CN101184104A - Distributed memory system and method - Google Patents
Distributed memory system and method Download PDFInfo
- Publication number
- CN101184104A CN101184104A CNA2007101254255A CN200710125425A CN101184104A CN 101184104 A CN101184104 A CN 101184104A CN A2007101254255 A CNA2007101254255 A CN A2007101254255A CN 200710125425 A CN200710125425 A CN 200710125425A CN 101184104 A CN101184104 A CN 101184104A
- Authority
- CN
- China
- Prior art keywords
- data
- data block
- group
- online
- stored
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a distributed storage system, which comprises: a group maintenance unit, which is used for creating a group through a group management server, wherein the group is composed of a plurality of members, and the group management server stores the information of the group members; a data release unit, which is used for transforming the storing data into a plurality of data blocks, and storing the data blocks into a plurality of on-line members of the group, as well as storing the distributed information of the data blocks to the group management server. The invention also discloses a distributed storage method. The invention can lower the system complexity of the distributed storage system and enhance the availability, fault tolerance and efficiency of the system by adding the connectivity between the storage nodes.
Description
Technical field
The present invention relates to the network data field of storage, more particularly, relate to a kind of distributed memory system and method based on group.
Background technology
In recent years, P2P (peer-to-peer) technology has all demonstrated great advantage in applications such as instant messaging, file-sharing and Streaming Media transmission, becomes one of the primary structure that makes up the novel large-scale internet, applications and technology.And the P2P storage system is considered to one of the most promising application.
The P2P storage system also is reciprocity storage system, is meant the storage networking that memory node is formed in a kind of mode of function equity.For example the encrypted file system of Massachusetts Polytechnics (Cryptographic Filesystem, CFS).This structure is corresponding with the focus control mode of traditional client/server.The large-scale stores service that it both can be used for organizing specialty also can be used for organizing unused tabletop machine resource to form the storage networking of helping each other.In the P2P storage system, by the availability and the fault-tolerance of technique guarantee systems such as many copies redundancy (for example complete copy redundancy and correcting and eleting codes redundancy etc.) and dynamic reparation.
Because adopt the technology of peerings, the P2P storage system has been compared following advantage with traditional storage system: do not rely on central authorities' control, system has high scalability naturally, and does not have single-point performance bottleneck problem; Each nodal function equity makes that whole system still can operate as normal behind the disappearance arbitrary node, and high fault tolerance is also promptly arranged.High scalability and high fault tolerance and then make that utilize a cheap group of planes to build extensive high-performance stores service becomes possibility.
Though there is inherent high fault-tolerant ability in the P2P system, because the viscosity between the node is low in the P2P storage system, each node all may the temporary transient or permanent system of leaving.Though used technology such as the redundant and dynamic reparation of many copies, still can not eliminate the adverse consequences that data failure brings fully.In addition, because in the P2P storage system, storage is on each node that is distributed widely in all over the world, and is transparent because which node storage data is this system use to the user, need the user of data often not to be familiar with the node users of storing data, when not having enough copy amounts to come recovery of stored data, can't reach the standard grade by the node that other approach notice has data data are provided.
Summary of the invention
The technical problem to be solved in the present invention is, the problem at can't restore data because node leaves system in the above-mentioned P2P storage system provides a kind of distributed memory system and method based on group.
The technical scheme that the present invention solves the problems of the technologies described above is, a kind of distributed memory system is provided, and comprising:
Group's maintenance unit is used for creating group by the management and group server, and described group comprises a plurality of members, and described management and group server stores has the information of described group member;
The data release unit, being used for data conversion to be stored is a plurality of data blocks, stores described a plurality of data blocks in the group a plurality of online members respectively, and stores the distributed intelligence of described a plurality of data blocks into described management and group server.
In a kind of distributed memory system of the present invention, described data release unit comprises:
The cutting subelement, being used for data cutting to be stored is m part, wherein m is the integer greater than 1;
The coding subelement is used for by encryption algorithm described m part being encoded to n data block, and any m in the described n data block can revert to described data to be stored, and wherein n is the integer greater than 1, and n＞m, and n＜N, described N are the group member sum;
Distribute subelement, be used for described n data block mean allocation given k online member of group, and the distributed intelligence of data block is sent to the management and group server stores.
In a kind of distributed memory system of the present invention, also comprise:
The distributed intelligence acquiring unit is used for the distributed intelligence of obtaining a plurality of data blocks of data from described management and group server;
Recover judging unit, be used for distributed intelligence, judge that online member's data blocks stored whether can restore data according to described a plurality of data blocks;
Member's notification unit is used for when described recovery judging unit confirms that online member's data blocks stored can not recover data blocks, and the not online member who stores described data block by the Short Message Service Gateway notice reaches the standard grade;
Data recovery unit is used for when described recovery judging unit confirms that online member's data blocks stored can recover data blocks, from described online member's downloading data block, and recovers described data to be stored according to described data downloaded piece.
In a kind of distributed memory system of the present invention, can whether described recovery judging unit recover less than m judgment data piece by the online number of members that judgement stores described data block, and described recovery judging unit confirms that at the online number of members that stores described data block data block can not recover, confirm that at the online number of members that stores described data block data block can recover during more than or equal to m during less than m.
In a kind of distributed memory system of the present invention, described data recovery unit comprises:
The data block count subelement is used to judge and whether downloads successful data block quantity less than m;
Download the notice subelement, be used for confirming to download successful data block quantity less than m and the not online member who waits to have data block when reaching the standard grade, notify from described member's downloading data block of reaching the standard grade in described database count sub-element;
Coding is gone back atomic unit, is used for when described database count sub-element confirms that the successful data block of download equals m a described m data block being reverted to data to be stored.
In a kind of distributed memory system of the present invention, also comprise a data block dump unit, be used for when group member withdraws from group the data block store of group member other online member in the group.
The present invention also provides a kind of distributed storage method, comprising:
(a) create group by the management and group server, described group comprises a plurality of members, and described management and group server stores has the information of described group member;
(b) be a plurality of data blocks with data conversion to be stored, store described a plurality of data blocks in the group a plurality of online members respectively, and store the distributed intelligence of described a plurality of data blocks into described management and group server.
In a kind of distributed storage method of the present invention, the member of described group adds up to N, and wherein N is the integer greater than 1, and described step (b) comprising:
(b1) be m part with data cutting to be stored, wherein m is the integer greater than 1
(b2) by encryption algorithm described m part is encoded to n data block, any m in the described n data block can revert to described data to be stored, and wherein n is the integer greater than 1, and n＞m, n＜N;
(b3) described n data block mean allocation given online member in the group, and the distributed intelligence of data block is sent to the management and group server stores.
In a kind of distributed storage method of the present invention, also comprise:
(c) obtain the distributed intelligence of a plurality of data blocks of data from the management and group server;
(d) according to the distributed intelligence of described a plurality of data blocks, judge that online member's data blocks stored whether can restore data, if can recover, execution in step (f) then, otherwise execution in step (e);
(e) notify the not online member who stores described data block to reach the standard grade by Short Message Service Gateway, return step (d) then;
(f) recover data to be stored from described online member's downloading data block, and according to described data block.
In a kind of distributed storage method of the present invention, can whether the online number of members that stores described data block by judgement in the described step (d) recover less than m judgment data piece, confirms that at the online number of members that stores described data block data block can not recover, confirm that at the online number of members that stores described data block data block can recover during more than or equal to m during less than m.
In a kind of distributed storage method of the present invention, described step (f) comprising:
(f1), and whether judge to download successful data block quantity less than m from described online member's downloading data block, as if less than m, execution in step (f2) then, otherwise execution in step (f3);
(f2) wait for that the not online member have data block reaches the standard grade, and after obtaining the notification message that the member reaches the standard grade execution in step (f1);
(f3) a described m data block is reverted to data to be stored.
A kind of distributed memory system of the present invention and method, by with storage to be stored to group member, thereby increased viscosity between memory node, reduced the system complexity of distributed memory system.In addition, the present invention reaches the standard grade by the member who uses communication system notice storage data, can improve availability, fault-tolerance and the efficient of system.
Description of drawings
The invention will be further described below in conjunction with drawings and Examples, in the accompanying drawing:
Fig. 1 is the application architecture figure of a kind of distributed memory system embodiment of the present invention;
Fig. 2 is the structured flowchart of a kind of distributed memory system embodiment of the present invention;
Fig. 3 is the structured flowchart of the embodiment of data release unit among Fig. 2;
Fig. 4 is the structural representation of a kind of another embodiment of distributed memory system of the present invention;
Fig. 5 is the structured flowchart of the embodiment of data recovery unit among Fig. 4;
Fig. 6 is the flow chart of a kind of distributed storage method embodiment of the present invention;
Fig. 7 is the flow chart of the embodiment of storage step among Fig. 6;
Fig. 8 is the flow chart of a kind of another embodiment of distributed storage method of the present invention.
Embodiment
As shown in Figure 1, be the application architecture figure of a kind of distributed memory system embodiment of the present invention.This system applies is in the group that is made up of client 12, and wherein a plurality of clients 12 are connected respectively to the Internet 11.This group carries out maintenance and management by the management and group server that is connected to the Internet 11, and each client 12 in the group is a member of group.In addition, this system also sends SMS message to mobile phone terminal 16 by Short Message Service Gateway 14 and wireless base station 15, reaches the standard grade to notify not on-line client 12.Wherein management and group server 13 is set up by enterprise or user's (also can be provided by the Internet service merchant), and Short Message Service Gateway 14, wireless base station 16 and mobile phone terminal 16 are parts of existing mobile communication system.
Management and group server 13 carries out user's registration, authentification of user, sets up group, adds group, withdraws from group etc. and operation such as administer and maintain according to the request of client 12, and storage group relevant information, for example announcement information in group member information, the group etc.When the user registers by each client 12, obtain username and password, and fill in the contact methods such as phone number of oneself, management and group server 13 is recorded in these information in its database.In the present embodiment, this management and group server 13 when realizing can with existing instant messaging (IM) server category seemingly.
In the present embodiment, directly link to each other by the Internet 11 between each client 12, be used to transmit data and control information.A communicating control information between client 12 and the management and group server 13 does not transmit actual file data.
As shown in Figure 2, be the schematic diagram of a kind of distributed memory system embodiment of the present invention, this system comprises group's maintenance unit 21, the data release unit 22 that is positioned at client 12.
Group's maintenance unit 21 is used to create group, and this group comprises a plurality of members.Can be after the user logins by client 12 by the request of group's maintenance unit 21 to management and group server 13 transmission establishment groups, if group creating is successful, then this user promptly becomes group master; Certainly also can send the request that adds group to management and group server 13, to become group member by this group's maintenance unit 21.In the present embodiment, this group's maintenance unit 21 is similar to existing instant communication instrument client terminal.
It is a plurality of data blocks that data release unit 22 is used for data conversion to be stored, and should a plurality of data blocks store a plurality of online members in the group respectively into, and management and group server 13 is stored in distributed intelligence that simultaneously will these a plurality of data blocks into.
In addition, said system also can comprise data block store unit (not shown), be used for when receiving the data block that other user sends (can for a plurality of), with data block store to local disk.Especially, this data block store unit in the data block of its distribution greater than 1 o'clock, judge whether it has other member who does not store data block (member who for example newly reaches the standard grade) during online,, then send a data block to this member who does not store data block if there is such member.Thereby as far as possible data block store is arrived different members.
As shown in Figure 3, be the structural representation of the embodiment of data release unit 22 among Fig. 2.This data release unit 22 comprises cutting subelement 221, coding subelement 222 and distributes subelement 223.
It is m part that cutting subelement 221 is used for data cutting to be stored, and wherein m is the integer greater than 1.
Coding subelement 222 is used for by encryption algorithm m the part that cutting subelement 221 switches gained being encoded to n data block, any m in the said n data block can revert to data to be stored, and wherein n is the integer greater than 1, and n＞m, n＜N, wherein N is member's total amount of group.N is much smaller than N in the ordinary course of things.Above-mentioned encryption algorithm can be the algorithm in the existing distributed memory system, Read-Solomon (Reed-Solomon) encryption algorithm for example, thus as long as any m that obtains in n the data block is individual, can revert to initial data to be stored.
Distribute subelement 223 to obtain online member's tabulation of group from management and group server 13, and give online member in the group with a said n data block mean allocation, send the coded data piece simultaneously to online member, simultaneously the distributed intelligence of data block (for example each data block store in which member, data to be stored by quantity of cutting etc.) is sent to management and group server 13.
As shown in Figure 4, in another embodiment of a kind of distributed memory system of the present invention, except comprising group's maintenance unit 41, data release unit 42, also comprise distributed intelligence acquiring unit 43, recover judging unit 44, member's notification unit 45 and data recovery unit 46.
Distributed intelligence acquiring unit 43 is used for obtaining from management and group server 13 distributed intelligence of a plurality of data blocks of data.
Recover judging unit 44 and be used for the distributed intelligence of a plurality of data blocks of obtaining according to distributed intelligence acquiring unit 43, judge whether online member's data blocks stored can restore data.Usually can judge whether by the online number of members that judgement stores data block can restore data.
Member's notification unit 45 is used for when recovering judging unit 44 and confirm that online member's data blocks stored can not recover data blocks, and the not online member who stores data block by Short Message Service Gateway 14 notices reaches the standard grade.
Data recovery unit 46 is used for when recovering judging unit 44 and confirm that online member's data blocks stored can recover data blocks, from a plurality of online member's downloading data block, and the data downloaded piece is reverted to data to be stored.When recovering data to be stored, can use the encryption algorithm of existing distributed memory system, for example Read-Solomon (Reed-Solomon) encryption algorithm.
Especially, can whether recover judging unit 44 can recover less than m judgment data piece by the online number of members that judgement stores data block, this recoverys judging unit 44 the online number of members that stores data block confirm during less than m data block can not recover, the online number of members that stores described data block during more than or equal to m the affirmation data block can recover.
Correspondingly, data recovery unit 46 can comprise: data block count subelement 461, download notice subelement 462 and coding are gone back atomic unit 463, as shown in Figure 4.
Whether data block count subelement 461 is used to judge downloads successful data block quantity less than m.
Coding is gone back atomic unit 463 and is used for when described database count sub-element confirms that the successful data block quantity of download equals m m data block being reverted to data to be stored.
In addition, in the said system, also can comprise a data block dump unit (not shown), be used for withdrawing from group time with the data block store of this group member other member in the group at group member.
As shown in Figure 6, be the flow chart of a kind of distributed storage method embodiment of the present invention, this method comprises:
Step S61: create the group comprise a plurality of members, and with the group member information stores to the management and group server.
Step S62: with data conversion to be stored is a plurality of data blocks, and stores above-mentioned a plurality of data blocks in the group a plurality of online members respectively, stores the distributed intelligence of a plurality of data blocks into management and group server 13 simultaneously.
As shown in Figure 7, be the detail flowchart of the embodiment of storage data step among Fig. 6.This step comprises:
Step S71: with data cutting to be stored is m part, and wherein m is the integer greater than 1.
Step S72: by encryption algorithm described m part is encoded to n data block, wherein n is the integer greater than 1, and n＞m, n＜N, and wherein N is member's sum of group, and N is the integer greater than 1.
Step S73: give the individual online member of the k in the group with described n data block mean allocation, and the distributed intelligence of data block is sent to the management and group server.
As shown in Figure 8, be the flow chart of another embodiment of a kind of distributed storage method of the present invention, this method comprises:
Step S81: create the group comprise a plurality of members, and with the group member information stores to the management and group server.
Step S82: with data conversion to be stored is a plurality of data blocks, and stores above-mentioned a plurality of data blocks in the group a plurality of online members respectively, stores the distributed intelligence of a plurality of data blocks into management and group server 13 simultaneously.
Step S83: the distributed intelligence of obtaining a plurality of data blocks of data from the management and group server.
Step S85: according to the distributed intelligence of described a plurality of data blocks, judge that online member's data blocks stored whether can restore data, if can recover, execution in step S87 then, otherwise execution in step S86.
In this step, can whether the online number of members that stores described data block by judgement recover less than m judgment data piece, confirms that at the online number of members that stores described data block data block can not recover, confirm that at the online number of members that stores described data block data block can recover during more than or equal to m during less than m.
Step S86: the not online member who stores described data block by the Short Message Service Gateway notice reaches the standard grade, and returns step S85 then.
Step S87: download a plurality of data blocks from a plurality of online members, and a plurality of data blocks are reverted to data to be stored.At first from online member's downloading data block, and judge and whether download successful data block quantity less than m, if less than m, wait for that then the not online member who has data block reaches the standard grade, and after obtaining the notification message that the member reaches the standard grade from the member's downloading data block of reaching the standard grade, equal m up to downloading successful data block quantity; Then m data block reverted to data to be stored.
In said method, can also comprise the data block store that will receive from other group member step to local disk.Especially, in this step, if the data block that online member distributes judges greater than 1 o'clock whether it has other member who does not store data block (member who for example newly reaches the standard grade) during online, if there is such member, then send a data block to this member who does not store data block.Thereby as far as possible data block store is arrived different members.
In said method, also can be included in group member step with the data block store of this group member other member in the group when withdrawing from group.
In said system and the method, can in management and group server 13, write down the corresponding relation of member's user name and terminal physical label, thereby when restore data, just be considered as reaching the standard grade when only using the physical terminal login that stores data block, use the member of other physical terminal login system then to be considered as not reaching the standard grade.
The above; only for the preferable embodiment of the present invention, but protection scope of the present invention is not limited thereto, and anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; the variation that can expect easily or replacement all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection range of claim.
Claims (11)
1. a distributed memory system is characterized in that, comprising:
Group's maintenance unit is used for creating group by the management and group server, and described group comprises a plurality of members, and described management and group server stores has the information of described group member;
The data release unit, being used for data conversion to be stored is a plurality of data blocks, stores described a plurality of data blocks in the group a plurality of online members respectively, and stores the distributed intelligence of described a plurality of data blocks into described management and group server.
2. a kind of distributed memory system according to claim 1 is characterized in that, described data release unit comprises:
The cutting subelement, being used for data cutting to be stored is m part, wherein m is the integer greater than 1;
The coding subelement is used for by encryption algorithm described m part being encoded to n data block, and any m in the described n data block can revert to described data to be stored, and wherein n is the integer greater than 1, and n＞m, and n＜N, described N are the group member sum;
Distribute subelement, be used for described n data block mean allocation given the online member of group, and the distributed intelligence of data block is sent to the management and group server stores.
3. a kind of distributed memory system according to claim 2 is characterized in that, also comprises:
The distributed intelligence acquiring unit is used for the distributed intelligence of obtaining a plurality of data blocks of data from described management and group server;
Recover judging unit, be used for distributed intelligence, judge that online member's data blocks stored whether can restore data according to described a plurality of data blocks;
Member's notification unit is used for when described recovery judging unit confirms that online member's data blocks stored can not recover data blocks, and the not online member who stores described data block by the Short Message Service Gateway notice reaches the standard grade;
Data recovery unit is used for when described recovery judging unit confirms that online member's data blocks stored can recover data blocks, from described online member's downloading data block, and recovers described data to be stored according to described data downloaded piece.
4. a kind of distributed memory system according to claim 3, it is characterized in that, can whether described recovery judging unit recover less than m judgment data piece by the online number of members that judgement stores described data block, and described recovery judging unit confirms that at the online number of members that stores described data block data block can not recover, confirm that at the online number of members that stores described data block data block can recover during more than or equal to m during less than m.
5. a kind of distributed memory system according to claim 3 is characterized in that, described data recovery unit comprises:
The data block count subelement is used to judge and whether downloads successful data block less than m;
Download the notice subelement, be used for confirming to download successful data block quantity less than m and the not online member who waits to have data block when reaching the standard grade, notify from described member's downloading data block of reaching the standard grade in described database count sub-element;
Coding is gone back atomic unit, is used for when described database count sub-element confirms that the successful data block quantity of download equals m a described m data block being reverted to data to be stored.
6. according to each described a kind of distributed memory system among the claim 1-5, it is characterized in that, also comprise a data block dump unit, be used for when group member withdraws from group the data block store of group member other online member in the group.
7. a distributed storage method is characterized in that, comprising:
(a) create group by the management and group server, described group comprises a plurality of members, and described management and group server stores has the information of described group member;
(b) be a plurality of data blocks with data conversion to be stored, store described a plurality of data blocks in the group a plurality of online members respectively, and store the distributed intelligence of described a plurality of data blocks into described management and group server.
8. a kind of distributed storage method according to claim 7 is characterized in that the member of described group adds up to N, and wherein N is the integer greater than 1, and described step (b) comprising:
(b1) be m part with data cutting to be stored, wherein m is the integer greater than 1
(b2) by encryption algorithm described m part is encoded to n data block, any m in the described n data block can revert to described data to be stored, and wherein n is the integer greater than 1, and n＞m, n＜N;
(b3) described n data block mean allocation given online member in the group, and the distributed intelligence of data block is sent to the management and group server stores.
9. a kind of distributed storage method according to claim 8 is characterized in that, also comprises:
(c) obtain the distributed intelligence of a plurality of data blocks of data from the management and group server;
(d) according to the distributed intelligence of described a plurality of data blocks, judge that online member's data blocks stored whether can restore data, if can recover, execution in step (f) then, otherwise execution in step (e);
(e) notify the not online member who stores described data block to reach the standard grade by Short Message Service Gateway, return step (d) then;
(f) recover data to be stored from described online member's downloading data block, and according to described data downloaded piece.
10. a kind of distributed storage method according to claim 9, it is characterized in that, can whether the online number of members that stores described data block by judgement in the described step (d) recover less than m judgment data piece, confirms that at the online number of members that stores described data block data block can not recover, confirm that at the online number of members that stores described data block data block can recover during more than or equal to m during less than m.
11. a kind of distributed storage method according to claim 10 is characterized in that, described step (f) comprising:
(f1), and whether judge to download successful data block quantity less than m from described online member's downloading data block, as if less than m, execution in step (f2) then, otherwise execution in step (f3);
(f2) wait for that the not online member have data block reaches the standard grade, and after obtaining the notification message that the member reaches the standard grade execution in step (f1);
(f3) a described m data block is reverted to data to be stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007101254255A CN101184104B (en) | 2007-12-21 | 2007-12-21 | Distributed memory system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007101254255A CN101184104B (en) | 2007-12-21 | 2007-12-21 | Distributed memory system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101184104A true CN101184104A (en) | 2008-05-21 |
| CN101184104B CN101184104B (en) | 2010-12-15 |
Family
ID=39449186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2007101254255A Active CN101184104B (en) | 2007-12-21 | 2007-12-21 | Distributed memory system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101184104B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901275A (en) * | 2010-08-23 | 2010-12-01 | 华中科技大学 | Distributed storage system and method thereof |
| CN102075456A (en) * | 2011-02-25 | 2011-05-25 | 中国科学院计算技术研究所 | Group creating and member adding method in distributed domain management system |
| CN102137339A (en) * | 2010-01-27 | 2011-07-27 | 深圳市源通世纪科技有限公司 | Method for reminding group member of getting online by push to talk terminal |
| CN103297493A (en) * | 2012-02-15 | 2013-09-11 | 国际商业机器公司 | Partition aware quality of service feature |
| CN103327085A (en) * | 2013-06-05 | 2013-09-25 | 深圳市中博科创信息技术有限公司 | Distributed data processing method, data center and distributed data system |
| CN104765871A (en) * | 2015-04-26 | 2015-07-08 | 成都创行信息科技有限公司 | Storage method for extracting big data from Internet |
| CN104765869A (en) * | 2015-04-26 | 2015-07-08 | 成都创行信息科技有限公司 | Film big data forwarding and storage method |
| CN105187546A (en) * | 2015-09-25 | 2015-12-23 | 南京伍安信息科技有限公司 | Network separation storage system and method of separating and storing files |
| 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) |
| CN109885424A (en) * | 2019-01-16 | 2019-06-14 | 平安科技（深圳）有限公司 | A kind of data back up method, device and computer equipment |
| CN113259481A (en) * | 2021-06-21 | 2021-08-13 | 湖南视觉伟业智能科技有限公司 | Distributed data storage method, system and readable storage medium |
| CN109885424B (en) * | 2019-01-16 | 2024-05-31 | 平安科技（深圳）有限公司 | Data backup method and device and computer equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832009B (en) * | 2017-10-30 | 2020-10-23 | 厦门万匹思网络科技有限公司 | Data distribution method, equipment and computer storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1368948A2 (en) * | 2000-10-26 | 2003-12-10 | Prismedia Networks, Inc. | Method and apparatus for large payload distribution in a network |
| CN100579016C (en) * | 2006-01-24 | 2010-01-06 | 华为技术有限公司 | Distributing storage downloading system, device and method for network data |
| WO2007133791A2 (en) * | 2006-05-15 | 2007-11-22 | Richard Kane | Data partitioning and distributing system |
-
2007
- 2007-12-21 CN CN2007101254255A patent/CN101184104B/en active Active
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102137339A (en) * | 2010-01-27 | 2011-07-27 | 深圳市源通世纪科技有限公司 | Method for reminding group member of getting online by push to talk terminal |
| CN101901275A (en) * | 2010-08-23 | 2010-12-01 | 华中科技大学 | Distributed storage system and method thereof |
| CN102075456A (en) * | 2011-02-25 | 2011-05-25 | 中国科学院计算技术研究所 | Group creating and member adding method in distributed domain management system |
| CN102075456B (en) * | 2011-02-25 | 2013-06-19 | 中国科学院计算技术研究所 | Group creating and member adding method in distributed domain management system |
| CN103297493A (en) * | 2012-02-15 | 2013-09-11 | 国际商业机器公司 | Partition aware quality of service feature |
| CN103327085A (en) * | 2013-06-05 | 2013-09-25 | 深圳市中博科创信息技术有限公司 | Distributed data processing method, data center and distributed data system |
| CN103327085B (en) * | 2013-06-05 | 2017-02-08 | 深圳市中博科创信息技术有限公司 | Distributed data processing method, data center and distributed data system |
| 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) |
| CN104765869A (en) * | 2015-04-26 | 2015-07-08 | 成都创行信息科技有限公司 | Film big data forwarding and storage method |
| CN104765871A (en) * | 2015-04-26 | 2015-07-08 | 成都创行信息科技有限公司 | Storage method for extracting big data from Internet |
| CN105187546A (en) * | 2015-09-25 | 2015-12-23 | 南京伍安信息科技有限公司 | Network separation storage system and method of separating and storing files |
| CN109885424A (en) * | 2019-01-16 | 2019-06-14 | 平安科技（深圳）有限公司 | A kind of data back up method, device and computer equipment |
| CN109885424B (en) * | 2019-01-16 | 2024-05-31 | 平安科技（深圳）有限公司 | Data backup method and device and computer equipment |
| CN113259481A (en) * | 2021-06-21 | 2021-08-13 | 湖南视觉伟业智能科技有限公司 | Distributed data storage method, system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101184104B (en) | 2010-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101184104B (en) | Distributed memory system and method | |
| US10613776B2 (en) | Appyling multiple hash functions to generate multiple masked keys in a secure slice implementation | |
| US10970276B2 (en) | Object loss reporting in a data storage system | |
| Prakash et al. | The storage versus repair-bandwidth trade-off for clustered storage systems | |
| US10180912B1 (en) | Techniques and systems for data segregation in redundancy coded data storage systems | |
| CN104580395B (en) | A kind of cloudy collaboration Storage Middleware Applying system based on existing cloud storage platform | |
| Monti et al. | RAIN: a bio-inspired communication and data storage infrastructure | |
| Pitkänen et al. | Redundancy and distributed caching in mobile dtns | |
| CN101647006A (en) | Be used for method of data backup and system | |
| Xu et al. | Cuckoo: towards decentralized, socio-aware online microblogging services and data measurements | |
| US20120173925A1 (en) | Method and a storage server for data redundancy | |
| CN103327085A (en) | Distributed data processing method, data center and distributed data system | |
| CN112035422B (en) | Distributed real-time data synchronization method, node equipment and system based on IPFS | |
| CN104080059A (en) | Method, device and system of implementing short message sending and receiving | |
| CN103457802A (en) | Information transmission system and method | |
| CN102984174B (en) | Reliability guarantee method and system in a kind of distribution subscription system | |
| JP4459999B2 (en) | Non-stop service system using voting and information updating and providing method in the system | |
| CN104426975A (en) | Method, equipment and system for data synchronization | |
| Martalò et al. | Randomized network coding in distributed storage systems with layered overlay | |
| WO2018081816A1 (en) | Segmented cloud storage | |
| Ribeiro et al. | Datacube: A p2p persistent data storage architecture based on hybrid redundancy schema | |
| US9940474B1 (en) | Techniques and systems for data segregation in data storage systems | |
| CN104869056A (en) | Institution personnel data synchronization method based on relational data separation | |
| CN108900625A (en) | It is a kind of based on government affairs application cloud on storage method | |
| Martalo et al. | A practical network coding approach for peer-to-peer distributed storage |
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 | ||
| ASS | Succession or assignment of patent right |
Owner name: SHENZHEN TENCENT COMPUTER SYSTEM CO., LTD. Free format text: FORMER OWNER: TECENT TECHNOLOGY (SHENZHEN) CO., LTD. Effective date: 20130105 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20130105 Address after: The South Road in Guangdong province Shenzhen city Fiyta building 518057 floor 5-10 Nanshan District high tech Zone Patentee after: Shenzhen Tencent Computer System Co., Ltd. Address before: 518057 Guangdong city of Shenzhen province high tech Park high-tech South Road Fiyta high-tech building 5-10 Patentee before: Tencent Technology (Shenzhen) Co., Ltd. |