Agere Systems Inc.

Lsi Corporation

Nevin C Heintze

Ambalavanar Arulambalam

Jian-Guo Chen

Richard Joseph Byrne

Qian Xu

Alan David Berenbaum

Jun Zhao

Eu Gene Goh

Silvester Tjandra

Stefanos Kaxiras

Tor E Jeremiassen

Hakan I Pekcan

Xing Zhao

Kent E Wires

Cheng Gang Duan

Zhi He

Yun Peng

Michael James Hunter

Rainer Buchty

Dino P Oliva

Jesse Thilo

Lin Hua

David E Clune

Jeffrey L Timbs

Thomas Klucsarits

Nigamanth Lakshminarayana

Nigamanth Lakshiminarayana

Described embodiments provide a server for transferring data packets of streaming data sessions between devices. A redundant array of inexpensive disks (RAID) array having one or more stripe sector units (SSU) stores media files corresponding to the one or more data sessions. The RAID control module receives a request to perform the write operation to the RAID array beginning at a starting data storage address (DSA) and pads the data of the write operation if the amount of data is less than a full SSU of data, such that the padded data of the write operation is a full SSU of data. The RAID control module stores the full SSU of data beginning at a starting data storage address (DSA) that is aligned with a second SSU boundary, without performing a read-modify-write operation.

Aligned data storage for network attached media streaming systems

Described embodiments provide a server for transferring data packets of streaming data sessions between devices. The server includes an accelerator that, for received data packets, i) extracts header fields of the packets, ii) determines, based on the header fields, a destination for the packets, and iii) provides the packets to the destination. For data to be transmitted, the accelerator i) groups the data into packets, ii) generates header fields for the packets, and iii) provides the packets to the network. A memory arbiter manages accesses to memory that buffers data and stores keys corresponding to the data sessions. A storage medium stores media files corresponding to the data sessions. A key manager includes i) a first memory for storing a master key of the server, ii) a second memory for storing one or more keys corresponding to the data sessions, and iii) a processor to encrypt and decrypt data.

Method and apparatus for secure key management and protection

In one embodiment, the invention provides a method for repairing a defective storage device in a physical storage-device array having a plurality of storage devices. The method comprises the steps of identifying a disk error associated with the defective storage device; effecting an error recovery pause based on the disk error; processing one or more outstanding data storage or retrieval requests; and generating a new data storage request instructing the physical disk device array having the defective storage device to store valid data associated with the data storage or retrieval request corresponding to the disk device error, whereby the defective storage device is repaired.

Method and apparatus for repairing uncorrectable drive errors in an integrated network attached storage device

In some examples, a protocol accelerator extracts a queue identifier from an incoming packet, for identifying a first buffer queue in which the packet is to be stored for transport layer processing. A packet having an error or condition is identified, such that the accelerator cannot perform the processing on that packet. A processor is interrupted. The identified packet is stored in a second buffer queue. The processor performs transport layer processing in response to the interrupt, while the accelerator continues transport layer processing of packets in the first buffer queue. In some examples, a TCP congestion window size is adjusted. A programmable congestion window increment value is provided. The window size is set to an initial value at the beginning of a TCP data transmission. The window size is increased by the increment value when an acknowledgement is received.

Protocol accelerator and method of using same

In one embodiment, the invention provides a method for accessing a physical storage-device array comprising a plurality of storage devices. The method includes (1) obtaining at least one parameter from a profile selected from two or more profiles concurrently defining two or more virtual arrays, each profile defining (i) a different virtual array associated with a corresponding set of storage devices and (ii) a parameter set of one or more parameters used for accessing the virtual array; and (2) generating an instruction, based on the at least one parameter, for accessing, or disallowing access to, information in the virtual array defined by the selected profile, wherein a parameter in each the parameter set defined by each profile indicates whether two or more storage devices in the corresponding virtual array are degraded.

Double degraded array protection in an integrated network attached storage device

A method includes storing video data in a disk by way of a first queue comprising a linked list of buffers. Video data are received into the first queue by way of a tail buffer. The tail buffer is at one end of the linked list of buffers in the first queue. Video data are copied from a head buffer to the disk. The head buffer is at another end of the linked list of buffers in the first queue. The video data are displayed in real-time directly from the buffers in the queue, without retrieving the displayed video data from the disk, and without interrupting the storing step.

Buffer management method and system with data displayed directly from buffers

A method comprises providing a free buffer pool in a memory including a non-negative number of free buffers that are not allocated to a queue for buffering data. A request is received to add one of the free buffers to the queue. One of the free buffers is allocated to the queue in response to the request, if the queue has fewer than a first predetermined number of buffers associated with a session type of the queue. One of the free buffers is allocated to the queue, if a number of buffers in the queue is at least as large as the first predetermined number and less than a second predetermined number associated with the session type, and the number of free buffers is greater than zero.

Buffer management method and system with two thresholds

Methods and apparatus are provided for reducing disk seek time to improve the overall throughput by improving the scheduling of read requests. One or more requests to read data from one or more disks are scheduled by suspending one or more requests to read data from the disk for a predefined period of time. The read suspension can be initiated, for example, in response to a request to read data from the disk, such as a speculative read operation. The predefined period of time may be approximately equal, for example, to an expected duration of the read request operation, an expected seek time, a predefined recovery time or a time since a last request less a recovery time. The read suspension can be conditioned upon one or more predefined criteria, such as a disk bandwidth threshold being satisfied, a time since a last request threshold being satisfied and a condition that only a request for a different stream than a currently requested stream is suspended.

Method and apparatus for scheduling disk read requests

In one embodiment, a method for reading data from a storage-device array including three or more storage devices. The array has a plurality of sector levels, each sector level containing one sector on each storage device in the array at corresponding addresses across the storage devices. Each sector level includes (i) parity data stored on a first storage device and (ii) information stored on the two or more remaining storage devices. The parity data for a current sector level is generated from the information stored at the current sector level on the remaining storage devices. The method includes: (a) generating an instruction for reading (i) the parity data from the first storage device at the current sector level and (ii) the information from the remaining storage devices at the current sector level; (b) receiving an indicator indicating whether one of the remaining storage devices is a degraded storage device; (c) if the indicator does not indicate a degraded storage device, then providing as output the information read from the remaining storage devices at the current sector level; and (d) if the indicator does indicate a degraded storage device, then: (d1) reconstructing information previously stored on the degraded storage device at the current sector level based on (i) the parity data read from the first storage device at the current sector level, and (ii) the information read from each remaining non-degraded storage device at the current sector level; and (d2) providing as output (i) the information read from the one or more non-degraded storage devices at the current sector level and (ii) the reconstructed information.

Back-annotation in storage-device array

A method includes storing first and second sets of parameters in a register. Each set of parameters defines a storage transaction to store data to a computer readable medium or a retrieval transaction to retrieve data from the computer readable medium. The first storage or retrieval transaction is performed according to the first set of parameters. The second set of parameters is retrieved from the register automatically when the first storage or retrieval transaction is completed, without waiting for a further command from a control processor. The second storage or retrieval transaction is performed according to the retrieved second set of parameters. A system for performing the method and a computer readable medium containing pseudocode for generating an application specific integrated circuit that performs the method are provided.

Method and apparatus for disk address and transfer size management

An apparatus and method are provided for extracting connection information from a traffic header in a communications network. The apparatus includes a first storage element containing a first look-up table for determining a first data packet header offset and data size for extracting a communications protocol type from the header and a second storage element containing a second look-up table for determining from the communications protocol type a second data packet header offset and second data size for extracting a connection address from the header. The storage elements may be in the form of content-addressable memories. Exception handling and hardware initialization can be controlled by a system processor.

Configurable network connection address forming hardware

A method includes assigning each of a plurality of disk write and disk read requests to respective ones of a plurality of queues. Each queue has an occupancy level and a weight. A score is assigned to each of the plurality of queues, based on the occupancy and weight of the respective queue. An operation type is selected to be granted a next disk access. The selection is from the group consisting of disk write, disk read, and processor request. One of the queues is selected based on the score assigned to each queue, if the selected operation type is disk write request or disk read request. The next disk access is granted to the selected operation type and, if the selected operation type is disk write or disk read, to the selected queue.

Buffer management method and system with access grant based on queue score

Disclosed is a vector indexed memory unit and method of operation. In one embodiment a plurality of values are stored in segments of a vector index register. Individual ones of the values are provided to an associated operator (e.g., adder or bit replacement). Individual ones of the operators operates on its associated vector index value and a base value to generate a memory address. These memory addresses are then concurrently accessed in one or more memory units. If the data in the memory units are organized as data tables, the apparatus allows for multiple concurrent table lookups. In an alternate embodiment, in addition to the above described operators generating multiple memory addresses, an adder is provided to add the base value to the value represented by the concatenation of the bits in the vector index register to generate a single memory address. Multiplexers controlled by a programmable mode select signal are used to provide either the multiple memory addresses or the single memory address to the memory units. This alternate embodiment provides an apparatus that can programmably function in either an vector indexed memory mode or a conventional memory addressing mode.

Vector indexed memory unit and method

A method and apparatus are disclosed for allocating functional units in a multithreaded very large instruction word (VLIW) processor. The present invention combines the techniques of conventional very long instruction word architectures and conventional multithreaded architectures to reduce execution time within an individual program, as well as across a workload. The present invention utilizes instruction packet splitting to recover some efficiency lost with conventional multithreaded architectures. Instruction packet splitting allows an instruction bundle to be partially issued in one cycle, with the remainder of the bundle issued during a subsequent cycle. The allocation hardware assigns as many instructions from each packet as will fit on the available functional units, rather than allocating all instructions in an instruction packet at one time. Those instructions that cannot be allocated to a functional unit are retained in a ready-to-run register. On subsequent cycles, instruction packets in which all instructions have been issued to functional units are updated from their thread's instruction stream, while instruction packets with instructions that have been held are retained. The functional unit allocation logic can then assign instructions from the newly-loaded instruction packets as well as instructions that were not issued from the retained instruction packets.

Growing community of inventors

Bethlehem, PA, United States of America

Nevin C Heintze