公开(公告)号：US06343351B1

公开(公告)日：2002-01-29

申请号：US09148181

申请日：1998-09-03

申请人： Robert Andrew Lackman ,  Donald Ingerman ,  Thomas B. Genduso ,  Shah Mohammad Rezaul Islam

发明人： Robert Andrew Lackman ,  Donald Ingerman ,  Thomas B. Genduso ,  Shah Mohammad Rezaul Islam

IPC分类号： G06F1200

CPC分类号： G06F3/0611 ,  G06F3/0659 ,  G06F3/0676

摘要： A method and system in data processing system are disclosed for the dynamic scheduling of a plurality of requests to access a disk. Each of the requests is associated with a location on the said disk which each of the requests is attempting to access. A scan queue is established for storing the plurality of requests. The plurality of requests are processed in a sequential order. The sequential order is determined utilizing the location on the disk being accessed by each of the requests. Upon one of the stored requests being urgent, the urgent request is processed. The urgent request is associated with a first location on said disk. Processing of the requests then continues in a second sequential order. The second sequential order is determined utilizing the first location. The next request to be processed is one of the requests which is associated with a physically closest location on the disk.

摘要翻译： 公开了一种数据处理系统中的方法和系统，用于多个磁盘访问请求的动态调度。 每个请求都与所述磁盘上的每个请求尝试访问的位置相关联。 建立扫描队列以存储多个请求。 多个请求按顺序处理。 使用由每个请求访问的盘上的位置来确定顺序。 在存储的请求之一紧急时，紧急请求被处理。 紧急请求与所述磁盘上的第一位置相关联。 然后处理请求以第二顺序继续。 利用第一位置确定第二顺序。 要处理的下一个请求是与磁盘上物理上最接近的位置相关联的请求之一。

公开(公告)号：US06282671B1

公开(公告)日：2001-08-28

申请号：US09189689

申请日：1998-11-10

申请人： Shah Mohammad Rezaul Islam ,  Linda Ann Riedle

发明人： Shah Mohammad Rezaul Islam ,  Linda Ann Riedle

IPC分类号： G06F1110

CPC分类号： G06F11/1076 ,  G06F2211/1009 ,  H03M13/09 ,  H03M13/1515

摘要： The method and system for improved efficiency and parity calculation in RAID data storage system. RAID data storage systems permit recovery of data in the event of a drive failure by storing a parity value for each stripe of data on a separate drive. Each time data is written to a RAID data storage the parity value for the associated data stripe must be updated. Parity may be calculated utilizing two different algorithms. New parity may be calculated utilizing the old data value, the new data value and the old parity value, or calculated utilizing the new data value and all remaining old data within the associated data stripe. The number of input/output operations required to calculate parity utilizing each algorithm is predetermined and the method requiring the least number of input/output operations is selected, unless data sequentiality is detected. If sequential data is present the parity value is calculated utilizing the new data and all old data in the associated data stripe, even if a greater number of input/output operations are initially required, as further sequential input/output operations will be more efficient.

摘要翻译： RAID数据存储系统中提高效率和奇偶校验计算的方法和系统。 RAID数据存储系统允许在驱动器发生故障的情况下通过将每个数据条带的奇偶校验值存储在单独的驱动器上来恢复数据。 每次将数据写入RAID数据存储时，必须更新相关数据条带的奇偶校验值。 可以使用两种不同的算法来计算奇偶校验。 可以使用旧的数据值，新的数据值和旧的奇偶校验值来计算新的奇偶校验，或者利用新的数据值和相关联的数据条带内的所有剩余的旧数据来计算。 使用每个算法计算奇偶校验所需的输入/输出操作的数量是预定的，并且除非检测到数据顺序性，否则选择需要最少数量的输入/输出操作的方法。 如果存在顺序数据，则即使最初需要更多数量的输入/输出操作，因此使用新数据和相关数据条带中的所有旧数据来计算奇偶校验值，因为进一步的顺序输入/输出操作将更有效。

公开(公告)号：US06195727B1

公开(公告)日：2001-02-27

申请号：US09282714

申请日：1999-03-31

申请人： Shah Mohammad Rezaul Islam ,  Linda Ann Riedle

发明人： Shah Mohammad Rezaul Islam ,  Linda Ann Riedle

IPC分类号： G06F1120

CPC分类号： G06F11/1076

摘要： A redundant array of inexpensive disks (RAID) includes a plurality of disk drives organized as a plurality of stripes, wherein each stripe includes a plurality of stripe units. A host processor system sends write commands in write-through mode to a RAID controller, some of which are immediately processed by the controller, and others of which are temporarily stored in a stash. Commands stored in the stash for data writes that only partially fill a stripe may be coalesced with another write command that also only partially fills the same stripe. This coalescing occurs for commands for data writes that span one or more stripes, and that may start or stop in the middle of a stripe, as well as in the middle of a stripe unit. In addition, two different commands for writing data to different stripe units, but from the same stripe, can also be coalesced. The coalescing of write commands in the stash reduces the number of disk I/O's and improves data throughput.

摘要翻译： 廉价磁盘（RAID）的冗余阵列包括被组织为多个条带的多个磁盘驱动器，其中每个条带包括多个条带单元。 主处理器系统以直写模式向RAID控制器发送写入命令，其中一些由控制器立即处理，其中一些暂时存储在存储器中。 存储在数据写入中的仅用于部分填充条带的命令可能与另一个仅部分填充相同条带的写命令合并。 这种合并发生在跨越一个或多个条带的数据写入命令，并且可能在条带中间以及条带单元的中间开始或停止。 另外，两个不同的命令用于将数据写入不同的条带单元，但是从相同的条带也可以合并。 写入命令的合并减少了磁盘I / O的数量，并提高了数据吞吐量。

公开(公告)号：US6058455A

公开(公告)日：2000-05-02

申请号：US49167

申请日：1998-03-27

申请人： Shah Mohammad Rezaul Islam ,  Bharatkumar Jayantilal Oza

发明人： Shah Mohammad Rezaul Islam ,  Bharatkumar Jayantilal Oza

IPC分类号： G06F3/06 ,  G06F11/22 ,  G06F13/10 ,  G06F12/02

CPC分类号： G06F11/2289 ,  G06F11/1096 ,  G06F13/10 ,  G06F2003/0697 ,  G06F3/0601

摘要： Because correct configuration data is essential to the operation of any RAID system, and because multiple copies of the configuration data are kept, not only in the RAID controller itself, but also in each disk drive unit in the configuration, it is imperative that the various copies of the configuration data do not become "out of synchronization", which means that one or more copies of the configuration data are different from one or more other copies of the configuration data. To maintain synchronization of all copies of the configuration data, the current invention compares the configuration data stored in the RAID controllers' NVRAM to that of the current system, and records any new, non-responding, repositioned or unidentified storage devices in a change list. The identities and the attachment points of any storage devices in the change list are then displayed to the user, and various options for correcting the lack of synchronization are provided by enabling one or more function keys that may be selected by the user. One such function key, an "accept change" key, causes the configuration data to be modified by changing the current operational state of any non-responding storage device. A "configuration adjustment" key, when selected by the user, causes the configuration data to be modified to reflect any changes in the attachments points of any repositioned storage deices. An "import configuration" key causes the configuration data to be changed to correspond to that of an unidentified storage device. And a "retry" key gives the user an opportunity to rearrange the system and then re-compares the configuration data in the controller to the current system configuration. When the system is operating in un-attended mode, means are disclosed to automatically perform the "accept change", "configuration adjustment" and "import configuration" functions in priority order so long as the "retry" key has not been enabled. The retry key implies attended operation.