公开(公告)号：WO2002071230A1

公开(公告)日：2002-09-12

申请号：PCT/US2002/006563

申请日：2002-03-04

Applicant: CHAPARRAL NETWORK STORAGE INC.

Inventor： BUSSER, Richard, W.

IPC: G06F12/08

CPC classification number: G06F11/1076 ,  G06F2211/1009 ,  G06F2211/1059

Abstract: A method for enhancing the performance on non-full stripe writes while closing the RAID5 write hole is disclosed. When a RAID controller receives data to be written to a disk array, the controller stores the data in nonvolatile memory, and opens a write operation. When the current write operation is initiated, the controller reads the old data from the disk array and checks for cached parity that corresponds to the stripe of data that is to be modified. If the parity is cached, the controller reads the cached parity, and if the parity is not cached the controller reads the old parity from the disk array. New parity is then computed. If the parity was cached, the controller will modify a parity log to show an outstanding data write. If the parity was not cached, the controller will open a parity log to show an outstanding data and parity write. The new parity is then cached in non-volatile memory. The controller then determines whether the following write operation is for the same stripe of data. If the following write operation is for the same stripe, the controller writes the new data to disk and opens a parity log for the following write operation to show an outstanding parity write, and terminates the current write operation. If the following write operation is not for the same stripe, the controller writes both the new data and new parity to disk, and terminates the current write operation.

Abstract translation: 公开了一种在关闭RAID5写入孔时提高非全条纹写入性能的方法。 当RAID控制器接收要写入磁盘阵列的数据时，控制器将数据存储在非易失性存储器中，并打开写入操作。 当启动当前的写入操作时，控制器从磁盘阵列中读取旧数据，并检查对应于要修改的数据条带的缓存奇偶校验。 如果奇偶校验被缓存，则控制器读取缓存的奇偶校验，并且如果奇偶校验未缓存，则控制器从磁盘阵列读取旧的奇偶校验。 然后计算新的奇偶校验。 如果奇偶校验被缓存，控制器将修改奇偶校验日志以显示未完成的数据写入。 如果奇偶校验没有缓存，控制器将打开一个奇偶校验日志以显示未完成的数据和奇偶校验写。 新的奇偶校验然后缓存在非易失性存储器中。 然后，控制器确定以下写入操作是否用于相同的数据条带。 如果以下写入操作是针对相同的条带，则控制器将新数据写入磁盘，并为下一次写入操作打开一个奇偶校验日志，以显示未完成的奇偶校验写入，并终止当前的写入操作。 如果以下写操作不是相同的条带，则控制器将新数据和新奇偶校验写入磁盘，并终止当前的写操作。

公开(公告)号：WO2003040932A1

公开(公告)日：2003-05-15

申请号：PCT/US2002/035460

申请日：2002-11-04

Applicant: CHAPARRAL NETWORK STORAGE, INC.

Inventor： BUSSER, Richard, W. ,  DAVIES, Ian, R.

IPC: G06F12/16

CPC classification number: G06F11/201 ,  G06F11/2089 ,  G06F11/2092 ,  G06F11/2097

Abstract: A network storage controller (100) for transferring data between a host computer and a storage device, such as a redundant array of inexpensive disks (RAI), is disclosed. The network storage controller (100) includes at least one channel interface module (136, 140) which is adapted to be connected to the host computer and storage device. The channel interface module (136, 140) is connected to a passive backplane (116), and selectively transfers data between the host computer and storage device and the passive backplane (116). The network storage controller (100) also includes at least one controller management module (104, 108), attached to the passive backplane (116). The controller management module (104, 108) communicates with the channel interface module (136, 140) via the passive backplane (116), and processes and temporarily stores data received from the host computer or storage device. In applications where redundancy is required, at least two controller management modules (104, 108) and at least two channel interface modules (136, 140) may be used. The controller management modules (104, 108) may mirror data between one another using the passive backplane (116) and a shared communication path on the channel interface modules (136, 140), thereby substantially avoiding the use of host or disk channels to mirror data. The channel interface modules (136, 140) are operable to connect the host computer or storage device to one or more controller memory modules (104, 108). The controller management modules (104, 108) may include a DMA engine to facilitate the transfer of mirrored data.

Abstract translation: 公开了一种用于在主计算机和诸如廉价磁盘冗余阵列（RAI）等存储设备之间传送数据的网络存储控制器（100）。 网络存储控制器（100）包括适于连接到主计算机和存储设备的至少一个通道接口模块（136,140）。 通道接口模块（136,140）连接到无源底板（116），并且在主计算机与存储设备和无源底板（116）之间选择性地传送数据。 网络存储控制器（100）还包括附接到无源底板（116）的至少一个控制器管理模块（104,108）。 控制器管理模块（104,108）经由无源底板（116）与信道接口模块（136,140）进行通信，并处理并临时存储从主计算机或存储设备接收的数据。 在需要冗余的应用中，可以使用至少两个控制器管理模块（104,108）和至少两个通道接口模块（136,140）。 控制器管理模块（104,108）可以使用无源底板（116）和通道接口模块（136,140）上的共享通信路径在彼此之间镜像数据，从而基本上避免使用主机或磁盘通道来镜像 数据。 信道接口模块（136,140）可操作以将主计算机或存储设备连接到一个或多个控制器存储器模块（104,108）。 控制器管理模块（104,108）可以包括DMA引擎以便于镜像数据的传送。

公开(公告)号：WO2002091111A3

公开(公告)日：2002-11-14

申请号：PCT/US2002/013970

申请日：2002-05-01

Applicant: CHAPARRAL NETWORK STORAGE INC.

Inventor： BUSSER, Richard, W.

IPC: H03M13/00

Abstract: A system and method for efficient parity mirroring between controllers of an active-active controller pair in a redundant array of inexpensive disks (RAID) system (600) is disclosed. When a second controller (616) in an active controller pair receives new data to be written to a disk array, it mirrors the new data to a first controller (608) in the active-active controller pair. The second controller (616) then computes new parity for the data stripe associated with the new data. The second controller (616) then opens a parity log and mirrors logical block address (LBA) information for the new data to a first controller (608) in the active-active controller pair. In the event of a failure of the second controller after mirroring the LBA information and prior to completing the write operation, the first controller uses the LBA information to complete the write operation, assuring that the new data and new parity are properly stored on the disk array. If a hard disk in the disk array fails, parity is mirrored between the first and second controllers, rather than just LBA information. If a hard disk and the second controller fail when the first controller contains LBA information, a list containing the LBA is created and a media error is returned in the event that a host requests in the form of a read operation data contained in the listed LBAs.

公开(公告)号：WO2003041329A3

公开(公告)日：2003-05-15

申请号：PCT/US2002/035160

申请日：2002-10-31

Applicant: CHAPARRAL NETWORK STORAGE INC.

Inventor： BUSSER, Richard, W. ,  DAVIES, Ian, R.

IPC: G06F9/00

Abstract: A data storage system (400) that includes first and second controllers ( 404,408) is provided. Data is mirrored from one controller (404) to the other controller (408) according to different steps depending on the amount of data to be mirrored. When the data to be mirrored is less than or equal to a predetermined number of bytes, one less interrupt is generated than when the data to be mirrored is greater than the predetermined number of bits.

公开(公告)号：WO2003041329A2

公开(公告)日：2003-05-15

申请号：PCT/US2002/035160

申请日：2002-10-31

Applicant: CHAPARRAL NETWORK STORAGE INC.

Inventor： BUSSER, Richard, W. ,  DAVIES, Ian, R.

IPC: H04L

CPC classification number: G06F3/0601 ,  G06F11/2089 ,  G06F2003/0697

Abstract: A data storage system that includes first and second controllers is provided. Data is mirrored from one controller to the other controller according to different steps depending on the amount of data to be mirrored. When the data to be mirrored is less than or equal to a predetermined number of bytes, one less interrupt is generated than when the data to be mirrored is greater than the predetermined number of bits.

Abstract translation: 提供了包括第一和第二控制器的数据存储系统。 根据不同的步骤，根据要镜像的数据量，将数据从一个控制器镜像到另一个控制器。 当要镜像的数据小于或等于预定数量的字节时，比要镜像的数据大于预定位数时产生一个以上的中断。