Abstract: Checksum values are used to detect low-level data corruption. I/O operations, such as, for example, read operations and write operations, cause data blocks to pass through a number of low-level drivers when the data blocks are transferred between an operating system and mass storage location. A checksum filter driver intercepts a data block as the data block passes between low-level drivers as a result of the performance of an I/O operation. The checksum filter driver calculates a first checksum value for the data block. The checksum filter subsequently intercepts the data block as the data block passes between low-level drivers as a result of the performance of a subsequent I/O operation. The checksum filter driver calculates a second checksum value for the data block. The first checksum value and the second checksum value are compared. Data corruption is detected when a checksum mismatch occurs.

Abstract: The present invention relates to a system and methodology to facilitate I/O access to a computer storage medium in a predictable and efficient manner. A scheduling system is provided that mitigates the problem of providing differing levels of performance guarantees for disk I/O in view of varying levels of data access requirements. In one aspect, the scheduling system includes an algorithm or component that provides high performance I/O updates while maintaining high throughput to the disk in a bounded or determined manner. This is achieved by dynamically balancing considerations of I/O access time and latency with considerations of data scheduling requirements. Also, the system provides latency boundaries for multimedia applications as well as managing accesses for other applications.

Abstract: Checksum values are used to detect low-level data corruption. I/O operations, such as, for example, read operations and write operations, cause data blocks to pass through a number of low-level drivers when the data blocks are transferred between an operating system and mass storage location. A checksum filter driver intercepts a data block as the data block passes between low-level drivers as a result of the performance of an I/O operation. The checksum filter driver calculates a first checksum value for the data block. The checksum filter subsequently intercepts the data block as the data block passes between low-level drivers as a result of the performance of a subsequent I/O operation. The checksum filter driver calculates a second checksum value for the data block. The first checksum value and the second checksum value are compared. Data corruption is detected when a checksum mismatch occurs.

Abstract: The present invention relates to a system and methodology to facilitate I/O access to a computer storage medium in a predictable and efficient manner. A scheduling system is provided that mitigates the problem of providing differing levels of performance guarantees for disk I/O in view of varying levels of data access requirements. In one aspect, the scheduling system includes an algorithm or component that provides high performance I/O updates while maintaining high throughput to the disk in a bounded or determined manner. This is achieved by dynamically balancing considerations of I/O access time and latency with considerations of data scheduling requirements. Also, the system provides latency boundaries for multimedia applications as well as managing accesses for other applications.

Abstract: The present invention provides for a method of congestion control for multicast transmission that is entirely managed at the source of the transmission. The various types of filters as well as round trip time estimators (130) that are used in the invention to determine when the rate of the multicast transmission should be reduced to alleviate congestion.

Abstract: Checksum values are used to detect low-level data corruption. I/O operations, such as, for example, read operations and write operations, cause data blocks to pass through a number of low-level drivers when the data blocks are transferred between an operating system and mass storage location. A checksum filter driver intercepts a data block as the data block passes between low-level drivers as a result of the performance of an I/O operation. The checksum filter driver calculates a first checksum value for the data block. The checksum filter subsequently intercepts the data block as the data block passes between low-level drivers as a result of the performance of a subsequent I/O operation. The checksum filter driver calculates a second checksum value for the data block. The first checksum value and the second checksum value are compared. Data corruption is detected when a checksum mismatch occurs.