Abstract: A magnetic recording device for recording data onto a magnetic disk in the form of a spiral track. A spindle motor rotates the disk about a pivot point. A transducer writes the data onto the disk as a digital bit stream. The transducer is positioned radially over the disk by a servomechanism. As the servomechanism positions the transducer radially across the spinning disk relative to the rotation of the disk, a spiral track is described upon the disk. A dedicated or an embedded servo system can be utilized with the spiral data track. Furthermore, the servo tracks can take the form of either concentric circles or a spiral. By recording data as a spiral rather than as concentric circles, cumulative seek time delays are minimized.

Abstract: A method and apparatus is disclosed for partitioning a data buffer to create separate read and write buffers, wherein the boundaries between the buffers and the sizes of the buffers change dynamically depending upon the command mix received from the host computer. Data buffer space is allocated to provide highest priority to processing the current host command, and next priority to preserving a read ahead cache.

Abstract: In a multiple-CPU, dynamic path allocation environment. The environment, several devices, such as input/output (I/O) devices, may be accessed through one of a plurality of dynamically configured paths from the CPU. Each path includes a channel, from the CPU, connected to a director. The director, in turn, is connected through respective control module interfaces, to a plurality of control modules, which control modules are used to access a string of devices. The connection method, carried out under control of the director, includes simultaneously polling all of the control modules to determine if any have devices attached thereto that are ready to be connected to the CPU. A response from the control modules, all received simultaneously at the director, identifies the CPU channel through which the connection is to be made. The specific address of the device to be connected is then determined, and the desired connection from the CPU to the device is completed.