Hewlett-packard Development Company, L.P.

Hewlett-packard Company

Western Digital Technologies, Inc.

Skhynix Inc.

Stephen J Silva

Michael S Allison

John A Morrison

Fred Sprague

Thomas W Yip

Richard W Gillespie

Johnny A Lam

Matthew Lewis Call

Leo J Embry

John R Metzner

Frederick K H Lee

Guy Lowell Kuntz

Stephen Patrick Hack

Richard Dickert Powers

Jing Booth

Nathan Jared Hughes

Ryan Lee Weaver

John R Feehrer

John A Strange

Justin Ha

David Matthew Bellia

Chritopher Wilson

Window based mapping is used to reduce the usage of volatile memory for storing the mapping of logical to physical addresses for accesses to data in a flash drive. Two separate mapping tables for translation of logical addresses to physical addresses (L2P), e.g., an L2P front map and an L2P back map, are used where the L2P front map acts as a window to the L2P back map. The L2P front map has smaller granularity for data accesses than the L2P back map. The data accessed using the L2P front map can allow the flash drive to function with relatively same performance as a fully mapped drive with a single mapping table.

Window based mapping

An embedded system may include an embedded device and a host device. The embedded device may provide a packet for a service, and generate a first transmission control protocol (TCP) segment including a piece of the packet and a first header with no checksum value. The host device may receive the first TCP segment, generate a second TCP segment including the piece of the packet and a second header with a checksum value based on the piece of the packet and the first header, and generate an Internet protocol (IP) packet based on the second TCP segment.

Embedded system and method thereof

Embodiments of systems and methods that ensure integrity of data during unexpected power interruption of loss are disclosed. In some embodiments, critical data is saved quickly and efficiently using backup power. Data integrity is ensured even when the reliability of backup power sources is an issue. In some embodiments, by skipping the updating and saving of system data while operating on backup power, significant reduction of time for saving critical data can be achieved. System data can be restored next time the data storage system is restarted. Improvements of data storage system reliability are thereby attained.

Fast saving of data during power interruption in data storage systems

Systems and methods for early warnings of power loss in solid state storage drives are disclosed. Early warnings of power loss can be used to power the drive to force the drive into a low power states before the energy in backup power sources, such as backup capacitors, is used. The low power states can allow for the reduction of power use by the drive which can provide cost savings and reduction in the risk that the drive will be rendered reconfigurable by a power failure event.

Power fail protection and recovery using low power states in a data storage device/system

Systems and methods for testing non-volatile storage devices are disclosed that provide functionality to control when testing of the non-volatile storage device is performed. In one embodiment, information stored in persistent memory indicates whether testing is enabled or disabled. For example, the testing information may indicate that testing is to be performed upon a first initialization of a non-volatile storage device, but not in connection with subsequent power-up events. Furthermore, functionality is disclosed for re-running and/or bypassing testing of the non-volatile storage device.

Automatic and on-demand testing of non-volatile storage devices

Routes between cells in an interconnection network are represented with a graph using graph theory. Failed links are identified, and using the graph, alternative routes between cells in the graph are found.

Network graph for alternate routes

To dynamically adjust at least one setting of an interface to a communications link in a system, in response to receiving an indication of a change in a characteristic of the communications link, a representation of potential solutions for parameters associated with the communications link is constructed. From the representation, at least one solution is selected from among the potential solutions, where the selected at least one solution specifies values for the parameters that define the at least one setting for the interface to the communications link.

Discovering parameters for a communications link

Systems, methodologies, media, and other embodiments associated with acquiring processor executable instructions from an option ROM are described. One exemplary method embodiment includes discovering input/output devices operably connected to a processor and updating a data structure with information concerning the input/output devices. The example method embodiment may also include obtaining a device driver from an option ROM associated with an input/output device, storing the device driver in non-MMIO memory and making the device driver available to input/output devices physically connected to the processor and for which information is stored in the data structure.

Option ROM code acquisition

A system and method updating firmware of cells in cellular, high availability, computing systems. One or more cells having missing, obsolete, corrupt, or otherwise errored firmware when compared to other cells in the partition are identified as mismatched cells. An update cell having desired firmware transmits an update message to each mismatched cell via a manageability system slow speed interconnect. In response to the update message, each mismatched cell enables a high speed interconnect over which they can receive the desired firmware. The update cell transmits the update firmware to each mismatched cell via the high speed interconnect.

System and method for high availability firmware load

A system and method generate a read only memory (ROM) image for a ROM. The ROM image generator operates with a data image builder. The ROM image generator processes an input file to identify data images for a build. The image identifier generates tokens for building each data image. A data image builder uses the tokens as an input to build each data image. A ROM image builder builds the ROM image using each data image build and generates a data image build validating signature for each data image build, such as a checksum. Once each data image build and associated validating signature is written to the ROM image, the ROM image is completed with a checksum of the entire ROM image.

Method for generating a read only memory image

The time required to boot a computer is reduced by reducing or eliminating the need to discover many or all devices within the computer and the machine topology. Access panels are monitored so that it is detected when they are opened. For the access panels that have not been opened, it is assumed that the system configuration, topology, devices, etc. have not changed since the last boot process and there is no need to spend time discovering these devices and machine topology. Stored, instead of discovered, configuration information is then used to configure these devices. This reduces the time required to boot since discovery of devices is not performed. A service processor or other logic may be used to detect which access panels are opened. Also, only those elements of the configuration that may be affected by the particular access panels that were opened need to be re-discovered.

Reducing boot times via intrusion monitoring

An apparatus and method for fault resilient booting of a multi-processor system. The apparatus attempts a cold reset of the system, during which each processor performs a built-in self test. The apparatus selects a boot strap processor to perform a warm reset, during which any failed processors are tristated using a flush command. If no boot strap processor is available, the apparatus performs the warm reset and tristates any failed processor including the processor predesignated to be the boot strap processor, and then repeats the attempt to establish the boot strap processor.

Apparatus and method for implementing fault resilient booting in a multi-processor system by using a flush command to control resetting of the processors and isolating failed processors

A distributed automated testing system is provided which is capable of being distributed over a network, such as the Internet, for testing hardware and software. A plurality of users operating computers interface to the automated testing system via user interfaces, which preferably are graphical user interfaces. Each user interface displays test parameter choices to the user from which the user may select test parameters relating to a test to be performed. The user interfaces generate data packets in response to selections by the users and output the data packets onto the network. The data packets output from the user interfaces comprise information relating to test parameters selected by the user, commands indicating that performance of a test is being requested, and an address of the location to which the packet is being sent. The data packets are routed to one or more dispatcher machines located on the network which are designated by the addresses contained in the data packets. Each of the dispatcher machines maintains a list of tests to be performed. The dispatcher machine designated by the address in the data packet receives the data packet and updates the list of tests to be performed. A plurality of test machines are in communication with the dispatcher machines via the network. When a test machine is available, the available test machine generates availability data packets which indicate that the test machine is available to perform a test. Each of the availability data packets contains an address of a dispatcher machine. These availability data packets are sent over the network and routed to the dispatcher machine designated by the address contained in the availability data packet. Upon receiving an availability data packet, the dispatcher machine determines whether one or more of the tests on the list of tests maintained by the dispatcher machine is capable of being performed by the test machine which generated the availability data packet. If one or more of the tests listed are capable of being performed by the available test machine, the dispatcher machine instructs the test machine to perform one of the tests, preferably the test having the highest priority.

Distributed automated testing system

The present invention comprises a testing system for testing X Servers. The testing system comprises a test harness that communicates with an X Server being tested to obtain the test results therefrom, an archive database for storing test archives to be used by the test harness for testing the X Server, a test result storage database for storing results of an X Server test, and a viewing tool that presents the user with a result file which the user analyzes to determine the X Server defect. Preferably, the test harness is object-oriented code that has a polymorphic and hierarchical structure. The basic units of the test harness are objects, such as display connections, screens, graphics contexts, pixmaps, colormaps and windows. Within the test context, each object encodes a unique hierarchy that indicates its dependencies on other test harness objects. These objects encapsulate Xlib routines and hide much of the detail of Xlib programming from the test writer, thus facilitating the test writer in writing tests. Once a test has been written, the test is run and the results of the test, if they are correct, are stored as an archive file in the test archive storage database for later use. When a test is run on an X Server, the test harness captures the image rendered to the screen by the X Server. The test harness then searches the archive database in a predetermined manner to obtain the appropriate test archive. The test archive is then compared to the test results. If the test failed, then a defect exists in the X Server.

Method and apparatus for testing X servers

A communications protocol for an automated testing system is provided which governs the generation and transmission of data packets within the automated testing system. The automated testing system is capable of being distributed over a network, such as the Internet, and is used for testing hardware and software. A plurality of users operating computers interface to the automated testing system via user interfaces, which preferably are graphical user interfaces. Each user interface displays test parameter choices to the user from which the user may select test parameters relating to a test to be performed. The user interfaces generate data packets in response to selections by the users and output the data packets onto the network. The data packets output from the user interfaces comprise information relating to test parameters selected by the user, commands indicating that performance of a test is being requested, and an address of the location to which the packet is being sent. The data packets are routed to one or more dispatcher machines located on the network which are designated by the addresses contained in the data packets. Each of the dispatcher machines maintains a list of tests to be performed. The dispatcher machine designated by the address in the data packet receives the data packet and updates the list of tests to be performed. A plurality of test machines are in communication with the dispatcher machines via the network. When a test machine is available, the available test machine generates an availability data packet which indicates that the test machine is available to perform a test. Each of the availability data packets contains an address of a dispatcher machine. These availability data packets are sent over the network and routed to the dispatcher machine designated by the address contained in the availability data packet. Upon receiving an availability data packet, the dispatcher machine determines whether one or more of the tests on the list of tests maintained by the dispatcher machine is capable of being performed by the test machine which generated the availability data packet. If one or more of the tests listed are capable of being performed by the available test machine, the dispatcher machine instructs the test machine to perform one of the tests, preferably the test having the highest priority.

Growing community of inventors

Ft. Collins, CO, United States of America

Stephen J Silva