CN102646127A - Replica selection method and device for distributed file systems - Google Patents

Replica selection method and device for distributed file systems Download PDF

Info

Publication number
CN102646127A
CN102646127A CN2012100503868A CN201210050386A CN102646127A CN 102646127 A CN102646127 A CN 102646127A CN 2012100503868 A CN2012100503868 A CN 2012100503868A CN 201210050386 A CN201210050386 A CN 201210050386A CN 102646127 A CN102646127 A CN 102646127A
Authority
CN
China
Prior art keywords
copy
version number
list
replica
distributed file
Prior art date
Application number
CN2012100503868A
Other languages
Chinese (zh)
Inventor
张明富
颜秉珩
Original Assignee
浪潮(北京)电子信息产业有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 浪潮(北京)电子信息产业有限公司 filed Critical 浪潮(北京)电子信息产业有限公司
Priority to CN2012100503868A priority Critical patent/CN102646127A/en
Publication of CN102646127A publication Critical patent/CN102646127A/en

Links

Abstract

The invention provides a replica selection method and device for distributed file systems, and relates to the field of cloud computing, and the method and the device are used for solving the problem of lacking a mechanism for quickly selecting the latest replica to operate. The method comprises the following steps: according to the frequency of replica updating, updating the version number of a corresponding replica, wherein the more the frequency of replica updating is, the larger the version number corresponding to the replica is; and when a read operation request or a write operation request is received, returning a replica with the largest version number. According to the technical scheme provided by the invention, the method and the device provided by the invention are applicable to cloud computing systems, and an effect of quickly and efficiently obtaining the latest replica from a plurality of replicas is achieved.

Description

分布式文件系统副本选择方法和装置 Distributed file system copy apparatus and method for selecting

技术领域 FIELD

[0001] 本发明涉及云计算领域,尤其涉及ー种分布式文件系统副本选择方法。 [0001] The present invention relates to the cloud, in particular a distributed file system copy selection method involves ー species.

背景技术 Background technique

[0002] 云存储是在云计算(cloud computing)基础上延伸和发展出来的ー个新概念,是指通过集群应用、网络技术和分布式文件系统等技木,将网络中大量不同类型的存储设备进行整合利用,形成统ー的存储池对外提供存储服务。 [0002] Cloud storage is extended and developed in the cloud (cloud computing) ー based on a new concept, refers to cluster applications, network technology and distributed file systems, wood technology, the number of different types of network storage integrate the use of equipment, the formation of unified storage pool ー provide external storage services.

[0003] 分布式文件系统作为云存储的核心组成部分在近几年中有了长足的发展。 [0003] Distributed File System as a core component of cloud storage has made great progress in recent years. 在分布式文件系统中如何选择副本是ー个很重要的问题。 How to choose the copy distributed file system, ー is a very important issue. 为了提高数据可靠性,可以通过对分布式文件系统中的对象文件建立多副本的方式增加数据冗余。 In order to improve data reliability, data redundancy can be increased by creating multiple copies of the object files distributed file system approach. 当进行文件读或文件写操作时,需要有一种机制能快速从众多的已存在副本中选择出最新的副本进行操作,目前尚缺乏这样ー种机制。 When a file is read or write a file, you need to have a mechanism to quickly select the latest copy operation from a number of existing copy of the current lack of such ー kinds of mechanisms.

发明内容 SUMMARY

[0004] 本发明提供了ー种分布式文件系统副本选择方法和装置,解决了缺乏快速选择最新副本进行操作机制的问题。 [0004] The present invention provides a distributed file system copy ー kinds of selection methods and means to solve the lack of rapid pick up the latest copy of the operating mechanism of the problem.

[0005] ー种分布式文件系统副本选择方法,包括: [0005] ー species distributed file system copy selection method, including:

[0006] 根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大; [0006] The version number is updated according to the number of copies for the copy updates, the more the larger the number of copies of the corresponding update version number value;

[0007] 在接收到读操作请求或写操作请求吋,返回版本号值最大的副本。 [0007] Upon receiving the request inches read request or a write operation, the copy version number returns the largest value.

[0008] 优选的,上述分布式文件系统副本选择方法还包括: [0008] Preferably, said distributed file system copy selection method further comprising:

[0009] 维护ー副本链表,该副本链表中包含至少ー个副本,各副本在所述副本链表中的存储对应一版本号。 [0009] Maintenance ー copy of the list, the list contains a copy of at least ー copies, each copy is stored in the copy of the linked list corresponding to a version number.

[0010] 优选的,所述根据副本更新次数更新相应副本的版本号包括: [0010] Preferably, according to the updated copy of the copy number of the corresponding update version number comprising:

[0011] 将被执行写操作的副本版本号的值增加I '及, [0011] I will be increased copy of the value of the version number of write operations' and,

[0012] 周期性的检查所述副本链表中各副本的版本号,根据版本号的值最大的副本更新所述副本链表中的其他副本,并将其他副本的版本号也修改为该最大的版本号值;及, [0012] periodic inspections of each copy of the copy of the list version number, updates the other replicas in the replica list according to the maximum value of the version number copy, and the other copy version number for the modified version of the biggest number value; and,

[0013] 在删除所述副本链表中的副本时,将副本内容清空,并将该副本在所述副本链表中所在位置对应的版本号置为O。 [0013] When deleting the copy of the copy of the linked list, empty the contents of the copy, and the version number of counter positions corresponding to the copy of the replica in the linked list is O.

[0014] 优选的,上述分布式文件系统副本选择方法还包括: [0014] Preferably, said distributed file system copy selection method further comprising:

[0015] 在创建副本时创建与该副本对应的版本号,并为该版本号设置ー初始值。 [0015] Create a version number corresponding to the replica when creating a copy, and set the initial value for the version number ー.

[0016] 优选的,所述版本号的初始值为I。 [0016] Preferably, the version number of the initial value I.

[0017] 优选的,在接收到读操作请求或写操作请求时,返回版本号值最大的副本。 [0017] Preferably, upon receiving a read request or a write operation request, it returns a copy of the version number of the maximum value.

[0018] 本发明还提供了ー种分布式文件系统副本选择装置,包括: [0018] The present invention further provides a distributed file system types ー replica selection means, comprising:

[0019] 版本号更新模块,用于根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大;[0020] 副本操作模块,用于在接收到读操作请求或写操作请求时,返回版本号值最大的副本。 [0019] The version number updating module configured to update the version number is updated according to the number of copies for the copy, copy updated more times greater value corresponding version number; [0020] The copy of the operating module for receiving a read operation request or write request, returns the largest value of a copy of the version number.

[0021] 优选的,上述分布式文件系统副本选择装置还包括: [0021] Preferably, said distributed file system copy selection means further comprises:

[0022] 链表维护模块,用于维护一副本链表,该副本链表中包含至少ー个副本,各副本在所述副本链表中的存储对应ー版本号。 [0022] The linked list maintenance module configured to maintain a copy of the linked list, the linked list contains a copy of at least ー copies, each copy is stored in a version number corresponding to the replica ー linked list.

[0023] 优选的,所述版本号更新模块包括: [0023] Preferably, the version number updating module comprises:

[0024] 第一更新単元,用于将被执行写操作的副本版本号的值增加I '及, [0024] The first update radiolabeling element, a value for a write operation to be performed is increased copy version I 'and,

[0025] 第二更新単元,用于周期性的检查所述副本链表中各副本的版本号,根据版本号的值最大的副本更新所述副本链表中的其他副本,并将其他副本的版本号也修改为该最大的版本号值'及' [0025] The second element radiolabeling updated, the version number of the copy list periodic inspections of each copy, the copy of the replica list update other in accordance with the maximum value of the version number copy, the copy version number and other also modify the version number for the maximum value 'and'

[0026] 第三更新単元,用于在删除所述副本链表中的副本时,将副本内容清空,并将该副本在所述副本链表中所在位置对应的版本号置为O。 When the [0026] third update radiolabeling element, for deleting the copy of the copy of the linked list, empty the contents of the copy, and the version number of counter positions corresponding to the copy of the replica in the linked list is O.

[0027] 本发明提供了ー种分布式文件系统副本选择方法和装置,根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大,在接收到读操作请求或写操作请求时,返回版本号值最大的副本,实现了快速高效从多个副本中获取最新副本,解决了缺乏快速选择最新副本进行操作机制的问题。 [0027] The present invention provides a distributed file system types ー copy selection methods and apparatus for the copy version number is updated according to the updated copy number, the more the number of copies to update its larger value corresponding to the version number, upon receiving a read operation request or write request, returns the largest value of a copy of the version number, to achieve a rapid and efficient to obtain the latest copy from multiple copies to solve the lack of rapid pick up the latest copy of the operating mechanism of the problem.

附图说明 BRIEF DESCRIPTION

[0028] 图I为本发明的实施例一提供的ー种分布式文件系统副本选择方法的流程图; A distributed file system flowchart ー selection method according to a copy provided in [0028] Figure I embodiment of the present invention;

[0029] 图2为本发明的实施例ニ提供的ー种分布式文件系统副本选择装置的结构示意图。ー structural diagram of a copy of a distributed file system types embodiment ni selection means provided Embodiment [0029] FIG. 2 of the present invention.

具体实施方式 Detailed ways

[0030] 为了提高数据可靠性,可以通过对分布式文件系统中的对象文件建立多副本的方式增加数据冗余。 [0030] In order to improve data reliability, data redundancy can be increased by creating multiple copies of the object files distributed file system approach. 当进行文件读或文件写操作吋,需要有一种机制能快速从众多的已存在副本中选择出最新的副本进行操作,目前尚缺乏这样ー种机制。 When reading files or file write-inch, you need a mechanism to quickly select the latest copy operation from a number of existing copy of the current lack of such ー kinds of mechanisms. 本发明所述的副本选择方法基于版本号的检测与更新的方式达到副本选择的目标。 Copy selection method of the present invention is based on detecting the update version number to reach the destination replica manner selected.

[0031] 下文中将结合附图对本发明的实施例进行详细说明。 [0031] below in conjunction with the accompanying drawings of embodiments of the present invention will be described in detail. 需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互任意組合。 Incidentally, in the case of no conflict, embodiments and features of the embodiments of the present application may be arbitrarily combined with each other.

[0032] 首先结合附图,对本发明的实施例一进行说明。 [0032] First the accompanying drawings, of an embodiment of the present invention will be described.

[0033] 本发明实施例提供了ー种分布式文件系统副本选择方法,使用该方法更新副本版本及在操作时选择最新版本副本的流程如图I所示,包括: [0033] Example embodiments of the present invention provides a distributed file system types ー copy selection method, the method using an updated copy of the latest version and the version of the selected copy operation flow shown in FIG. I, comprising:

[0034] 步骤101、维护ー副本链表,该副本链表中包含至少ー个副本,各副本在所述副本链表中的存储对应一版本号; [0034] Step 101, linked list maintenance ー copy, the copy list contained at least ー copies, each copy is stored in the copy of the linked list corresponding to a version number;

[0035] 本步骤中,在创建副本时将副本的版本号(Version)的值初始化为I,表示该副本为新建副本。 [0035] In this step, a version number (Version) value is initialized when creating a copy of copy I, show that the copy for the new replica.

[0036] 步骤102、根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大; [0036] Step 102, the corresponding version number is updated according to the number of copies of an updated copy, the greater the more the number of copies of the corresponding update version number value;

[0037] 本步骤中,具体的,包括以下四种情况:[0038] I、当有文件读操作时,通过给出的索引找到对应的块chunk,该chunk下面维护有ー个副本的链表。 [0037] In this step, specifically, it includes the following four cases: [0038] I, when a file read operation, to find the corresponding block index is given by the chunk, the chunk ー below maintains a copy of the list. 依次扫描这些副本的Version,从中找出Version值最大的副本(可能有多个)将其对应的存储节点ip和port发送给客户端,供其进行读文件操作。 Version sequentially scanned copies of these, find out the maximum value of a copy of Version (there may be more) sends its corresponding storage node ip and port to the client, for its read file operations.

[0039] 2、当有文件写操作时,通过给出的索引若找到对应的块chunk,从该chunk下面的副本链中选择Version最大的返回给客户端进行写操作,同时将它们的Version加一,表示该副本进行了更新。 [0039] 2. When a file write operation, the corresponding block index is given by the chunk if found, selected from the following copy chunk Version largest chain back to the client write operations, while adding their Version First, it shows that the copy has been updated.

[0040] 3、周期性的随机检查某个chunk下的副本链表,发现各副本的Version不一致时,则以Version最大的副本作为源,对其他“旧的”副本进行更新,然后重新设置这些副本的Version。 [0040] 3, a copy of the list under periodic random checks of a chunk, found inconsistent with each copy of Version, Version largest places a copy as the source, update the other "old" copy, and then re-set these copies the Version.

[0041 ] 4、当需要删除某个副本时(比如重新设置副本数),将Version设置为O表示该副本不可用。 [0041] 4, when the need to delete a copy (such as re-set the number of copies), the Version is set to O show that the copy is not available. 之后在周期检测中,发现Version值为O的副本对其进行实际删除工作。 After the cycle test, found a copy of Version O is actually deleted them work.

[0042] 步骤103、在接收到读操作请求或写操作请求吋,返回版本号值最大的副本。 [0042] Step 103, upon receiving a read or write operation request requests inches, the maximum value of return a copy of the version number.

[0043] 下面结合附图,对本发明的实施例ニ进行说明。 [0043] below with the accompanying drawings, embodiments of the present invention will be described ni.

[0044] 本发明实施例提供了ー种分布式文件系统副本选择装置,其结构如图2所示,包括: [0044] Example embodiments of the present invention provides a distributed file system types ー replica selection means, the structure shown in Figure 2, comprising:

[0045] 版本号更新模块201,用于根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大; [0045] The version number updating module 201, a version number is updated according to the number of copies for the copy updates, the update frequency and the larger the more copies of the corresponding version number value;

[0046] 副本操作模块202,用于在接收到读操作请求或写操作请求时,返回版本号值最大的副本。 [0046] The copy of the operating module 202, when receiving a read or write operation request operation request, returns the largest value of the version number copy.

[0047] 优选的,上述分布式文件系统副本选择装置还包括: [0047] Preferably, said distributed file system copy selection means further comprises:

[0048] 链表维护模块203,用于维护一副本链表,该副本链表中包含至少ー个副本,各副本在所述副本链表中的存储对应一版本号。 [0048] The linked list maintenance module 203 maintains a copy of the linked list, the linked list contains a copy of at least ー copies, each copy is stored in the copy of the linked list corresponding to a version number.

[0049] 优选的,所述版本号更新模块201包括: [0049] Preferably, the version number updating module 201 comprises:

[0050] 第一更新単元,用于将被执行写操作的副本版本号的值增加I '及, [0050] The first update radiolabeling element, a value for a write operation to be performed is increased copy version I 'and,

[0051] 第二更新単元,用于周期性的检查所述副本链表中各副本的版本号,根据版本号的值最大的副本更新所述副本链表中的其他副本,并将其他副本的版本号也修改为该最大的版本号值'及' [0051] The second element radiolabeling updated, the version number of the copy list periodic inspections of each copy, the copy of the replica list update other in accordance with the maximum value of the version number copy, the copy version number and other also modify the version number for the maximum value 'and'

[0052] 第三更新単元,用于在删除所述副本链表中的副本时,将副本内容清空,并将该副本在所述副本链表中所在位置对应的版本号置为O。 When the [0052] third update radiolabeling element, for deleting the copy of the copy of the linked list, empty the contents of the copy, and the version number of counter positions corresponding to the copy of the replica in the linked list is O.

[0053] 本发明提供了ー种分布式文件系统副本选择方法和装置,根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大,在接收到读操作请求或写操作请求时,返回版本号值最大的副本,实现了快速高效从多个副本中获取最新副本,解决了缺乏快速选择最新副本进行操作机制的问题。 [0053] The present invention provides a distributed file system types ー copy selection methods and apparatus for the copy version number is updated according to the updated copy number, the more the number of copies to update its larger value corresponding to the version number, upon receiving a read operation request or write request, returns the largest value of a copy of the version number, to achieve a rapid and efficient to obtain the latest copy from multiple copies to solve the lack of rapid pick up the latest copy of the operating mechanism of the problem.

[0054] 通过副本版本号从众多副本中选择最新副本进行操作,然后更新该副本版本号,其他副本依据版本号来进行数据一致性维护工作,版本号的值的变化体现了该副本的更新次数,Version值最大的副本为最新更新的副本,所有其他副本都以它为基准进行自更新。 [0054] a copy of the version number by selecting from a number of copies of the latest copy of the instructions, and then update the copy of the version number, the other copy for data consistency maintenance based on a version number change, and the value of the version number reflects the number of copies of the update the maximum value for the latest copy of Version updated copy, all other copies have to update it self as a benchmark. 通过引入版本号的概念能较容易的进行多副本情况下的数据更新控制和副本选择操作,降低了系统复杂度和响应时间。 Data can be updated more easily controlled and the copy operation in the selected case by introducing the concept of multiple copies of the version number, and the system complexity and response time.

[0055] 本领域普通技术人员可以理解上述实施例的全部或部分步骤可以使用计算机程序流程来实现,所述计算机程序可以存储于ー计算机可读存储介质中,所述计算机程序在相应的硬件平台上(如系统、设备、装置、器件等)执行,在执行时,包括方法实施例的步骤之一或其组合。 [0055] Those of ordinary skill in the art understand that all or part of the steps of the above-described embodiments may be implemented using a computer program process, the computer program may be stored in a computer-readable storage medium ー, the computer program in the appropriate hardware platform (such as system, apparatus, equipment, device) to perform, when executed, the method comprising the steps of the one embodiment or a combination thereof.

[0056] 可选地,上述实施例的全部或部分步骤也可以使用集成电路来实现,这些步骤可以被分别制作成ー个个集成电路模块,或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。 [0056] Alternatively, all or part of the steps of the above-described embodiments may be implemented using an integrated circuit, these steps may be respectively made into integrated circuit module ー all, or by making them into a single step or a plurality of modules integrated circuit module. 这样,本发明不限制于任何特定的硬件和软件结合。 Thus, the present invention is not limited to any particular hardware and software combination.

[0057] 上述实施例中的各装置/功能模块/功能単元可以采用通用的计算装置来实现,它们可以集中在单个的计算装置上,也可以分布在多个计算装置所组成的网络上。 [0057] The above embodiments each device / function modules / functions radiolabeling membered general computing means may be employed to implement, they can be integrated on a single computing device or distributed in a network composed of multiple computing devices.

[0058] 上述实施例中的各装置/功能模块/功能单元以软件功能模块的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。 When [0058] the above-described embodiments each device / function modules / functional unit is implemented as an independent product sold or used in the form of functional software modules may be stored in a computer-readable storage medium. 上述提到的计算机可读取存储介质可以是只读存储器,磁盘或光盘等。 The above-mentioned computer-readable storage medium may be a read-only memory, magnetic or optical disk.

[0059] 任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本发明的保护范围之内。 [0059] Any skilled in the art in the art within the technical scope of the present invention is disclosed, variations or replacement that can be easily, shall fall within the protection scope of the present invention. 因此,本发明的保护范围应以权利要求所述的保护范围为准。 Accordingly, the scope of the present invention should be the scope of the claims and their equivalents. ,

Claims (9)

1. ー种分布式文件系统副本选择方法,其特征在于,包括: 根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大; 在接收到读操作请求或写操作请求时,返回版本号值最大的副本。 1. The distributed file system copy selection method ー species, characterized by comprising: a version number is updated according to the number of copies for the copy updates, the more the number of copies to update its larger value corresponding to the version number; in a read operation request is received when or write request, it returns the largest value of a copy of the version number.
2.根据权利要求I所述的分布式文件系统副本选择方法,其特征在于,该方法还包括: 维护ー副本链表,该副本链表中包含至少ー个副本,各副本在所述副本链表中的存储对应一版本号。 The distributed file system copy selection method of claim I, wherein the method further comprising: maintaining a list ー copy, the copy list contained at least ー copies, each copy of the replica list corresponding to a version number is stored.
3.根据权利要求2所述的分布式文件系统副本选择方法,其特征在干,所述根据副本更新次数更新相应副本的版本号包括: 将被执行写操作的副本版本号的值增加I ;及, 周期性的检查所述副本链表中各副本的版本号,根据版本号的值最大的副本更新所述副本链表中的其他副本,并将其他副本的版本号也修改为该最大的版本号值;及, 在删除所述副本链表中的副本时,将副本内各清空,并将该副本在所述副本链表中所在位置对应的版本号置为O。 The distributed file system copy selection method according to claim 2, characterized in that the dry, respective copies of the updated version number comprising the updated copy times: to be executed copy of the value of the version number of write operations increases I; and, periodically checking the copies of each copy of the list version number, updates the other replicas in the replica list according to the maximum value of the version number copy, and the copy version number of other modifications for the largest version number value; and, when deleting the copy of the replica list, copies of the empty inner and the copy of the replica in the location list corresponding to the version number is set to O.
4.根据权利要求I或3所述的分布式文件系统副本选择方法,其特征在于,该方法还包括: 在创建副本时创建与该副本对应的版本号,并为该版本号设置ー初始值。 The distributed file system copy I or selection method according to claim 3, characterized in that, the method further comprising: creating a version number corresponding to the copy when creating a copy, and set an initial value for the version number ー.
5.根据权利要求4所述的分布式文件系统副本选择方法,其特征在于,所述版本号的初始值为I。 The distributed file system copy selection method of claim 4, wherein the initial value of the version number I.
6.根据权利要求I所述的分布式文件系统副本选择方法,其特征在于,在接收到读操作请求或写操作请求吋,返回版本号值最大的副本。 According to claim I of the distributed file system copy selection method, wherein, upon receiving a read or write operation request requests inches, the maximum value of return a copy of the version number.
7. ー种分布式文件系统副本选择装置,其特征在于,包括: 版本号更新模块,用于根据副本更新次数更新相应副本的版本号,更新次数越多的副本其对应的版本号值越大; 副本操作模块,用于在接收到读操作请求或写操作请求时,返回版本号值最大的副本。 7. A distributed file system copy ー selection device comprising: a version number updating module configured to update the version number in accordance with the number of copies for the copy updates, the more the number of copies to update its larger value corresponding to the version number ; copy operation module, when receiving a read or write operation request operation request, returns the largest value of the version number copy.
8.根据权利要求7所述的分布式文件系统副本选择装置,其特征在于,该装置还包括: 链表维护模块,用于维护一副本链表,该副本链表中包含至少ー个副本,各副本在所述副本链表中的存储对应ー版本号。 Distributed file system according to claim 7, wherein the copy of the selection means, wherein the apparatus further comprises: a linked list maintenance module configured to maintain a copy of the linked list, the linked list contains a copy of at least ー copies, each copy storing data corresponding to the version number copy ー linked list.
9.根据权利要求7所述的分布式文件系统副本选择装置,其特征在干,所述版本号更新模块包括: 第一更新単元,用于将被执行写操作的副本版本号的值增加I ;及, 第二更新単元,用于周期性的检查所述副本链表中各副本的版本号,根据版本号的值最大的副本更新所述副本链表中的其他副本,并将其他副本的版本号也修改为该最大的版本号值;及, 第三更新単元,用于在删除所述副本链表中的副本时,将副本内容清空,并将该副本在所述副本链表中所在位置对应的版本号置为O。 9. A distributed file system according to claim 7, wherein the copy of the selection means, characterized in that the dry, the version number updating module comprises: a first updating radiolabeling element, the value of I is increased for the version number copy write operation ; and, a second element radiolabeling updated, the version number of the copy list periodic inspections of each copy, the copy of the replica list update other in accordance with the maximum value of the version number copy, the copy version number and other also modified to the largest version number value; and when, third update radiolabeling element, for deleting the copy of the copy of the linked list, empty the contents of the copy, and the copy corresponding to the location in the list of the copy version number is set to O.
CN2012100503868A 2012-02-29 2012-02-29 Replica selection method and device for distributed file systems CN102646127A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2012100503868A CN102646127A (en) 2012-02-29 2012-02-29 Replica selection method and device for distributed file systems

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2012100503868A CN102646127A (en) 2012-02-29 2012-02-29 Replica selection method and device for distributed file systems

Publications (1)

Publication Number Publication Date
CN102646127A true CN102646127A (en) 2012-08-22

Family

ID=46658946

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2012100503868A CN102646127A (en) 2012-02-29 2012-02-29 Replica selection method and device for distributed file systems

Country Status (1)

Country Link
CN (1) CN102646127A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103559319A (en) * 2013-11-21 2014-02-05 华为技术有限公司 Cache synchronization method and equipment for distributed cluster file system
CN103559139A (en) * 2013-10-23 2014-02-05 华为技术有限公司 Data storage method and device
CN103729352A (en) * 2012-10-10 2014-04-16 腾讯科技(深圳)有限公司 Distributed file system and method for processing multiple replica data in distributed file system
CN103761162A (en) * 2014-01-11 2014-04-30 深圳清华大学研究院 Data backup method of distributed file system
WO2014117717A1 (en) * 2013-01-31 2014-08-07 Huawei Technologies Co., Ltd. Distributed storage object delete
CN105516230A (en) * 2014-10-15 2016-04-20 深圳市腾讯计算机系统有限公司 Data processing method and device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1524239A (en) * 2001-06-01 2004-08-25 甲骨文国际公司 Consistent read in a distributed database environment
CN101197657A (en) * 2007-11-12 2008-06-11 中兴通讯股份有限公司 Data synchronization method of distributed system single panel
CN101771723A (en) * 2010-01-05 2010-07-07 深圳中兴网信科技有限公司 Data synchronization method
CN101964820A (en) * 2010-10-08 2011-02-02 中兴通讯股份有限公司 Method and system for keeping data consistency
CN102088489A (en) * 2010-12-31 2011-06-08 北京理工大学 Distributed data synchronizing system and method
EP2387200A1 (en) * 2010-04-23 2011-11-16 ILT Productions AB Distributed data storage

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1524239A (en) * 2001-06-01 2004-08-25 甲骨文国际公司 Consistent read in a distributed database environment
CN101197657A (en) * 2007-11-12 2008-06-11 中兴通讯股份有限公司 Data synchronization method of distributed system single panel
CN101771723A (en) * 2010-01-05 2010-07-07 深圳中兴网信科技有限公司 Data synchronization method
EP2387200A1 (en) * 2010-04-23 2011-11-16 ILT Productions AB Distributed data storage
CN101964820A (en) * 2010-10-08 2011-02-02 中兴通讯股份有限公司 Method and system for keeping data consistency
CN102088489A (en) * 2010-12-31 2011-06-08 北京理工大学 Distributed data synchronizing system and method

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103729352A (en) * 2012-10-10 2014-04-16 腾讯科技(深圳)有限公司 Distributed file system and method for processing multiple replica data in distributed file system
CN103729352B (en) * 2012-10-10 2017-07-28 腾讯科技(深圳)有限公司 Distributed multiple copies of the file system and the data processing system
US9104717B2 (en) 2013-01-31 2015-08-11 Futurewei Technologies, Inc. Distributed storage object delete
WO2014117717A1 (en) * 2013-01-31 2014-08-07 Huawei Technologies Co., Ltd. Distributed storage object delete
CN103559139A (en) * 2013-10-23 2014-02-05 华为技术有限公司 Data storage method and device
CN103559139B (en) * 2013-10-23 2016-08-17 华为技术有限公司 A data storage method and apparatus
CN103559319A (en) * 2013-11-21 2014-02-05 华为技术有限公司 Cache synchronization method and equipment for distributed cluster file system
CN103559319B (en) * 2013-11-21 2017-07-07 华为技术有限公司 Cache synchronization method and apparatus for distributed cluster file system
CN103761162B (en) * 2014-01-11 2016-12-07 深圳清华大学研究院 Data backup method of distributed file system
CN103761162A (en) * 2014-01-11 2014-04-30 深圳清华大学研究院 Data backup method of distributed file system
CN105516230A (en) * 2014-10-15 2016-04-20 深圳市腾讯计算机系统有限公司 Data processing method and device

Similar Documents

Publication Publication Date Title
US10229125B2 (en) Remote data protection in a networked storage computing environment
JP5671615B2 (en) MapReduce immediately distributed file system
US8103628B2 (en) Directed placement of data in a redundant data storage system
George HBase: the definitive guide: random access to your planet-size data
US20160210201A9 (en) Techniques for backup restore and recovery of a pluggable database
US8315977B2 (en) Data synchronization between a data center environment and a cloud computing environment
JP6448609B2 (en) Data acquisition method and system
CN102177505B (en) Method for optimizing cleaning of maps in flashcopy cascades containing incremental maps
CN104160381B (en) Multi-tenant environments tenant-specific data set management method and system
Bailis et al. Bolt-on causal consistency
Sammer Hadoop operations
WO2007002855A2 (en) Parallel filesystem traversal for transparent mirroring of directories and files
US20150134796A1 (en) Dynamic partitioning techniques for data streams
US8972405B1 (en) Storage resource management information modeling in a cloud processing environment
JP5514903B2 (en) File-level hierarchical storage management system, method, and apparatus
CN102521009B (en) Ready to create and deploy virtual hard disk service
CN102541987A (en) Online database availability during upgrade
US9424151B2 (en) Disk failure recovery for virtual disk with policies
CN101964820B (en) Method and system for keeping data consistency
JP5740529B2 (en) Cloud storage
US9471590B2 (en) Method and apparatus for replicating virtual machine images using deduplication metadata
US20130218934A1 (en) Method for directory entries split and merge in distributed file system
US9043540B2 (en) Systems and methods for tracking block ownership
US9276959B2 (en) Client-configurable security options for data streams
US9705730B1 (en) Cloud storage using Merkle trees

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)