公开(公告)号：US20050193230A1

公开(公告)日：2005-09-01

申请号：US10781200

申请日：2004-02-17

申请人： James Springer ,  Yu-Cheng Hsu ,  Gilad Sharaby ,  Aaron Mahar ,  Angelique Budaya

发明人： James Springer ,  Yu-Cheng Hsu ,  Gilad Sharaby ,  Aaron Mahar ,  Angelique Budaya

IPC分类号： G06F11/00 ,  G06F11/14 ,  G06F11/20

CPC分类号： G06F11/1441 ,  G06F11/2069

摘要： A data storage control unit is coupled to one or more host devices and to one or more physical storage units. Data is stored in one of the storage units and, for data integrity, copied to another storage unit. An updated state of the copy process (metadata) is maintained and updated in metadata tracks in a memory of the storage controller and periodically destaged to corresponding metadata tracks of a storage unit. If the copy process is interrupted, such as by a power failure, an error handling routine commences. Track state fields associated with each in-memory metadata track are initialized to an ‘invalid’ state and background staging of metadata tracks from the storage unit to the memory. After a track is staged, the associated track state field is changed to a ‘valid’ state. If a request is received to access a track of copy state data and the track has been staged (as indicated by the state of the associated track state field), the track is accessed. If the requested track has not been staged, requester waits while the requested track is staged; then the requested track is accessed. Once the error handling routine is completed, normal I/O operations with customer data may resume. Preferably, completion of the error handling routine is independent of the completion of the staging of copy state data tracks.

摘要翻译： 数据存储控制单元耦合到一个或多个主机设备和一个或多个物理存储单元。 数据存储在其中一个存储单元中，为了数据的完整性，数据被复制到另一个存储单元。 复制过程（元数据）的更新状态在存储控制器的存储器中的元数据轨道中被维护和更新，并且周期性地转移到存储单元的相应元数据轨道。 如果复制过程中断，例如电源故障，则会启动错误处理例程。 与每个存储器间元数据轨道相关联的跟踪状态字段被初始化为从存储单元到存储器的元数据轨迹的“无效”状态和背景分段。 在轨道分段后，相关的轨道状态字段将更改为“有效”状态。 如果接收到访问复制状态数据的轨道的请求，并且轨道已经被分段（如由相关联的轨道状态字段的状态所指示的），则该轨道被访问。 如果所请求的轨道尚未分段，则请求者在所请求的轨道分段时等待; 然后访问所请求的轨道。 一旦完成了错误处理程序，可以恢复与客户数据的正常I / O操作。 优选地，错误处理例程的完成与复制状态数据轨道的分段的完成无关。

公开(公告)号：US20060041780A1

公开(公告)日：2006-02-23

申请号：US10921443

申请日：2004-08-19

申请人： Angelique Budaya ,  Aaron Mahar ,  James Springer

发明人： Angelique Budaya ,  Aaron Mahar ,  James Springer

IPC分类号： G06F11/00

CPC分类号： G06F9/5016 ,  G06F9/50 ,  G06F11/0727 ,  G06F11/0793 ,  Y10S707/99942

摘要： Tracks of meta data are cleared in a storage server by allocating task control blocks for executing associated tasks in parallel. Throttling and recycling of task control blocks is provided to efficiently use memory and processing resources. Under the control of a master task, task control blocks are allocated to different hierarchical levels of storage resources in the storage server, such as a logical subsystem level and a subordinate volume level. The task control blocks are not deallocated from memory until there are no further tasks to process.

摘要翻译： 通过分配用于并行执行相关任务的任务控制块，在存储服务器中清除元数据的跟踪。 提供任务控制块的调节和回收，以有效利用存储器和处理资源。 在主任务的控制下，将任务控制块分配给存储服务器中的诸如逻辑子系统级和从属卷级之间的不同层级的存储资源。 任务控制块不会从内存释放，直到没有进一步的任务来处理。

公开(公告)号：US20060020618A1

公开(公告)日：2006-01-26

申请号：US10898603

申请日：2004-07-23

申请人： Angelique Budaya ,  Aaron Mahar ,  James Springer

发明人： Angelique Budaya ,  Aaron Mahar ,  James Springer

IPC分类号： G06F17/00

CPC分类号： G06F3/0659 ,  G06F3/0619 ,  G06F3/0652 ,  G06F3/0689

摘要： A system is employed to maintain persistent operation information for implementation on persistent data. Bitmaps are created to track outstanding persistent operations. Should a volume of information became inaccessible, the bitmaps are evaluated to determine if outstanding persistent operations exist and, if so, these outstanding operations are performed before the volume is integrated into the logical memory space. Additionally, operation-in-progress bitmaps are utilized to indicate that persistent data within a volume is being modified.

摘要翻译： 采用一种系统来维护持久化的操作信息，以便在持久数据上实现。 创建位图以跟踪未完成的持久性操作。 如果信息量无法访问，则会对位图进行评估，以确定是否存在未完成的持久性操作，如果是，则在将卷集成到逻辑内存空间之前执行这些未完成的操作。 另外，运行中的位图用于指示卷内的持久数据正被修改。

公开(公告)号：US20060106971A1

公开(公告)日：2006-05-18

申请号：US10993022

申请日：2004-11-18

申请人： Aaron Mahar ,  Angelique Budaya ,  James Springer

发明人： Aaron Mahar ,  Angelique Budaya ,  James Springer

IPC分类号： G06F12/14

CPC分类号： G06F3/064 ,  G06F3/0605 ,  G06F3/061 ,  G06F3/0622 ,  G06F3/065 ,  G06F3/0683 ,  G06F11/1471 ,  G06F11/1474 ,  G06F2211/104 ,  G06F2212/466

摘要： Methods, systems, computer program products and methods for deploying computing infrastructure for managing metadata in a storage subsystem are provided. A call is received from a client to update a portion of a metadata track. Data is also received from the client identifying at least one field of the metadata track to be updated, associated update values for the at least one field to be updated and an update type for the at least one field. A data structure field of a client interface is then populated with the identity of the at least one field and the associated update values and an opcode field of the client interface is populated with the update type. A task control block (TCB) is then allocated to the client call and, at the direction of the TCB, various operations are performed without further activity by the client. The metadata track may also be validated before being updated to ensure that the client has access only to valid updates.

摘要翻译： 提供了用于部署用于管理存储子系统中的元数据的计算基础设施的方法，系统，计算机程序产品和方法。 从客户端接收到更新元数据轨道的一部分的呼叫。 还从客户端接收识别要更新的元数据轨道的至少一个字段的数据，关于要被更新的至少一个字段的相关联的更新值以及用于该至少一个字段的更新类型。 然后，用至少一个字段的标识和相关联的更新值填充客户机接口的数据结构字段，并且使用更新类型填充客户端接口的操作码字段。 然后，任务控制块（TCB）被分配给客户端呼叫，并且在TCB的方向上执行各种操作，而不进行客户端的进一步的活动。 也可以在更新元数据跟踪之前验证元数据跟踪，以确保客户端只能访问有效的更新。

公开(公告)号：US20060106891A1

公开(公告)日：2006-05-18

申请号：US10993087

申请日：2004-11-18

申请人： Aaron Mahar ,  Angelique Budaya ,  James Springer

发明人： Aaron Mahar ,  Angelique Budaya ,  James Springer

IPC分类号： G06F17/30 ,  G06F12/00

CPC分类号： G06F17/30067

摘要： Methods, systems, computer program products and methods for deploying computing infrastructure for managing metadata in a storage subsystem are provided. A first metadata track is staged from disk storage to a cache storage after which a journal entry is stored in a nonvolatile storage (NVS). The journal entry includes an opcode and update data for the track. The opcode identifies the type of update to be performed and the number of tracks to be updated in the operation. Each of the other metadata tracks is staged and a corresponding journal entry stored. The journaled updates are then applied to the respective metadata track in the cache storage and the tracks destaged from cache to the disk storage.

摘要翻译： 提供了用于部署用于管理存储子系统中的元数据的计算基础设施的方法，系统，计算机程序产品和方法。 第一个元数据磁道从磁盘存储器升级到高速缓存存储器，之后日志条目存储在非易失性存储器（NVS）中。 日记帐分录包含轨迹的操作码和更新数据。 操作码标识要执行的更新类型和操作中要更新的轨道数。 每个其他元数据跟踪都会被暂存，并存储相应的日记帐分录。 然后将所记录的更新应用于高速缓存存储器中的相应元数据轨道和从高速缓存迁移到磁盘存储器的轨道。

公开(公告)号：US20060106829A1

公开(公告)日：2006-05-18

申请号：US10993048

申请日：2004-11-18

申请人： Angelique Budaya ,  Aaron Mahar ,  James Springer ,  Warren Stanley ,  Gail Spear

发明人： Angelique Budaya ,  Aaron Mahar ,  James Springer ,  Warren Stanley ,  Gail Spear

IPC分类号： G06F7/00

CPC分类号： G06F17/30067

摘要： Methods, systems, computer program products and methods for deploying computing infrastructure for clearing metadata in a storage subsystem. The method includes identifying one or more metadata tracks to clear, receiving a request from a client to clear the identified tracks, quiescing any active processes, clearing the identified tracks and resuming the quiesced processes. The request may be a single request operable to clear all metadata tracks. Alternatively, target volumes having metadata tracks to be cleared are identified and a request is received from a client for each target volume. A dynamic function list may also be created for each target volume, the list including list of functions in which the target volume is associated. After active processes are quiesced, each function in the dynamic function list of each target volume is invoked whereby the metadata tracks are cleared. The quiesced processes are then resumed.

摘要翻译： 用于部署用于清除存储子系统中的元数据的计算基础设施的方法，系统，计算机程序产品和方法。 该方法包括识别一个或多个元数据轨道以清除，接收来自客户端的请求以清除所识别的轨道，停止任何活动进程，清除所识别的轨道并恢复静默过程。 请求可以是可用于清除所有元数据轨道的单个请求。 或者，识别具有待清除的元数据轨迹的目标卷，并且从客户端接收针对每个目标卷的请求。 也可以为每个目标卷创建动态功能列表，该列表包括目标卷相关联的功能列表。 在活动进程停顿后，将调用每个目标卷的动态功能列表中的每个功能，从而清除元数据轨。 然后恢复静态过程。

公开(公告)号：US20060106873A1

公开(公告)日：2006-05-18

申请号：US10993092

申请日：2004-11-18

申请人： James Springer ,  Yu-Cheng Hsu ,  Lloyd Wiebe ,  Kurt Lovrien ,  David Mannenbach ,  Angelique Budaya

发明人： James Springer ,  Yu-Cheng Hsu ,  Lloyd Wiebe ,  Kurt Lovrien ,  David Mannenbach ,  Angelique Budaya

IPC分类号： G06F17/00

CPC分类号： G06F3/0652 ,  G06F3/0605 ,  G06F3/0614 ,  G06F3/0683 ,  G06F11/1435

摘要： Method for selectively clearing persistent data such as metadata in a storage subsystem. The method includes identifying one or more metadata tracks to clear, receiving a request from a client to clear the identified metadata tracks, passing the request to a storage device driver, and clearing the identified metadata tracks. The metadata tracks to be cleared may be identified by a specific storage function associated with the metadata to be cleared or by a specific storage target associated with metadata. Alternatively, both a storage function and a storage target may be specified. Preferably, the request to clear one or more identified metadata tracks may be executed without affecting unrelated storage functions. In addition, the request may be executed while preserving metadata tracks unrelated to the identified metadata tracks. Thus, execution of a request to selectively clear identified global metadata tracks in accordance with the present invention will typically not cause the loss of configuration information and will not necessitate a reboot of the system. In addition, a request as described above may be executed at any point in time while the storage system is running.

摘要翻译： 用于选择性地清除诸如存储子系统中的元数据的持久性数据的方法。 该方法包括识别一个或多个元数据轨道以清除，接收来自客户端的请求以清除所识别的元数据轨道，将请求传递到存储设备驱动器，以及清除所识别的元数据轨道。 要清除的元数据轨迹可以通过与要清除的元数据或与元数据相关联的特定存储目标相关联的特定存储功能来识别。 或者，可以指定存储功能和存储目标。 优选地，可以执行清除一个或多个所识别的元数据轨道的请求而不影响不相关的存储功能。 此外，可以在保留与所识别的元数据轨道无关的元数据轨道的同时执行请求。 因此，根据本发明的执行选择性地清除所标识的全局元数据轨迹的请求通常不会导致配置信息的丢失，并且不会使系统重新启动。 此外，当存储系统运行时，可以在任何时间点执行如上所述的请求。