Digital Equipment Corporation

Quantum Corporation

Fernando A Zayas

Robert C Frame

Edward A Gardner

William D Lewis

Bernardo Rub

Patrick L Hearn

Antonios E Prentakis

Kenneth F Veseskis

Matthew F Giovanetti

A method and arrangement for preventing the locking out of devices which are coupled to a bus by either of two of the devices which have become initiator and target devices respectively. The devices arbitrate for control of the bus after the bus enters a bus free phase. The device which wins the arbitration becomes an initiator. A timer in each device on the bus is started upon the initiation of arbitration. The initiator device is removed from the bus when an elapsed time after the timers have been started reaches a predetermined value. The distributed clock of the invention ensures that the devices coupled to the bus will clear the bus after the initiator has been on the bus for a pre-determined time, thereby obviating skew problems associated with single clocked systems.

Double unequal bus timeout

A method and apparatus for selecting a particular node from a plurality of nodes connected to a common bus to allow the node to use the bus. The nodes have a pre-determined priority. After initially enabling the nodes, the bus is monitored for a bus idle condition. It is then determined which of the nodes are enabled message nodes, which are enabled nodes that have a message to send on the bus. There is then arbitration between the enabled message nodes after the bus is in the bus idle condition for a first period of time, such that the enabled message node having the highest pre-determined priority among the enabled message nodes is disabled for arbitration purposes, and also at the same time selects a target and performs a transfer. This procedure is repeated until all the enabled message nodes have been disabled. Thereafter, all of the nodes on the bus are enabled when the bus is in the bus idle condition for a second period of time, which is longer than the first period of time.

Fair arbitration scheme for arbitrating between multiple nodes in a

A method and apparatus for optimizing the track seeking operation of disc drives by adaptively changing the seek velocity profile in response to the actual performance of the drive during track seeking operations based upon the amount of head overshoot and the actuator power dissipation.

Adaptive track seeking for disk drives

A method and arrangement for preventing the locking out of devices which are coupled to a bus by either of two of the devices which have become initiator and target devices respectively. The devices arbitrate for control of the bus after the bus enters a bus free phase. The device which wins the arbitration becomes an initiator. A timer in each device on the bus is started upon the initiation of the arbitration. The initiator device is removed from the bus when an elasped time after the timers have been started reaches a pre-determined value. The distributed clock of the invention ensures that the devices coupled to the bus will clear the bus after the initiator has been on the bus for a pre-determined time, thereby obviating skew problems associated with single clocked systems.

An atomic ordered sequence of information phase transitions allows for the design of a pure hardware protocol controller for use in a small storage interconnect bus. The information phase transitions follow the sequence: Command Out phase, Data Out phase, and Status In phase. The only other transition sequence allowed is from the Command Out phase directly to the Status In phase. The Command Out phase is actually a header delivering header information. Included in the header are a REQ/ACK offset byte, source destination ID verify byte, frame length bytes, and a checksum byte. The Data Out phase contains any number of bytes that were defined in the Command Out frame length byte. The Status In phase is a single byte which is used to signal the outcome of the attempted data delivery.

Method and apparatus for transferring information over a common parallel

In the manufacture of a high capacity data storage device having multiple surfaces for recording information, the yield of the manufacturing process is improved by providing the storage device with a spare surface. If a recording surface is found to be totally defective, or, substantially worse than the other surfaces, as determined by the manufacturing testing procedures, that surface is, by means of a remapping table, logically retired and the information intended for the defective surface is stored on the logically reallocated spare surface.

Growing community of inventors

Stow, MA, United States of America

Fernando A Zayas