公开(公告)号：JP2006260582A

公开(公告)日：2006-09-28

申请号：JP2006107735

申请日：2006-04-10

Applicant: Network Appliance Inc ,  ネットワーク・アプライアンス・インコーポレイテッド

Inventor： HITZ DAVID ,  MALCOLM MICHAEL ,  LAU JAMES ,  RAKITZIS BYRON

IPC: G06F3/06 ,  G06F11/10 ,  G06F12/00 ,  G06F17/30

CPC classification number: G06F11/1076 ,  G06F3/0601 ,  G06F3/0613 ,  G06F3/0643 ,  G06F3/0689 ,  G06F2003/0697 ,  Y10S707/99955

Abstract: PROBLEM TO BE SOLVED: To integrate a file system with a RAID array so as to export precise information about the arrangement of data blocks in the RAID subsystem. SOLUTION: Individual CWL pointers are used for each disk 1022 in the disk array 1030. The algorithm aims to improve efficiency of RAID and read-out performance. For the above purpose, it always writes on the disk 1022 with the lowest CWL pointer. In addition, another disk is chosen only when space for a new file is start to be allocated or when N blocks on the same disk 1022 has been allocated for a single file. The result is that CWL pointers are never more than N blocks apart even on different disks 1024, and a large file can also be allocated in N consecutive blocks on the same disk 1022. COPYRIGHT: (C)2006,JPO&NCIPI

Abstract translation: 要解决的问题：将文件系统与RAID阵列集成，以便导出关于RAID子系统中数据块排列的精确信息。 解决方案：单个CWL指针用于磁盘阵列1030中的每个磁盘1022.该算法旨在提高RAID和读出性能的效率。 为了上述目的，它始终以最低的CWL指针写在盘1022上。 此外，仅当新文件的空间开始分配时，或者当同一磁盘1022上的N个块已被分配给单个文件时，才选择另一个磁盘。 结果是即使在不同的磁盘1024上，CWL指针也不会超过N个块，并且大的文件也可以在同一个磁盘102上的N个连续块中分配。（C）2006年，JPO和NCIPI

公开(公告)号：JP2004038928A

公开(公告)日：2004-02-05

申请号：JP2003075430

申请日：2003-03-19

Applicant: Network Appliance Inc ,  ネットワーク・アプライアンス・インコーポレイテッド

Inventor： FEDERWISCH MICHAEL L ,  OWARA SHANE S ,  MANLEY STEPHEN L ,  KLEIMAN STEVEN R

IPC: G06F3/06 ,  G06F11/14 ,  G06F11/20 ,  G06F12/00 ,  G06F17/30

CPC classification number: G06F11/2074 ,  G06F11/1451 ,  G06F11/2066 ,  G06F17/30144 ,  G06F17/30212

Abstract: PROBLEM TO BE SOLVED: To enhance versatility and utility of a snapshot duplication means. SOLUTION: A system and a method are for performing remote asynchronous duplication, namely, mirroring of change of source file system snapshots to a duplicated file system at a destination by identifying a block changed by difference of block volume numbers identified in the case of scanning a logical file block index of each snapshot by utilizing scan (by a scanner) of blocks constituting two versions of snapshots of the source file system. A tree of the block regarding the file is checked, a pointer without changes between versions is bypassed and proceeded downward and changes of hierarchy of trees are identified and the changes are transmitted to a destination mirror, namely, a duplicated snapshot. At the destination, the destination snapshot is updated by using source change. Every deleted or changed inode already existing on the destination is transferred to a temporary directory, namely, "momentary" directory and when it is reused, it is re-linked with the reconstructed duplicated snapshot directory. COPYRIGHT: (C)2004,JPO

公开(公告)号：WO2009058190A3

公开(公告)日：2010-02-18

申请号：PCT/US2008011503

申请日：2008-10-06

Applicant: NETWORK APPLIANCE INC

Inventor： PAWLOWSKI BRIAN

IPC: G06F9/50 ,  G06F9/445 ,  H04L29/08

CPC classification number: G06F9/5083 ,  G06F9/45533 ,  H04L67/10

Abstract: A system and method employs one or more clients of a virtualized compute cluster as an execution engine for a portion of a storage operating system implemented as a virtual machine on a storage system node of a storage system cluster. If there is processing bandwidth of a client that is not fully utilized and the load on the storage system node is high, the portion of the storage operating system is ported to the client of the compute cluster in a manner that externally distributes the storage architecture from the storage system cluster. Advantageously, the processing performance of the storage system cluster is improved by, among other things, offloading some of the net- work processing load from the storage system node.

Abstract translation: 系统和方法使用虚拟化计算集群的一个或多个客户端作为在存储系统集群的存储系统节点上实现为虚拟机的存储操作系统的一部分的执行引擎。 如果客户端的处理带宽没有得到充分利用并且存储系统节点的负载较高，那么存储操作系统的部分将以从外部分配存储体系结构的方式移植到计算集群的客户端 存储系统集群。 有利的是，除了别的以外，存储系统集群的处理性能通过从存储系统节点卸载一些网络处理负载来改善。

公开(公告)号：WO2008094594A3

公开(公告)日：2009-07-09

申请号：PCT/US2008001219

申请日：2008-01-29

Applicant: NETWORK APPLIANCE INC ,  MOORTHI JAY R ,  MERRICK JEFFREY D

Inventor： MOORTHI JAY R ,  MERRICK JEFFREY D

IPC: G06F17/30

CPC classification number: G06F17/30079 ,  G06F17/30085

Abstract: Methods of iterating through a set of data objects on a source server, copying them to a destination server, and preparing a mapping database correlating source and destination data object identifiers are described and claimed. The mapping database also includes data retention policy information and policy discrepancy information. Systems using similar methods, and software to perform similar methods, are also described and claimed.

Abstract translation: 对源服务器上的一组数据对象进行迭代，将其复制到目标服务器以及准备关联源数据对象标识符和目标数据对象标识符的映射数据库的方法进行描述和声明。 映射数据库还包括数据保留策略信息和策略差异信息。 还描述和要求保护使用类似方法的系统和执行类似方法的软件。

公开(公告)号：WO2009058189A1

公开(公告)日：2009-05-07

申请号：PCT/US2008/011502

申请日：2008-10-06

Applicant: NETWORK APPLIANCE, INC.

Inventor： ENGLISH, Robert, M. ,  KLEIMAN, Steven, R.

IPC: G06F3/06

CPC classification number: G06F3/0656 ,  G06F3/0613 ,  G06F3/0643 ,  G06F3/0644 ,  G06F3/0689 ,  G06F12/0804

Abstract: An improved system and method enhances performance of updates to sequential block storage of a storage system. A disk-based sort procedure is provided to establish locality among updates (write data) held in a disk-based log, thereby enabling the write data to be efficiently written to home locations on a home location array. As the write data is received, a log manager of the storage system temporarily stores the data efficiently on the disk-based log. As more write data arrives, the log manager sorts the data in the log in accordance with the sort procedure, thus increasing the locality of data when stored on the home location array. When the log approaches capacity, the log manager writes the sorted data to their home locations on the array with high locality and performance.

Abstract translation: 改进的系统和方法增强了对存储系统的顺序块存储的更新的性能。 提供基于磁盘的分类程序以在保持在基于磁盘的日志中的更新（写入数据）之间建立位置，从而使写入数据能够有效地写入归属位置阵列上的归属位置。 当接收到写入数据时，存储系统的日志管理器将有效的数据临时存储在基于磁盘的日志上。 随着更多的写入数据到达，日志管理器根据分类过程对日志中的数据进行排序，从而在存储在归属位置数组上时增加数据的位置。 当日志接近容量时，日志管理器将排序数据写入阵列的本地位置和性能很高。

公开(公告)号：WO2008153821A1

公开(公告)日：2008-12-18

申请号：PCT/US2008/006805

申请日：2008-05-29

Applicant: NETWORK APPLIANCE, INC.

Inventor： MILLER, Steven, C. ,  STAGER, Roger

IPC: H03M7/30

CPC classification number: G06F17/30156 ,  H03M7/3084

Abstract: A sampling based technique for eliminating duplicate data (de-duplication) stored on storage resources, is provided. According to the invention, when a new data set, e.g., a backup data stream, is received by a server, e.g., a storage system or virtual tape library (VTL) system implementing the invention, one or more anchors are identified within the new data set. The anchors are identified using a novel anchor detection circuitry in accordance with an illustrative embodiment of the present invention. Upon receipt of the new data set by, for example, a network adapter of a VTL system, the data set is transferred using direct memory access (DMA) operations to a memory associated with an anchor detection hardware card that is operatively interconnected with the storage system. The anchor detection hardware card may be implemented as, for example, a FPGA is to quickly identify anchors within the data set. As the anchor detection process is performed using a hardware assist, the load on a main processor of the system is reduced, thereby enabling line speed de-duplication.

Abstract translation: 提供了用于消除存储在存储资源上的重复数据（重复数据删除）的基于抽样的技术。 根据本发明，当服务器（例如，实施本发明的存储系统或虚拟磁带库（VTL））系统接收到诸如备份数据流的新数据集时，在新的数据集中识别出一个或多个锚点 数据集。 根据本发明的说明性实施例，使用新颖的锚定检测电路来识别锚。 在通过例如VTL系统的网络适配器接收到新数据集时，使用直接存储器访问（DMA）操作将数据集传送到与锚定检测硬件卡相关联的存储器，该存储器与存储器可操作地互连 系统。 锚定检测硬件卡可以被实现为例如FPGA快速识别数据集内的锚点。 由于使用硬件辅助进行锚定检测处理，系统的主处理器上的负载减少，从而实现线速度重复数据删除。

公开(公告)号：WO2008094433A2

公开(公告)日：2008-08-07

申请号：PCT/US2008/000900

申请日：2008-01-24

Applicant: NETWORK APPLIANCE, INC.

Inventor： STAGER, Roger

CPC classification number: G06F3/0608 ,  G06F3/0641 ,  G06F3/0686 ,  G06F11/1451 ,  G06F11/1453 ,  G06F11/1469

Abstract: A method and an apparatus to store data patterns are presented. In one embodiment, the method includes searching a pattern repository to find prior copies of a pattern and to reference one of the prior copies, or insert a new copy, based on the access time of the prior copy and the effect on the sequential stream performance.

Abstract translation: 提出了存储数据模式的方法和装置。 在一个实施例中，该方法包括搜索模式存储库以基于先前副本的访问时间以及对顺序流性能的影响来查找模式的先前副本并且引用先前副本之一或插入新副本 。

公开(公告)号：WO2008024317A3

公开(公告)日：2008-06-19

申请号：PCT/US2007018431

申请日：2007-08-20

Applicant: NETWORK APPLIANCE INC ,  SUSARLA SAI RAMA KRISHNA ,  EISLER MICHAEL R

Inventor： SUSARLA SAI RAMA KRISHNA ,  EISLER MICHAEL R

IPC: G06F3/06

CPC classification number: G06F3/061 ,  G06F3/0635 ,  G06F3/067 ,  G06F11/2092 ,  H04L67/1002 ,  H04L67/1008 ,  H04L67/1019 ,  H04L67/1023 ,  H04L67/28 ,  H04L67/2842

Abstract: A cache is used in a network storage system that includes a plurality of data storage nodes in a storage cluster, to automatically spread read and write access load, by a plurality of storage clients, for file system data and metadata, across the plurality of data storage nodes.

Abstract translation: 在包括存储集群中的多个数据存储节点的网络存储系统中使用高速缓存，以便跨多个数据自动扩展由多个存储客户端读取和写入文件系统数据和元数据的访问负载 存储节点。

公开(公告)号：WO2008005211A3

公开(公告)日：2008-06-19

申请号：PCT/US2007014664

申请日：2007-06-25

Applicant: NETWORK APPLIANCE INC

Inventor： ZHENG LING ,  FONG YINFUNG

IPC: G06F17/00

CPC classification number: G06F17/30159 ,  G06F3/0608 ,  G06F3/0641 ,  G06F3/0689

Abstract: A system and method for calculating and storing block fingerprints for data dedu- plication. A fingerprint extraction layer generates a fingerprint of a predefined size, e.g., 64 bits, for each data block stored by a storage system. Each fingerprint is stored in a fingerprint record, and the fingerprint records are, in turn, stored in a fingerprint database for access by the data deduplication module. The data deduplication module may peri¬ odically compare the fingerprints to identify duplicate fingerprints, which, in turn, indi¬ cate duplicate data blocks.

Abstract translation: 用于计算和存储用于数据删除的块指纹的系统和方法。 指纹提取层为存储系统存储的每个数据块产生预定义大小的指纹，例如64位。 每个指纹存储在指纹记录中，并且指纹记录又存储在指纹数据库中以供重复数据删除模块访问。 重复数据删除模块可以周期性地比较指纹以识别重复的指纹，其又指示重复的数据块。

公开(公告)号：WO2008054762A1

公开(公告)日：2008-05-08

申请号：PCT/US2007/022966

申请日：2007-10-31

Applicant: NETWORK APPLIANCE, INC.

Inventor： RAJAN, Vijayan

IPC: G06F3/06

CPC classification number: G06F3/0643 ,  G06F3/0607 ,  G06F3/067 ,  H04L67/1097

Abstract: A system and method for examining the content of a client file system stored on an exported lun is provided. A client agent interfaces with a client file system to detemine block layout information of data containers within the client file system. This block layout information is then transmitted to the storage system exporting the lun. The storage system utilizes the block layout information to generate a shadow volume utilizing the storage system's file system.

Abstract translation: 提供了一种用于检查存储在导出的LUN上的客户端文件系统的内容的系统和方法。 客户端代理与客户端文件系统接口，以确定客户端文件系统内的数据容器的块布局信息。 然后将该块布局信息发送到导出lun的存储系统。 存储系统利用块布局信息来利用存储系统的文件系统生成影子卷。