Simultaneous writing and reconstruction of a redundant array of independent limited performance storage devices

A method in a data processing system comprising:

• writing a first superblock to a redundant array of storage devices, wherein the storage devices include storage media, and wherein the first superblock includes a first plurality of data blocks and a first plurality of error correction blocks, each of the first plurality of error correction blocks containing error correction information;
• detecting a failure in a particular storage device in the redundant array of storage devices;
• in response to detecting the failure, writing a second superblock of data from the original source to the redundant array of storage devices, wherein the second superblock includes a second plurality of data blocks and a second plurality of error correction blocks, wherein a combined cardinality of the second plurality of data blocks and the second plurality of error correction blocks is less than a combined cardinality of the first plurality of data blocks and the first plurality of error correction blocks;
• generating, using cached data, at least one additional block corresponding to the second superblock;
• and
• writing the at least one additional block to a replacement storage device concurrently with continuously writing additional superblocks to the redundant array of storage devices.

A computer program product in a computer-readable storage medium comprising functional descriptive material that, when executed by a computer, enables the computer to perform acts including:

• writing a first superblock to a redundant array of storage devices, wherein the storage devices include storage media, and wherein the first superblock includes a first plurality of data blocks and a first plurality of error correction blocks, each of the first plurality of error correction blocks containing error correction information;
• detecting a failure in a particular storage device in the redundant array of storage devices;
• in response to detecting the failure, writing a second superblock to the redundant array of storage devices, wherein the second superblock includes a second plurality of data blocks and a second plurality of error correction blocks, wherein a combined cardinality of the second plurality of data blocks and the second plurality of error correction blocks is less than a combined cardinality of the first plurality of data blocks and the first plurality of error correction blocks;
• detecting completion of writing to the redundant array of storage devices;
• and
• in response to detecting the completion of writing to the redundant array of storage devices, writing at least one additional block corresponding to the second superblock to at least one replacement storage device.

A computer program product in a computer-readable storage medium comprising functional descriptive material that, when executed by a computer, enables the computer to perform acts including:

• writing a first superblock to a redundant array of storage devices, wherein the storage devices include storage media, and wherein the first superblock includes a first plurality of data blocks and a first plurality of error correction blocks, each of the first plurality of error correction blocks containing error correction information;
• detecting a failure in a particular storage device in the redundant array of storage devices;
• in response to detecting the failure, writing a second superblock of data from the original source to the redundant array of storage devices, wherein the second superblock includes a second plurality of data blocks and a second plurality of error correction blocks, wherein a combined cardinality of the second plurality of data blocks and the second plurality of error correction blocks is less than a combined cardinality of the first plurality of data blocks and the first plurality of error correction blocks;
• generating, using cached data, at least one additional block corresponding to the second superblock;
• and
• writing the at least one additional block to a replacement storage device concurrently with continuously writing additional superblocks to the redundant array of storage devices.

A data processing system comprising:

• means for writing a first superblock to a redundant array of storage devices, wherein the storage devices include storage media, and wherein the first superblock includes a first plurality of data blocks and a first plurality of error correction blocks, each of the first plurality of error correction blocks containing error correction information;
• means for detecting a failure in a particular storage device in the redundant array of storage devices;
• means, responsive to detecting the failure, for writing a second superblock to the redundant array of storage devices, wherein the second superblock includes a second plurality of data blocks and a second plurality of error correction blocks, wherein a combined cardinality of the second plurality of data blocks and the second plurality of error correction blocks is less than a combined cardinality of the first plurality of data blocks and the first plurality of error correction blocks;
• means for detecting completion of writing to the redundant array of storage devices;
• and
• means, responsive to detecting the completion of writing to the redundant array of storage devices, for writing at least one additional block corresponding to the second superblock to at least one replacement storage device.

A data processing system comprising:

• means for writing a first superblock to a redundant array of storage devices, wherein the storage devices include storage media, and wherein the first superblock includes a first plurality of data blocks and a first plurality of error correction blocks, each of the first plurality of error correction blocks containing error correction information;
• means for detecting a failure in a particular storage device in the redundant array of storage devices;
• means, responsive to detecting the failure, for writing a second superblock of data from the original source to the redundant array of storage devices, wherein the second superblock includes a second plurality of data blocks and a second plurality of error correction blocks, wherein a combined cardinality of the second plurality of data blocks and the second plurality of error correction blocks is less than a combined cardinality of the first plurality of data blocks and the first plurality of error correction blocks;
• means for generating, using cached data, at least one additional block corresponding to the second superblock;
• and
• means for writing the at least one additional block to a replacement storage device concurrently with continuously writing additional superblocks to the redundant array of storage devices.