network delivery to storage cluster,
Group system loads NFS module, starts NFS service, now NFS meeting loading configuration file, reads config directory list and user
Authority, just can monitor client request, the most externally provide NFS service;When there being client connection request, store system meeting
According to configuration file item identification client, if the request allowed, just set up with client and be connected, return connection response;This
Time client just can be normally carried out read-write operation.Background scheduling connection procedure is transparent to front end, so user may sense
Know there is the biggest difference less than with non-fused NFS.
Application program calls the process of API, can be divided into following three step:
(1) icfs context initialization
Icfs=icfs_new (" volname ");
icfs_set_volfile_server(icfs,transport,server,port);
icfs_init(icfs)
(2) libicfsapi interface interchange
icfspreadv_async(),icfs_writev_async()
icfs_open(),icfs_creat(),icfs_close()
icfs_truncate(),icfs_fstat()
icfs_fsync_async()
(3) icfs Environment release
icfs_fini()
The distributed type assemblies provided the embodiment of the present invention below merges the device that realizes of NFS protocol and is introduced, hereafter
The distributed type assemblies described merges the realization realizing device and above-described distributed type assemblies fusion NFS protocol of NFS protocol
Method can be mutually to should refer to.
Fig. 8 merges the structured flowchart realizing device of NFS protocol, reference for the distributed type assemblies that the embodiment of the present invention provides
Fig. 8 distributed type assemblies merges the device that realizes of NFS protocol and may include that
Receiver module 100, for receiving the enabled instruction of user's input;
Calling module 200, is used for calling user's space data access interface API Access node object storage device data,
By network delivery to storage cluster;
Monitoring module 300, load NFS module for described storage cluster, start NFS service, monitoring client connects please
Ask;
Identification module 400, for when having listened to client connection request, knows the identity of described client
, set up with described client after not being identified by and be connected
What distributed type assemblies provided by the present invention merged NFS protocol realizes device, decreases User space and kernel state
Alternately, the access path of NFS is shortened;Invocation step is simple simultaneously, easy left-hand seat;Improving system access efficiency, performance carries
High.
In this specification, each embodiment uses the mode gone forward one by one to describe, and what each embodiment stressed is and other
The difference of embodiment, between each embodiment, same or similar part sees mutually.For filling disclosed in embodiment
For putting, owing to it corresponds to the method disclosed in Example, so describe is fairly simple, relevant part sees method part
Illustrate.
Professional further appreciates that, in conjunction with the unit of each example that the embodiments described herein describes
And algorithm steps, it is possible to electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate hardware and
The interchangeability of software, the most generally describes composition and the step of each example according to function.These
Function performs with hardware or software mode actually, depends on application-specific and the design constraint of technical scheme.Specialty
Technical staff specifically should can be used for using different methods to realize described function to each, but this realization should not
Think beyond the scope of this invention.
The method described in conjunction with the embodiments described herein or the step of algorithm can direct hardware, processor be held
The software module of row, or the combination of the two implements.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, depositor, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Implementation method and device that distributed type assemblies provided by the present invention merges NFS protocol above have been carried out in detail
Introduce.Principle and the embodiment of the present invention are set forth by specific case used herein, the explanation of above example
It is only intended to help to understand method and the core concept thereof of the present invention.It should be pointed out that, the ordinary skill people for the art
For Yuan, under the premise without departing from the principles of the invention, it is also possible to the present invention is carried out some improvement and modification, these improve and
Modify in the protection domain also falling into the claims in the present invention.
Claims (9)
1. the implementation method of a distributed type assemblies fusion NFS protocol, it is characterised in that including:
Receive the enabled instruction of user's input;
Call user's space data access interface API Access node object storage device data, by network delivery to storing collection
Group;
Described storage cluster loads NFS module, starts NFS service, monitors client connection request;
When having listened to client connection request, the identity of described client is identified, with described visitor after being identified by
Family end is set up and is connected.
2. distributed type assemblies as claimed in claim 1 merges the implementation method of NFS protocol, it is characterised in that in described monitoring
Also include before client connection request:
Described NFS module loading configuration file, reads config directory list and user right configuration information.
3. distributed type assemblies as claimed in claim 2 merges the implementation method of NFS protocol, it is characterised in that described to described
The identity of client is identified, and sets up to be connected with described client include after being identified by:
According to the configuration file described client of item identification;If described configuration file item judges the request being to allow, then identify logical
Cross.
4. the distributed type assemblies as described in any one of claims 1 to 3 merges the implementation method of NFS protocol, it is characterised in that
Set up with described client and also include after being connected:
Return connection response, so that described client is written and read operation.
5. distributed type assemblies as claimed in claim 4 merges the implementation method of NFS protocol, it is characterised in that described to institute
State after the identity of client is identified and also include:
When identifying described client and there is no authority, generate warning information.
6. distributed type assemblies as claimed in claim 2 merges the implementation method of NFS protocol, it is characterised in that also include:
Subdirectory file in described config directory list is shown.
7. distributed type assemblies as claimed in claim 6 merges the implementation method of NFS protocol, it is characterised in that also include:
Receive the order of the amendment share directory of user's input, the share directory list in described configuration file is updated.
8. distributed type assemblies as claimed in claim 7 merges the implementation method of NFS protocol, it is characterised in that also include:
Receive the order of the inquiry share directory of user's input, show share directory list to described user.
9. what a distributed type assemblies merged NFS protocol realizes device, it is characterised in that including:
Receiver module, for receiving the enabled instruction of user's input;
Calling module, is used for calling user's space data access interface API Access node object storage device data, passes through network
It is transferred to storage cluster;
Monitor module, load NFS module for described storage cluster, start NFS service, monitor client connection request;
Identification module, for when having listened to client connection request, is identified the identity of described client, identifies logical
Later set up with described client and be connected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610674991.0A CN106302733A (en) | 2016-08-16 | 2016-08-16 | A kind of distributed type assemblies merges implementation method and the device of NFS protocol |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610674991.0A CN106302733A (en) | 2016-08-16 | 2016-08-16 | A kind of distributed type assemblies merges implementation method and the device of NFS protocol |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106302733A true CN106302733A (en) | 2017-01-04 |
Family
ID=57679836
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610674991.0A Pending CN106302733A (en) | 2016-08-16 | 2016-08-16 | A kind of distributed type assemblies merges implementation method and the device of NFS protocol |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106302733A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111475469A (en) * | 2020-03-19 | 2020-07-31 | 中山大学 | Virtual file system-based small file storage optimization system in KUBERNETES user mode application |
CN111881103A (en) * | 2020-06-21 | 2020-11-03 | 苏州浪潮智能科技有限公司 | LDAP domain user ACL permission control method and device based on NFS sharing |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102255866A (en) * | 2010-05-17 | 2011-11-23 | 腾讯科技(深圳)有限公司 | Method and device for downloading data |
CN103986702A (en) * | 2014-05-12 | 2014-08-13 | 浪潮电子信息产业股份有限公司 | User authentication implementation method for distributed cluster storage system |
CN104301442A (en) * | 2014-11-17 | 2015-01-21 | 浪潮电子信息产业股份有限公司 | Method for achieving client of access object storage cluster based on fuse |
CN105302497A (en) * | 2015-11-24 | 2016-02-03 | 浪潮(北京)电子信息产业有限公司 | Cache management method and cache management system |
CN105338118A (en) * | 2015-11-30 | 2016-02-17 | 上海斐讯数据通信技术有限公司 | Distributed storage system |
-
2016
- 2016-08-16 CN CN201610674991.0A patent/CN106302733A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102255866A (en) * | 2010-05-17 | 2011-11-23 | 腾讯科技(深圳)有限公司 | Method and device for downloading data |
CN103986702A (en) * | 2014-05-12 | 2014-08-13 | 浪潮电子信息产业股份有限公司 | User authentication implementation method for distributed cluster storage system |
CN104301442A (en) * | 2014-11-17 | 2015-01-21 | 浪潮电子信息产业股份有限公司 | Method for achieving client of access object storage cluster based on fuse |
CN105302497A (en) * | 2015-11-24 | 2016-02-03 | 浪潮(北京)电子信息产业有限公司 | Cache management method and cache management system |
CN105338118A (en) * | 2015-11-30 | 2016-02-17 | 上海斐讯数据通信技术有限公司 | Distributed storage system |
Non-Patent Citations (3)
Title |
---|
DAOWOO: "Ceph代码分析-OSD篇", 《CSDN博客》 * |
NANY01: "glusterfs 源码框架学习归纳总结", 《CSDN博客》 * |
刘爱贵: "Gluster libgfapi接口和应用实例", 《CSDN博客》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111475469A (en) * | 2020-03-19 | 2020-07-31 | 中山大学 | Virtual file system-based small file storage optimization system in KUBERNETES user mode application |
CN111475469B (en) * | 2020-03-19 | 2021-12-14 | 中山大学 | Virtual file system-based small file storage optimization system in KUBERNETES user mode application |
CN111881103A (en) * | 2020-06-21 | 2020-11-03 | 苏州浪潮智能科技有限公司 | LDAP domain user ACL permission control method and device based on NFS sharing |
CN111881103B (en) * | 2020-06-21 | 2022-07-19 | 苏州浪潮智能科技有限公司 | LDAP domain user ACL authority control method and device based on NFS sharing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103237046B (en) | Support distributed file system and the implementation method of mixed cloud storage application | |
US9535739B2 (en) | Virtual machine storage | |
CN104111804B (en) | A kind of distributed file system | |
CN101997918B (en) | Method for allocating mass storage resources according to needs in heterogeneous SAN (Storage Area Network) environment | |
CN110377436A (en) | Data storage access method, equipment and the device of persistence memory | |
EP2369494A1 (en) | Web application based database system and data management method therof | |
CN107046563A (en) | A kind of implementation method, system and the cloud platform of distribution type high efficient cloud disk | |
US20090063556A1 (en) | Root node for carrying out file level virtualization and migration | |
CN103561101A (en) | Network file system | |
CN106446159B (en) | A kind of method of storage file, the first virtual machine and name node | |
US10579597B1 (en) | Data-tiering service with multiple cold tier quality of service levels | |
CN106648462B (en) | Date storage method and device | |
CN103617007B (en) | Multistage intelligent Realization of Storing and system | |
CN108089912A (en) | A kind of virtual machine surpasses emerging system construction method and device with container | |
WO2021008425A1 (en) | System startup method and related device | |
CN105677251A (en) | Storage system based on Redis cluster | |
US10152493B1 (en) | Dynamic ephemeral point-in-time snapshots for consistent reads to HDFS clients | |
CN103067488A (en) | Implement method of unified storage | |
CN109783018A (en) | A kind of method and device of data storage | |
US20200401329A1 (en) | Opportunistic storage service | |
CN113946291A (en) | Data access method, device, storage node and readable storage medium | |
CN106293522A (en) | A kind of storage performance optimization method based on TGT and device | |
CN108073723A (en) | A kind of file in distributed type assemblies storage is from compressing method and equipment | |
CN110457263A (en) | A kind of date storage method and device | |
CN115774703A (en) | Information processing method and device |
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: 20170104 |
|
RJ01 | Rejection of invention patent application after publication |