Compaq Computer Corporation, Inc.

Hewlett-packard Development Company, L.P.

Intel-ne, Inc.

John S Lacombe

Siamak Tavallaei

Robert O Sharp

Kenneth G Keels

Jeffrey S Autor

Brian S Hausauer

Jeffery L Galloway

Robert E Van Cleve

An T Vu

Jose A Santin

Theodore F Emerson

Melvin K Benedict

Thomas T Hardt

Michael R Garrett

Tim W Majni

Gregory T Noren

Paul J Muraski

Michael E McGowen

Rene Gaudet

Wade D Vinson

James A Mouton

Rene Richard Gaudet

Vivian McDaniels-Sanders

Mark I Bain

Richard L Purvis

Paul S Bailey

Stephen D Cochran

Peter M Yee

Clarence Rick Thompson

A flexible arrangement allows a single arrangement of Ethernet channel adapter (ECA) hardware functions to appear as needed to conform to various operating system deployment models. A PCI interface presents a logical model of virtual devices appropriate to the relevant operating system. Mapping parameters and values are associated with the packet streams to allow the packet streams to be properly processed according to the presented logical model and needed operations. Mapping occurs at both the host side and at the network side to allow the multiple operations of the ECA to be performed while still allowing proper delivery at each interface.

Method and apparatus for using a single multi-function adapter with different operating systems

The specification discloses a structure and related method for determining whether a particular BIOS routine is supported on a computer system, and if so, the service number for that BIOS routine. This determination is made by a software program accessing a table which correlates unique identification numbers for each BIOS routine with a BIOS call service number. The presence or absence of a unique identification number in the table is an indication to the calling program whether the BIOS implements the desired BIOS routine. If the unique identification number exists in the table, it thus identifies the service number for the particular BIOS routine.

Entrypoint discovery techniques in a bios entity

An application watchdog, comprising a dedicated watchdog counter in the hardware layer and a watchdog driver operating in the kernel mode layer of the computer operating system. The driver comprises a system thread configured to monitor a plurality of designated user applications operating in the user mode of the operating system and a message passing interface for receiving periodic signals from each of the user applications. The driver also uses an interface for transmitting timer reset commands to the dedicated watchdog counter. If the system thread receives a message from each of the designated user applications within an allotted period of time, the watchdog driver sends a timer reset command to the dedicated watchdog counter. Otherwise, the dedicated watchdog counter fails to receive the reset command and subsequently issues a system reset command. Early warning signals may be issued prior to system reset to alert system management.

Hardware implementation of an application-level watchdog timer

A software implementation of an application watchdog, comprising a restart service operating in the user mode and a watchdog driver operating in the kernel mode of a computer operating system. The driver incorporates a system thread configured to monitor a plurality of user applications operating in the user mode. The driver provides a first IOCTL signal interface for communicating control signals between the watchdog driver and one of the user applications and a second IOCTL signal interface for communicating control signals between the watchdog driver and the restart service. A communication interface exists for coordinating timer events with the operating system scheduler. If the system thread does not receive a message from one of said applications within an allotted period of time, the timer event alerts the watchdog driver that the allotted time has elapsed and the watchdog driver signals the restart service to restart that application.

Application-level software watchdog timer

A fan controller is described herein that can be connected to other fan controllers to provide fault information from one controller to the other(s). The fan controllers each control one or more fans. The controllers include signal(s) connected between the controllers that transmit fault information from one fan controller to the other(s) without the involvement of the host processor. Further, the controllers are capable of performing a 'free wheeling' test in which idle fans are spun and tested.

Cascadable dual fan controller

A computer system includes a microprocessor, a storage device, and a system memory. The storage device is accessible by the microprocessor. The system memory is accessible by the microprocessor and adapted to store data. The data includes operating system software. The operating system software, when executed by the microprocessor, is adapted to detect an error condition, and in response to the error condition, read at least a portion of the data stored in the system memory, compress the portion to generate compressed data, and store the compressed data on the storage device. A method for responding to an unrecoverable error in a computer system includes identifying the unrecoverable error and reading at least a first portion of the data stored in a memory device of the computer system. The first portion is compressed to generate compressed data, and the compressed data is stored on a storage device of the computer system.

Method and apparatus for accelerating a memory dump

A computer system in accordance with the present invention provides a method of communicating asynchronous events from a mini-port driver of a computer system to a software component without polling the mini-port driver. The computer system provides a monolithic driver as a dispatch between a mini-port driver and a software component. Until an asynchronous event is detected, an event thread in the monolithic driver to a software component is blocked. When an asynchronous event is detected by the mini-port driver, the mini-port driver calls the monolithic driver with a monolithic driver entry point which queues the event and unblocks the event thread. The monolithic driver provides the asynchronous event to the software component through the unblocked event thread. The event thread is then re-blocked and remains blocked until another asynchronous event is detected. Asynchronous events are thereby communicated from a mini-port driver to a software component without polling the mini-port driver.

Method of communicating asynchronous elements from a mini-port driver

A cooling system for a high-end server includes four hot-pluggable fans plugged into a fan control board. The fans are arranged in two groups, with each group having two fans, one behind the other. One of the groups of fans is used to cool the processor boards and the other group is used to cool the system I/O board slots. Under normal operation, only one fan from each group is active, while the other fan freewheels, providing redundancy. A fan control board delivers power to each of the fans and further provides a signal, responsive to temperature sensors, to each of the fans to control their speeds. Each of the fans provides a fan fault signal and a fan not present signal to the fan control board. The temperature sensors are placed proximate the processors and I/O components to monitor the operating temperatures thereof, and communicate the respective temperatures back to the fan control board, via I.sup.2 C bus. An operating system is utilized to drive the fan controller but can be overridden by the fan controller during critical conditions. An air ramp is positioned between the processors to help direct the flow of air generated by the fans onto some of the processors. Additionally, each of the fans are configured with a quick installment device to facilitate single-hand insertion and removal of the fans from the computer system.

System and associated method for cooling components within a computer

Apparatus, and an associated method, for determining the level of power supply redundancy in a modular computer system. Determination of the level of power supply redundancy is made dynamically, during on-line operation of the computer system. Reconfiguration of the computer system, such as to increase the load which must be powered by modular power supply components, or removal or addition of power supply components to form portions of the computer system cause initiation of a new determination of the level of power supply redundancy. Indications of inadequate levels of power supply redundancy are provided to a user of the computer system so that corrective action can be taken.

Method and apparatus for determining computer system power supply

A nonintrusive monitoring system is used to determine the onset and duration times of an electrical power outage-caused down condition of a computer without requiring a pre-power outage polling of a running component of the computer and thereby degrading computer system performance. In response to a supply power outage the monitoring system switches on a battery-powered counter device, representatively a digital counter or a real time clock, and then switches the counter device back off in response to resumption of power supply to the computer. A software portion of the monitoring system then detects the count value of the counter device, and utilizes the count value to compute the onset and duration times of the previous power outage. Using an alternative nonintrusive technique, the monitoring system permits the counter device to run during power supply to the computer, while using the computer system clock to generate periodic time stamps, and disables the counter device during computer supply power outages. Upon resumption of supply power to the computer, the monitoring system compares the time stamp information to the count value to determine the onset and duration times of the previous supply power outage.

Nonintrusive monitoring of a computer system's downtime due to a supply

Improved techniques for facilitating identification of a computer system's hardware features to software executing on the computer system are disclosed. In one embodiment, the software is system management software that serves to monitor and control the computer system to reduce failures and/or improve performance. In a general sense, the invention provides a system feature table within a computer system to describe each of the hardware features of the computer system, including feature data and appropriate access mechanisms for additional information. In addition, a user can be notified when the software does not support all the hardware features of the computer system. The invention also is able to identify locations of failing hardware features for easy replacement or examination.

Method and apparatus for identification of features associated with

Through a menu driven selection procedure, a user is given options for how a server should respond to an actuation of a power switch. In one option, the power switch is disabled to prevent accidental shut down of the power supply in response to power switch actuation. In another option, the shut down of the power supply follows soon after the expiration of a count down timer which is triggered by power switch actuation. A subsequent actuation of the power switch in this option aborts the count down. In yet another option, the shut down of the power supply follows soon after the completion of a graceful shut down of the server operating system which is triggered by power switch actuation. A subsequent actuation of the power switch in this option causes an immediate shut down of the power supply.

Growing community of inventors

Austin, TX, United States of America

John S Lacombe