CN108241553B - Data backup control method - Google Patents
Data backup control method Download PDFInfo
- Publication number
- CN108241553B CN108241553B CN201611209486.5A CN201611209486A CN108241553B CN 108241553 B CN108241553 B CN 108241553B CN 201611209486 A CN201611209486 A CN 201611209486A CN 108241553 B CN108241553 B CN 108241553B
- Authority
- CN
- China
- Prior art keywords
- backup
- data
- client
- file
- area
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a data backup control method, which comprises the following steps: the client performs partition processing on the local file according to a data backup strategy provided by the control platform, and sends data of each partitioned area to a backup node calculated based on the data backup strategy; when a fault occurs, carrying out data restoration on the fault client according to the area data stored in the selected backup node; the method can perform adaptive backup according to the type of the fault, and only the backup data with high correctness is selected for data restoration in consideration of the correctness of the backup data when the backup data is restored; and the data protection (restoration) speed can be improved, and the data restoration time is reduced.
Description
[ technical field ] A method for producing a semiconductor device
The invention belongs to the field of data processing, and particularly relates to a data backup control method.
[ background of the invention ]
With the popularization of computers in various industries, a large amount of data is stored by the computers, which puts higher requirements on data backup technology, especially on the aspects of high availability and safety of mass data. For some important systems, it is required to implement real data disaster recovery protection to avoid the irreparable consequences of data caused by system failure, user misoperation, unexpected events, etc., so that it is more and more important to protect high availability and security of data.
In the prior art, backup data is generally used for data recovery of a failed disk (including hardware failure and software failure). When the failure of the disk is a software failure (such as a false deletion), all data of the backup disk still needs to be restored to the primary disk, which causes the restoration process of the data to take a lot of time, and the data protection (restoration) speed is slow, which cannot meet the requirement of the user. Based on the above problems, there is a need for a new data backup control method, which can perform adaptive backup according to the type of failure, and can select only backup data with high accuracy for data recovery in consideration of the accuracy of the backup data when recovering the backup data; and the data protection (restoration) speed can be improved, and the data restoration time is reduced.
[ summary of the invention ]
In order to solve the above problems in the prior art, the invention adopts the following technical scheme: a data backup control method is characterized by comprising the following steps:
step 1: the client performs partition processing on the local file according to a data backup strategy provided by the control platform, and sends data of each partitioned area to a backup node calculated based on the data backup strategy; wherein: a plurality of backup nodes store a plurality of backups for the same area data; the multiple backups for the same area data are stored in different positions of the multiple backup nodes; the zone data of a plurality of different clients are stored at different positions of the same backup node or different positions of different backup nodes;
step 2: when a fault occurs, selecting a backup node with high correctness, and performing data recovery on the fault client according to the area data stored in the selected backup node; in the data recovery, different area data are transmitted to different physical positions of the client through different backup node ports; the reduction of the data of the different zones takes place in parallel;
further, the data backup strategy comprises a file partition strategy and a backup node calculation strategy; according to the backup node calculation strategy, the number of backup nodes to which different zone data can be backed up and the number of a plurality of backup nodes to which the same zone data can be backed up can be calculated.
Further, multiple clients may initiate data backup requests simultaneously, which may be in parallel since the partition process is performed locally.
Further, the zone data of different clients are stored at different positions in the backup node, and the backup node can ensure that the zone data are not overlapped during backup.
Further, when the size of the same area data exceeds the size of the available space of one allocated backup node, the area data is abandoned to be saved in the backup node, and when the size of the same area data exceeds the size of the available space of all allocated backup nodes, the control platform is requested to allocate the backup node to which the area data is to be backed up again.
Further, when the client performs file partitioning, the difference value between the partitioned area data size and the control platform preset area size needs to be within a first error range, and the preset area size value is updated in real time according to the running state of the backup node.
Further, the plurality of clients are independent, and the independence comprises physical independence and/or virtual independence.
Further, when the type of the fault is not a hardware fault, the client selects the time for restoring the data and whether to accept the restoration of the data.
Further, the client selects a data restoring time, specifically: and selecting the time for restoring the data when the failure range and the failure importance degree exceed the set value.
Further, the client may log in the control center to manage the backup data, where the management includes: viewing, editing, deleting, adding, and incrementally modifying.
The beneficial effects of the invention include: the method can perform adaptive backup according to the type of the fault, and can only select backup data with high correctness for data restoration by considering the correctness of the backup data when restoring the backup data; and the data protection (restoration) speed can be improved, and the data restoration time is reduced.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, and are not to be considered limiting of the invention, in which:
fig. 1 is a flowchart of a data backup control method of the present invention.
Fig. 2 is a block diagram of a data backup control system of the present invention.
[ detailed description ] embodiments
The present invention will now be described in detail with reference to the drawings and specific embodiments, wherein the exemplary embodiments and descriptions are provided only for the purpose of illustrating the present invention and are not to be construed as limiting the present invention.
Referring to fig. 1, the basic steps of a data backup control method of the present invention are shown:
step 1: the client performs partition processing on the local file according to a data backup strategy provided by the control platform, and sends data of each partitioned area to a backup node calculated based on the data backup strategy; wherein: a plurality of backup nodes store a plurality of backups for the same area data; the multiple backups for the same area data are stored in different positions of the multiple backup nodes; the zone data of a plurality of different clients are stored at different positions of the same backup node or different positions of different backup nodes;
step 2: when a fault occurs, selecting a backup node with high correctness, and performing data recovery on the fault client according to the area data stored in the selected backup node; in the data recovery, different area data are transmitted to different physical positions of the client through different backup node ports; the reduction of the data of the different zones takes place in parallel;
referring to fig. 2, the present invention is a data backup control system, which includes a plurality of clients, a plurality of backup nodes, and a control platform, under the control of the control platform, storing file data in the clients into one or more backup nodes; the client, the backup node and the control platform are in communication connection;
based on the above system, a data backup control method of the present invention is described in detail below:
(1) a client sends a backup request to a control platform, wherein the request carries the number n of files to be backed up by the client, the average size FS of the files and a client identification ID;
the client periodically sends a backup request in an idle time zone or before initiating important data operation;
the client can select files needing to be backed up, and the mode needing to be backed up is selected to be incremental or full.
(2) The control platform receives the backup request, determines and sends a partition strategy to the request client according to the available condition of the storage resources of the current backup node; the partition strategy comprises a current partition reference value Z and a partition file redundancy part reference value R;
specifically, the method comprises the following steps: acquiring a priority PR of the client from a corresponding table between the client identification ID and the client priority PR which are prestored locally according to the client identification ID;
calculating a file partition reference value Z according to formula (1) based on the priority PR and the average file size FS; considering that when the size of a file is large, the file should be allocated to different backup nodes as much as possible to improve the reduction speed of the file, and meanwhile, when the priority of a client is high, the file is allocated to a plurality of backup nodes to improve the reduction speed of the file, so that a high-priority user can better experience the reduction;
maximum value Z of reference value of divisionmaxCalculating according to a formula (3);
Zmax=FS×n/∑(CP/NM)×Rmaxxw formula (3)
Wherein, CP is the available space size of a backup node, and sigma (CP/NM) is the average available space size of all available backup nodes; NM is the total number of available backup nodes; rmaxThe maximum redundancy number, w, is an adjustment coefficient, and can be preset by the control platform according to the current backup node operation status, and the backup node operation status includes: backup nodes available computing resources, available ports, available storage resources; when the redundancy number is too large, the client cannot provide enough ports for parallel restoration, and the security cannot be improved any more, so that the R can be set empiricallymaxA value;
the redundancy number reference value R is set by the control platform according to the number of the current available backup nodes or the total number of the backup nodes in the system; r is dynamically adjustable;
(3) the client partitions the file according to the file partition reference value Z and calculates the area LjRedundant number of copies R ofj(ii) a Specifically, the method comprises the following steps: the data of the client is sequentially numbered by taking the file as an organization unit; the files numbered sequentially are: f1,F2,···,Fi,···,Fn(ii) a Wherein n is the total number of files of the client; divide n files into Z zone files, L1,L2···,Lj,···LZ(ii) a Wherein: fiWill be allocated to the region LimodZPerforming the following steps; calculating region L according to equation (2)jRedundant number of copies R ofjWherein NLjIs region LjNumber of files in, FPRjK is the region LjK-th file L in (1)jK File priority, FPRmaxIs the highest file priority;
the file priority can be set by the client according to the importance degree of the file; or can be set by the control platform after submitting the basic information of the file; FPRmaxThe priority of the highest file is uniformly set by the control platform; the preset number is preset by the control platform;
storing the file number, the physical position of the file at the client (the initial position of file storage), the area where the file is located and the position of the file in the area in a file and area comparison table in a related manner; storing the area, the file number contained in the area and the position of the file in the area in an area directory table;
preferably: numbering according to the front and back sequence of the physical position of the file at the client;
(4) the control platform calculates a backup node set S corresponding to each zonej,Sz+j···,SRj(ii) a Wherein S is a backup nodeThe number of the point; specifically, the method comprises the following steps: calculating the communication cost C from all the backup nodes to the client ID, sorting the communication cost from small to large, and selecting the first Z backup nodes from the communication cost C to form a first backup node group { S }1,S2,···Sj,···Sz}; continuously selecting a second backup node group { S } from the Z +1 th backup nodez+1,Sz+2,···Sz+j,···Sz+zIf zone LjRedundant number of copies R ofjLess than 2, then Sz+ j ═ 0, meaning that no backup node was selected; similarly, the next backup node group is continuously selected until the number of the backup node groups is larger than the FPRmaxXr, or until all backup nodes are assigned; similarly, if the current allocation has exceeded zone LjRedundant number of copies R ofjIf yes, setting the corresponding backup node distribution number as 0, and indicating that no backup node is selected; zone file LjThe corresponding set of backup nodes is set to { Sj,Sz+j···,SRj(if the backup node is allocated, the number of allocated backup nodes is less than RjOne);
considering that the reduction speed is high under the condition of low communication overhead, the backup node with the minimum communication overhead is preferentially selected for each zone file to carry out zone backup; selecting more backup nodes for the areas with more redundancy parts for backup;
(5) the client end sequentially sends the data to each zone LjCorresponding backup node set Sj,Sz+j···,SRjCarrying out zone backup; the method specifically comprises the following steps: from L1Starting at LZFor each LjFirst towards LjThe first backup node S in the corresponding set of backup nodesjSending a backup request, backing up the zone files, and sending LjAll files contained in it are backed up to the backup node SjPerforming the following steps; then to Lj+1The first backup node S in the corresponding set of backup nodesj+1Sending a backup request, backing up the zone data, and storing the zone Lj+1All files contained in it are backed up to the backup node Sj+1Performing the following steps; until the first backup node in the backup node set corresponding to all the zones is backed up; then start for each LjCompleting the backup to the second backup node in the corresponding backup node set, specifically: to LjThe second backup node S in the corresponding set of backup nodesz+jSending a backup request, backing up the zone files, and sending LjAll files contained in it are backed up to the backup node Sz+jPerforming the following steps; until the second backup nodes in the backup node sets corresponding to all the zones are backed up; performing backup according to the mode until the backup of each backup node in all backup node sets corresponding to all the zones is completed; wherein, if the backup node number is 0, it represents the zone LjAfter the corresponding redundant copies are completely backed up, skipping the direct processing of the backup of the next backup node;
backing up all files contained in one area to one backup node, specifically: will be zone LjAll files contained in it are saved to the backup node SjThe corresponding relation between the Lj and the storage position is stored in the appropriate available space; the method also comprises the step of selecting a proper available space, which specifically comprises the following steps: searching backup node SjThe size of all available space in (1), calculate LjSize, selection and LjThe available space with the closest size is used as the suitable available space; less than L in all available spacesjAt the time of L, thejPartitioning is carried out, and L isjPartitioning according to the size of the available space from large to small until the size of the residual area does not need partitioning any more, and respectively storing the partitions into the available spaces with corresponding sizes, wherein the available spaces with corresponding sizes are suitable available spaces; preservation of LjThe block of (a) and the appropriate available spatial locations; preferably: the corresponding relation can be stored in the backup node SjOr stored in the control platform; preferably: will be zone LjOr region LjThe partition of (a) is saved at the start position of the appropriate available space;
(6) the control platform monitors the running state of each client in real time, and when the client fails, the control platform restores the data of the failed client according to the data stored in the backup node;
specifically, the method comprises the following steps: judging the fault type of the client, if the fault type is a local fault, determining the number of the file with the fault, searching the file and the area comparison table to obtain the area L where the fault file is locatedjWill be zone LjAll the files in (1) are restored; if the fault is a global fault, sequentially carrying out L treatment on each zone in all zones of the clientjWill be zone LjAll the files in (1) are restored;
determining a local fault, specifically: determining the number of the files with faults, and determining the files as local faults when the number of the files with faults exceeds a first preset number or the number of the files with faults higher than the specified priority contained in the files with faults is higher than a second preset number; otherwise, continuing to keep the operation of the client without restoring; because each restoration requires little time and space overhead, the local fault is considered only when the fault reaches a certain degree;
determining a global fault, specifically: determining that the number of the files with faults exceeds a third preset number or the client has hardware faults, and determining that the files with the faults are global faults;
wherein the region LjAll the files in (1) are restored, and the method specifically comprises the following steps: acquisition region LjSet of all backup nodes Sj,Sz+j···,SRjAcquiring the port number NP of a fault client, and selecting NP backup nodes from all backup node sets for the backup; the NP backup nodes are: a first backup node, a second backup node, ·, an NP backup node; establishing binding relationship between NP backup nodes and NP ports of client, making NP backup nodes to be contained in L area of client through NP portsjThe files in (1) are restored in parallel;
selecting NP backup nodes from all the backup node sets for the backup, specifically: for each backup node in all backup node sets, saved zone LjCalculate the region LjCalculating the average value of all data signature values; calculating the saved area L in each backup nodejSelecting NP backup nodes corresponding to the front NP data signatures with the minimum distance as the selected NP backup nodes;
because the data stored in the backup node may also be in error, the correctness of the data stored in the backup node needs to be checked, and the backup node with high correctness is selected for restoration;
the NP backup nodes are led to the client-side contained area L through the NP portsjThe parallel reduction of the files in the method comprises the following specific steps: having each different one of the NP backup nodes store L while taking into account communication overheadjBackup pair LjRestoring different contained files; preferably: obtaining the physical position of the file at the client by searching the file and the area comparison table, and restoring the file to the stored physical position; in this way, the file can be restored to the original position at the same time of file restoration; lookup region directory Table acquisition LjThe file size information is obtained from all the files contained in the file list, the files are sequenced from large to small, the communication cost C between the NP backup nodes and the client is obtained, and the files are distributed to the backup nodes with the communication cost sequenced from small to large from large in sequence for restoration; by balancing the size and the communication overhead, the progress speeds of the files which are restored in parallel can be kept approximately consistent, and the occurrence of short-board conditions is avoided;
establishing a binding relationship between the NP backup nodes and NP ports of the client, which specifically comprises the following steps: under the control of the control platform, each backup node in the NP backup nodes respectively establishes a binding relationship with each of the NP ports, and after the binding relationship is established, the backup nodes actively carry out data restoration and store the stored data into the corresponding position of the client;
preferably: the NP ports of the client are provided independent ports of a plurality of physical devices contained in the client;
the data backup control method can perform adaptive backup according to the type of the fault, and only select backup data with high correctness for data recovery by considering the correctness of the backup data when the backup data is recovered; and the data protection (restoration) speed can be improved, and the data restoration time is reduced.
The above description is only a preferred embodiment of the present invention, and all equivalent changes or modifications of the structure, characteristics and principles described in the present invention are included in the scope of the present invention.
Claims (3)
1. A data backup control method is characterized by comprising the following steps:
step 1: the client performs partition processing on the local file according to a data backup strategy provided by the control platform, and sends data of each partitioned area to a backup node calculated based on the data backup strategy; wherein: a plurality of backup nodes store a plurality of backups for the same area data; the multiple backups for the same area data are stored in different positions of the multiple backup nodes; the zone data of a plurality of different clients are stored at different positions of the same backup node or different positions of different backup nodes;
step 2: when a fault occurs, selecting a backup node with high correctness, and performing data recovery on the fault client according to the area data stored in the selected backup node; in the data recovery, different area data are transmitted to different physical positions of the client through different backup node ports; the reduction of the data of the different zones takes place in parallel; the zone data of different clients are stored at different positions in the backup node, and the backup node ensures that the zone data are not overlapped during backup;
when the size of the data in the same area exceeds the size of the available space of one allocated backup node, the data in the area is abandoned to be saved in the backup node, and when the size of the data in the same area exceeds the size of the available space of all the allocated backup nodes, the control platform is requested to allocate the backup node of which the data in the area is to be backed up again; when a client partitions a file, the difference value between the partitioned area data size and the control platform preset area size needs to be within a first error range; the size value of the control platform preset area is updated in real time according to the running state of the backup node;
the plurality of clients are independent, and the independence comprises physical independence and/or virtual independence;
when the type of the fault is not a hardware fault, the client needs to select the time for data recovery and whether to accept the data recovery;
the time for selecting the data restoration by the client comprises the following steps: selecting the time for restoring the data when the fault range and the importance degree of the fault exceed the set values;
the client can log in the control center to manage the backup data, and the management comprises the following steps: viewing, editing, deleting, adding and modifying in increments;
the data backup control method further comprises:
(1) a client sends a backup request to a control platform, wherein the request carries the number n of files to be backed up by the client, the average size FS of the files and a client identification ID;
the client periodically sends a backup request in an idle time zone or before initiating important data operation;
the client can select files to be backed up, and the mode to be backed up is selected to be increment or full;
(2) the control platform receives the backup request, determines and sends a partition strategy to the request client according to the available condition of the storage resources of the current backup node; the partition strategy comprises a current partition reference value Z and a partition file redundancy part reference value R;
acquiring a priority PR of the client from a corresponding table between the client identification ID and the client priority PR which are prestored locally according to the client identification ID;
calculating a file partition reference value Z according to formula (1) based on the priority PR and the average file size FS;
maximum value Z of reference value of divisionmaxCalculating according to a formula (3);
Zmax=FS×n/∑(CP/NM)×Rmaxx w formula (3)
Wherein, CP is the available space size of a backup node, and sigma (CP/NM) is the average available space size of the available backup node; NM is the total number of available backup nodes; rmaxThe maximum redundancy number, w, is an adjustment coefficient, and can be preset by the control platform according to the current backup node operation status, and the backup node operation status includes: backup nodes available computing resources, available ports, available storage resources; when the redundancy number is too large, the client cannot provide enough ports for parallel restoration, and the security cannot be improved any more, so that the R can be set empiricallymaxA value;
the redundancy number reference value R is set by the control platform according to the number of the current available backup nodes or the total number of the backup nodes in the system; r is dynamically adjustable;
(3) the client partitions the file according to the file partition reference value Z and calculates the area LjRedundant number of copies R ofj(ii) a Specifically, the method comprises the following steps: the data of the client is sequentially numbered by taking the file as an organization unit; the files numbered sequentially are: f1,F2,···,Fi,···,Fn(ii) a Wherein n is the total number of files of the client; divide n files into Z zone files, L1,L2···,Lj,···LZ(ii) a Wherein: fiWill be allocated to the region Li mod ZPerforming the following steps; calculating region L according to equation (2)jRedundant number of copies R ofjIn which N isLjIs region LjNumber of files in, FPRjK is the region LjK-th file L in (1)jK File priority, FPRmaxIs the highest file priority;
the file priority can be set by the client according to the importance degree of the file; or can be set by the control platform after submitting the basic information of the file; FPRmaxThe priority of the highest file is uniformly set by the control platform; the preset number is preset by the control platform;
storing the file number, the physical position of the file at the client, the area where the file is located and the position of the file in the area in a file and area comparison table in a related manner; storing the area, the file number contained in the area and the position of the file in the area in an area directory table;
the files are numbered in the sequence from the front to the back of the physical location of the client.
2. The data backup control method according to claim 1, wherein the data backup policy includes a file partition policy and a backup node calculation policy; according to the backup node calculation strategy, the number of backup nodes to which different zone data can be backed up and the number of a plurality of backup nodes to which the same zone data can be backed up can be calculated.
3. The data backup control method according to any one of claims 1 to 2, characterized in that a plurality of clients can simultaneously initiate a data backup request, and the data backup can be parallel since the partition processing is performed locally.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611209486.5A CN108241553B (en) | 2016-12-23 | 2016-12-23 | Data backup control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611209486.5A CN108241553B (en) | 2016-12-23 | 2016-12-23 | Data backup control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108241553A CN108241553A (en) | 2018-07-03 |
CN108241553B true CN108241553B (en) | 2022-04-08 |
Family
ID=62704416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611209486.5A Active CN108241553B (en) | 2016-12-23 | 2016-12-23 | Data backup control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108241553B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111221678B (en) * | 2018-11-27 | 2023-04-11 | 阿里巴巴集团控股有限公司 | Hbase data backup/recovery system, method and device and electronic equipment |
CN111752756B (en) * | 2020-06-24 | 2021-02-19 | 厦门靠谱云股份有限公司 | Method for setting database backup strategy through autonomous learning |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101295299A (en) * | 2007-04-26 | 2008-10-29 | 王霞 | Distributed storage method of wireless radio frequency identification data |
CN101630282A (en) * | 2009-07-29 | 2010-01-20 | 国网电力科学研究院 | Data backup method based on Erasure coding and copying technology |
CN102169453A (en) * | 2011-03-08 | 2011-08-31 | 杭州电子科技大学 | File online backup method |
CN103067525A (en) * | 2013-01-18 | 2013-04-24 | 广东工业大学 | Cloud storage data backup method based on characteristic codes |
WO2014069007A1 (en) * | 2012-10-30 | 2014-05-08 | 株式会社 東芝 | Storage device and data backup method |
CN104618153A (en) * | 2015-01-20 | 2015-05-13 | 北京大学 | Dynamic fault-tolerant method and dynamic fault-tolerant system based on P2P in distributed parallel graph processing |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102187127B1 (en) * | 2013-12-03 | 2020-12-04 | 삼성전자주식회사 | Deduplication method using data association and system thereof |
CN104331346B (en) * | 2014-11-21 | 2017-08-25 | 四川神琥科技有限公司 | A kind of data guard method |
CN105718221B (en) * | 2016-01-22 | 2018-09-21 | 华为技术有限公司 | A kind of methods, devices and systems of data storage |
-
2016
- 2016-12-23 CN CN201611209486.5A patent/CN108241553B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101295299A (en) * | 2007-04-26 | 2008-10-29 | 王霞 | Distributed storage method of wireless radio frequency identification data |
CN101630282A (en) * | 2009-07-29 | 2010-01-20 | 国网电力科学研究院 | Data backup method based on Erasure coding and copying technology |
CN102169453A (en) * | 2011-03-08 | 2011-08-31 | 杭州电子科技大学 | File online backup method |
WO2014069007A1 (en) * | 2012-10-30 | 2014-05-08 | 株式会社 東芝 | Storage device and data backup method |
CN103067525A (en) * | 2013-01-18 | 2013-04-24 | 广东工业大学 | Cloud storage data backup method based on characteristic codes |
CN104618153A (en) * | 2015-01-20 | 2015-05-13 | 北京大学 | Dynamic fault-tolerant method and dynamic fault-tolerant system based on P2P in distributed parallel graph processing |
Non-Patent Citations (1)
Title |
---|
D-SQL分布式数据库系统的启动与恢复;罗朝劲;《中国优秀硕士学位论文全文数据库 信息科技辑》;20021215(第2期);正文第1-3页 * |
Also Published As
Publication number | Publication date |
---|---|
CN108241553A (en) | 2018-07-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10922191B2 (en) | Virtual proxy based backup | |
US10915397B2 (en) | Data storage method, apparatus, and system | |
US10019192B2 (en) | Policy-based hierarchical data protection in distributed storage | |
US9773015B2 (en) | Dynamically varying the number of database replicas | |
CN110445822B (en) | Object storage method and device | |
RU2449358C1 (en) | Distributed file system and data block consistency managing method thereof | |
US7689764B1 (en) | Network routing of data based on content thereof | |
CN105406980A (en) | Multi-node backup method and multi-node backup device | |
EP1516252A2 (en) | Business continuation policy for server consolidation environment | |
US9501544B1 (en) | Federated backup of cluster shared volumes | |
CN108241553B (en) | Data backup control method | |
CN106899654A (en) | A kind of sequence value generation method, apparatus and system | |
CN112988065B (en) | Data migration method, device, equipment and storage medium | |
US8458509B1 (en) | Multipath failover | |
JP2007520003A (en) | A method for manipulating multiple computer arrays in the event of a computer failure | |
CN109408299A (en) | Data processing method, device, equipment and the storage medium of three controller clusters | |
US20200089575A1 (en) | Dynamic prioritized recovery | |
CN107943615B (en) | Data processing method and system based on distributed cluster | |
CN111309260B (en) | Data storage node selection method | |
CN108241544B (en) | Fault processing method based on clusters | |
US20220100619A1 (en) | Computer cluster using expiring recovery rules | |
CN106844487B (en) | A kind of distributed memory system replicated based on library | |
CN108241552B (en) | Client file recovery method | |
CN110535898B (en) | Method for storing and complementing copies and selecting nodes in big data storage and management system | |
CN110532135B (en) | Service migration method, system, equipment and storage medium of cluster system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information |
Address after: 101399 No. 2 East Airport Road, Shunyi Airport Economic Core Area, Beijing (1st, 5th and 7th floors of Industrial Park 1A-4) Applicant after: Zhongke Star Map Co., Ltd. Address before: 101399 Building 1A-4, National Geographic Information Technology Industrial Park, Guomen Business District, Shunyi District, Beijing Applicant before: Space Star Technology (Beijing) Co., Ltd. |
|
CB02 | Change of applicant information | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |