CN103049390B - Application metadata data processing method and storage system - Google Patents

Application metadata data processing method and storage system Download PDF

Info

Publication number
CN103049390B
CN103049390B CN 201210541231 CN201210541231A CN103049390B CN 103049390 B CN103049390 B CN 103049390B CN 201210541231 CN201210541231 CN 201210541231 CN 201210541231 A CN201210541231 A CN 201210541231A CN 103049390 B CN103049390 B CN 103049390B
Authority
CN
Grant status
Grant
Patent type
Application number
CN 201210541231
Other languages
Chinese (zh)
Other versions
CN103049390A (en )
Inventor
代海军
Original Assignee
华为技术有限公司
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
Grant date

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/06Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication

Abstract

本发明涉及一种应用元数据的数据处理方法及存储系统。 The present invention relates to data processing method and storage system for application metadata. 其中,应用的元数据包括:用于存储逻辑地址与物理地址映射关系的映射区和用于查询逻辑地址与物理地址映射关系在所述映射区中的位置的索引区;所述方法包括:存储系统接收数据的读或写请求,所述读或写请求中携带逻辑地址;根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址之间的映射关系;如果所述MP区中保存有所述映射关系,在所述映射关系对应的物理地址上对所述数据进行读或写处理。 Wherein the metadata application includes: means for mapping the logical address area storing the address mapping relationship between the physical index and a region of the location query logic address and the physical address mapping in the mapping region; the method comprising: storing system receives a read or write request for data, the read or write request carries a logical address; whether the data of the logical addresses and physical addresses of the logical address according to the index information by querying the index area of ​​the mapping area mapping relationship between; MP if the area is stored in the mapping relationship, the read data on a physical address corresponding to the mapping relationship or write process.

Description

应用元数据的数据处理方法及存储系统 Application metadata data processing method and storage system

技术领域 FIELD

[0001] 本发明涉及计算机技术领域,尤其涉及一种应用元数据的数据处理方法及存储系统。 [0001] The present invention relates to computer technology, and in particular relates to a data processing method, and a storage system metadata application.

背景技术 Background technique

[0002] 随着信息科学和技术的发展,需要存储的数据量以令人难以置信的速度迅猛增长,因此对存储系统资源的合理分类和利用也提出了更高的要求。 [0002] With the development of information science and technology, the amount of data that needs to be stored at an incredible rate of rapid growth, so a reasonable classification and utilization of storage system resources also put forward higher requirements. 一方面,存储系统需要满足当前业务的需求,通过简单的配置就能管理海量数据的存储;另一方面,在业务不算增长的过程中,存储系统能够扩充,并随着业务的增长而按需分配存储资源。 On the one hand, the storage system needs to meet the current needs of the business, through simple configuration able to manage mass data storage; on the other hand, in the course of business is not growing, the storage system can be expanded, and as your business grows and press need to allocate storage resources. 由此,自动精简配置技术应运而生。 Thus, thin provisioning technology came into being.

[0003]自动精简配置技术是从传统的空间分配方式直接演化而来的一种存储虚拟化技术,该技术将所有存储空间汇集到精简池中进行统一管理,在精简池上创建精简逻辑单元,按需从精简池获得物理存储空间。 [0003] Thin provisioning is a storage space allocation from the traditional direct evolved virtualization technology that will bring together all the storage space to the thin pool unified management, to create a streamlined logic unit in thin pool, according to required to obtain physical storage from the thin pool. 自动精简配置技术的使用可简化存储资源的配置管理,节约物理存储资源。 Thin use of storage resources to simplify the configuration of configuration management technology, saving physical storage resources.

[0004] 在自动精简配置技术中,元数据主要用于存储逻辑地址和物理地址的映射关系。 [0004] In the thin provisioning, the metadata is mainly used to store the mapping relationship between logical addresses and physical addresses. 元数据的可靠性是自动精简配置技术中最核心的技术。 Reliability metadata is thin provisioning technology in the core technology. 而现有的数据处理方法中,存储系统利用具有B树或B树变体(如B+树)结构的元数据对数据进行读写处理。 The existing data processing method using the storage system having a B-tree or a B-tree variant thereof (e.g., B + tree) metadata structure data write processing. 在B树元数据的节点中会存储有逻辑地址与物理地址映射关系,利用B树结构可以有效提高元数据的访问效率,具有很好的扩展性。 B-tree node metadata stored logical address and the physical address mapping relationship, using the B-tree structure can effectively improve the efficiency of access to the metadata, with good scalability. 但是,一旦B树元数据的一个节点损坏,会丢失该节点存储的逻辑地址与物理地址映射关系,同时会影响存储系统查找该损坏节点的下层节点,导致存储系统无法在元数据受影响的部分存储的逻辑地址与物理地址映射关系对应的物理地址上对数据进行处理。 However, once a node B-tree metadata corrupted, lost logical addresses and physical address mapping of the node stored will also affect the storage system to find the defective node is lower nodes, causes the storage system affected in the metadata portion processing the data on the physical address logical address-physical address mapping stored corresponding relationship.

发明内容 SUMMARY

[0005] 有鉴于此,本发明实施例提供了一种应用元数据的数据处理方法及存储系统,以实现当元数据部分损坏时,不会影响存储系统在元数据其他部分存储的逻辑地址与物理地址映射关系对应的物理地址上对数据进行处理。 [0005] In view of this, the embodiment provides a data processing method, and a storage system of the present invention, the application metadata to achieve when the damaged portion of the metadata, the metadata does not affect other parts of the storage system stores a logical address and processing the data on the physical address corresponding to physical address mapping relationship.

[0006] 在第一方面,本发明实施例提供了一种应用元数据的数据处理方法。 [0006] In a first aspect, embodiments of the present invention provides a data processing method for application metadata. 其中,所述元数据包括:用于存储逻辑地址与物理地址映射关系的映射区和用于查询逻辑地址与物理地址映射关系在所述映射区中的位置的索引区;所述方法包括: Wherein the metadata comprises: means for storing mapping logical addresses and physical addresses for the mapping relationship in the index area and the location query logic address and a physical address mapping in the mapping region; the method comprising:

[0007] 存储系统接收数据的读或写请求,所述读或写请求中携带逻辑地址; Read or write [0007] The data storage system receives a request, the read or write request carries a logical address;

[0008] 根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址之间的映射关系; [0008] The logical address whether the stored mapping relationship between the logical addresses and physical addresses of the index area index information query the mapping region;

[0009] 如果所述映射区中保存有所述映射关系,在所述映射关系对应的物理地址上对所述数据进行读或写处理。 [0009] If the stored mapping relationship of the mapping area, to read the data on a physical address corresponding to the mapping relationship or write process.

[0010] 在第一方面的第一种可能的实现方式中,所述映射区包括多个区域,每个区域预留一段空间用于存储逻辑地址与物理地址映射关系。 [0010] In a first possible implementation manner of the first aspect, the mapping area comprises a plurality of regions, each region is a space reserved for storing the logical addresses and physical address mappings.

[0011] 结合第一方面的第一种可能的实现方式,在第二种可能的实现方式中,所述方法还包括:如果所述映射区中没有保存所述映射关系,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址分配物理地址;在分配的物理地址上对所述数据进行写处理;根据所述分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中;根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与分配的物理地址之间的映射关系的位置。 [0011] The first possible implementation of the first aspect, in a second possible implementation, the method further comprising: if there is no save the mapping relationship of the mapping region, and the read or the write request is a write request, the write request was carried in the physical address logical address allocation; write processing the data on the physical address assignment; according to the physical address assigned to the write request corresponding to the mapping said stored mapping relationship in the region; according to the write request carries a logical address, the logical location of the mapping relationship between the physical address and the address stored in the assigned area map recorded in the index area.

[0012] 结合第一方面的第一种可能的实现方式,在第三种可能的实现方式中,所述方法还包括:在所述根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址的映射关系的同时,对元数据进行检测;如果映射区中保存所述映射关系的区域损坏,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址重新分配物理地址;在重新分配的物理地址上对所述数据进行写处理;根据所述重新分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中;根据所述写请求携带的逻辑地址,在所述索引区记录中映射区中保存所述逻辑地址与重新分配的物理地址之间的映射关系的位置。 [0012] The first possible implementation of the first aspect, in a third possible implementation, the method further comprises: by the index information in the index area according to the logical address query whether the stored mapping relationship between logical addresses and physical addresses in said mapping area while metadata is detected; damage mapping area if the mapping relationship stored in the region, and the read or write request is a write request, was carried in a logical address of the write request to reassign a physical address; write process on the data of the physical address reassignment; the physical address of the reassignment, the write request corresponding to the mapping relationship stored in the mapping region; logical address according to the write request carries, the mapping between the position of the region map stored in the logical addresses and physical addresses reassigned recorded in the index area.

[0013] 结合第一方面的第三种可能的实现方式,在第四种可能的实现方式中,所述方法还包括:如果所述索引区局部或全部损坏,根据映射区中每个区域保存的所述映射关系中的逻辑地址恢复所述索引区。 [0013] A third possible implementation manner of binding of the first aspect, in a fourth possible implementation manner, the method further comprising: if the region index partial or full breakdown, according to the mapping stored in the area of ​​each region logical addresses in the mapping of the index recovery zone.

[0014] 在第二方面,本发明实施例提供了一种应用元数据的存储系统。 [0014] In a second aspect, the present invention provides a storage system for application metadata. 其中,所述元数据包括:用于存储逻辑地址与物理地址映射关系的映射区和用于查询逻辑地址与物理地址映射关系在所述映射区中的位置的索引区;所述存储系统包括: Wherein the metadata comprises: a storage area for mapping the logical addresses and physical addresses for the mapping relationship between the index area and the location query logic address and a physical address mapping in the mapping region; the storage system comprising:

[0015] 接收单元,用于接收数据的读或写请求,所述读或写请求中携带逻辑地址; Read or write [0015] receiving means for receiving a request for data, the read or write request carries a logical address;

[0016] 查询单元,用于根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址之间的映射关系; [0016] The query unit, according to whether the logical address stored mapping relationship between the logical addresses and physical addresses of the index area index information query the mapping region;

[0017] 处理单元,用于如果所述映射区中保存有所述映射关系,在所述映射关系对应的物理地址上对所述数据进行读或写处理。 [0017] a processing unit for, if the mapping relation is stored in the mapping area, to read the data on a physical address corresponding to the mapping relationship or write process.

[0018] 在第二方面的第一种可能的实现方式中,所述映射区包括多个区域,每个区域预留一段空间用于存储逻辑地址与物理地址映射关系。 [0018] In a first possible implementation manner of the second aspect, the mapping area comprises a plurality of regions, each region is a space reserved for storing the logical addresses and physical address mappings.

[0019] 结合第一方面的第一种可能的实现方式,在第二种可能的实现方式中,所述存储系统还包括:分配单元,用于如果所述映射区中没有保存所述映射关系,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址分配物理地址;所述处理单元还用于在分配的物理地址上对所述数据进行写处理; [0019] In a first possible implementation manner of the first aspect, in a second possible implementation, the storage system further comprising: a dispensing unit, if the mapping relationship for mapping area is not stored in the and the read or write request is a write request, the write request was carried in the physical address logical address allocation; the processing unit is further configured to process the write data in the physical address assignment;

[0020] 记录单元,用于根据所述分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中,根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与分配的物理地址之间的映射关系的位置。 [0020] The recording unit according to the physical address assigned to the write request corresponding to the mapping relationship stored in the map area, the logical address according to the write request carried recorded in the index area the position mapping area saved mapping relationship between logical addresses and physical addresses assigned.

[0021] 结合第二方面的第一种可能的实现方式,在第三种可能的实现方式中,所述存储系统还包括:检测单元,用于在所述查询单元根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址的映射关系的同时,对元数据进行检测;分配单元,用于如果映射区中保存所述映射关系的区域损坏,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址重新分配物理地址;所述处理单元还用于在重新分配的物理地址上对所述数据进行写处理;记录单元,用于根据所述重新分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中,根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与重新分配的物理地址之间的映射关系的位置。 [0021] The first possible implementation of the second aspect, in a third possible implementation, the storage system further comprising: a detection unit configured by the query unit according to the logical address of the querying the index information mapping area of ​​said index area whether the stored mapping relationship between logical addresses and physical addresses while detecting the metadata; dispensing unit, if the region map region for storing the mapping relationship in damaged, and the read or write request is a write request, the write request was carried in the physical address logical address reassignment; the processing unit is further configured to write processed data in the reallocated physical address; a recording unit for the re-allocation according to the physical address of the write request corresponding to the mapping relationship stored in the map area, the logical address according to the write request carried in the mapping area recorded in the index area location mapping relationship between the stored logical addresses and physical addresses reassigned.

[0022] 结合第二方面的第三种可能的实现方式,在第四种可能的实现方式中,所述存储系统还包括:恢复单元,用于如果所述索引区局部或全部损坏,根据映射区中每个区域保存的所述映射关系中的逻辑地址恢复所述索引区。 [0022] The binding third possible implementation of the second aspect, in a fourth possible implementation manner, the storage system further comprising: a restoring unit configured to partially or completely damaged if the index area, the map the logical address area stored mapping relationship in each region to restore the index area.

[0023] 通过上述方案,由于元数据的索引区和映射区是独立的,存储系统通过索引区查找映射区中保存数据的读或写请求对应的逻辑地址与物理地址映射关系的位置时,如果映射区的部分发生损坏,只会丢失损坏部分的存储的逻辑地址与物理地址映射关系,不会影响存储系统通过索引区查找映射区其它部分存储的逻辑地址与物理地址映射关系,从而不会影响存储系统在未损坏部分保存的逻辑地址与物理地址映射关系对应的物理地址上对数据进行读或写处理。 [0023] By the above-described embodiment, due to the metadata index area and the mapped area are independent, the storage system by searching the mapping area for storing data read or write request position logical mapping between addresses and physical addresses corresponding to indexed by region, if partially mapped region is damaged, lost only logical addresses and physical addresses stored mapping relationship between the damaged part and will not affect the storage system looks logical address, address mapping other parts of the region and the physical memory mapping index by region, so as not to affect in the storage system physical address logical address-physical address mapping relation section undamaged stored data with the corresponding read or write process.

附图说明 BRIEF DESCRIPTION

[0024] 图1为本发明实施例应用的元数据结构示意图; [0024] FIG. 1 is a schematic diagram application metadata structure embodiment of the invention;

[0025] 图2为本发明实施例一提供的一种应用元数据的数据处理方法的流程图; [0025] FIG 2 is a flowchart diagram of a method for processing data provided in an application metadata embodiment of the invention;

[0026]图3为本发明实施例二提供的一种应用元数据的存储系统的结构示意图; [0026] FIG. 3 is a schematic structure of a storage system according to a second embodiment of an application of the present invention, the metadata;

[0027]图4为本发明实施例二提供的另一种应用元数据的存储系统的结构示意图; [0027] FIG. 4 is a schematic of another configuration of the storage system application metadata according to a second embodiment of the invention;

[0028]图5为本发明实施例三提供的一种存储系统的结构示意图。 [0028] FIG. 5 is a schematic structure of a storage system according to a third embodiment of the present invention.

具体实施方式 detailed description

[0029] 为了使本发明的目的、技术方案和优点更加清楚,下面将结合附图对本发明作进一步地详细描述,显然,所描述的实施例仅仅是本发明一部份实施例,而不是全部的实施例。 [0029] To make the objectives, technical solutions, and advantages of the present invention will become apparent in conjunction with the accompanying drawings below of the present invention will be further described in detail, obviously, the described embodiments are merely part of embodiments of the invention, rather than all embodiment. 基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例,都属于本发明保护的范围。 Based on the embodiments of the present invention, all other embodiments of ordinary skill in the art without any creative effort shall fall within the scope of the present invention.

[0030] 首先,以图1为例介绍本发明实施例应用的元数据结构。 [0030] First, FIG. 1 describes an example embodiment of a metadata structure of the embodiment of the present invention is applied. 图1为本发明实施例应用的元数据结构示意图。 1 a schematic diagram of a metadata structure of the embodiment of the present invention is applied. 该元数据包括映射区(Mapping Partitn,MP,以下简称MP区)和索引区(Index Partitn,IP,以下简称IP区)。 The metadata includes a mapping region (Mapping Partitn, MP, hereinafter referred to as MP region) and the index area (Index Partitn, IP, IP zone hereinafter). 其中,MP区用于存储逻辑地址和物理地址映射关系(Logic address and Physicaladdress Mapping,LPM)。 Wherein, MP area for storing the logical address and the physical address mapping relationship (Logic address and Physicaladdress Mapping, LPM). MP 区包括多个区域。 MP zone comprises a plurality of regions. 具体的,在物理磁盘上的每1G物理空间预留一段区域保存LPM,如图1所示,每1G为一个区域,每个区域中黑色部分为存储的LPM,每个黑格代表一个LPM,白色部分为存储的该区域中LPM对应的物理地址上的数据。 Specifically, each of the 1G physical space on the physical disk storage areas reserved section of the LPM, as shown in Figure 1, each of a 1G regions, each of the black portion to store the LPM, the LPM each represents a Haig, the white part of the area on the physical address corresponding to the stored data LPM. 需要说明的是,本发明不限制MP区每个区域的大小,MP区每个区域的大小为1G仅为本发明实施例的一种情况,并且MP区可无限扩展。 Incidentally, the present invention does not limit the size of each region MP areas, size of each region as a region where MP embodiment 1G of the embodiment of the present invention only, and MP can be infinitely extended area. IP区用于根据逻辑地址查询该逻辑地址对应的LPM在MP区中的位置。 IP for querying the position of the region corresponding to the logical address LPM in the MP according to a logical address area. IP区可以为B树结构,但不仅限于B树结构,IP区可为其他能够实现引索功能的结构。 IP zone may be a B-tree structure, the tree structure B but not limited to, IP zone may lead to other possible structures of the search functions.

[0031] 由图1可以看出,该元数据的IP区和MP区是两个独立的区域,当MP区的部分区域损坏时,不会影响IP区查找MP区未损坏区域的LPM。 [0031] As can be seen from FIG. 1, and the MP regions of the district IP metadata are two separate areas, when the damaged portion MP zone region, without affecting the MP IP lookup zone area is not damaged region LPM. 并且,当IP区发生损坏时,还可根据MP区进行恢复。 And, when the IP is damaged zone, may be recovered in accordance with MP region. 因此,在存储系统中应用该元数据,当因MP区的部分发生损坏导致部分LPM丢失时,不会影响存储系统利用IP区查找元数据MP区其它部分存储的LPM,从而不会影响存储系统在MP区其它部分存储的LPM对应的物理地址上进行数据读写处理。 Thus, application of the metadata in the storage system, when a damage caused due to partial loss occurs LPM portion MP of the region, the system will not affect the storage area IP lookup using other portions of the stored metadata MP LPM area, so as not to affect the storage system reading and writing data on the MP processing region LPM physical address corresponding to the other portions of the storage. 当IP区发生损坏时,不会影响整个存储系统对数据的处理。 When the IP is damaged zone, it will not affect the entire processing of the data storage system.

[0032] 下面以图2为例详细说明本发明实施例一提供的一种应用元数据的数据处理方法,图2为本发明实施例一提供的一种应用元数据的数据处理方法的流程图。 [0032] In the following detailed description of FIG. 2 as an example a data processing method of providing an application metadata embodiment of the present invention, FIG 2 is a flowchart diagram of a method for processing data provided in an application metadata embodiment of the present invention, . 该应用元数据的数据处理方法的执行主体为存储系统,该存储系统中应用上述元数据。 It performs the main data processing method for application metadata storage system, the storage system applying the metadata. 如图2所示,该应用元数据的数据处理方法包括以下步骤: As shown, the data processing method comprises the application metadata Step 2:

[0033] 步骤S201,存储系统接收数据的读或写请求。 [0033] step S201, the data storage system read or write request received.

[0034] 每个数据的读请求和写请求携带相同的逻辑地址,存储系统在接收到数据的读或写请求后,会根据读或写请求携带的逻辑地址查找相应的LPM,从而查找到逻辑地址对应的物理地址,在物理地址上对该数据进行读或写操作。 [0034] each of the read requests and the write data request carries the same logical address, the storage system upon receiving a read or write request for data, finds the corresponding logical address according LPM read or write request carried thereby find logic address of the corresponding physical address, the physical address on the data read or write operation.

[0035] 步骤S202,根据数据的读或写请求携带的逻辑地址通过IP区的索引信息查询MP区中是否保存有该数据的读或写请求携带的逻辑地址与物理地址的LPM。 [0035] In step S202, the read or write data in a logical address carried in the request by determining whether the stored data read or write request LPM logical addresses and physical addresses of the index information query carried region MP IP zone.

[0036] 存储系统首先根据数据的读或写请求携带的逻辑地址通过IP区的索引信息查询到该数据的读或写请求对应的MP区的区域,然后判断该区域中是否保存有与该数据的读或写请求携带的逻辑地址相关的LPM。 [0036] The storage system first the read or write request for data carried in a logical address queries to the data by the index information IP zone read or write request area MP region corresponding to, and then determines whether the area if stored with the data LPM logical address of a read or write request carries relevant. 如果查询到与该数据的读或写请求携带的逻辑地址相关的LPM,则说明MP区中保存有该数据的读或写请求对应的LPM,执行步骤S203。 If the query request carries a logical address to read or write the data to the associated LPM, then the MP region is stored in read or write the data corresponding to the request LPM, step S203. 如果没查询到与该数据的读或写请求携带的逻辑地址相关的LPM,则说明MP区中没有保存该数据的读或写请求对应的LPM,执行步骤S204。 If the query is not a logical address carried in the request to read or write the data associated LPM, then the MP region of the data is not stored in a read or write request corresponding LPM, step S204.

[0037] 例如,IP区的数据结构可以是哈希Hash表、B树及其变体、排序链表等多种结构。 [0037] For example, the data structure of IP zone can be the Hash table, B tree and variants thereof, and other structures sorted list. 下面以Hash表为例来描述根据逻辑地址查找物理地址的方法,该Hash表中Key值为逻辑地址,Value值为LPM在MP区的地址。 Hash table below to an example described according to the physical address logical address lookup method, the Key Hash table is a logical address, Value is the MP LPM address area. 该首先根据逻辑地址在Hash表中保存的key值与Value值的对应关系查询该读或写请求对应的LPM在MP区的地址,然后对LPM在MP区的地址进行读取即可获取读或写请求对应的LPM,从而根据LPM获取相应的物理地址。 The first query the read or write logical address according to the correspondence table stored in the key value and the Hash Value LPM value corresponding to the request in the address area of ​​the MP, and then read the address MP LPM area to read or obtain corresponding to the write request LPM, so as to obtain the corresponding physical address in accordance with LPM.

[0038] 步骤S203,如果MP区中保存有该数据的读或写请求对应的LPM,在该LPM对应的物理地址上对该数据进行读或写处理。 [0038] step S203, the read or write is stored if the data corresponding to the request LPM, read the data on the physical address corresponding to the LPM MP or write processing zone.

[0039] 如果MP区中保存有该数据的读或写请求对应的LPM,则根据LPM获知该数据的读或写请求携带的逻辑地址所对应的物理地址,然后在该物理地址上对该数据进行读或写处理。 [0039] If the stored data read or write request corresponding to the LPM, the known physical address read or write request carries the data corresponding to the logical address according to the LPM, and the data in the physical address area MP read or write processing.

[0040] 步骤S204,如果MP区中没有保存该数据的读或写请求对应的LPM,且该数据的读或写请求为该数据的写请求,为该数据的写请求携带的逻辑地址分配物理地址。 [0040] step S204, if the area does not store the MP data read or write request corresponding to the LPM, and the data read or write request for the data write request, the write data is carried in the request for a logical address allocated physical address.

[0041] 另外,如果MP区中没有保存该数据读或写请求对应的LPM,且该数据的读或写请求为该数据的读请求,则返回全0数据,以告知读取数据的设备该存储系统中没有保存相应的数据。 Read request [0041] Further, if the area does not store the MP data read or write request corresponding to the LPM, and the data read or write request for data, the data is all 0 returns the read data to the device to inform the the storage system does not store the corresponding data.

[0042] 步骤S205,在分配的物理地址上对该数据进行写处理。 [0042] In step S205, the physical address assigned to the data write process.

[0043] 存储系统在为该数据的写请求携带的逻辑地址分配物理地址后,便可在该物理地址上写入该数据。 After the [0043] storage system assigns a logical address in a physical address for the data write request is carried, the data can be written on the physical address. 在该物理地址上完成写入数据后,为保证之后能够通过元数据查找到该物理地址,对该物理地址上写入的数据进行处理,需要将该数据的写请求对应的LPM记录在元数据中,因此存储系统还需要执行以下步骤。 After the completion of the write data in the physical address, is then guaranteed by the metadata to find the physical address, processing the data written on the physical address, the need to write data corresponding to the request is recorded in the metadata LPM , so the storage system further requires the following steps.

[0044] 步骤S206,根据分配的物理地址,将该数据的写请求对应的LPM保存于MP区中。 [0044] step S206, the physical address allocation, the write data corresponding to the request stored in the MP LPM region.

[0045] 将写请求中携带的逻辑地址与分配的物理地址组成映射关系LPM,LPM保存在MP区的具体哪个位置,本专利不做限制,例如可以将MP区分成1G为单位的连续物理空间,每1G连续空间记为一个区域,将每个区域最前面的固定区域用于保存该区域所有物理地址对应的LPM。 [0045] A write physical address logical address assignment request carries the mapping relationship between the composition LPM, LPM which is stored in the specific area of ​​position MP, the present patent is not limited, and examples 1G MP area may be divided into units of physical space as a continuous each 1G referred to as a continuous space area, each area for fixing the front region of all physical addresses stored in the region corresponding to the LPM.

[0046] 存储系统首先根据分配的物理地址确定在MP区中保存该LPM的区域,然后在该区域中分配空间保存该LPM。 [0046] First, the storage system is determined according to the physical address assigned to the storage area in the MP region LPM, the LPM and allocates space in the storage area.

[0047] 步骤S207,根据该数据的写请求携带的逻辑地址,在IP区中记录MP区中保存该数据的写请求对应的LPM的位置。 [0047] step S207, according to the logical address of the data write request carried in the IP zone MP saves the data recording area of ​​the write request corresponding to the position of LPM.

[0048] 以IP区的数据结构为Hash表为例,该Hash表中Key值为逻辑地址,Value值为LPM在MP区的地址。 [0048] The structure of an IP data area is an example Hash table, the Key Hash table is a logical address, Value is the MP LPM address area. 该步骤即是在Hash表中增加一条记录。 This step is to add a record that is in the Hash table. 以便于存储系统再接收到该数据的读或写请求时,根据读或写请求携带的逻辑地址通过IP区的Hash表中的Key值与Value值的对应关系查询MP中保存该数据的读或写请求对应的LPM的地址,从而在该数据的读或写请求对应的LPM所对应的物理地址上对该数据进行读或写处理。 In order to stop receiving the storage system when the data read or write request, the read data is stored or corresponding relational query value MP Key Value Hash value IP zone table in the read or write request through logical address carried LPM write request corresponding to the address, thereby requesting the data read or write processing on a corresponding physical address corresponding to the LPM read or write the data.

[0049] 本实施例提供的应用元数据的处理方法中,除上述存储系统对数据进行读或写处理的方法之外,还包括当元数据发生损坏时,存储系统对数据的处理方法及恢复元数据的方法。 [0049] The application metadata processing method provided in this embodiment, in addition to the above data storage system read or write processing method further comprising when the metadata damaged, the processing method of the data storage and recovery system the method of metadata.

[0050] 具体的,步骤S202,根据数据的读或写请求携带的逻辑地址通过IP区的索引信息查询MP区中是否保存有该数据的读或写请求对应的LPM的同时,存储系统对元数据进行检测。 [0050] Specifically, the step S202, the read or write request for data carried in a logical address whether the data read or write the data while corresponding to the request LPM, the storage system metadata index information query MP area IP zone data detection. 如果元数据没有损坏,则执行上述步骤S203-S207。 If the metadata is not damaged, the above steps S203-S207 is executed.

[0051] 如果元数据的MP区中保存该数据的读或写请求对应的LPM的区域损坏,且该数据的读或写请求为数据的写请求,则重新为该数据的写请求携带的逻辑地址重新分配物理地址,在重新分配的物理地址上对该数据进行写处理,以保证在MP区部分区域发生损坏时,该数据能够正常写入。 [0051] If the MP region metadata stored in the read or write request for data corresponding to the LPM damaged area, and the data read or write request is a data write request, the write request for the data re logic carried address reassignment physical address, the data write process on the physical address reassignment to ensure that when the damaged zone MP partial region, the data can be normally written.

[0052] 为使得之后存储系统能够通过元数据查找到该重新分配的物理地址,对该物理地址上写入的数据进行处理,需要将该数据的写请求对应的LPM记录在元数据中,记录方法同步骤S206-S207,在此不再赘述。 [0052] After such storage system is able to find the physical address of the redistribution by the metadata, the data is written on the physical address for processing, the need to write data corresponding to the request LPM recorded in the metadata, the recording A method with the steps S206-S207, which will not be repeated herein.

[0053] 另外,如果元数据的MP区中保存该数据的读或写请求对应的LPM的区域损坏,且该数据的读或写请求为数据的读请求,则向读取该数据的设备返回错误消息。 [0053] Further, if the MP region metadata stored in the read or write request data corresponding to the LPM damaged area, and the data read or write request is a data read request, the device data is returned to the reader wrong information.

[0054] 如果元数据的IP区发生损坏,则根据MP区中每个区域保存的LPM中逻辑地址恢复IP区。 [0054] If the IP metadata damaged region, the recovery IP zone according to the logical address region LPM MP stored in each region. 具体的,存储系统依次访问物理磁盘每1G空间中用于存储LPM的空间,读取LPM。 Specifically, the disk storage system sequentially access the physical memory space for each of the LPM 1G space read LPM. 由于LPM中包括数据的读或写请求携带的逻辑地址,则存储系统根据读取的LPM重建IP区,具体的,可以采用哈希Hash表、B树及其变体、排序链表等的多种结构根据逻辑地址重建IP区。 Since the LPM comprises a read or write logical address of data carried in the request, the storage system in accordance with the read LPM reconstructed IP zone, particularly, may be employed a variety of the Hash table, B tree and variants thereof, and the like sorted list The logical structure reconstruction area IP address. 完成恢复后,IP区可正常进行索引。 After the recovery, IP area normally be indexed.

[0055] 利用本发明实施例一提供的应用元数据的处理方法,存储系统在接收到数据的读或写请求后,利用元数据的IP区查找MP区中存储的LPM,由于IP区和MP区是独立的,因此,当因MP区部分损坏导致部分数据丢失时,不会影响存储系统利用元数据的IP区查找MP区未损坏部分保存的LPM,从而不会影响存储系统对未丢失的数据进行读或写处理。 [0055] With the present invention, the processing method according to a first application metadata storage system embodiment after receiving the data read or write request using the IP zone metadata to find the LPM MP in the storage area, due to the IP region and MP region are independent, thus, when the damaged portion by portion MP region cause data loss does not affect the storage system metadata region using the IP lookup region portion MP LPM saved undamaged, so as not to affect the storage system is not lost data read or write processing. 并且,当元数据的IP区发生损坏时,可根据MP区中保存的LPM进行恢复,不会影响存储系统利用IP区查询MP区中的LPM,然后对数据进行读或写处理。 And, when the IP zone metadata damaged, can be restored according to the stored zone of the LPM MP, the storage system will not affect the query using the MP IP zone region the LPM, and the data read or write processing.

[0056] 相应的,本发明实施例二提供一种用以实现实施例一所述方法的存储系统。 [0056] Accordingly, according to a second embodiment of the present invention to provide a memory system for implementing the method of the one embodiment. 如图3所示,其为本发明实施例二提供的一种应用元数据的存储系统的结构示意图。 As shown in FIG. 3, a schematic configuration of the storage system according to an application of metadata according to a second embodiment of the present invention which. 该存储系统中应用的元数据包括用于存储LPM的MP区和用于查询LPM在所述MP区中的位置的IP区。 The metadata storage system for storing application includes the MP region LPM LPM queries for location in the region of the MP IP zone. 其中,MP区包括多个区域,每个区域预留一段空间用于存储LPM。 Wherein, the MP region comprises a plurality of regions, each region is a space reserved for storing LPM. 该存储系统包括:接收单元310,查询单元320和处理单元330。 The storage system comprising: a receiving unit 310, a query processing unit 320 and the unit 330.

[0057] 接收单元310用于接收数据的读或写请求。 [0057] The receiving unit 310 for receiving data read or write request. 同一数据的读或写请求中携带有相同的逻辑地址。 Read or write request carries the same data in the same logical address.

[0058] 查询单元320用于根据接收单元310接收到的数据的读或写请求携带的逻辑地址通过IP区的索引信息查询MP区中是否保存有该数据的读或写请求携带的逻辑地址与物理地址的LPM。 [0058] The inquiry unit 320 is used to read or write to the receiving unit 310 receives data through a logical address carried in the request whether the data read or write logical address of the data query request carries index information MP IP zone with the region LPM physical address.

[0059] 查询单元320首先根据数据的读或写请求携带的逻辑地址利用IP区查询到该数据的读或写请求对应的MP区的区域,然后判断该区域中是否保存有与该数据的读或写请求携带的逻辑地址相关的LPM。 [0059] The query unit 320 firstly the read or write request for data carried in a logical address using IP zone queried region MP region to read or write the data corresponding to the request, and then determines the region whether the data read and the data LPM or write logical address request carries relevant. 如果查询单元320查询到与该数据的读或写请求携带的逻辑地址相关的LPM,则说明MP区中保存有该数据的读或写请求对应的LPM。 If the query unit 320 queries the LPM carrying read or write request and the data associated with a logical address, then the MP region is stored in read or write the data corresponding to the request LPM. 如果查询单元320没查询到与该数据的读或写请求携带的逻辑地址相关的LPM,则说明MP区中没有保存该数据的读或写请求对应的LPM。 If the query is not a query unit 320 to carry LPM read or write request and the data associated with a logical address, then the area is not stored in MP read or write the data corresponding to the request LPM.

[0060] 处理单元330用于如果MP区中保存有该数据的读或写请求对应的LPM,在该数据的读或写请求对应的LPM所对应的物理地址上对该数据进行读或写处理。 [0060] The processing unit 330 for the data read or write processing on a physical address is stored in area if the MP read or write the data corresponding to the request LPM, read or write the data corresponding to the request corresponding to the LPM .

[0061] 另外,该存储系统还包括:分配单元340及记录单元350。 [0061] Further, the storage system further comprising: a dispensing unit 340 and the recording unit 350. 如图4所示,其为本发明实施例二提供的另一种应用元数据的存储系统的结构示意图。 4, a schematic view of another configuration of the storage system metadata application thereof according to a second embodiment of the present invention.

[0062] 分配单元340用于如果MP中没有保存该数据的读或写请求对应的LPM,且该数据的读或写请求为该数据的写请求,为该数据的写请求携带的逻辑地址分配物理地址。 [0062] If the MP for assignment unit 340 does not store the data corresponding to the read or write request to the LPM, and the data read or write request for the data write request, the write data is carried in the request for a logical address assignment physical address. 则处理单元330还用于在分配单元340分配的物理地址上对该数据进行写处理。 The processing unit 330 for further processing on the write data on a physical address allocation unit 340 allocation.

[0063] 记录单元350用于根据分配单元340分配的物理地址,将该数据的写请求对应的LPM保存于MP区中,根据该数据的写请求携带的逻辑地址,在所述IP区记录MP区中保存该数据的写请求对应的LPM的位置。 [0063] The recording unit 350 according to the physical address assigned to the dispensing unit 340, the write data corresponding to the request stored in the MP LPM region, according to the logical address of the write request data is carried in the IP recording area MP It saves the data area of ​​the write request corresponding to the position of LPM. 记录完成后,查询单元320便可根据该数据的读或写请求携带的逻辑地址通过元数据查找到该分配的物理地址,以使得处理单元330对该物理地址上写入的数据进行处理。 After the recording is completed, query unit 320 can be carried in the request to read or write the data to find the physical address of the logical address assigned by the metadata, so that the processing unit 330 processes the data written on the physical address.

[0064] 该存储系统还可以包括:检测单元360和恢复单元370。 [0064] The storage system may further comprise: a detection unit 360 and a recovery unit 370.

[0065] 检测单元360用于在查询单元320根据数据的读或写请求携带的逻辑地址通过IP区的索引信息查询MP区中是否保存有该数据的读或写请求对应的LPM的同时,对元数据进行检测,以使得当元数据发生损坏时,对数据做相应的处理及恢复损坏的元数据。 [0065] The detecting unit 360 for query unit 320 while the read or write data in a logical address carried in the request whether the data read or write the data corresponding to the request LPM index information query IP zone MP region of metadata is detected, so that when the metadata is damaged, the data processing and accordingly restore corrupted metadata. 则分配单元340还用于如果MP区中保存该数据的读或写请求对应的LPM的区域损坏,且该数据的读或写请求为该数据的写请求,为该数据的写请求携带的逻辑地址重新分配物理地址。 The dispensing unit 340 is further configured to save area if the MP of the data read or write requests corresponding to the LPM damaged area, and the data read or write request for the data write request, the write request for a logical data carried address reassign physical address. 相应的,处理单元330还用于在重新分配的物理地址上对该数据进行写处理。 Accordingly, the processing unit 330 for further processing on the write data on the physical address reassignment. 而记录单元350还用于根据重新分配的物理地址,将该数据的写请求对应的LPM保存于MP区中,然后根据改数据的写请求携带的逻辑地址,在IP区记录MP区中保存该数据的写请求对应的LPM的位置。 And the recording unit 350 is further configured to reassign a physical address of the write data corresponding to the request stored in the MP LPM area, then write the modified data according to the logical address carried in the request, the MP area of ​​the recording area IP saved LPM positions corresponding to the write request data.

[0066] 恢复单元370用于如果IP区局部或全部损坏,根据MP区中每个区域保存的LPM恢复IP区。 [0066] If the IP restoring unit 370 for partial or full breakdown zone, the recovery zone IP zone according MP stored in each region LPM. 具体的,恢复单元370依次访问物理磁盘每1G空间中用于存储LPM的空间,读取LPM。 Specifically, the recovery unit 370 sequentially access the physical disk storage space for each of the LPM 1G space read LPM. 由于LPM中包括数据的读或写请求携带的逻辑地址,所以恢复单元370根据读取的LPM中的逻辑地址重建IP区。 Since the LPM comprises a read or write logical address of data carried in the request, the restore unit 370 according to the logical address area reconstructed IP LPM in the read. 完成恢复后,IP区可正常进行索引。 After the recovery, IP area normally be indexed.

[0067] 需要说明的是,本实施例提供的一种应用元数据的存储系统所包括的各个单元只是按照功能逻辑进行划分的,但并不局限于上述的划分,只要能够实现相应的功能即可•'另夕卜,各功能单元的具体名称也只是为了便于相互区分,并不用于限制本发明的保护范围。 [0067] Incidentally, each unit an application metadata storage system according to this embodiment comprises only the divided according to functional logic, but are not limited to the division can be achieved as long as the corresponding function i.e. may be • 'Bu Xi another, specific names of the functional units are only to facilitate distinguished from each other, it is not intended to limit the scope of the present invention.

[0068] 利用本发明实施例二提供的应用元数据的存储系统,存储系统在接收到数据的读或写请求后,利用元数据的IP区查找MP区中存储的LPM,由于IP区和MP区是独立的,因此,当因MP区部分损坏导致部分数据丢失时,不会影响存储系统利用元数据的IP区查找MP区未损坏部分保存的LPM,从而不会影响存储系统对未丢失的数据进行读或写处理。 [0068] With the present invention, a storage system according to a second application metadata embodiment, the storage system upon receiving a data read or write request using the IP zone metadata to find the LPM MP in the storage area, due to the IP region and MP region are independent, thus, when the damaged portion by portion MP region cause data loss does not affect the storage system metadata region using the IP lookup region portion MP LPM saved undamaged, so as not to affect the storage system is not lost data read or write processing. 并且,当元数据的IP区发生损坏时,可根据MP区中保存的LPM进行恢复,不会影响存储系统利用IP区查询MP区中的LPM,然后对数据进行读或写处理。 And, when the IP zone metadata damaged, can be restored according to the stored zone of the LPM MP, the storage system will not affect the query using the MP IP zone region the LPM, and the data read or write processing.

[0069] 在硬件实现上,以上接收单元310可以为接收机或收发机。 [0069] In the hardware implementation, the above receiving unit 310 may be a receiver or a transceiver. 以上除接收单元310以外的其它单元可以以硬件形式内嵌于或独立于存储系统的处理器中,也可以以软件形式存储于存储系统的存储器中,以便于处理器调用执行以上各个模块对应的操作。 Other than the above other units receiving unit 310 may be embedded in hardware form or storage system independently of a processor, it may be stored in a memory storage system in the form of software, in order to perform the above respective modules corresponding to the call processor operating. 该处理器可以为中央处理单元(CPU )、微处理器、单片机等。 The processor may be a central processing unit (CPU), a microprocessor, microcontroller, etc.

[0070] 如图5所示,其为本发明实施例三提供的一种存储系统的结构示意图。 [0070] As shown in FIG. 5, a schematic structure of a storage system according to a third embodiment of the present invention. 该存储系统包括收发机510、存储器520以及分别与收发机510和存储器520连接的处理器530。 The storage system includes a transceiver 510, a processor 530 and memory 520 are connected to the transceiver 510 and a memory 520. 当然,存储系统还可以包括天线、基带处理部件、中射频处理部件、输入输出装置等通用部件,本发明实施例在此不再任何限制。 Of course, the storage system may further include a common antenna means, baseband processing section, the RF processing section, the input and output devices, embodiments of the invention which is not any restriction.

[0071] 其中,存储器520中存储一组程序代码,且处理器530用于调用存储器520中存储的程序代码,用于执行以下操作: [0071] wherein, the memory 520 stores a set of program code, and the processor 530 for invoking the memory 520 stores program code for performing the following operations:

[0072] 接收数据的读或写请求,所述读或写请求中携带逻辑地址; Read or write [0072] requests received data, the read or write request carries a logical address;

[0073] 根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址之间的映射关系; [0073] The logical address whether the stored mapping relationship between the logical addresses and physical addresses of the index area index information query the mapping region;

[0074] 如果所述映射区中保存有所述映射关系,在所述映射关系对应的物理地址上对所述数据进行读或写处理。 [0074] If the stored mapping relationship of the mapping area, to read the data on a physical address corresponding to the mapping relationship or write process.

[0075] 进一步地,存储器520中存储一组程序代码,且处理器530用于调用存储器520中存储的程序代码,还可以用于执行以下操作: [0075] Further, the memory 520 stores a set of program code, and the processor 530 calls the program code stored in memory 520, may also be used to perform the following operations:

[0076] 如果所述映射区中没有保存所述映射关系,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址分配物理地址; [0076] If the mapping area is not stored in the mapping relationship, and the read or write request is a write request, the write request was carried in the physical address logical address allocation;

[0077] 在分配的物理地址上对所述数据进行写处理; [0077] The data write process on the physical address assignment;

[0078] 根据所述分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中; [0078] The physical address of the allocated, the write request corresponding to the mapping relationship stored in the mapping region;

[0079] 根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与分配的物理地址之间的映射关系的位置。 [0079] The logical address of the write request carried in the index area storing the map area recording a mapping relationship between the logical position and the physical address of the address assignment.

[0080] 进一步地,存储器520中存储一组程序代码,且处理器530用于调用存储器520中存储的程序代码,还可以用于执行以下操作: [0080] Further, the memory 520 stores a set of program code, and the processor 530 calls the program code stored in memory 520, may also be used to perform the following operations:

[0081] 在所述根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址的映射关系的同时,对元数据进行检测; [0081] The logical address is at the same time whether the stored mapping relationship between the logical addresses and physical addresses of the index information of the index area querying the mapping area, the metadata in said detecting;

[0082] 如果映射区中保存所述映射关系的区域损坏,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址重新分配物理地址; [0082] If the region map stored in the mapping relationship between the damaged area, and the read or write request is a write request, reallocation of a physical address logical address of the write request was carried;

[0083] 在重新分配的物理地址上对所述数据进行写处理; [0083] The process of the write data in the physical address reassignment;

[0084] 根据所述重新分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中; [0084] The physical address of the reassignment, the write request corresponding to the mapping relationship stored in the mapping region;

[0085] 根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与重新分配的物理地址之间的映射关系的位置。 [0085] The logical address of the write request carries the mapping relationship between the logical position and the physical address of the address reassignment area map stored in the index recording area.

[0086] 进一步地,存储器520中存储一组程序代码,且处理器530用于调用存储器520中存储的程序代码,还可以用于执行以下操作: [0086] Further, the memory 520 stores a set of program code, and the processor 530 calls the program code stored in memory 520, may also be used to perform the following operations:

[0087] 如果所述索引区局部或全部损坏,根据映射区中每个区域保存的所述映射关系中的逻辑地址恢复所述索引区。 [0087] If the index area of ​​partial or full breakdown, according to the mapping relationship between the logical address stored in the mapping area in each region of the index recovery zone.

[0088] 需要说明的是,实施例二和实施例三中所提供的存储系统均可以用于实现实施例一所提供的方法,且关于元数据等的描述同实施例二中的描述,在此不再赘述。 [0088] Incidentally, according to the second embodiment, and the storage system in the third embodiment can be provided in one embodiment for implementing the methods provided in the embodiments, and the like described with metadata in the two embodiments described, in this will not be repeated.

[0089] 利用本发明实施例三提供的存储系统,存储系统在接收到数据的读或写请求后,利用元数据的IP区查找MP区中存储的LPM,由于IP区和MP区是独立的,因此,当因MP区部分损坏导致部分数据丢失时,不会影响存储系统利用元数据的IP区查找MP区未损坏部分保存的LPM,从而不会影响存储系统对未丢失的数据进行读或写处理。 [0089] With the present invention, a storage system according to a third storage system implemented upon receiving a data read or write request using the IP zone metadata to find the LPM MP in the storage area, due to the IP region and the MP region are independent Therefore, when the damaged portion by portion MP region cause data loss does not affect the storage system metadata region using the IP lookup region portion MP LPM saved undamaged, so as not to affect the storage system to read data is not lost or write processing. 并且,当元数据的IP区发生损坏时,可根据MP区中保存的LPM进行恢复,不会影响存储系统利用IP区查询MP区中的LPM,然后对数据进行读或写处理。 And, when the IP zone metadata damaged, can be restored according to the stored zone of the LPM MP, the storage system will not affect the query using the MP IP zone region the LPM, and the data read or write processing.

[0090] 专业人员应该还可以进一步意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、计算机软件或者二者的结合来实现,为了清楚地说明硬件和软件的可互换性,在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。 [0090] professionals should also be further appreciated that, as disclosed herein in conjunction with units and algorithm steps described exemplary embodiments, by electronic hardware, computer software, or a combination thereof. In order to clearly illustrate hardware and software interchangeability, in the above description, according to functions generally described compositions and steps of the examples. 这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。 Whether these functions are performed by hardware or software depends upon the particular application and design constraints of the technical solutions. 专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本发明的范围。 Professional technical staff may use different methods for each specific application to implement the described functionality, but such implementation should not be considered outside the scope of the present invention.

[0091] 结合本文中所公开的实施例描述的方法或算法的步骤可以用硬件、处理器执行的软件模块,或者二者的结合来实施。 [0091] The steps of a method or algorithm described in the embodiments disclosed herein may be implemented in hardware, or a combination thereof, in a software module executed by a processor to implement. 软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。 A software module may be placed in a random access memory (RAM), a memory, a read only memory (ROM), electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, CD-ROM, or within the technical field known any other form of storage medium.

[0092] 以上所述的具体实施方式,对本发明的目的、技术方案和有益效果进行了进一步详细说明,所应理解的是,以上所述仅为本发明的具体实施方式而已,并不用于限定本发明的保护范围,凡在本发明的精神和原则之内,所做的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。 [0092] The foregoing specific embodiments, objectives, technical solutions, and advantages of the invention will be further described in detail, it should be understood that the above descriptions are merely specific embodiments of the present invention, but not intended to limit the scope of the present invention, all within the spirit and principle of the present invention, any changes made, equivalent substitutions and improvements should be included within the scope of the present invention.

Claims (10)

  1. 1.一种应用元数据的数据处理方法,其特征在于,所述元数据的数据结构包括:用于存储逻辑地址与物理地址映射关系的映射区和用于存储逻辑地址和所述映射关系在所述映射区中的位置的对应关系的索引区;所述方法包括: 存储系统接收数据的读或写请求,所述读或写请求中携带逻辑地址; 根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址之间的映射关系; 如果所述映射区中保存有所述映射关系,则在所述索引区中获取所述映射关系在所述映射区中的位置,根据所获取的所述映射关系在所述映射区中的位置在所述映射区找到所述映射关系,在所述映射关系中所述逻辑地址对应的物理地址上对所述数据进行读或写处理。 1. A data processing method for application of metadata, wherein the metadata data structure comprising: means for storing mapping logical addresses and physical addresses of the mapping area for storing the relationship between the logical address and the mapping relationship index area corresponding relationship between the position of the mapping region; the method comprising: receiving a read or write request for data storage system, the read or write request carries a logical address; according to the logical address of said index area index information query whether the mapping area stores a mapping relationship between the logical addresses and physical addresses; if the mapping relation is stored in the mapping area, the mapping relation is acquired in the index area position in the mapping area, the mapping relationship between the position acquired in the mapping area is found in the mapping relationship of the mapping area, the mapping relationship between the physical address of the logical address corresponding to on the data read or write processing.
  2. 2.根据权利要求1所述的方法,其特征在于,所述映射区包括多个区域,每个区域预留一段空间用于存储所述映射关系。 2. The method according to claim 1, wherein the mapping area comprises a plurality of regions, each region is a space reserved for storing the mapping relation.
  3. 3.根据权利要求2所述的方法,其特征在于,所述方法还包括: 如果所述映射区中没有保存所述映射关系,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址分配物理地址; 在分配的物理地址上对所述数据进行写处理; 根据所述分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中; 根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与分配的物理地址之间的映射关系的位置。 3. The method according to claim 2, wherein said method further comprises: if there is no save the mapping relationship of the mapping region, and the read or write request is a write request, the write was logical address allocation request carries physical addresses; write processing the data on the physical address assignment; according to the physical address assigned to the write request corresponding to the mapping relationship stored in the mapping region; according said write logical address carried in the request, stored in the mapping area recording location mapping relationship between logical addresses and physical addresses assigned in the index area.
  4. 4.根据权利要求2所述的方法,其特征在于,所述方法还包括: 在所述根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址的映射关系的同时,对元数据进行检测; 如果映射区中保存所述映射关系的区域损坏,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址重新分配物理地址; 在重新分配的物理地址上对所述数据进行写处理; 根据所述重新分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中;根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与重新分配的物理地址之间的映射关系的位置。 4. The method according to claim 2, wherein said method further comprises: if the stored logical address is the logical address according to the index information of the index area querying the mapping region and mapping relationship of the physical address at the same time, the metadata detection; mapping area if the mapping relationship of the storage area of ​​damage, and the read or write request is a write request, the write request was carried logical address re- assign a physical address; write process on the data of the physical address reassignment; the physical address of the reassignment, the write request corresponding to the mapping relationship stored in the mapping region; according to the write request logical address carried in the location of the mapping between the logical addresses and physical addresses reassigned map area records stored in the index area.
  5. 5.根据权利要求4所述的方法,其特征在于,所述方法还包括: 如果所述索引区局部或全部损坏,根据映射区中每个区域保存的所述映射关系中的逻辑地址恢复所述索引区。 The method according to claim 4, characterized in that the method further comprises: if the index area damaged part or in whole, to restore the logical address according to the mapping relationship stored in each area of ​​the mapping area said index area.
  6. 6.一种应用元数据的存储系统,其特征在于,所述元数据的数据结构包括:用于存储逻辑地址与物理地址映射关系的映射区和用于存储逻辑地址和所述映射关系在所述映射区中的位置的对应关系的索引区;所述存储系统包括: 接收单元,用于接收数据的读或写请求,所述读或写请求中携带逻辑地址; 查询单元,用于根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址之间的映射关系; 处理单元,用于如果所述映射区中保存有所述映射关系,则在所述索引区中获取所述映射关系在所述映射区中的位置,根据所获取的所述映射关系在所述映射区中的位置在所述映射区找到所述映射关系,在所述映射关系中所述逻辑地址对应的物理地址上对所述数据进行读或写处理。 A storage system application metadata, wherein the metadata data structure comprising: a storage area for mapping the logical addresses and physical addresses and for storing a mapping relationship between the logical address and the mapping relationship index area corresponding relationship between the position of said mapping region; the storage system comprising: receiving means for receiving a request to read or write data, the read or write request carries a logical address; query unit, according to the said logical address whether the stored mapping relationship between the logical addresses and physical addresses of the index area index information query the mapping region; a processing unit for, if the region map stored in the mapping relationship , in the index region is acquired in the mapping of the positional relationship of the mapping area, the mapping relationship found in the mapping area according to the mapping relationship between the position acquired in the mapping region, the read or write processing on a physical address in the mapping of the logical address corresponding to the data.
  7. 7.根据权利要求6所述的存储系统,其特征在于,所述映射区包括多个区域,每个区域预留一段空间用于存储所述映射关系。 The storage system according to claim 6, wherein the mapping area comprises a plurality of regions, each region is a space reserved for storing the mapping relation.
  8. 8.根据权利要求7所述的存储系统,其特征在于,所述存储系统还包括: 分配单元,用于如果所述映射区中没有保存所述映射关系,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址分配物理地址; 所述处理单元还用于在分配的物理地址上对所述数据进行写处理; 记录单元,用于根据所述分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中,根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与分配的物理地址的之间映射关系的位置。 8. The storage system of claim 7, wherein the storage system further comprising: a dispensing unit for, if the mapping relation is not saved in the mapping area, and the read or write request is a write request, the write request was carried in the physical address logical address allocation; the processing unit is further configured to process the write data in the physical address assignment; a recording unit, the allocated physical addresses in accordance with, between the write request corresponding to the mapping relationship stored in the map area, the logical address according to the write request carried in the index area storing the map area recording the logical address physical address assigned mapping positional relationship.
  9. 9.根据权利要求7所述的存储系统,其特征在于,所述存储系统还包括: 检测单元,用于在所述查询单元根据所述逻辑地址通过所述索引区的索引信息查询所述映射区中是否保存有所述逻辑地址与物理地址的映射关系的同时,对元数据进行检测; 分配单元,用于如果映射区中保存所述映射关系的区域损坏,且所述读或写请求为写请求,则为所述写请求携带的逻辑地址重新分配物理地址; 所述处理单元还用于在重新分配的物理地址上对所述数据进行写处理; 记录单元,用于根据所述重新分配的物理地址,将所述写请求对应的所述映射关系保存于映射区中,根据所述写请求携带的逻辑地址,在所述索引区中记录映射区中保存所述逻辑地址与重新分配的物理地址之间的映射关系的位置。 9. The memory system of claim 7, wherein the storage system further comprising: a detection unit for index information in the query unit queries the index area according to the mapping of the logical address whether the data area of ​​the mapping between logical addresses and physical addresses while, the metadata detection; dispensing unit, for mapping area if the damaged region of the mapping relationship stored in, and the read or write request is a write request, the logical address of the write request was carried reassign a physical address; the processing unit is further configured to process the write data on a physical address reassignment; a recording unit, according to the reallocation physical address, the write request corresponding to the mapping relationship stored in the mapping area in accordance with the write request carries a logical address map stored in the logical address region and redistribute in the index recording area location mapping relationship between the physical address.
  10. 10.根据权利要求9所述的存储系统,其特征在于,所述存储系统还包括: 恢复单元,用于如果所述索引区局部或全部损坏,根据映射区中每个区域保存的所述映射关系中的逻辑地址恢复所述索引区。 10. The storage system according to claim 9, wherein the storage system further comprising: a restoring unit configured to partially or completely damaged, if the region index based on the mapping area map stored in each area restoring the logical address in the index relationship zone.
CN 201210541231 2012-12-14 2012-12-14 Application metadata data processing method and storage system CN103049390B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201210541231 CN103049390B (en) 2012-12-14 2012-12-14 Application metadata data processing method and storage system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN 201210541231 CN103049390B (en) 2012-12-14 2012-12-14 Application metadata data processing method and storage system
PCT/CN2013/080973 WO2014089981A1 (en) 2012-12-14 2013-08-07 Data processing method and storing system for applied metadata

Publications (2)

Publication Number Publication Date
CN103049390A true CN103049390A (en) 2013-04-17
CN103049390B true CN103049390B (en) 2016-03-09

Family

ID=48062037

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201210541231 CN103049390B (en) 2012-12-14 2012-12-14 Application metadata data processing method and storage system

Country Status (2)

Country Link
CN (1) CN103049390B (en)
WO (1) WO2014089981A1 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049390B (en) * 2012-12-14 2016-03-09 华为技术有限公司 Application metadata data processing method and storage system
CN104182508A (en) * 2014-08-19 2014-12-03 华为技术有限公司 Data processing method and data processing device
CN105516001A (en) * 2014-09-22 2016-04-20 中兴通讯股份有限公司 Method and device for controlling data recovery after soft reset, and packet transport network equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101510144A (en) * 2009-03-24 2009-08-19 中国科学院计算技术研究所 Distributed cache system based on distributed virtual machine manager and working method thereof
CN102483714A (en) * 2009-07-24 2012-05-30 苹果公司 Restore Index Page
CN102651009A (en) * 2011-02-28 2012-08-29 国际商业机器公司 Method and equipment for retrieving data in storage system

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8005792B2 (en) * 2004-05-14 2011-08-23 Oracle International Corporation System and method for managing versions of metadata
US7774575B2 (en) * 2004-09-21 2010-08-10 Intel Corporation Integrated circuit capable of mapping logical block address data across multiple domains
CN101656094B (en) * 2009-09-25 2012-04-18 杭州华三通信技术有限公司 Data storage method and storage device
US9430155B2 (en) * 2010-03-25 2016-08-30 International Business Machines Corporation File index, metadata storage, and file system management for magnetic tape
CN101814044B (en) * 2010-04-19 2013-03-20 中兴通讯股份有限公司 Method and device for processing metadata
CN102024044B (en) * 2010-12-08 2012-11-21 华为技术有限公司 Distributed file system
CN102629247B (en) * 2011-12-31 2014-09-17 华为数字技术(成都)有限公司 Method, device and system for data processing
CN102779080B (en) * 2012-06-18 2015-05-27 上海爱数软件有限公司 Method for generating snapshot, method and device for data recovery by using snapshot
CN103049390B (en) * 2012-12-14 2016-03-09 华为技术有限公司 Application metadata data processing method and storage system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101510144A (en) * 2009-03-24 2009-08-19 中国科学院计算技术研究所 Distributed cache system based on distributed virtual machine manager and working method thereof
CN102483714A (en) * 2009-07-24 2012-05-30 苹果公司 Restore Index Page
CN102651009A (en) * 2011-02-28 2012-08-29 国际商业机器公司 Method and equipment for retrieving data in storage system

Also Published As

Publication number Publication date Type
WO2014089981A1 (en) 2014-06-19 application
CN103049390A (en) 2013-04-17 application

Similar Documents

Publication Publication Date Title
US7930515B2 (en) Virtual memory management
US7676628B1 (en) Methods, systems, and computer program products for providing access to shared storage by computing grids and clusters with large numbers of nodes
US20100191919A1 (en) Append-based shared persistent storage
US20140068224A1 (en) Block-level Access to Parallel Storage
US20070136506A1 (en) Large page optimizations in a virtual machine environment
US20140282514A1 (en) Virtualization support for storage devices
US8751763B1 (en) Low-overhead deduplication within a block-based data storage
US20120110293A1 (en) Method and system for managing virtual machine storage space and physical host
CN101221536A (en) Internal memory managing method and device of embedded system
CN1532708A (en) Static internal storage management method
US20140052946A1 (en) Techniques for opportunistic data storage
CN102185929A (en) Storage area network (SAN)-resource-based video monitoring data storage method and device
US20130054924A1 (en) Preemptively allocating extents to a data set
CN103365929A (en) Management method and management system of database connection
US20080270690A1 (en) System and method for efficient updates of sequential block storage
CN102326149A (en) Realization method and apparatus for internal memory migration
US20130227198A1 (en) Flash memory device and electronic device employing thereof
CN1560746A (en) Page transport and copy method based on operation system reverse page table
CN101692252A (en) Method for distributing and reclaiming idle blocks of file
US20050102465A1 (en) Managing a cache with pinned data
US20130061009A1 (en) High Performance Free Buffer Allocation and Deallocation
CN102255962A (en) Distributive storage method, device and system
CN102650931A (en) Method and system for writing data
CN103455437A (en) Data-storage device and flash memory control method
US20110276776A1 (en) Addressing for Huge Direct-Mapped Object Systems

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C14 Grant of patent or utility model