公开(公告)号：US4785452A

公开(公告)日：1988-11-15

申请号：US855645

申请日：1986-04-25

申请人： Bruce R. Petz ,  Richard P. Rieger ,  Andrew D. Walls

发明人： Bruce R. Petz ,  Richard P. Rieger ,  Andrew D. Walls

IPC分类号： G06F11/10 ,  G06F12/16 ,  G06F11/00

CPC分类号： G06F11/1008 ,  G06F11/1012 ,  G06F11/1076

摘要： A variable number of parity bits or error correction code per word is used to increase error detection for words having the extra parity bits in a control store. Since some words do not utilize all the architected space available for words, extra parity bits are generated at development time for such words and stored with the words. A decoder identifies the location and number of parity bits. Parity checking against the extra parity bits is then performed on different groups of bits in the word. This provides an inexpensive means of increasing error detection with minimal hardware cost.

摘要翻译： 使用可变数量的奇偶校验位或每字的纠错码来增加在控制存储器中具有额外奇偶校验位的字的检错。 由于一些单词不能利用所有可用于单词的架构空间，因此在开发时会为这些单词生成额外的奇偶校验位，并与单词一起存储。 解码器识别奇偶校验位的位置和数量。 然后对该字中的不同比特组执行对额外奇偶校验位的奇偶校验。 这提供了以最小的硬件成本增加错误检测的便宜方式。

公开(公告)号：US09098397B2

公开(公告)日：2015-08-04

申请号：US13079432

申请日：2011-04-04

申请人： Lee D. Cleveland ,  John C. Elliott ,  Yu-Cheng Hsu ,  Andrew D. Walls

发明人： Lee D. Cleveland ,  John C. Elliott ,  Yu-Cheng Hsu ,  Andrew D. Walls

IPC分类号： G06F12/00 ,  G06F13/00 ,  G06F12/02 ,  G06F12/08 ,  H04L29/08

CPC分类号： G06F12/0246 ,  G06F12/0868 ,  H04L67/2852

摘要： Mechanisms are provided for extending cache for an external storage system into individual servers. Certain servers may have cards with cache in the form of dynamic random access memory (DRAM) and non-volatile storage, such as flash memory or solid-state drives (SSDs), which may be viewed as actual extensions of the external storage system. In this way, the storage system is distributed across the storage area network (SAN) into various servers. Several new semantics are used in communication between the cards and the storage system to keep the read caches coherent.

公开(公告)号：US08880835B2

公开(公告)日：2014-11-04

申请号：US12498424

申请日：2009-07-07

申请人： Michael T. Benhase ,  Andrew D. Walls

发明人： Michael T. Benhase ,  Andrew D. Walls

IPC分类号： G06F12/16 ,  G06F11/34 ,  G06F3/06

CPC分类号： G06F11/3485 ,  G06F3/061 ,  G06F3/0649 ,  G06F3/0688 ,  G06F2201/88

摘要： Mechanisms for managing data segments in a tiered storage system are provided. The mechanisms maintain at least one counter for each data segment in the tiered storage system. Each counter in the at least one counter counts a number of access operations to a corresponding data segment for a predetermined time interval. The mechanisms further perform one or more analytical operations based on one or more values of the at least one counter for each data segment to make residence determinations for each data segment. The mechanisms also adjust a storage location of one or more data segments in tiers of the tiered storage system to thereby move the one or more data segments to appropriate tiers of the tiered storage system based on results of the one or more analytical operations.

摘要翻译： 提供了在分层存储系统中管理数据段的机制。 这些机制为分层存储系统中的每个数据段维护至少一个计数器。 所述至少一个计数器中的每个计数器对预定时间间隔对相应的数据段进行多次访问操作。 所述机构还基于每个数据段的所述至少一个计数器的一个或多个值进行一个或多个分析操作，以对每个数据段进行居住确定。 这些机制还调整分层存储系统的层中的一个或多个数据段的存储位置，从而基于一个或多个分析操作的结果将一个或多个数据段移动到分层存储系统的适当层。

公开(公告)号：US08850153B2

公开(公告)日：2014-09-30

申请号：US13250416

申请日：2011-09-30

申请人： Gary A. Tressler ,  Andrew D. Walls

发明人： Gary A. Tressler ,  Andrew D. Walls

IPC分类号： G06F12/00 ,  G06F3/06 ,  G06F12/02

CPC分类号： G06F3/0613 ,  G06F3/0655 ,  G06F3/0659 ,  G06F3/0679 ,  G06F3/0688 ,  G06F12/0246 ,  G06F2206/1014

摘要： A mechanism is provided for enabling throttling on average write throughput instead of peak write throughput for solid-state storage devices. The mechanism assures an average write throughput within a range but allows excursions of high throughput with periods of low throughput offsetting against those of heavy usage. The mechanism periodically determines average throughput and determines whether average throughput exceeds a high throughput threshold for a certain amount of time without being offset by periods of low throughput.

摘要翻译： 提供了一种机制，用于实现平均写入吞吐量的节流，而不是固态存储设备的峰值写入吞吐量。 该机制确保了一个范围内的平均写入吞吐量，但允许高吞吐量的偏移量与低吞吐量的周期抵消了大量使用的吞吐量。 该机制周期性地确定平均吞吐量，并确定平均吞吐量是否超过一个高吞吐量阈值达一定时间量，而不会被低吞吐量周期所抵消。

公开(公告)号：US08635407B2

公开(公告)日：2014-01-21

申请号：US13250343

申请日：2011-09-30

申请人： Lee D. Cleveland ,  Andrew D. Walls

发明人： Lee D. Cleveland ,  Andrew D. Walls

IPC分类号： G06F12/00 ,  G06F12/08

CPC分类号： G06F3/0689 ,  G06F3/0611 ,  G06F3/0656 ,  G06F3/0688 ,  G06F12/0246 ,  G06F12/1027 ,  G06F2212/7201

摘要： A storage device is provided for direct memory access. A controller of the storage device performs a mapping of a window of memory addresses to a logical block addressing (LBA) range of the storage device. Responsive to receiving from a host a write request specifying a write address within the window of memory addresses, the controller initializes a first memory buffer in the storage device and associates the first memory buffer with a first address range within the window of memory addresses such that the write address of the request is within the first address range. The controller writes to the first memory buffer based on the write address. Responsive to the buffer being full, the controller persists contents of the first memory buffer to the storage device using logical block addressing based on the mapping.

摘要翻译： 提供存储设备用于直接存储器访问。 存储设备的控制器执行存储器地址窗口到存储设备的逻辑块寻址（LBA）范围的映射。 响应于从主机接收指定存储器地址窗口内的写入地址的写请求，控制器初始化存储设备中的第一存储器缓冲器，并将第一存储器缓冲器与存储器地址窗口内的第一地址范围相关联，使得 请求的写入地址在第一个地址范围内。 控制器根据写入地址写入第一个存储缓冲区。 响应于缓冲器已满，控制器使用基于映射的逻辑块寻址将第一存储器缓冲器的内容保持到存储设备。

公开(公告)号：US20130086302A1

公开(公告)日：2013-04-04

申请号：US13250416

申请日：2011-09-30

申请人： Gary A. Tressler ,  Andrew D. Walls

发明人： Gary A. Tressler ,  Andrew D. Walls

IPC分类号： G06F12/00

CPC分类号： G06F3/0613 ,  G06F3/0655 ,  G06F3/0659 ,  G06F3/0679 ,  G06F3/0688 ,  G06F12/0246 ,  G06F2206/1014

摘要： A mechanism is provided for enabling throttling on average write throughput instead of peak write throughput for solid-state storage devices. The mechanism assures an average write throughput within a range but allows excursions of high throughput with periods of low throughput offsetting against those of heavy usage. The mechanism periodically determines average throughput and determines whether average throughput exceeds a high throughput threshold for a certain amount of time without being offset by periods of low throughput.

公开(公告)号：US20120254508A1

公开(公告)日：2012-10-04

申请号：US13079247

申请日：2011-04-04

申请人： Andrew D. Walls

发明人： Andrew D. Walls

IPC分类号： G06F12/16 ,  G06F12/00

CPC分类号： G06F11/1464 ,  G06F3/0601 ,  G06F3/0619 ,  G06F3/0647 ,  G06F3/065 ,  G06F3/067 ,  G06F3/0688 ,  G06F11/2087 ,  G06F12/0246 ,  G06F2201/84

摘要： Mechanisms for storing data to a storage system comprising a set of one or more solid state storage devices and a set of non-solid state storage devices are provided. A request to write data to the storage system is received and the data is written to the set of one or more solid state storage devices in response to receiving the request. Moreover, a mirror copy of the data is written to the set of non-solid state storage devices in response to receiving the request. Thus, the non-solid state storage devices serve as a mirror backup copy of the data stored to the solid state storage devices.

摘要翻译： 提供了将数据存储到包括一组一个或多个固态存储设备和一组非固态存储设备的存储系统的机制。 接收向存储系统写入数据的请求，并且响应于接收到请求将数据写入一个或多个固态存储设备的集合。 此外，响应于接收到请求，数据的镜像副本被写入非固态存储设备集合。 因此，非固态存储装置用作存储到固态存储装置的数据的镜像备份副本。

公开(公告)号：US08201020B2

公开(公告)日：2012-06-12

申请号：US12617023

申请日：2009-11-12

申请人： Brian J. Cagno ,  John C. Elliott ,  Gregg S. Lucas ,  Andrew D. Walls

发明人： Brian J. Cagno ,  John C. Elliott ,  Gregg S. Lucas ,  Andrew D. Walls

IPC分类号： G06F11/07

CPC分类号： G06F11/2094 ,  G06F11/2089 ,  G06F11/2092 ,  G06F11/2097

摘要： A redundant and fault tolerant solid state disk (SSD) includes a determination module configured to identify a first solid state disk controller (SSDC) configured to connect to a flash array and a second SSDC configured to connect to the flash array. A capture module is configured to capture a copy of an I/O request received by the first SSDC from a port of a dual port connector, and/or capture a copy of an I/O request received by the second SSDC from a port of the dual port connector, and identify a write I/O request from the I/O request. A detection module is configured to detect a failure in the first SSDC. A management module is configured to manage access to a flash array by the first SSDC and the second SSDC. An error recovery and failover module is configured to automatically reassign work from the first SSDC to the second SSDC.

摘要翻译： 冗余和容错固态盘（SSD）包括确定模块，其被配置为识别被配置为连接到闪存阵列的第一固态盘控制器（SSDC）和被配置为连接到闪存阵列的第二SSDC。 捕获模块被配置为从双端口连接器的端口捕获由第一SSDC接收的I / O请求的副本，和/或从第二SSDC的端口捕获由第二SSDC接收的I / O请求的副本 双端口连接器，并从I / O请求中识别写入I / O请求。 检测模块被配置为检测第一SSDC中的故障。 管理模块被配置为管理由第一SSDC和第二SSDC对闪存阵列的访问。 错误恢复和故障切换模块被配置为自动将工作从第一SSDC重新分配给第二SSDC。

公开(公告)号：US20110010514A1

公开(公告)日：2011-01-13

申请号：US12498424

申请日：2009-07-07

申请人： Michael T. Benhase ,  Andrew D. Walls

发明人： Michael T. Benhase ,  Andrew D. Walls

IPC分类号： G06F12/00 ,  G06F12/02 ,  G06F12/16

CPC分类号： G06F11/3485 ,  G06F3/061 ,  G06F3/0649 ,  G06F3/0688 ,  G06F2201/88

摘要： Mechanisms for managing data segments in a tiered storage system are provided. The mechanisms maintain at least one counter for each data segment in the tiered storage system. Each counter in the at least one counter counts a number of access operations to a corresponding data segment for a predetermined time interval. The mechanisms further perform one or more analytical operations based on one or more values of the at least one counter for each data segment to make residence determinations for each data segment. The mechanisms also adjust a storage location of one or more data segments in tiers of the tiered storage system to thereby move the one or more data segments to appropriate tiers of the tiered storage system based on results of the one or more analytical operations.

摘要翻译： 提供了在分层存储系统中管理数据段的机制。 这些机制为分层存储系统中的每个数据段维护至少一个计数器。 所述至少一个计数器中的每个计数器对预定时间间隔对相应的数据段进行多次访问操作。 所述机构还基于每个数据段的所述至少一个计数器的一个或多个值进行一个或多个分析操作，以对每个数据段进行居住确定。 这些机制还调整分层存储系统的层中的一个或多个数据段的存储位置，从而基于一个或多个分析操作的结果将一个或多个数据段移动到分层存储系统的适当层。

公开(公告)号：US07562265B2

公开(公告)日：2009-07-14

申请号：US10807075

申请日：2004-03-23

申请人： Michael J. Azevedo ,  Hugh W. McDevitt ,  Carol Spanel ,  Andrew D. Walls

发明人： Michael J. Azevedo ,  Hugh W. McDevitt ,  Carol Spanel ,  Andrew D. Walls

IPC分类号： G06F11/00

CPC分类号： G06F11/0793 ,  G06F11/0709 ,  G06F11/0757

摘要： A method, apparatus and program storage device for providing self-quiesced logic for handling an error recovery instruction such as a reset or self-test instruction. For example, during a reset or self test procedure, the logic is isolated without adversely affecting the local processor. Self-quiesced logic processes an error recovery instruction by monitoring the processor interface for an idle condition and withholding access to the local processor. Once the local processor interface has been quiesced and the internal logic paths are idle, the logic will proceed with the reset or self-test.

摘要翻译： 一种用于提供用于处理诸如复位或自检指令的错误恢复指令的自静态逻辑的方法，装置和程序存储装置。 例如，在复位或自检过程中，逻辑是隔离的，而不会对本地处理器产生不利影响。 自静态逻辑通过监视处理器接口处于空闲状态并禁止对本地处理器的访问来处理错误恢复指令。 一旦本地处理器接口停顿并且内部逻辑路径空闲，逻辑将继续进行复位或自检。