公开(公告)号：US08086914B2

公开(公告)日：2011-12-27

申请号：US13087710

申请日：2011-04-15

Applicant: Jeffrey S. Kimmel ,  Rajesh Sundaram ,  George Totolos, Jr. ,  Michael W. J. Hordijk

Inventor： Jeffrey S. Kimmel ,  Rajesh Sundaram ,  George Totolos, Jr. ,  Michael W. J. Hordijk

IPC: G11C29/00

CPC classification number: G06F12/0246 ,  G06F11/1666 ,  G06F11/20 ,  G06F2212/1032 ,  G06F2212/7208 ,  G11C29/76

Abstract: Described herein are method and apparatus for storing data to a low-latency random read memory (LLRRM) device using non-aligned data striping, the LLRRM device being implemented on a storage system. The LLRRM device may comprise a bank comprising a plurality of memory chips, each chip being simultaneously accessible for storing data on a plurality of erase-units (EUs). A storage operating system may maintain, for each chip, a reserve data structure listing reserve EUs and a remapping data structure for tracking remappings between defective EUs to reserve EUs in the chip. A defective EU in a chip may be mapped to a reserve EU from the reserve data structure. Upon receiving a data block to be stored to the LLRRM device at the defective EU, the storage operating system may stripe the received data block across a plurality of chips in a non-aligned manner using the remapped reserve EU.

公开(公告)号：US07437727B2

公开(公告)日：2008-10-14

申请号：US10105039

申请日：2002-03-21

Applicant: James Leong ,  Rajesh Sundaram ,  Douglas P. Doucette ,  Stephen H. Strange ,  Srinivasan Viswanathan

Inventor： James Leong ,  Rajesh Sundaram ,  Douglas P. Doucette ,  Stephen H. Strange ,  Srinivasan Viswanathan

IPC: G06F9/46 ,  G06F3/00 ,  G06F12/00

CPC classification number: G06F9/4856 ,  G06F3/0601 ,  G06F9/4881 ,  G06F9/5016 ,  G06F9/524 ,  G06F2003/0697 ,  G06F2209/484

Abstract: The present invention implements an I/O task architecture in which an I/O task requested by the storage manager, for example a stripe write, is decomposed into a number of lower-level asynchronous I/O tasks that can be scheduled independently. Resources needed by these lower-level I/O tasks are dynamically assigned, on an as-needed basis, to balance the load and use resources efficiently, achieving higher scalability. A hierarchical order is assigned to the I/O tasks to ensure that there is a forward progression of the higher-level I/O task and to ensure that resources do not become deadlocked.

Abstract translation: 本发明实现了I / O任务架构，其中由存储管理器请求的I / O任务（例如条带写入）被分解成可以独立调度的多个较低级别的异步I / O任务。 这些较低级I / O任务所需的资源根据需要动态分配，以有效平衡负载和使用资源，实现更高的可扩展性。 分层次序分配给I / O任务，以确保上级I / O任务有前进的进程，并确保资源不会成为死锁。

公开(公告)号：US20080155287A1

公开(公告)日：2008-06-26

申请号：US11644474

申请日：2006-12-21

Applicant: Rajesh Sundaram ,  Rodney R. Rozman ,  Sanjay S Talreja

Inventor： Rajesh Sundaram ,  Rodney R. Rozman ,  Sanjay S Talreja

IPC: G06F1/32 ,  G06F3/00

CPC classification number: G11C16/30

Abstract: Some embodiments of the invention may use a single control line signal as both a wake up signal and as an indicator of a device selection command. In a command-based protocol on a non-volatile memory bus, a host memory controller may assert a signal on a control line to bring all the memory devices on the bus into an operational mode, while concurrently placing a device selection command on the input/output lines. The memory device selected by the selection command may remain operational to perform a sequence of operations as directed by the host controller. The remaining (non-selected) memory devices may return to a sleep mode until a new signal on the control line is received, indicating a new selection command.

Abstract translation: 本发明的一些实施例可以使用单个控制线信号作为唤醒信号和作为设备选择命令的指示符。 在非易失性存储器总线上的基于命令的协议中，主机存储器控制器可以在控制线路上断言一个信号，使总线上的所有存储器件都进入操作模式，同时在输入端同时放置一个设备选择命令 /输出线。 由选择命令选择的存储器件可以保持运行，以执行由主机控制器指导的操作序列。 剩余的（未选择的）存储器件可以返回睡眠模式，直到接收到控制线上的新信号，指示新的选择命令。

公开(公告)号：US07319616B2

公开(公告)日：2008-01-15

申请号：US10713841

申请日：2003-11-13

Applicant: Rajesh Sundaram ,  Jahanshir Javanifard ,  Kerry D. Tedrow ,  Priya Walimbe ,  Tom H. Ly ,  Raymond W. Zeng

Inventor： Rajesh Sundaram ,  Jahanshir Javanifard ,  Kerry D. Tedrow ,  Priya Walimbe ,  Tom H. Ly ,  Raymond W. Zeng

IPC: G11C16/06

CPC classification number: G11C16/08 ,  G11C8/08

Abstract: In one embodiment, the present invention includes a method to supply a negative voltage to at least one deselected wordline of a memory array. Further, while the negative voltage is supplied to deselected wordlines, a positive voltage may be supplied to a selected wordline. The memory array may be a flash memory incorporating multi-level cell architecture, in one embodiment.

Abstract translation: 在一个实施例中，本发明包括将负电压提供给存储器阵列的至少一个未选择的字线的方法。 此外，当将负电压提供给未选择的字线时，可以向所选择的字线提供正电压。 在一个实施例中，存储器阵列可以是并入多级单元架构的闪速存储器。

公开(公告)号：US07165188B1

公开(公告)日：2007-01-16

申请号：US11047082

申请日：2005-01-31

Applicant: Steven H. Rodrigues ,  Rajesh Sundaram

Inventor： Steven H. Rodrigues ,  Rajesh Sundaram

IPC: G06F11/00 ,  G06F13/00 ,  G06F9/46

CPC classification number: G06F11/008 ,  G06F11/1076 ,  G06F2211/104 ,  G06F2211/1088

Abstract: A method for managing a long-running process carried out upon a plurality of disks is disclosed. A registry is established, the registry having a plurality of entries, each entry corresponding to one of the plurality of disks, each entry having a value indicative of a respective time at which its corresponding disk was last acted-upon by the long-running process. The long-running process executes on each of the disks based upon an order in which the disk having an oldest last acted-upon time is processed first and the disk having the newest last acted-upon time is processed last.

Abstract translation: 公开了一种用于管理在多个盘上执行的长时间运行的方法。 建立注册表，注册表具有多个条目，每个条目对应于多个盘中的一个，每个条目具有指示其对应的盘最后一次被执行的相应时间的值通过长时间运行的处理 。 基于最后一次执行时间最早的盘被首先处理并且具有最新的最后一次动作时间的盘被最后处理的顺序，在每个盘上执行长时间运行的进程。

公开(公告)号：US07139850B2

公开(公告)日：2006-11-21

申请号：US10176967

申请日：2002-06-21

Applicant: Takeshi Amemiya ,  Tariq Mustafa ,  Uday A. Prabhune ,  Rajesh Sundaram

Inventor： Takeshi Amemiya ,  Tariq Mustafa ,  Uday A. Prabhune ,  Rajesh Sundaram

IPC: G06F3/00

CPC classification number: G06F9/451

Abstract: System for processing programmable buttons using system control interrupts in a portable device. The system comprises a programmable button that comprises logic to generate a selected system control interrupt when actuated. The system also comprises interrupt logic coupled to receive the selected system control interrupt. The interrupt logic comprises logic to generate a button report that includes a button identifier, which indicates that the programmable button has been actuated. The system also comprises button support logic that is coupled to receive the button report, the button support logic comprises logic to determine a selectable device function associated with the button identifier, and logic to activate the selectable device function.

Abstract translation: 用于使用便携式设备中的系统控制中断处理可编程按钮的系统。 该系统包括可编程按钮，其包括当被致动时产生所选择的系统控制中断的逻辑。 该系统还包括耦合以接收所选择的系统控制中断的中断逻辑。 中断逻辑包括用于生成包括按钮标识符的按钮报告的逻辑，该按钮标识符指示可编程按钮已被致动。 该系统还包括耦合以接收按钮报告的按钮支持逻辑，按钮支持逻辑包括用于确定与按钮标识符相关联的可选设备功能的逻辑，以及激活可选设备功能的逻辑。

公开(公告)号：US20060190654A1

公开(公告)日：2006-08-24

申请号：US10851187

申请日：2004-05-24

Applicant: Joseph Joy ,  Georgios Chrysanthakopoulos ,  Rajesh Sundaram ,  Arvind Murching

Inventor： Joseph Joy ,  Georgios Chrysanthakopoulos ,  Rajesh Sundaram ,  Arvind Murching

IPC: G06F13/14

CPC classification number: H04L12/40058 ,  H04L12/40065 ,  H04L47/13 ,  H04L49/205

Abstract: The invention provides quality-of-service (QoS) delivery services over a computer bus having isochronous data transfer capabilities. A transmitting node on the bus transmits a message to an intended recipient indicating a requested bandwidth for a connection. If the intended recipient has sufficient resources, it allocates an isochronous data channel on the bus and notifies the transmitter of the allocated channel. Thereafter, the transmitter transmits the data on the allocated channel. If the recipient cannot allocate a channel, it does not respond, and the transmitter thereafter detects a time-out condition and begins transmitting using a “best efforts” scheme (i.e., non-guaranteed time delivery). In a second variation, a receiving node detects that it is receiving large quantities of data from a transmitting node. In response, the receiving node allocates an isochronous data channel on the bus and notifies the transmitter of the allocated channel. Thereafter, the transmitter transmits using the allocated isochronous channel. In a third variation, multiple receiving nodes that need to receive streaming data from a single transmitting node share a common isochronous data channel. In any of these variations, each receiver can periodically transmit a “deadman” timer message on a broadcast channel to indicate that it is still receiving on a given channel. If a transmitter detects that the deadman timer has expired, it reverts to transmitting data using a “best-efforts” scheme. A transmitter can transmit both to receivers that can handle QoS services and those that cannot explicitly support QoS services.

公开(公告)号：US20060075281A1

公开(公告)日：2006-04-06

申请号：US10951644

申请日：2004-09-27

Applicant: Jeffrey Kimmel ,  Sunitha Sankar ,  Rajesh Sundaram ,  Nitin Muppalaneni ,  Emily Eng ,  Eric Hamilton

Inventor： Jeffrey Kimmel ,  Sunitha Sankar ,  Rajesh Sundaram ,  Nitin Muppalaneni ,  Emily Eng ,  Eric Hamilton

IPC: G06F11/00

CPC classification number: G06F11/073 ,  G06F11/1076 ,  G06F2211/1007 ,  G06F2211/104

Abstract: A storage system, such as a file server, receives a request to perform a write operation that affects a data block. In response, the storage system writes to a storage device the data block together with context information which uniquely identifies the write operation with respect to the data block. When the data block is subsequently read from the storage device together with the context information, the context information that was read with the data block is used to determine whether a previous write of the data block was lost.

Abstract translation: 诸如文件服务器的存储系统接收到执行影响数据块的写入操作的请求。 作为响应，存储系统与数据块一起写入存储设备以及唯一地标识关于数据块的写入操作的上下文信息。 当数据块随后与上下文信息一起从存储设备读取时，使用数据块读取的上下文信息用于确定数据块的先前写入是否丢失。

公开(公告)号：US07003714B1

公开(公告)日：2006-02-21

申请号：US10832100

申请日：2004-04-26

Applicant: Rajesh Sundaram ,  Srinivvasan Viswanathan ,  Alan Rowe ,  Steven R. Kleiman ,  John K. Edwards

Inventor： Rajesh Sundaram ,  Srinivvasan Viswanathan ,  Alan Rowe ,  Steven R. Kleiman ,  John K. Edwards

IPC: G11C29/00

CPC classification number: G06F11/1076

Abstract: A data storage system, such as RAID, upgraded dynamically including multiple stages, providing error checking data without taking the system off-line. Checksums are computed from the data and placed in block 63 of the same disk. The combination of parity bits across the parity disk, the remaining uncorrupted data in the data disks, and checksums within each disk includes sufficient information to enable restoration of corrupt data. The system is upgraded by reserving permanent checksum blocks, writing the checksums to a volume block number, and placing the checksums in permanently reserved checksum block locations after first moving data already there to unreserved blocks.

Abstract translation: 诸如RAID的数据存储系统，动态地升级包括多级，提供错误检查数据而不使系统离线。 校验和是根据数据计算的，并放在同一个磁盘的块63中。 奇偶校验磁盘上的奇偶校验位的组合，数据磁盘中的其余未被破坏的数据以及每个磁盘内的校验和包括足够的信息以使恢复损坏的数据。 通过保留永久校验和块，将校验和写入卷块号，并在首先将数据移动到未保留的块之后将校验和放置在永久保留的校验和块位置，升级系统。

公开(公告)号：US06851070B1

公开(公告)日：2005-02-01

申请号：US09928389

申请日：2001-08-13

Applicant: Steven H. Rodrigues ,  Rajesh Sundaram

Inventor： Steven H. Rodrigues ,  Rajesh Sundaram

IPC: G06F11/00 ,  G06F11/10

CPC classification number: G06F11/008 ,  G06F11/1076 ,  G06F2211/104 ,  G06F2211/1088

Abstract: A system and method for managing a time-limited long-running process that acts upon disks of a disk array is based upon a general rule of acting upon each disk in an order based upon the length of time from when it was last acted-upon. Disks having the greatest last acted-upon time value (e.g. were processed the longest-time ago) are queued first by the process for acting-upon in the present run. The greatest last acted-upon time includes disks that have no prior last acted-upon time (e.g. newly added/mounted disks). A registry key entry is maintained in a registry file for each of the RAID groups that includes the volume's file system identifier (FSID) and particular RAID group identifier to (RGID). The RGID includes the last acted-upon time for the RAID group. This is set to a positive time number if the process has last acted-upon the group to completion. Alternatively, the last acted-upon time value is set to zero if the volume has not previously been acted-upon to completion or the RAID group is newly mounted.

Abstract translation: 用于管理作用在磁盘阵列的磁盘上的受时间限制的长时间运行进程的系统和方法基于基于从最后一次执行的时间长度的顺序对每个磁盘执行的一般规则 。 最后一次执行时间最大值的磁盘（例如，最早处理的磁盘）首先由当前运行的进程排队。 最大的最后一个动作时间包括没有先前最后一次动作的磁盘（例如新添加/安装的磁盘）。 对于包含卷的文件系统标识符（FSID）和特定的RAID组标识符（RGID）的每个RAID组，注册表项保留在注册表文件中。 RGID包括RAID组的最后一个动作时间。 如果进程最后一次执行，则将其设置为正时间号码 - 完成该组。 或者，如果卷以前未被执行完毕或RAID组新安装，则最后一个动作时间值被设置为零。