초록 ▼

A continuous media file is comprised of stripe sets over disk drives in one or more RAID sets. In a preferred embodiment, the RAID set includes n disk drives. The data storage of each disk drive in the RAID set is partitioned into an integer number m of hyper-volumes, and the parity is stored in one

A continuous media file is comprised of stripe sets over disk drives in one or more RAID sets. In a preferred embodiment, the RAID set includes n disk drives. The data storage of each disk drive in the RAID set is partitioned into an integer number m of hyper-volumes, and the parity is stored in one hyper-volume of each of m disk drives in the RAID set. The stripe set includes a series of transfer units of data in respective ones of the disk drives. Each transfer unit includes an integer number j of data blocks, and each hyper-volume includes an integer number k of transfer units. Each stripe set includes (m)(n-1) transfer units of data. The transfer units of the RAID set are allocated for the storage of continuous media data in a right-to-left and then top-to-bottom order in which the transfer units appear in an m row by n column matrix in which the rows of the matrix represent parity groups of hyper-volumes in the disk drives and the columns of the matrix represent storage in the respective disk drives. At most one write access to each parity hyper-volume need be performed during write access to a stripe set. Parity changes for the data being written are accumulated in non-volatile memory, and written to the RAID set after completion of the writing of the data.

대표청구항 ▼

[ What is claimed is:] [1.] A method of striping a sequence of continuous media data across a plurality of n disk drives in a RAID set storing data and associated parity across the disk drives, wherein the data storage of each disk drive in the RAID set is partitioned into an integer number m of hyp

[ What is claimed is:] [1.] A method of striping a sequence of continuous media data across a plurality of n disk drives in a RAID set storing data and associated parity across the disk drives, wherein the data storage of each disk drive in the RAID set is partitioned into an integer number m of hyper-volumes, parity is distributed among the disk drives in the RAID set and is stored in at least one hyper-volume of each of m disk drives in the RAID set, and transfer units of data storage in the n disk drives are associated with the sequence of continuous media data in a right-to-left and then top-to-bottom order in which the transfer units appear in an m row by n column matrix in which the rows of the matrix represent parity groups of hyper-volumes in the disk drives and the columns of the matrix represent the data storage in the respective n disk drives in the RAID set, which further includes allocating data storage in the RAID set for the stream of continuous media data in fixed size stripe sets, each stripe set comprising a segment of the sequence of continuous media data distributed across each of the disk drives and each of the parity groups of hyper-volumes in the disk drives,wherein the transfer unit has a predetermined size, and each stripe set includes (m)(n-1) transfer units of data.