CN102546780B - Operation method for file distributed storage based on thin client - Google Patents
Operation method for file distributed storage based on thin client Download PDFInfo
- Publication number
- CN102546780B CN102546780B CN201110448040.9A CN201110448040A CN102546780B CN 102546780 B CN102546780 B CN 102546780B CN 201110448040 A CN201110448040 A CN 201110448040A CN 102546780 B CN102546780 B CN 102546780B
- Authority
- CN
- China
- Prior art keywords
- file
- client computer
- storage
- server
- client
- 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.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an operation method for file distributed storage based on thin client, which belongs to the technical field of distributed storage. A system for implementing the method includes a thin client and so on. The operation method comprises the steps of constructing a LAMP (Linux, Apache, MySQL and PHP) architecture on a MFS (MooseFS) client; deploying source files of a web disk below Apache of the architecture; setting a file folder on the MFS client to serve as the store directory of files uploaded by a subscriber, and setting the store directory as a mount directory of the client; and the client executing distributed read-write operation based on the directory to achieve distributed storage of the files uploaded by the subscriber. The subscriber can view the Web page of the web disk to execute file uploading and downloading operation by accessing the web disk below Apache through the internet. The method provided by the invention changes the conventional network storage and local storage modes, breaks the performance bottleneck of a single server for concentrated storage, and provides a novel storage mode by combining network storage with distributed storage, thereby greatly improving the storage performance.
Description
Technical field
The operation method that the present invention relates to a kind of file distribution formula storage based on thin-client, belongs to technical field of distributed memory.
Background technology
Along with the application and development of cloud computing, will serve in a large number with resource and be placed on remote server cluster, user only need become a kind of epoch trend from the pattern of terminal or the needed resource of PC access.And for this pattern, if adopt expensive, to configure high-end and complicated operation PC, will cause redundancy and the waste of local resource.So the novel information pattern based on " thin-client+network+cloud computing server " is arisen at the historic moment.Thin-client be a this locality without hard disk, the client of browser is only housed, be furnished with the most simply input (keyboard, mouse) and output equipment (display) and complete and the function of network service.In view of thin-client does not have memory space in this locality, so how user's privately owned file is carried out to effective store and management and become a key issue that must solve.The present invention completes the safe and effective storage to user file by network disk and distributed memory system, has broken through traditional file memory module.
Traditional file storage is divided into local storage and the network storage.Wherein, local storage is that file is stored among the hard disk of computer, and the size of hard disk is had high requirements.And the network storage be by file data centralized stores on a server, the performance of storage server becomes the bottleneck of systematic function, is also faced with the problem of reliability and fail safe.And current network storage disk, if 115 net dishes, 126 net dishes, association's net dish etc. are all to provide service for PC, toward contact, need some technical support of operating system, exist that transmission speed is slow, poor stability, operation costs are high, recovery capability is low problem.Although for improving the server bottleneck of centralized stores, there are many load balance scheduling algorithms to propose, but remain based on centralized stores, problem is not solved well, if the patent No. is 200710152665, the patent that name is called < < storage subsystem, master computer, storage system, load-balancing method and program > > just belongs to these row.
Novel distributed memory system is that a large amount of dissimilar memory devices are gathered to collaborative work, and data are disperseed to be stored on the equipment of many platform independent, forms the data-storage system of a safety, and access interface is externally provided.It adopts extendible system configuration, utilizes many storage servers to share storage load, by management server, locates storage information, has greatly improved reliability, availability, extensibility and the storage efficiency of storage system.In the situation that data access amount and file memory space are all very huge, distributed memory system is undoubtedly a kind of efficient highly reliable storage mode.Traditional memory module can not meet user's demand, and distributed storage will become the memory module of main flow.
Summary of the invention
For the deficiency of traditional file memory module and the restriction of thin-client itself, the present invention proposes a kind of operation method of the file distribution formula storage based on thin-client, being intended to, by traditional network storage and the organic set of distributed storage, provides a kind of effective document memory module based on thin-client.
Technical scheme of the present invention is as follows:
A kind of operation method of the file distribution formula storage based on thin-client, by following system, realized, this system comprises thin-client, network disk and MooseFS (being called for short MFS), wherein thin-client is the client based on built-in Linux operating system, and it only provides input-output equipment and Web browser, network disk is the network file storage application system based on Web, MFS is a kind of distributed file system, its file system structure comprises management server (master), metadata log server (metalogger), data storage server (chunkservers) and client computer (client), thin-client, running between network disk and MFS three is: by many physical servers, form an extendible server cluster, on every physical server, fictionalize many stylobates in the virtual machine of (SuSE) Linux OS, on the virtual machine of server cluster, build MFS, in the client computer of MFS, build LAMP (Linux+Apache+MySQL+PHP) framework, network disk source file is placed under Apache, network disk database is placed under Mysql, the storage directory of a file as user's upload file is set in the client computer of MFS, and the mount directory using this storage directory as client computer, the kernel of Client OS can be (newly-built to the operation of file under this catalogue, read, revise) pass to fuse module, this module meeting and mfsmount process communicate, mfsmount process communicates by network and management server and data storage server again, client computer just can be carried out distributed read-write operation based on this storage directory like this, user on thin-client by the network disk under internet access Apache, user just can see the Web page of network disk on the browser of thin-client, the upload and download operation of execute file, this operation method step is as follows:
1) on the virtual machine of server cluster, build MFS, and at the client computer deploy LAMP of MFS framework, network disk source file is placed under the Apache of LAMP framework, the database file of network disk is placed under the MySQL of LAMP framework;
A) virtual machine is selected: select a virtual machine as management server, select another virtual machine as metadata log server, select other many (>=3) virtual machines as data storage server, select in addition a virtual machine as client computer, these virtual machines are all based on (SuSE) Linux OS again;
B) dispose management server: editor's configuration file is set, and appointment can long-rangely be mounted to the IP address of the client computer of MFS management server, and authorizes this client access authority;
C) dispose metadata log server: editor's configuration file is set, indicates the IP address of management server, for carrying out data backup, to carry out data transfer and recovery when management server breaks down;
D) dispose data storage server: a newly-increased hard disk is separately for MFS carries out file storage, and editor's configuration file, indicate IP address and the communication port of management server;
E) dispose client computer: fuse module is installed and carries out carry deployment;
2) configuration file of modification PHP, the file size that can upload to increase user;
3) storage directory of a file as user's upload file is set in the client computer of MFS, and this storage directory is set as to client computer and is mounted to the mount directory of management server;
4) start the Apache under MFS and LAMP framework;
5) user logins the network disk Web page from thin-client browser, and after registering and logging in, the file that generation is named using this user name in storage directory, as this user's memory space, then proceeds to respectively step 6) and step 7);
6) the privately owned storage folder of user based on oneself carried out the upload operation of file, and user clicks file and uploads button, and the Apache in client computer submits upload request to, after its response, file uploaded to memory space.Client computer can be sent write request to management server, and MFS carries out write operation, the file of uploading of this user under storage directory is divided into multiple data blocks and is stored in data storage server, realizes distributed storage, then proceeds to step 8);
7) the privately owned storage folder of user based on oneself carried out the down operation of file, and user clicks download button, to Apache, submits request to, after its response, to file storage file reading.Client computer can be sent read request to management server, MFS carries out read operation, from each data storage server, read the data block information of this file, client computer is integrated the data block information of obtaining and turn back in mount directory, the merging of realization to distributed document data block, then proceeds to next step;
8), after read-write operation, user sees network disk Web renewal of the page content afterwards by thin-client.
Above-mentioned LAMP is the open source software of building in the client computer of MFS one group and be used for building dynamic website or server, comprises Linux, Apache, MySQL and PHP, has jointly formed a powerful web application platform.Wherein, Linux is in lowermost layer, and operating system is provided; Inferior low layer is Apache, and it is a Web server, and Apache provides the mechanism that can allow user obtain the Web page; MySQL is a small-sized Relational DBMS, storage data; PHP is the abbreviation of English supertext preliminary treatment language Hypertext Preprocessor, mean supertext preliminary treatment, the embedded language of its a kind of HTML, is a kind of script of the embedding html document of carrying out at server end, the style of language is similar to C language, is used widely.
Above-mentioned network disk is the network file storage application system being deployed under LAMP framework, and its source file is based on PHP language compilation, comprises JavaScript, HTML, CSS, PHP and database file.Wherein, JavaScript is a kind of based on object and event-driven and have the client script language of relative safety, is also a kind of script that is widely used in client Web exploitation simultaneously, is commonly used to add dynamic function to html web page; CSS is the abbreviation of English Cascading Style Sheets (CSS list), and it is a kind of computer language that is used for showing the file styles such as HTML or XML.Network disk source file is placed under Apache, and database file is placed under MySQL, and user can obtain by Apache the Web page of this network disk.
Above-mentioned server cluster is that many physical servers are put together to the cluster that carries out together same service, In the view of user, similarly is to only have a server.
Above-mentioned virtual machine (Virtual Machine) refer to by software simulation have complete hardware system function, operate in a complete computer in complete isolation environment.Can on a physical computer, simulate one or more virtual computer, these virtual machines can carry out work completely as real computer.
Above-mentioned Apache is the Web server under LAMP framework just, for user provides the access Web mechanism of the page.
Above-mentioned fuse module is user's space file system (Filesystem in Userspace) module, is the module that arrives local file system in Linux for some cyberspace of carry.Fuse module provides the interface of a file operation, then fuse monitoring file operation on this interface, once there be operation (newly-built, read, revise) to occur, fuse module can hand over mfsmount process to process control.
Above-mentioned mfsmount process is the process of in MFS, file operation in mount directory in client computer being processed, and can be set up and be communicated by letter by network with data storage server with the management server of MFS.
<1> client computer is sent write data requests based on mount directory to management server;
The IP address of each data storage server of <2> management server queries, and each IP address is returned to client computer;
<3> client computer is set up and is communicated by letter with data storage server, the file that user is uploaded is written to data storage server with data block (chunk), each data block is 64MB to the maximum, if file is less than 64MB, the size of data block is this file size, if file exceedes 64MB, this file will be divided equally, the size of each piece of data piece is to be no more than 64MB as principle, each is dispersed on the hard disk that is stored in data storage server, and each data block can independently be set the backup number needing, to improve fault freedom and the security performance of system,
Between each data storage server of <4>, copy communication, guarantee that each data block has copy on different data storage servers, to realize the optimal storage to data;
Each data storage server of <5> returns to client computer by the message successfully writing;
<6> client computer is sent and is written to function signal to management server, finishes this write operation.
By said process, with regard to having realized the file that user is uploaded, carry out the function of distributed storage.
1. client computer is sent the request of reading file data to management server;
2. management server retrieve data, obtains each data storage server IP address of this file data blocks of storage, and the address of data storage server is returned to client computer;
3. client computer is set up and is communicated by letter with each data storage server, to concrete data storage server, initiates request reading out data;
4. each data storage server returns to client computer by the data block of file;
5. client computer merges processing by each data block reading, and forms complete file, and sends and read into function signal to management server, finishes this read operation.
By said process, just realized the function that each data block of distributed storage is merged into complete file.
The present invention traditional network storage and MFS is be provided provide a kind of new file storage service based on thin-client, user is uploaded to file on network disk and be dispersed into multiple data blocks and be put on different servers and store.The key realizing is to have a storage directory for storage networking disk user upload file in the client computer of MFS, this catalogue is also the mount directory of the client computer of MFS simultaneously, by mfsmount module, can process the file operation under this catalogue.So, once user's upload file is under this catalogue, just be equivalent to occur under this catalogue the operation of new files, the fuse module of client computer will will be given mfsmount resume module to the control of this file operation so, mfsmount module can be set up and communicate by letter with data storage server with management server by network, and the file distribution formula under this catalogue is stored in each data storage server.Thus, network disk and MFS set up contact by this storage directory physically, and centralized stores has been become to distributed storage effectively.
MFS in the present invention is the distributed file system of a lightweight.It mainly comprises four parts:
A. management server: only have one, be responsible for the management of each data storage server, file read-write scheduling, file space is reclaimed and is recovered multinode and copies;
B. metadata log server: be responsible for the journal file that archive management server changes, carry out work so that take over it when management server goes wrong; The existence of metadata log server has solved MFS system effectively only has the drawback of a management server, has avoided Single Point of Faliure, has improved fail safe and the restorability of system;
C. data storage server: can have many, be responsible for connection management server, accept the management and dispatching of management server, memory space is provided, and provide transfer of data for client.After data storage server starts, can initiatively contact with management server, allowing management server know has how many data storage servers in network;
D. client computer: can have many, by kernel loads fuse module, then by and the communication of management server, subregion shared data storage server is mounted to this locality, then carry out read-write operation.The high availability of MFS is that the multiple copies by store each file on multiple data storage servers are realized.Data file is divided into a lot of data blocks, and each data block is 64MB to the maximum, and each data block shows as an independently file on data storage server.Between data storage server, can complete by communication the copy of data, to realize many copy storages of the each data block to a file.For client computer, it can hand to fuse module by operating system to all operations of file, and by fuse module and mfsmount process communication.And mfsmount process will be linked up by network and management server and data storage server.In client computer, the file to carry on MFS operates and is on all four in this locality.
The advantage of operation method of the present invention is to change traditional network storage and local memory module, breaks the individual server performance bottleneck of centralized stores, produces a kind ofly by the novel memory module of the network storage and distributed storage combination, greatly improves memory property.
Accompanying drawing explanation
Fig. 1 is the FB(flow block) of operation method of the present invention.Wherein, 1)-8) be its each step.
Fig. 2 is step 6 in operation method of the present invention) in the FB(flow block) of write operation of execution MFS file.Wherein, <1>-<6GreatT.Gre aT.GT is its each step.
Fig. 3 is step 7 in operation method of the present invention) in the FB(flow block) of read operation of execution MFS file.Wherein, 1.-be 5. its each step.
Embodiment
Below in conjunction with drawings and Examples, the present invention will be further described, but be not limited to this.
Embodiment:
The embodiment of the present invention as shown in Figure 1, a kind of operation method of the file distribution formula storage based on thin-client, by following system, realized, this system comprises thin-client, network disk and MooseFS (being called for short MFS), wherein thin-client is the client based on built-in Linux operating system, and it only provides input-output equipment and web browser, network disk is the network file storage application system based on Web, MooseFS is a kind of distributed file system, its file system structure comprises management server (master), metadata log server (metalogger), data storage server (chunkservers) and client computer (client), thin-client, running between network disk and MFS three is: by many physical servers, form an extendible server cluster, on every physical server, fictionalize many stylobates in the virtual machine of (SuSE) Linux OS, on the virtual machine of server cluster, build MFS, in the client computer of MFS, build LAMP (Linux+Apache+MySQL+PHP) framework, network disk source file is placed under Apache, network disk database is placed under Mysql, the storage directory of a file as user's upload file is set in the client computer of MFS, and the mount directory using this storage directory as client computer, the kernel of Client OS can be (newly-built to the operation of file under this catalogue, read, revise) pass to fuse module, this module meeting and mfsmount process communicate, mfsmount process communicates by network and management server and data storage server again, client computer just can be carried out distributed read-write operation based on this storage directory like this, user on thin-client by the network disk under internet access Apache, user just can see the Web page of network disk on the browser of thin-client, the upload and download operation of execute file, this operation method step is as follows:
1) on the virtual machine of server cluster, build MFS, and at the client computer deploy LAMP of MFS framework, network disk source file is placed under the Apache of LAMP framework, the database file of network disk is placed under the MySQL of LAMP framework;
A) virtual machine is selected: select a virtual machine as management server, select another virtual machine to take as metadata daily record
Business device, selects other 3 virtual machines as data storage server, selects in addition a virtual machine as client computer again,
These virtual machines are all based on (SuSE) Linux OS;
B) dispose management server: editor's configuration file is set, and appointment can long-rangely be mounted to the IP address of the client computer of MFS management server, and authorizes this client access authority;
C) dispose metadata log server: editor's configuration file is set, indicates the IP address of management server, for carrying out data backup, to carry out data transfer and recovery when management server breaks down;
D) dispose data storage server: a newly-increased hard disk is separately for MFS carries out file storage, and editor's configuration file, indicate IP address and the communication port of management server;
E) dispose client computer: fuse module is installed and carries out carry deployment;
2) configuration file of modification PHP, the file size that can upload to increase user;
3) storage directory of a file as user's upload file is set in the client computer of MFS, and this storage directory is set as to client computer and is mounted to the mount directory of management server;
4) start the Apache under MFS and LAMP framework;
5) user logins the network disk Web page from thin-client browser, and after registering and logging in, the file that generation is named using this user name in storage directory, as this user's memory space, then proceeds to respectively step 6) and step 7);
6) the privately owned storage folder of user based on oneself carried out the upload operation of file, and user clicks file and uploads button, and the Apache in client computer submits upload request to, after its response, file uploaded to memory space.Client computer can be sent write request to management server, and MFS carries out write operation, the file of uploading of this user under storage directory is divided into multiple data blocks and is stored in data storage server, realizes distributed storage, then proceeds to step 8);
7) the privately owned storage folder of user based on oneself carried out the down operation of file, and user clicks download button, to Apache, submits request to, after its response, to file storage file reading.Client computer can be sent read request to management server, MFS carries out read operation, from each data storage server, read the data block information of this file, client computer is integrated the data block information of obtaining and turn back in mount directory, the merging of realization to distributed document data block, then proceeds to next step;
8), after read-write operation, user sees network disk Web renewal of the page content afterwards by thin-client.
<1> client computer is sent write data requests based on mount directory to management server;
The IP address of each data storage server of <2> management server queries, and each IP address is returned to client computer;
<3> client computer is set up and is communicated by letter with data storage server, the file that user is uploaded is written to data storage server with data block (chunk), each data block is 64MB to the maximum, if file is less than 64MB, the size of data block is this file size, if file exceedes 64MB, this file will be divided equally, the size of each piece of data piece is to be no more than 64MB as principle, each is dispersed on the hard disk that is stored in data storage server, and each data block can independently be set the backup number needing, to improve fault freedom and the security performance of system,
Between each data storage server of <4>, copy communication, guarantee that each data block has copy on different data storage servers, to realize the optimal storage to data;
Each data storage server of <5> returns to client computer by the message successfully writing;
<6> client computer is sent and is written to function signal to management server, finishes this write operation.
By said process, with regard to having realized the file that user is uploaded, carry out the function of distributed storage.
1. client computer is sent the request of reading file data to management server;
2. management server retrieve data, obtains each data storage server IP address of this file data blocks of storage, and the address of data storage server is returned to client computer;
3. client computer is set up and is communicated by letter with each data storage server, to concrete data storage server, initiates request reading out data;
4. each data storage server returns to client computer by the data block of file;
5. client computer merges processing by each data block reading, and forms complete file, and sends and read into function signal to management server, finishes this read operation.
Claims (3)
1. the operation method of the file distribution formula storage based on thin-client, by following system, realized, this system comprises that thin-client, network disk and MooseFS are MFS, wherein thin-client is the client based on built-in Linux operating system, and it only provides input-output equipment and web browser, network disk is the network file storage application system based on Web, MooseFS is a kind of distributed file system, its file system structure comprises management server, metadata log server, data storage server and client computer, thin-client, running between network disk and MFS three is: by many physical servers, form an extendible server cluster, on every physical server, fictionalize many stylobates in the virtual machine of (SuSE) Linux OS, on the virtual machine of server cluster, build MFS, in the client computer of MFS, build LAMP framework, network disk source file is placed under Apache, network disk database is placed under Mysql, the storage directory of a file as user's upload file is set in the client computer of MFS, and the mount directory using this storage directory as client computer, the kernel of Client OS can be the operation of file under this catalogue is passed to fuse module, this module meeting and mfsmount process communicate, mfsmount process communicates by network and management server and data storage server again, client computer just can be carried out distributed read-write operation based on this storage directory like this, user on thin-client by the network disk under internet access Apache, user just can see the Web page of network disk on the browser of thin-client, the upload and download operation of execute file, this operation method step is as follows:
1) on the virtual machine of server cluster, build MFS, and at the client computer deploy LAMP of MFS framework, network disk source file is placed under the Apache of LAMP framework, the database file of network disk is placed under the MySQL of LAMP framework;
A) virtual machine is selected: select a virtual machine as management server, select another virtual machine as metadata log server, select other 3 or 4 virtual machines as data storage server, select in addition a virtual machine as client computer, these virtual machines are all based on (SuSE) Linux OS again;
B) dispose management server: editor's configuration file is set, and appointment can long-rangely be mounted to the IP address of the client computer of MFS management server, and authorizes this client access authority;
C) dispose metadata log server: editor's configuration file is set, indicates the IP address of management server, for carrying out data backup, to carry out data transfer and recovery when management server breaks down;
D) dispose data storage server: a newly-increased hard disk is separately for MFS carries out file storage, and editor's configuration file, indicate IP address and the communication port of management server;
E) dispose client computer: fuse module is installed and carries out carry deployment;
2) configuration file of modification PHP, the file size that can upload to increase user;
3) storage directory of a file as user's upload file is set in the client computer of MFS, and this storage directory is set as to client computer and is mounted to the mount directory of management server;
4) start the Apache under MFS and LAMP framework;
5) user logins the network disk Web page from thin-client browser, and after registering and logging in, the file that generation is named using this user name in storage directory, as this user's memory space, then proceeds to respectively step 6) and step 7);
6) the privately owned storage folder of user based on oneself carried out the upload operation of file, and user clicks file and uploads button, and the Apache in client computer submits upload request to, after its response, file uploaded to memory space.Client computer can be sent write request to management server, and MFS carries out write operation, the file of uploading of this user under storage directory is divided into multiple data blocks and is stored in data storage server, realizes distributed storage, then proceeds to step 8);
7) the privately owned storage folder of user based on oneself carried out the down operation of file, and user clicks download button, to Apache, submits request to, after its response, to file storage file reading.Client computer can be sent read request to management server, MFS carries out read operation, from each data storage server, read the data block information of this file, client computer is integrated the data block information of obtaining and turn back in mount directory, the merging of realization to distributed document data block, then proceeds to next step;
8), after read-write operation, user sees network disk Web renewal of the page content afterwards by thin-client.
2. the MFS in the step 6) of operation method as claimed in claim 1 carries out write operation, and step is as follows:
<1> client computer is sent write data requests based on mount directory to management server;
The IP address of each data storage server of <2> management server queries, and each IP address is returned to client computer;
<3> client computer is set up and is communicated by letter with data storage server, the file that user is uploaded is written to data storage server with data block, each data block is 64MB to the maximum, if file is less than 64MB, the size of data block is this file size, if file exceedes 64MB, this file will be divided equally, the size of each piece of data piece is to be no more than 64MB as principle, each is dispersed on the hard disk that is stored in data storage server, and each data block can independently be set the backup number needing, to improve fault freedom and the security performance of system,
Between each data storage server of <4>, copy communication, guarantee that each data block has copy on different data storage servers, to realize the optimal storage to data;
Each data storage server of <5> returns to client computer by the message successfully writing;
<6> client computer is sent and is written to function signal to management server, finishes this write operation.
By said process, with regard to having realized the file that user is uploaded, carry out the function of distributed storage.
3. the MFS in the step 7) of operation method as claimed in claim 1 carries out read operation, and step is as follows:
1. client computer is sent the request of reading file data to management server;
2. management server retrieve data, obtains each data storage server IP address of this file data blocks of storage, and the address of data storage server is returned to client computer;
3. client computer is set up and is communicated by letter with each data storage server, to concrete data storage server, initiates request reading out data;
4. each data storage server returns to client computer by the data block of file;
5. client computer merges processing by each data block reading, and forms complete file, and sends and read into function signal to management server, finishes this read operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110448040.9A CN102546780B (en) | 2011-12-28 | 2011-12-28 | Operation method for file distributed storage based on thin client |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201110448040.9A CN102546780B (en) | 2011-12-28 | 2011-12-28 | Operation method for file distributed storage based on thin client |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102546780A CN102546780A (en) | 2012-07-04 |
CN102546780B true CN102546780B (en) | 2014-04-16 |
Family
ID=46352726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201110448040.9A Active CN102546780B (en) | 2011-12-28 | 2011-12-28 | Operation method for file distributed storage based on thin client |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102546780B (en) |
Families Citing this family (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102917050A (en) * | 2012-10-17 | 2013-02-06 | 山东大学 | Remote security monitoring system and method based on android embedded type thin client end |
CN103024020B (en) * | 2012-12-05 | 2015-06-03 | 蓝盾信息安全技术股份有限公司 | Network data file storing method and device based on WEB application |
CN103067505A (en) * | 2012-12-30 | 2013-04-24 | 乐视网信息技术(北京)股份有限公司 | Method for uploading files to server |
CN103458048A (en) * | 2013-09-16 | 2013-12-18 | 浪潮电子信息产业股份有限公司 | Examination system set-up method based on cloud computation |
CN103747064B (en) * | 2013-12-26 | 2017-06-20 | 广东中科遥感技术有限公司 | Hanging method, client and system based on MooseFS Distribute file systems |
CN104090913B (en) * | 2014-06-10 | 2017-11-03 | 深信服科技股份有限公司 | File operation method and device based on thin client |
CN105490999A (en) * | 2014-12-23 | 2016-04-13 | 哈尔滨安天科技股份有限公司 | Distributed storage system based on extensible messaging and presence protocol (XMPP) |
CN105069009A (en) * | 2015-07-06 | 2015-11-18 | 无锡天脉聚源传媒科技有限公司 | Folder uploading/downloading method and device |
CN105242988B (en) * | 2015-10-10 | 2018-02-02 | 国家电网公司 | The data back up method of distributed file system and distributed file system |
CN105975328B (en) * | 2016-04-29 | 2019-10-08 | 上海交通大学 | Journal file safety auditing system and method based on secure virtual machine |
US9665714B1 (en) * | 2016-05-31 | 2017-05-30 | AO Kaspersky Lab | System and method of detecting malicious files on virtual machines in a distributed network |
CN106202350A (en) * | 2016-07-05 | 2016-12-07 | 浪潮(北京)电子信息产业有限公司 | A kind of distributed file system simplifies the method and system of configuration automatically |
CN107707507A (en) * | 2016-08-08 | 2018-02-16 | 深圳中电长城信息安全系统有限公司 | Control method and system based on safe pool network data transmission |
CN107733667B (en) * | 2016-08-10 | 2021-05-25 | 北京京东尚科信息技术有限公司 | Log management method and system |
CN106993004A (en) * | 2017-06-12 | 2017-07-28 | 深圳市永达电子信息股份有限公司 | A kind of method that super large annex is uploaded in B/S framework system |
CN107580232A (en) * | 2017-09-28 | 2018-01-12 | 郑州云海信息技术有限公司 | A kind of video living transmission system and method |
CN109726041B (en) * | 2017-10-27 | 2023-09-08 | 伊姆西Ip控股有限责任公司 | Method, apparatus and computer readable medium for restoring files in a virtual machine disk |
CN109725913A (en) * | 2017-10-27 | 2019-05-07 | 北京京东尚科信息技术有限公司 | The method and apparatus that data update |
CN107832423B (en) * | 2017-11-13 | 2020-05-15 | 中山大学 | File reading and writing method for distributed file system |
CN109977083B (en) * | 2019-03-27 | 2021-04-06 | 深圳市瑞云科技有限公司 | File transmission system based on file system hanging disc technology |
CN110321077B (en) * | 2019-06-17 | 2023-04-14 | 浩云科技股份有限公司 | Method and device for managing centrally stored files |
CN112667565B (en) * | 2020-12-30 | 2021-12-03 | 湖南博匠信息科技有限公司 | Storage unit file management method and system based on FUSE |
CN112764830B (en) * | 2021-01-19 | 2023-04-21 | 长沙证通云计算有限公司 | Data migration method and system applied to localization substitution |
CN114895852A (en) * | 2022-05-09 | 2022-08-12 | 北京星辰天合科技股份有限公司 | Data processing method, system, device, storage medium and electronic equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101135971A (en) * | 2006-09-01 | 2008-03-05 | 环达电脑(上海)有限公司 | Accessing route device install configuring method based on personal computer hardware equipment |
CN102012933A (en) * | 2010-12-02 | 2011-04-13 | 清华大学 | Distributed file system and method for storing data and providing services by utilizing same |
-
2011
- 2011-12-28 CN CN201110448040.9A patent/CN102546780B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101135971A (en) * | 2006-09-01 | 2008-03-05 | 环达电脑(上海)有限公司 | Accessing route device install configuring method based on personal computer hardware equipment |
CN102012933A (en) * | 2010-12-02 | 2011-04-13 | 清华大学 | Distributed file system and method for storing data and providing services by utilizing same |
Non-Patent Citations (2)
Title |
---|
S._J.S.Tsai,Member,IEEE,and C.C.Luo.synchronized power-quality measurement network with LAMP.《IEEE/IEE Electronic Library(IEL)数据库》.2009,第24卷(第1期),全文. |
synchronized power-quality measurement network with LAMP;S._J.S.Tsai,Member,IEEE,and C.C.Luo;《IEEE/IEE Electronic Library(IEL)数据库》;20090131;第24卷(第1期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN102546780A (en) | 2012-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102546780B (en) | Operation method for file distributed storage based on thin client | |
US10387673B2 (en) | Fully managed account level blob data encryption in a distributed storage environment | |
Gu et al. | Sector and Sphere: the design and implementation of a high-performance data cloud | |
JP6250189B2 (en) | Client configurable security options for data streams | |
Hupfeld et al. | The XtreemFS architecture—a case for object‐based file systems in Grids | |
EP3069274B1 (en) | Managed service for acquisition, storage and consumption of large-scale data streams | |
JP6357243B2 (en) | Data stream ingestion and persistence policy | |
US20210019063A1 (en) | Utilizing data views to optimize secure data access in a storage system | |
US10922303B1 (en) | Early detection of corrupt data partition exports | |
US20210055885A1 (en) | Enhanced data access using composite data views | |
Dwivedi et al. | Analytical review on Hadoop Distributed file system | |
CN102523101A (en) | Machine manager service fabric | |
US11818012B2 (en) | Online restore to different topologies with custom data distribution | |
US11079960B2 (en) | Object storage system with priority meta object replication | |
Won et al. | Moving metadata from ad hoc files to database tables for robust, highly available, and scalable HDFS | |
Salunkhe et al. | Luster a scalable architecture file system: A research implementation on active storage array framework with Luster file system | |
Azagury et al. | GPFS-based implementation of a hyperconverged system for software defined infrastructure | |
Wei et al. | DSC: Dynamic stripe construction for asynchronous encoding in clustered file system | |
US11093465B2 (en) | Object storage system with versioned meta objects | |
US20200401312A1 (en) | Object Storage System with Meta Object Replication | |
Zainab et al. | Moving a repository of scholarly content to a cloud | |
Arteaga et al. | Towards scalable application checkpointing with parallel file system delegation | |
Gu et al. | Sector and sphere: Towards simplified storage and processing of large scale distributed data | |
Liu et al. | User-oriented Mobile Filesystem Middleware for Mobile Cloud Systems. | |
Klaver et al. | Distributed file system on the SURFnet network Report |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |