CN103076994A - Method for realizing off-line file writing in SAN (Storage Area Network) shared-file system - Google Patents
Method for realizing off-line file writing in SAN (Storage Area Network) shared-file system Download PDFInfo
- Publication number
- CN103076994A CN103076994A CN2012105877260A CN201210587726A CN103076994A CN 103076994 A CN103076994 A CN 103076994A CN 2012105877260 A CN2012105877260 A CN 2012105877260A CN 201210587726 A CN201210587726 A CN 201210587726A CN 103076994 A CN103076994 A CN 103076994A
- Authority
- CN
- China
- Prior art keywords
- metadata
- client
- file
- data server
- meta data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention relates to a method for realizing off-line file writing in an SAN (Storage Area Network) shared-file system. The method comprises the following steps of: opening a file; acquiring metadata, wherein a client side acquires metadata of a balance disk space in addition to normal acquisition of metadata of a file to be written; judging whether a metadata server is online or not; writing the file on line; writing the file off line; and ending file writing. According to the invention, when the client side is used to acquire the metadata from the metadata server, a metadata pre-acquisition caching process is available, and when the metadata server or an LAN (Local Area Network) is in fault, the client side server can continuously and normally write the file content to be written, into the balance disk space according to a local metadata backup. The method disclosed by the invention has the advantages of effectively improving the write-in efficiency of the SAN shared-file system, guaranteeing the continuity, fault tolerance and antijamming property during file writing, and improving the safety of the SAN shared-file system.
Description
Technical field
The present invention relates in a kind of SAN shared-file system to realize the method for off-line written document, is the method that a kind of network system is included video file, is the file off-line wiring method under a kind of SAN shared-file system that is applicable to the broadcasting and TV application.
Background technology
At present, general SAN shared-file system is comprised of by lan network and SAN network meta data server (MDS), shared storage and multi-client, meta data server and client can directly be accessed by FC or ISCSI agreement and be shared storage, are respectively FC-SAN and IP-SAN framework.The SAN network is owing to be Optical Fiber Transmission, and bandwidth, capacity is large, speed is fast, is commonly used to the huge file of transmitted data amount, as: video file.
Metadata in the SAN shared-file system is the data structure of data of description method for organizing, the metadata essential record some association attributeses etc. of division methods, deposit position and the file of this document on block device in the SAN shared-file system.The SAN shared-file system becomes file structure by metadata with continuous block device storage organization, and the size of metadata is compared very little with file data, thus do not need very high transmission bandwidth, so transmit with lan network.Metadata information on the SAN shared-file system is by the meta data server unified management.Client links to each other with meta data server and communication by the tcp/ip agreement under lan network.
When client will be carried out file write operation in the SAN shared-file system, need constantly to initiate the metadata request of this document to meta data server by lan network, meta data server returns to client according to the space size of client application with the corresponding element data message of this document at every turn, client writes the disk relevant position according to the metadata information that obtains with file, when writing end, the write operation end is sent to meta data server, meta data server is integrated the metadata information of data writing, carries out read and write access for other clients in the system.Although this general SAN shared-file system has efficient height, characteristics that applicability is wide, but meta data server is wherein bottleneck and single point failure point, in case meta data server goes wrong, whole SAN network will be paralysed and can't be worked, therefore the modes that adopt two-node cluster hot backup or cluster guarantee that the meta data server height is available more; Even if under these circumstances, still be difficult to avoid go wrong or meta data server the machine fault when lan network, cause client can't with all meta data server communications in the system, cause the SAN network paralysis.Traditional SAN shared-file system way is to stop write operation in this case, waits for after the meta data server recovery is communicated by letter, and then carries out write operation.
Summary of the invention
Overcome the problem of prior art, the objective of the invention is to propose to realize in a kind of SAN shared-file system the method for off-line written document.Described method is at all meta data servers because the machine fault or lan network problem can't continue to communicate by letter the time, client is proceeded the file write operation according to the corresponding temporary disc of the metadata space of pre-first to file, when treating that meta data server recovers communication, the Data Migration that is written to the temporary disc space to the tram, and is merged the corresponding metadata information of these data.When guaranteeing that meta data server can't communication, the file that client still can be proceeded in the SAN network writes work, keeps professional continuity.
The object of the present invention is achieved like this: the method that realizes the off-line written document in a kind of SAN shared-file system, employed hardware system comprises in the described method: a plurality of clients are connected with the disk array with meta data server by the SAN network of transmitting video files, described a plurality of client is connected with meta data server by the lan network of transmission unit data, and the step of described method is as follows:
The step that opens file: be used for client and send request to meta data server, require to open file to be written in the disk array;
Obtain the step of metadata: be used for client according to the content of file to be written, to the corresponding metadata of meta data server application content to be written, client is obtained respective meta-data, and client accepts to distribute to the chance lock of oneself simultaneously;
Client also will be obtained the metadata in the pre-volume of disk space in described " obtaining the step of metadata " outside normally obtaining the metadata for the treatment of written document;
Judge whether online step of meta data server: be used for judging whether described meta data server normally works online, if "Yes" then enter " step of online writing in files ", if "No" then enter " step of off-line writing in files ";
The step of online writing in files: be used for described client and obtain metadata section, and according to the metadata section that obtains, disk array is initiated the blocks of data request of writing in files, write to finish these metadata section corresponding blocks data, the application metadata section of circulation and write blocks of data corresponding to metadata section, until finish in the resident space that writes disk array of whole file, enter afterwards " step that file writes end "; If meta data server off-line in the file ablation process then enters " step of off-line writing in files ";
The step of off-line writing in files: be used for described client and use the metadata in pre-volume space file to be write the pre-volume space of disk array, whether constantly detect simultaneously meta data server reaches the standard grade, if meta data server is reached the standard grade, then will write in the disk array that the file synchronization in the pre-volume of the disk space sets to meta data server and enter " step that file writes end ", if the pre-volume of disk space is all write full, client still is not communicated with meta data server, then enters " step that file writes end ";
File writes the step of end: be used for client and send requirement to meta data server, close opened writing in files handle, finish this file and write.
The beneficial effect that the present invention produces is: the present invention utilizes client in the writing in files flow process, when obtaining metadata to meta data server, the pre-acquisition methods of specific metadata and caching method are provided, so that when standard is write flow process and is normally carried out, client keeps the metadata backup in the pre-volume of a disk space in this locality, and guarantee consistance and the validity of this metadata by method for synchronous, like this when meta data server or lan network break down, client-server can continue normally file content to be written to be write in the pre-volume of the disk space according to the metadata backup of this locality, after present invention can be implemented in meta data server and quitting work, client-server continues to write the function of SAN shared file according to the backup metadata of this locality.When being checked through meta data server when effective, client-server is again to meta data server application metadata, and to guarantee the correctness of metadata, meta data server is finished the synchronizing function of corresponding data simultaneously.The present invention improves the file write efficiency of SAN shared system effectively, has guaranteed continuity, fault-tolerance and anti-interference that file writes, has improved the security of SAN shared-file system.Owing in the application of broadcast television industry, exist long-time continual large data to look audio frequency and include, guarantee professional continuity, the very applicable file off-line wiring method of the present invention of this application.
Description of drawings
The invention will be further described below in conjunction with drawings and Examples.
Fig. 1 is the employed hardware system synoptic diagram of inventive embodiments one described method;
Fig. 2 is the schematic flow sheet of inventive embodiments one described method;
Fig. 3 is the method flow diagram that inventive embodiments two described pre-volume Metadatas obtain;
Fig. 4 is the method flow diagram that inventive embodiments three described files write pre-volume space.
Embodiment
Embodiment one:
Present embodiment is the method that realizes the off-line writing in files in a kind of SAN shared-file system, the employed hardware system of described method as shown in Figure 1, comprise: a plurality of clients are connected with the disk array with meta data server by the SAN network of transmitting video files, and described a plurality of clients are connected with meta data server by the lan network of transmission unit data.Wherein client can be common PC workstation, can be server also, has the ability that connects the SAN network, and can process large-scale file, for example the high definition video file.The described SAN network of present embodiment is the broadband network that bandwidth surpasses 1G by the optical networking that optical fiber switch and optical cable form, and video file that can transmission of high-definition also can consist of the SAN network with the Fast Ethernet of thousand M or ten thousand M.The described lan network of present embodiment is comprised of ethernet switch and uses TCP/IP to be the Ethernet of communications protocol, has the bandwidth of hundreds of K, can transmit fast the meta data file of hundreds of K.Can go wrong for fear of meta data server under normal conditions and affect the normal operation of whole SAN system, can increase a meta data server for subsequent use, namely two meta data servers backup each other it, realize that on the basis of synchrodata meta data server is redundant.Memory device in the system uses disk array usually, and disk array links to each other with meta data server with client by the SAN network, and client and meta data server can conduct interviews to it by fc agreement or iscsi agreement.
The basic ideas of present embodiment are: disk array is divided into two parts, and a part is resident space, and a part is pre-volume space.Resident space will be stored the space that file normally writes when being meta data server work, client write in this part disk space from the data of being about to be stored file when pre-volume space then was the meta data server off-line, to avoid because the meta data server off-line causes whole system to paralyse.When making the meta data server off-line, it can be client writing in files in pre-volume space, when client is sent normal metadata at the request metadata server, also require meta data server to send the metadata in the pre-volume of cover space, and in client terminal local disk or internal memory, keep the backup metadata in this pre-volume space.When the meta data server in the SAN system or lan network go wrong, client still can write off-line data in the disk array by the metadata in the pre-volume of local backup disk space, guarantees to write normally professionally not paralyse when fault occurs and proceed.The described method of present embodiment can be expressed as: client-server is in the writing in files flow process, when obtaining metadata to meta data server, specific metadata application method and caching method are provided, so that when standard is write flow process and is normally carried out, client keeps the backup of the metadata in the pre-volume of a disk space in this locality, and guarantee one of this metadata validity of making peace by method for synchronous, like this when meta data server or lan network break down, the backup of the metadata in the pre-volume of the disk space that client-server can keep according to this locality continues normally to carry out file and writes work.With this file write efficiency that can effectively improve the SAN shared system, guaranteed continuity, fault-tolerance and anti-interference that file writes, improved the security of SAN shared-file system.
The flow process of the described method of present embodiment as shown in Figure 2, concrete steps are as follows:
1, the step that opens file: be used for client and send request to meta data server, require to open file to be written in the disk array.This step is basic step, and when the user need to write a file, the user opened the handle of file to be written in client, and client is sent request according to the handle of this document to meta data server, at disk application space data writing.When client and a meta data server connect, create corresponding processing threads, this thread is used for the background process off-line and writes relevant function, if not at running background, the standard that may affect writes the efficient of flow process.
2, obtain the step of metadata: client is according to the content of file to be written, and to the corresponding metadata of meta data server application content to be written, client is obtained respective meta-data, and client accepts to distribute to the chance lock of oneself simultaneously.Client also will be obtained the metadata in the pre-volume of disk space outside normally obtaining the metadata for the treatment of written document.
The difference that writes of this step and traditional SAN shared file is: traditional metadata (metadata section) that only is to apply for some that writes; with that data are write blocks of files corresponding with this metadata section in the disk array; this step then also needs to obtain in addition the metadata in the pre-volume of the disk space of certain space outside normally obtaining the metadata for the treatment of written document, and opens up storage area at client terminal local and store these metadata.
3, judge whether online step of meta data server: be used for judging whether described meta data server normally works online, if "Yes" then enter " step of online writing in files ", if "No" then enter " step of off-line writing in files ".
4, the step of online writing in files: be used for client and obtain metadata section, and according to the metadata section that obtains, disk array is initiated the blocks of data request of writing in files, write to finish these metadata section corresponding blocks data, the application metadata section of circulation and write blocks of data corresponding to metadata section, until finish in the resident space that writes disk array of whole file, enter afterwards " step that file writes end "; If meta data server off-line in the file ablation process then enters " step of off-line writing in files ".
If all meta data servers break down in 5 ablation process, then to start off-line and write.The step of off-line writing in files: be used for described client and use the metadata in pre-volume space file to be write the pre-volume space of disk array, whether constantly detect simultaneously meta data server reaches the standard grade, if meta data server is reached the standard grade, then will write in the disk array that the file synchronization in the pre-volume of the disk space sets to meta data server and enter " step that file writes end ", if the pre-volume of disk space is all write full, client still is not communicated with meta data server, then enters " step that file writes end ".
6, file writes the step of end: be used for client and send requirement to meta data server, close opened writing in files handle, finish this file and write.
Embodiment two:
Present embodiment is the improvement of embodiment one, is embodiment one about the refinement of the metadata of obtaining the pre-volume of disk space in " obtaining the step of metadata ", and its flow process as shown in Figure 3.The metadata that the described client of present embodiment is obtained the pre-volume of disk space comprises following substep:
(1) detects the substep whether raw readings is arranged: be used for whether client has the metadata in pre-volume space local internal memory or hard disk inspection backup, if "No" then enter " substep of opening up storage space ", if "Yes" then enter the next son step.
This substep is a step that detects and judge, judges the metadata that whether has had the pre-volume of disk space in local hard drive or the internal memory.The situation that has metadata to exist generally is that this client of use write data and opened off-line and write function in the past, and whether can enter the next son step in this case: it is effective to detect this metadata.If do not find corresponding metadata, then need to start the process of obtaining pre-volume Metadata.
Effectively whether the metadata that (2) detects pre-volume space substep: whether being used for client, to detect the metadata backup in pre-volume space of local internal memory or hard disk effective, if "Yes" then enter " obtain metadata finish substep ", if "No" then enter the next son step.
This substep is the step of a judgement, judges in local hard drive or the internal memory it is to have existed the metadata in the pre-volume of disk space whether effective.May cause the metadata in the local in the past pre-volume space of application no longer valid because client is not used for a long time or changed meta data server, need to re-start detection validation.Present embodiment is when the off-line writing in files, because disconnect communication with meta data server, so need a cover mechanism to guarantee the validity (being data consistency) of metadata, when client is sent the metadata in the pre-volume of application space to meta data server, meta data server locks this section space by lock mechanism, only allow this client to conduct interviews, do not allow other clients to conduct interviews, also just directly guaranteed all data's consistencies.
Satisfy above condition, when meta data server breaks down in data writing process, can use the backup of the metadata in the local pre-volume of disk space of preserving to carry out data writing, and the data inconsistency problem can not occur, write otherwise will withdraw from.
(3) open up the substep of storage space: be used for client and open up storage space be used to the metadata of storing pre-volume space at local internal memory or hard disk.
The situation that generalized case double base data server all breaks down is not a lot, can open up storage space at hard disk as required.
(4) substep of selection processing: for client metadata is deposited in request and select to be placed on backstage formation wait or real-time processing, put into the metadata request formation and wait for if the request of then metadata being deposited in is waited on the backstage, if in real time processing then enters the next son step.
To process the read-write of file, can carry out simultaneously a plurality ofly in client, can to open up a plurality of file read-write threads in order raising the efficiency, so just have the operation queue of a plurality of threads, needing processing be just can take out from formation, processes.If running background, with the formation that joins request of the step of back, transfer to the processing threads of previous establishment and process; If not running background, directly in this thread, process.
(5) obtain the substep of the metadata in pre-volume space: be used for client according to communication rule circulation obtain the whole metadata in pre-volume space to meta data server, as the backup metadata, be kept in the storage space of having opened up according to the self-defining data structure of client.
Whole metadata of obtaining a pre-volume space are the same with the file ablation process, after one section metadata of application, or not to write corresponding blocks of data just, but continue request application metadata, so circulation is until complete with the application of pre-volume space, and is stored in the local hard drive or internal memory of client.
(6) obtain the substep that metadata finishes: be used for finishing to obtain metadata.
Embodiment three:
Present embodiment is the improvement of above-described embodiment, be above-described embodiment about the refinement of off-line writing in files, its flow process is as shown in Figure 4.The step of the described off-line writing in files of present embodiment comprises following substep:
(1) detects the substep whether client has the backup metadata in pre-volume space: check for internal memory or the hard disk of client to this locality, whether the metadata backup in pre-volume space is arranged, if not then enter " substep that file writes end ", if having then enter the next son step.
(2) whether effectively the client backup substep that detects the backup metadata: whether being used for client, to detect the metadata in pre-volume space of local internal memory or hard disk effective, if "No" then enter " step that file writes end ", if "Yes" then enter next step.
(3) use the substep that backs up the metadata writing in files: be used for client and obtain backup Metadata about metadata section from local internal memory or hard disk, and utilize described metadata section to the disk array writing in files.
Client is obtained backup Metadata about metadata section from local internal memory or hard disk, if the success disk array would be initiated the blocks of data request of file to be written, write to finish these metadata section corresponding blocks data, what circulate reads metadata section and writes blocks of data corresponding to metadata section, until client again is communicated with meta data server or finishes writing of whole file and finish.
(4) whether detect client and detect the substep that whether is communicated with that is connected with meta data server: it is unimpeded with being connected of meta data server to be used for the client detection, if "No" then enter the next son step, if "Yes" then enter " substep from metadata section to meta data server that again apply for ".In backup metadata that client is used the pre-volume space in local internal memory or the hard disk pre-volume space writing in files in the disk array, to constantly detect simultaneously the connectedness with meta data server, if be communicated with, then apply for up-to-date metadata, do not re-use original backup metadata.
(5) judge whether pre-volume disk space writes full substep: be used for described client and judge whether the pre-volume space of disk array is write completely, if "Yes" then enter " step that file writes end ", if "No" then enter the next son step.When utilizing the backup metadata to the pre-volume space writing in files in the disk array, write completely if find pre-volume space, owing to can not get new disk space, can only ends file write disk.
(6) judge whether to finish the substep that file content writes: be used for described client and judge that whether use backup metadata is with the complete pre-volume space that writes disk array of file, if "Yes" then stop written document, if "No" then enter " substep that uses backup metadata writing in files ".Write in the process in pre-volume space at file, to constantly detect meta data server and whether recover normal operation, if Metadata Service does not recover normal operation, client can only continue file is write pre-volume space, and when complete file data has write the pre-volume space of disk array, meta data server does not also recover, and the ablation process that then client can't ends file can only stop written document.
(7) again apply for the substep of metadata section to meta data server: be used for client and again apply for metadata to meta data server, the resident space of request.
(8) the synchronous substep of meta data server data: be used for the connectivity that meta data server detects all clients, all data with the client in pre-volume space are processed synchronously, make the data in the pre-volume space move into resident space.After meta data server recovers, if find the client that reconnects pre-volume space is arranged, forbid that then client continues to pre-volume space data writing, and the data that write before the data in the pre-volume of this client space and the meta data server off-line in resident are integrated, then give this client with up-to-date data allocations, make this client continue data are write resident space.Simultaneously meta data server checks that those have pre-volume space but whether the corresponding pre-volume of the client space that is not connected with meta data server has had data newly to write, if discovery new data, forbid that then client is to this pre-volume space data writing, and the relevant position of the data mobile in this pre-volume space in the resident space, to guarantee that data are correct.
(9) substep of teasel root written document: be used for the metadata that described client provides according to meta data server, file write in the resident space of disk array.Meta data server finish corresponding data synchronously after, respective meta-data is sent to client, client is initiated the blocks of data request of file to be written to disk array according to metadata, write to finish these metadata section corresponding blocks data, the circulation the application metadata section and write blocks of data corresponding to metadata section, until finish writing of whole file to be written.
It should be noted that at last, below only unrestricted in order to technical scheme of the present invention to be described, although with reference to the preferred arrangement scheme the present invention is had been described in detail, those of ordinary skill in the art is to be understood that, can make amendment or be equal to replacement technical scheme of the present invention (such as the front and back sequential scheduling of pre-the volume space and set-up mode metadata, step), and not break away from the spirit and scope of technical solution of the present invention.Method of the present invention can be worked out as being applied to the program of computer system, and runs in the computer network system of the present invention.
Claims (3)
1. realize the method for off-line written document in the SAN shared-file system, employed hardware system comprises in the described method: a plurality of clients are connected with the disk array with meta data server by the SAN network of transmitting video files, described a plurality of client is connected with meta data server by the lan network of transmission unit data, and the step of described method is as follows:
The step that opens file: be used for client and send request to meta data server, require to open file to be written in the disk array;
Obtain the step of metadata: be used for client according to the content of file to be written, to the corresponding metadata of meta data server application content to be written, client is obtained respective meta-data, and client accepts to distribute to the chance lock of oneself simultaneously;
It is characterized in that:
Client also will be obtained the metadata in the pre-volume of disk space in described " obtaining the step of metadata " outside normally obtaining the metadata for the treatment of written document;
Judge whether online step of meta data server: be used for judging whether described meta data server normally works online, if "Yes" then enter " step of online writing in files ", if "No" then enter " step of off-line writing in files ";
The step of online writing in files: be used for described client and obtain metadata section, and according to the metadata section that obtains, disk array is initiated the blocks of data request of writing in files, write to finish these metadata section corresponding blocks data, the application metadata section of circulation and write blocks of data corresponding to metadata section, until finish in the resident space that writes disk array of whole file, enter afterwards " step that file writes end "; If meta data server off-line in the file ablation process then enters " step of off-line writing in files ";
The step of off-line writing in files: be used for described client and use the metadata in pre-volume space file to be write the pre-volume space of disk array, whether constantly detect simultaneously meta data server reaches the standard grade, if meta data server is reached the standard grade, then will write in the disk array that the file synchronization in the pre-volume of the disk space sets to meta data server and enter " step that file writes end ", if the pre-volume of disk space is all write full, client still is not communicated with meta data server, then enters " step that file writes end ";
File writes the step of end: be used for client and send requirement to meta data server, close opened writing in files handle, finish this file and write.
2. method according to claim 1 is characterized in that, the metadata of obtaining the pre-volume of disk space in described " obtaining the step of metadata " comprises following substep:
Whether detect the substep whether raw readings is arranged: being used for client has the backup of the metadata in pre-volume space local internal memory or hard disk inspection, if "No" then enter " substep of opening up storage space ", if "Yes" then enter the next son step;
Whether the metadata that detects pre-volume space effectively substep: whether being used for client, to detect the metadata backup in pre-volume space of local internal memory or hard disk effective, if "Yes" then enter " obtain metadata finish substep ", if "No" then enter the next son step;
Open up the substep of storage space: be used for client and open up storage space be used to the metadata of storing pre-volume space at local internal memory or hard disk;
The substep that selection is processed: for client metadata is deposited in request and select to be placed on backstage formation wait or in real time processing, put into the metadata request formation and wait for if the request of then metadata being deposited in is waited on the backstage, if in real time processing then enters the next son step;
Obtain the substep of the metadata in pre-volume space: circulate according to communication rule for client and obtain the whole metadata in pre-volume space to meta data server, as the backup metadata, be kept in the storage space of having opened up according to the self-defining data structure of client;
Obtain the substep that metadata finishes: be used for finishing to obtain metadata.
3. method according to claim 1 and 2 is characterized in that, described " step of off-line writing in files " comprises following substep:
Whether have the substep of the backup metadata in pre-volume space: check for internal memory or the hard disk of client to this locality if detecting client, whether the metadata backup in pre-volume space is arranged, if not then enter " substep that file writes end ", if having then enter the next son step;
Effectively whether the backup that client detects the backup metadata substep: whether being used for client, to detect the metadata in pre-volume space of local internal memory or hard disk effective, if "No" then enter " step that file writes end ", if "Yes" then enter next step;
Use the substep of backup metadata writing in files: be used for client and obtain backup Metadata about metadata section from local internal memory or hard disk, and utilize described metadata section to the disk array writing in files;
Whether the detection client detects the substep that whether is communicated with that is connected with meta data server: be used for client and detect unimpeded with being connected of meta data server, if "No" then enter the next son step, if "Yes" then enter " substep from metadata section to meta data server that again apply for ";
Judge whether pre-volume disk space writes full substep: be used for described client and judge whether the pre-volume space of disk array is write completely, if "Yes" then enter " step that file writes end ", if "No" then enter the next son step;
Judge whether to finish the substep that file content writes: be used for described client and judge that whether use backup metadata is with the complete pre-volume space that writes disk array of file, if "Yes" then stop written document, if "No" then enter " substep that uses backup metadata writing in files ";
Again apply for the substep of metadata section to meta data server: be used for client and again apply for metadata to meta data server, the resident space of request;
The substep that the meta data server data are synchronous: be used for the connectivity that meta data server detects all clients, all data with the client in pre-volume space are processed synchronously, make the data in the pre-volume space move into resident space;
The substep of teasel root written document: be used for the metadata that described client provides according to meta data server, file write in the resident space of disk array.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210587726.0A CN103076994B (en) | 2012-12-31 | 2012-12-31 | The method of off-line written document is realized in a kind of SAN shared-file system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210587726.0A CN103076994B (en) | 2012-12-31 | 2012-12-31 | The method of off-line written document is realized in a kind of SAN shared-file system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103076994A true CN103076994A (en) | 2013-05-01 |
| CN103076994B CN103076994B (en) | 2016-02-03 |
Family
ID=48153534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210587726.0A Expired - Fee Related CN103076994B (en) | 2012-12-31 | 2012-12-31 | The method of off-line written document is realized in a kind of SAN shared-file system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103076994B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202387A (en) * | 2014-08-27 | 2014-12-10 | 华为技术有限公司 | Metadata recovery method and related device |
| CN105512321A (en) * | 2015-12-18 | 2016-04-20 | 浪潮(北京)电子信息产业有限公司 | Method for writing data of storage area networking (SAN) shared-file system and device |
| CN105718484A (en) * | 2014-12-04 | 2016-06-29 | 中兴通讯股份有限公司 | File writing method, file reading method, file deletion method, file query method and client |
| CN111651631A (en) * | 2020-04-28 | 2020-09-11 | 长沙证通云计算有限公司 | High-concurrency video data processing method, electronic equipment, storage medium and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1426006A (en) * | 2001-12-21 | 2003-06-25 | 鸿富锦精密工业（深圳）有限公司 | Distributed case management system and its method |
| US20080177807A1 (en) * | 2007-01-23 | 2008-07-24 | International Business Machines Corporation | Backing-up and restoring files including files referenced with multiple file names |
| CN102546776A (en) * | 2011-12-27 | 2012-07-04 | 北京中科大洋科技发展股份有限公司 | Method for realizing off-line reading files in SAN (Storage Area Networking) shared file system |
-
2012
- 2012-12-31 CN CN201210587726.0A patent/CN103076994B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1426006A (en) * | 2001-12-21 | 2003-06-25 | 鸿富锦精密工业（深圳）有限公司 | Distributed case management system and its method |
| US20080177807A1 (en) * | 2007-01-23 | 2008-07-24 | International Business Machines Corporation | Backing-up and restoring files including files referenced with multiple file names |
| CN102546776A (en) * | 2011-12-27 | 2012-07-04 | 北京中科大洋科技发展股份有限公司 | Method for realizing off-line reading files in SAN (Storage Area Networking) shared file system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104202387A (en) * | 2014-08-27 | 2014-12-10 | 华为技术有限公司 | Metadata recovery method and related device |
| WO2016029744A1 (en) * | 2014-08-27 | 2016-03-03 | 华为技术有限公司 | Metadata recovery method and relevant device |
| CN105718484A (en) * | 2014-12-04 | 2016-06-29 | 中兴通讯股份有限公司 | File writing method, file reading method, file deletion method, file query method and client |
| CN105512321A (en) * | 2015-12-18 | 2016-04-20 | 浪潮(北京)电子信息产业有限公司 | Method for writing data of storage area networking (SAN) shared-file system and device |
| CN111651631A (en) * | 2020-04-28 | 2020-09-11 | 长沙证通云计算有限公司 | High-concurrency video data processing method, electronic equipment, storage medium and system |
| CN111651631B (en) * | 2020-04-28 | 2023-11-28 | 长沙证通云计算有限公司 | High concurrency video data processing method, electronic equipment, storage medium and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103076994B (en) | 2016-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102546776B (en) | Method for realizing off-line reading files in SAN (Storage Area Networking) shared file system | |
| CN106331098B (en) | Server cluster system | |
| CN103699580B (en) | Database synchronization method and device | |
| CN104320401B (en) | A kind of big data storage based on distributed file system accesses system and method | |
| US20130145105A1 (en) | Data Storage Systems and Methods | |
| CN107832138B (en) | Method for realizing flattened high-availability namenode model | |
| CN102833580B (en) | Based on HD video application system and the method for infiniband | |
| CN101964795A (en) | Log collecting system, log collection method and log recycling server | |
| CN106301938A (en) | A kind of high availability and the data base cluster system of strong consistency and node administration method thereof | |
| CN103076994A (en) | Method for realizing off-line file writing in SAN (Storage Area Network) shared-file system | |
| CN105069160A (en) | Autonomous controllable database based high-availability method and architecture | |
| CN103905247B (en) | Two-unit standby method and system based on multi-client judgment | |
| CN103795801A (en) | Metadata group design method based on real-time application group | |
| CN101771548A (en) | File synchronizing method and system | |
| CN106603319A (en) | Fault processing method, management server, and logic server | |
| CN106850255A (en) | A kind of implementation method of multi-computer back-up | |
| CN107995318A (en) | A kind of high-availability system of network cloud disk | |
| CN104298574A (en) | Data high-speed storage processing system | |
| CN109739690A (en) | Backup method and Related product | |
| CN106095959A (en) | A kind of collecting method, Apparatus and system | |
| CN105828017A (en) | Cloud storage access system and method for video conferences | |
| CN114357252A (en) | Storage method, system and storage medium of cross-source multi-domain distributed data | |
| CN103067418A (en) | Method, device and system for reconstructing metadata | |
| CN107291387B (en) | A kind of disk cut-in method of double control disk array | |
| CN103384267A (en) | Parastor200 parallel storage management node high availability method based on distributed block 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 | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160203 Termination date: 20201231 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |