Distributed multi-level protection in a RAID array based storage system

A method for use in a computing system, the method comprising:

• writing a RAID stripe to a plurality of storage devices in a redundant array of independent disks (RAID) configuration, wherein writing the RAID stripe includes:
• for each storage device of a subset of the plurality of storage devices, writing within a page of the storage device, user data and a checksum that validates the user data stored on the storage device;
• writing within a page of a particular storage device of the plurality storage devices,
• inter-device protection data, the inter-device protection data protecting the user data stored on each storage device of the subset of the plurality of storage devices;
• intra-page protection data, the intra-page protection data protecting the inter-device protection data stored on the particular storage device;
• and
• inter-page protection data, the inter-page protection data protecting the checksums stored on each storage device of the subset of storage devices.

A non-transitory computer readable storage medium storing program instructions, wherein the program instructions are executable to:

• write a RAID stripe to a plurality of storage devices in a redundant array of independent disks (RAID) configuration, wherein writing the RAID stripe includes:
• for each storage device of a subset of the plurality of storage devices, writing within a page of the storage device, user data and a checksum that validates the user data stored on the storage device;
• writing within a page of a particular storage device of the plurality storage devices,
• inter-device protection data, the inter-device protection data protecting the user data stored on each storage device of the subset of the plurality of storage devices;
• intra-page protection data, the intra-page protection data protecting the inter-device protection data stored on the particular storage device;
• and
• inter-page protection data, the inter-page protection data protecting the checksums stored on each storage device of the subset of storage devices.

A computer system comprising:

• a data storage subsystem comprising a plurality of storage devices in a redundant array of independent drives (RAID) configuration;
• and
• a storage controller to:
• write a first RAID stripe to the plurality of storage devices including:
• for each storage device of a subset of the plurality of storage devices, writing within a page of the storage device, user data, and a checksum that validates the user data stored on each storage device of the subset of the plurality of storage devices;
• and
• writing, within a page of a particular storage device of the plurality of storage devices:
• inter-device redundancy data, the inter-device redundancy data to protect the user data stored on each storage device of a first subset of the plurality of storage devices,
• intra-page error recovery data, the intra-page error recovery data to protect the inter-device redundancy data stored on the particular storage device, and
• inter-page protection data, the inter-page protection data to protect the checksums stored on each storage device of the subset of the plurality of storage devices.

A method, comprising:

• writing, by a storage controller of a data storage subsystem comprising a plurality of storage devices in a redundant array of independent drives (RAID) configuration, a first RAID stripe to the plurality of storage devices, wherein writing the first RAID stripe comprises:
• for each storage device of a subset of the plurality of storage devices, writing within a page of the storage device, user data, and a checksum that validates the user data stored on each storage device of the subset of the plurality of storage devices;
• and
• writing, within a page of a particular storage device of the plurality of storage devices:
• inter-device redundancy data, the inter-device redundancy data to protect the user data stored on each storage device of a first subset of the plurality of storage devices,
• intra-page error recovery data, the intra-page error recovery data to protect the inter-device protection data stored on the particular storage device, and
• inter-page protection data, the inter-page protection data to protect the checksums stored on each storage device of the subset of the plurality of storage devices.