公开(公告)号：US20160246677A1

公开(公告)日：2016-08-25

申请号：US14696001

申请日：2015-04-24

Applicant: NetApp, Inc.

Inventor： Dheeraj Raghavender Sangamkar ,  Ajay Bakre ,  Vladimir Radu Avram ,  Emalayan Vairavanathan ,  Viswanath Chandrasekara Bharathi

IPC: G06F11/10 ,  G06F3/06 ,  H04L29/08

CPC classification number: G06F11/1076 ,  G06F3/0619 ,  G06F3/064 ,  G06F3/067 ,  G06F3/1234 ,  G06F11/1402 ,  G06F11/1471 ,  G06F11/1489 ,  G06F2211/1028 ,  H04L67/1097

Abstract: Technology is disclosed for storing data in a distributed storage system using a virtual chunk service (VCS). In the VCS based storage technique, a storage node (“node”) is split into multiple VCSs and each of the VCSs can be assigned a unique ID in the distributed storage. A set of VCSs from a set of nodes form a storage group, which also can be assigned a unique ID in the distributed storage. When a data object is received for storage, a storage group is identified for the data object, the data object is encoded to generate multiple fragments and each fragment is stored in a VCS of the identified storage group. The data recovery process is made more efficient by using metadata, e.g., VCS to storage node mapping, storage group to VCS mapping, VCS to objects mapping, which eliminates resource intensive read and write operations during recovery.

Abstract translation: 公开了用于使用虚拟块服务（VCS）在分布式存储系统中存储数据的技术。 在基于VCS的存储技术中，存储节点（“节点”）被分成多个VCS，并且可以在分布式存储器中为每个VCS分配唯一的ID。 来自一组节点的一组VCS形成存储组，也可以在分布式存储器中分配唯一的ID。 当接收到数据对象进行存储时，为数据对象识别存储组，对数据对象进行编码以生成多个片段，并将每个片段存储在所识别的存储组的VCS中。 通过使用元数据（例如VCS到存储节点映射，存储组到VCS映射，VCS到对象映射），可以使数据恢复过程更加高效，从而消除了恢复期间的资源密集型读写操作。

公开(公告)号：US20160246519A1

公开(公告)日：2016-08-25

申请号：US14627825

申请日：2015-02-20

Applicant: NetApp, Inc.

Inventor： Brian D. McKean ,  Sandeep Kumar R. Ummadi

IPC: G06F3/06

CPC classification number: G06F3/0619 ,  G06F3/0611 ,  G06F3/064 ,  G06F3/0653 ,  G06F3/068 ,  G06F3/0685

Abstract: A storage manager can reduce the overhead of parity based fault tolerance by leveraging the access performance of SSDs for the parities. Since reading a parity value can be considered a small read operation, the reading of parity from an SSD is an effectively “free” operation due to the substantially greater SSD read performance. With reading parity being an effectively free operation, placing parity on SSDs eliminates the parity read operations (in terms of time) from the parity based fault tolerance overhead. A storage manager can selectively place parity on SSDs from HDDs based on a criterion or criteria, which can relate to frequency of access to the data corresponding to the parity. The caching criterion can be defined to ensure the reduced overhead gained by reading parity values from a SSD outweighs any costs (e.g., SSD write endurance).

Abstract translation: 存储管理器可以通过利用SSD的访问性能来减少基于奇偶校验的容错的开销。 由于读取奇偶校验值可以被认为是小的读取操作，由于SSD读取性能大幅提高，因此从SSD读取奇偶校验是有效的“自由”操作。 读取奇偶校验是一个有效的免费操作，将SSD上的奇偶校验从基于奇偶校验的容错开销中消除奇偶读取操作（在时间上）。 存储管理器可以基于标准或标准来选择性地将HDD上的奇偶校验放置在HDD中，标准或标准可以与对应于奇偶校验的数据的访问频率有关。 可以定义缓存标准，以确保通过从SSD读取奇偶校验值而获得的减少的开销超过任何成本（例如，SSD写入耐力）。

公开(公告)号：US20160246517A1

公开(公告)日：2016-08-25

申请号：US14627034

申请日：2015-02-20

Applicant: NetApp, Inc.

Inventor： Vivek Venkatesan ,  Alvin Lam ,  Varun Ganesh ,  Emalayan Vairavanathan

IPC: G06F3/06

CPC classification number: G06F3/0619 ,  G06F3/0605 ,  G06F3/0649 ,  G06F3/065 ,  G06F3/067 ,  G06F3/0685

Abstract: A method, non-transitory computer readable medium, and storage platform computing apparatus that obtains a lifecycle management policy and configuration information for a cloud repository identified in the lifecycle management policy. The configuration information includes at least one access parameter for the cloud repository. The lifecycle management policy is applied to determine when an object is required to be replicated to the cloud repository in response to a received write request. A request to store the object in the cloud repository is generated, when the object is determined to be required to be stored in the cloud repository, wherein the request includes the access parameter. The request is sent to the cloud repository using a representational state transfer (REST) interface associated with the cloud repository.

Abstract translation: 一种方法，非暂时性计算机可读介质和存储平台计算装置，其获取生命周期管理策略中标识的云库的生命周期管理策略和配置信息。 配置信息包括用于云存储库的至少一个访问参数。 应用生命周期管理策略来确定何时需要将对象复制到云存储库以响应接收到的写入请求。 当确定对象被要求存储在云存储库中时，生成将对象存储在云存储库中的请求，其中请求包括访问参数。 该请求使用与云库相关联的表示状态转移（REST）接口发送到云存储库。

公开(公告)号：US09424301B2

公开(公告)日：2016-08-23

申请号：US14088196

申请日：2013-11-22

Applicant: NETAPP, INC.

Inventor： Poonam Dhavale ,  Manish Bhuwania ,  Arun Ramachandran ,  Herman M. Mutiso

IPC: G06F17/30

CPC classification number: G06F17/30348

Abstract: A system and method of negotiated takeover of storage objects includes one or more processors, a storage controller, and memory coupled to the one or more processors. The memory stores a data structure that includes information about a plurality of storage objects manageable by the storage controller. The storage controller is configured to assume, one by one, current ownership of a first subset of the storage objects and assume, concurrently, current ownership of a second subset of the storage objects. The first subset of storage objects and the second subset of storage objects are currently owned by a second storage server coupled to the storage server. In some embodiments, current ownership of the first subset of storage objects is transferred by iteratively detecting a particular storage object from the first subset of the storage objects whose current ownership can be assumed and bringing the particular storage object online.

Abstract translation: 协商接管存储对象的系统和方法包括耦合到一个或多个处理器的一个或多个处理器，存储控制器和存储器。 存储器存储包括关于由存储控制器可管理的多个存储对象的信息的数据结构。 存储控制器被配置为逐个地假设存储对象的第一子集的当前所有权并同时假设存储对象的第二子集的当前所有权。 存储对象的第一子集和存储对象的第二子集目前由耦合到存储服务器的第二存储服务器所拥有。 在一些实施例中，存储对象的第一子集的当前所有权通过迭代地从存储对象的第一子集迭代地检测特定存储对象来传送，该存储对象的当前所有权可以被假设并且使特定存储对象在线。

公开(公告)号：US09424273B2

公开(公告)日：2016-08-23

申请号：US13875186

申请日：2013-05-01

Applicant: NetApp, Inc.

Inventor： Peter Schay

IPC: G06F17/30

CPC classification number: G06F17/30203

Abstract: A system and method for utilizing a network-based file system from a client terminal. In examples described herein, an input command is processed on a client terminal for use of the network-based file system. A task is initiated in response to the input command. The performance of the task includes concatenating multiple file system operations associated with the input command and communicating the multiple file system operations to the network-based file system as a single communication. One or more replies to the one or more file system operations are asynchronously processed.

Abstract translation: 一种用于从客户终端利用基于网络的文件系统的系统和方法。 在这里描述的示例中，在用于基于网络的文件系统的客户终端上处理输入命令。 响应于输入命令启动任务。 任务的执行包括连接与输入命令相关联的多个文件系统操作，并将多个文件系统操作传送到基于网络的文件系统作为单个通信。 对一个或多个文件系统操作的一个或多个答复被异步处理。

公开(公告)号：US20160239437A1

公开(公告)日：2016-08-18

申请号：US15137906

申请日：2016-04-25

Applicant: NetApp, Inc.

Inventor： Nam Le ,  Paul Yuedong Mu ,  John Russell Boyles ,  John Eric Hoffman

IPC: G06F12/14 ,  H04L29/06 ,  G06F11/20 ,  H04L29/08

CPC classification number: H04L63/102 ,  G06F3/0607 ,  G06F3/0622 ,  G06F3/0635 ,  G06F3/0637 ,  G06F3/0659 ,  G06F3/067 ,  G06F11/2069 ,  G06F12/1483 ,  G06F16/10 ,  G06F21/6218 ,  G06F2201/805 ,  G06F2212/1052 ,  G06F2212/154 ,  H04L63/083 ,  H04L63/10 ,  H04L63/101 ,  H04L67/10 ,  H04L67/1097

Abstract: Described herein are method and apparatus for servicing software components of nodes of a cluster storage system. During data-access sessions with clients, client IDs and file handles for accessing files are produced and stored to clients and stored (as session data) to each node. A serviced node is taken offline, whereby network connections to clients are disconnected. Each disconnected client is configured to retain its client ID and file handles and attempt reconnections. Session data of the serviced node is made available to a partner node (by transferring session data to the partner node). After clients have reconnected to the partner node, the clients may use the retained client IDs and file handles to continue a data-access session with the partner node since the partner node has access to the session data of the serviced node and thus will recognize and accept the retained client ID and file handles.

Abstract translation: 这里描述了用于维护集群存储系统的节点的软件组件的方法和装置。 在与客户端的数据访问会话期间，生成用于访问文件的客户端ID和文件句柄，并将其存储到客户端并存储（作为会话数据）到每个节点。 服务节点脱机，从而断开与客户端的网络连接。 每个断开连接的客户端被配置为保留其客户端ID和文件句柄并尝试重新连接。 服务节点的会话数据使对方节点可用（通过将会话数据传送到伙伴节点）。 在客户端重新连接到伙伴节点之后，客户端可以使用保留的客户端ID和文件句柄来继续与伙伴节点的数据访问会话，因为伙伴节点可以访问服务节点的会话数据，并且因此将识别和 接受保留的客户端ID和文件句柄。

公开(公告)号：US20160239384A1

公开(公告)日：2016-08-18

申请号：US15143437

申请日：2016-04-29

Applicant: NetApp, Inc.

Inventor： David Anthony Slik ,  Barry Patrick Benight

IPC: G06F11/10 ,  H03M13/15

CPC classification number: G06F11/1076 ,  G06F11/1092 ,  G06F17/30312 ,  G06F2003/0692 ,  H03M13/154 ,  H04L67/1097 ,  H04L69/40

Abstract: Systems and techniques for managing data storage are disclosed. In some aspects, a front-end node responds to a request to write an object by dividing the object into multiple source data segments. The front-end node generates redundancy data for the multiple source data segments using a rateless erasure encoding. The front-end node associates a respective subset of the redundancy data with each of the multiple source data segments, wherein each subset of redundancy data and associated source data segment form an encoded segment. The rateless erasure encoding further includes defining multiple segment-level fragments within each of the encoded segments. The front-end node transmits each of the encoded segments to a selected one of multiple storage nodes, wherein each of the selected storage nodes are selected based on a determined storage layout of the encoded segments across the multiple storage nodes. For each of the received encoded segments, the storage node generates one or more protection fragments based on redundancy data generated from the segment-level fragments and stores the segment-level fragments and corresponding protection fragments across multiple storage media devices managed by the selected storage node.

Abstract translation: 公开了用于管理数据存储的系统和技术。 在某些方面，前端节点通过将对象划分成多个源数据段来响应写入对象的请求。 前端节点使用无可擦除擦除编码生成多个源数据段的冗余数据。 前端节点将冗余数据的相应子集与多个源数据段中的每一个相关联，其中冗余数据和相关源数据段的每个子集形成编码段。 无限擦除编码还包括在每个编码段内定义多个片段级片段。 前端节点将每个编码的段传输到多个存储节点中的一个选定的一个，其中基于所确定的跨多个存储节点的编码段的存储布局来选择所选择的存储节点中的每一个。 对于每个接收到的编码段，存储节点基于从段级别片段生成的冗余数据生成一个或多个保护片段，并将片段级片段和对应的保护片段存储在由所选存储节点管理的多个存储媒体设备 。

公开(公告)号：US20160234962A1

公开(公告)日：2016-08-11

申请号：US14618637

申请日：2015-02-10

Applicant: NetApp Inc.

Inventor： Macen Shinsato

IPC: H05K7/14

CPC classification number: G11B33/128

Abstract: The present disclosure provides a chassis housing an increased density of smaller storage devices. The chassis houses one or more power supplies, one or more input/output modules, and hot swappable, front accessible field replaceable units. The field replaceable units have a depth that is greater than their width and height, so as to accommodate dual storage devices one in front of the other. The proximal storage device connects to a midplane of the chassis via an interposer card situated between the proximal and distal storage devices. The interposer card conditions any signals that exhibit signal integrity problems after traversing between the midplane and the interposer card. The interposer card connects to the midplane via a bridge card and a flexible connector running underneath the distal storage device. Each field replaceable unit is placed into the front end of the chassis in a vertical orientation with respect to the chassis.

Abstract translation: 本公开提供了一种容纳更小密度的较小存储装置的底架。 机箱装有一个或多个电源，一个或多个输入/输出模块，以及可热插拔的前置可接近现场可更换单元。 现场可更换单元的深度大于其宽度和高度，以便容纳在另一个之前的双存储设备。 近端存储设备经由位于近端存储设备和远端存储设备之间的插入器卡连接到机架的中平面。 插入卡可以处理在中平面和插入卡之间横穿之后出现信号完整性问题的任何信号。 插入卡通过桥接卡和位于远端存储设备下面的柔性连接器连接到中平面。 每个现场可更换单元相对于机箱以垂直方向放置在机箱的前端。

公开(公告)号：US20160234066A1

公开(公告)日：2016-08-11

申请号：US15078468

申请日：2016-03-23

Applicant: NETAPP, INC.

Inventor： Larry Lancaster ,  Milan Bag

IPC: H04L12/24 ,  H04L12/26

CPC classification number: H04L41/0813 ,  G06F11/0727 ,  G06F11/0781 ,  H04L43/04

Abstract: A method and system for managing and dynamically suppressing event notification is provided. The method and system receives an indication of an event from a storage environment to be processed by a support system according to a set of default delivery parameters. Next, the method and system determines if one or more event specific delivery parameters have been associated with the event. If this is the case, then the method and system modifies the default delivery parameters for the information associated with the event according to the one or more event specific delivery parameters. Those event specific delivery parameters are also used to determine when to transmit a notification of the event to the support system. The dynamic suppression of events combines events gathered into an event log together into a set of one or more recurring events. From these events, the method and system then identifies a high frequency subset as one or more recurring events considered to occur at a higher frequency compared with a low frequency subset having one or more recurring events that occur at a lower frequency. Based on this information gathered, the method and system then eliminates a portion of the events in the high frequency subset until the frequency of events in the high frequency subset approximates the frequency of events in the low frequency subset.

Abstract translation: 提供了一种用于管理和动态抑制事件通知的方法和系统。 方法和系统根据一组默认传送参数从存储环境接收要由支持系统处理的事件的指示。 接下来，方法和系统确定一个或多个事件特定传送参数是否已经与事件相关联。 如果是这种情况，则该方法和系统根据一个或多个事件特定传送参数修改与事件相关联的信息的默认传送参数。 这些事件特定传送参数也用于确定何时将事件的通知传送到支持系统。 动态抑制事件将收集到事件日志中的事件组合成一组一个或多个重复事件。 从这些事件中，该方法和系统随后将高频子集识别为与具有以较低频率发生的一个或多个重复事件的低频子集相比被认为以较高频率发生的一个或多个重复事件。 基于收集的信息，该方法和系统然后消除高频子集中事件的一部分，直到高频子集中事件的频率近似于低频子集中事件的频率。

公开(公告)号：US09411834B2

公开(公告)日：2016-08-09

申请号：US14154992

申请日：2014-01-14

Applicant: NETAPP, INC.

Inventor： Curtis Hrischuk ,  Siu Wu ,  Leon Fairbanks ,  Kevin Faulkner

IPC: G06F17/30

CPC classification number: G06F17/30289 ,  G06F3/06 ,  G06F11/3034 ,  G06F11/3409 ,  G06F11/3419 ,  G06F11/3442 ,  G06F11/3485 ,  G06F17/30306 ,  G06F2201/81 ,  G06F2201/875 ,  G06F2201/88

Abstract: Methods and systems for identifying a victim storage volume from among a plurality of storage volumes based on a comparison of current Quality of Service (QOS) data with a dynamic threshold value that is based on historical QOS collected data for the plurality of storage volumes are provided. A performance manager collects the current and historical QOS data from a storage operating system of the storage system, which includes a response time in which each of the plurality of storage volumes respond to an input/output (I/O) request. The current and historical QOS data for the resources used by the victim storage volume are retrieved and compared with the current QOS data of each resource to an expected range based on the historical QOS data. Another storage volume is identified as a bully when its usage of a resource in contention contributes to creating the victim storage volume.

Abstract translation: 提供了基于当前服务质量（QOS）数据与基于多个存储卷的历史QOS收集数据的动态阈值的比较来从多个存储卷中识别受害者存储卷的方法和系统 。 性能管理器从存储系统的存储操作系统收集当前和历史的QOS数据，其包括多个存储卷中的每一个对输入/输出（I / O）请求做出响应的响应时间。 根据历史QOS数据，检索受害者存储卷使用的资源的当前和历史QOS数据，并将其与每个资源的当前QOS数据进行比较，达到预期范围。 当资源在争用中的使用有助于创建受害者存储卷时，另一个存储卷被识别为欺凌。