摘要:
Systems, methods, and apparatus to identify and prioritize application processes in one or more subsystems. Some embodiments identifying applications and processes associated with each application executing on a system, apply one or more priority rules to the identified applications and processes to generate priority information, and transmit the priority information to a subsystem. The subsystem then matches received requests with the priority information and services the processes according to the priority information.
摘要:
A method and apparatus for detecting a presence of a fail over switch is described. In one embodiment, during an Serial ATA sequence initialization handshake, a host transmits a COMRESET to a device. In return, the host receives a COMWAKE from the device. If the host is of a first type of host, then the host identifies a presence of a fail over switch, in response to receipt of the COMWAKE. If the host is of a second type of host, then the host ignores the COMWAKE. The host then receives a COMINIT from the device, in accordance with the Serial ATA sequence handshake. The host transmits a COMWAKE to the device, and the host receives a COMWAKE in return from the device.
摘要:
A method for writing data on an optical storage medium in an optical storage device includes transferring data by a direct memory access process from a host buffer allocated in a memory of a host device to a local write buffer associated with the optical storage device. The data is then written from the write buffer to the optical storage medium.
摘要:
Systems, methods, and apparatus to identify and prioritize application processes in one or more subsystems. Some embodiments identifying applications and processes associated with each application executing on a system, apply one or more priority rules to the identified applications and processes to generate priority information, and transmit the priority information to a subsystem. The subsystem then matches received requests with the priority information and services the processes according to the priority information.
摘要:
Methods and arrangements to interface a data storage device such as a small form factor IDE/ATA hard drive are disclosed. Embodiments may comprise a host and/or a data storage device. The host and data storage device may form, e.g., a handheld device such as an MP3 player, a cellular phone, or the like. The host may comprise a new interface referred to as a CE-ATA interface that facilitates interaction with the data storage device. In many embodiments, the CE-ATA interface combines an ATA command layer or emulator with a Multimedia Card (MMC) electrical interface, advantageously accommodating a fast time-to-market solution by leveraging existing technologies. More specifically, ATA commands may be mapped into an MMC register space to transmit the commands to the data storage device. Several embodiments also implement interrupt functions for the data storage device. Other embodiments may be disclosed and claimed.
摘要:
Data is read in response to a request for a predetermined amount of data. The amount of data that has been read is determined prior to completing reading the predetermined amount of data. The predetermined amount of data may include prefetch data and demand data, where demand data is data for a computer program and prefetch data is data adjacent to the demand data.
摘要:
An apparatus is programmed with a plurality of programming instructions for generating, if possible, an alternative disk block allocation for a current disk block allocation that will yield improved overall access time for a sequence of disk accesses. In some embodiments, the programming instructions include the logic for tracing the sequence of disk accesses to determine the current disk block allocation, the logic for generating the alternative disk block allocation, if possible, using the trace results, and the logic for effectuating the alternate disk block allocation, if generated. In one particular embodiment, the logic for generating the alternative disk block allocation employs a random search approach, while in another embodiment, the logic for generating the alternative disk block allocation employs a heuristic approach.
摘要:
A locality characteristic generator and a response surface characteristic generator are provided either jointly or separately to one or more computer systems for generating locality characteristic data for workloads, and response surface characteristic data for locality dependent subsystem, independent of each other, which in turn are used to generate independent locality and response surface characteristic profiles. Each locality characteristic profile reflects the probability that the first occurrence of an access to a location with a stride of size s from the current location takes place between the reference distance of d/2 to d from the current reference. Each response surface characteristic profile reflects what the expected response time will be if the first occurrence of an access to a location having a stride of size s from the current location takes place between the reference distance of d/2 to d from the current reference. Accordingly, any one of the locality characteristic profiles can be used in conjunction with any one of the independent response surface characteristic profiles to analyze the interaction between the particular combination of workload and locality dependent subsystem. Alternatively, the generated locality and response characteristic data can be used to generate performance indices for various combinations of workloads and locality dependent subsystems.