System and method for reorganizing data in a raid storage system

• US 6,898,668 B2
• Filed: 06/24/2002
• Issued: 05/24/2005
• Est. Priority Date: 06/24/2002
• Status: Expired due to Fees

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Thompson, Mark J., Schultz, Stephen M.
• Primary Examiner(s): Thai, Tuan V.
• Application Number:
  US10/179,727
• Publication Number:
  US 20030236944A1
• Time in Patent Office: 1,065 Days
• Field of Search: 711/100, 711/112, 711/114, 711/154, 711/202, 714/8, 714/20, 714/763, 714/766
• US Class Current: 711/114
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 2211/1035 Keeping track, i.e. keeping track of data and parity changes
• CPC Class Codes: G06F 3/0605 by facilitating the interaction with a user or administrator
• CPC Class Codes: G06F 3/0608 Saving storage space on storage systems
• CPC Class Codes: G06F 3/064 Management of blocks
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G11B 2220/2516 Hard disks
• CPC Class Codes: G11B 2220/415 Redundant array of inexpensive disks [RAID] systems
• CPC Class Codes: G11B 27/002 Programmed access in sequence to a plurality of record carriers or indexed parts, e.g. tracks, thereof, e.g. for editing; transfer of record carriers from magazine G11B15/68, G11B17/10; G11B17/22
• CPC Class Codes: G11B 27/105 of operating discs

Abstract

A method of operating a storage controller that receives data access requests containing a logical block address and a count of blocks involved in the access request. A record is generated and persistently stored indicating whether particular logical block addresses have been accessed since creation. The persistent record is subsequently accessed to enable selected operations to be skipped or aborted when they selected operations involve logical block addresses that have never been accessed.

Claims

1. A method of operating a storage controller comprising:

receiving data access requests containing a logical block address and a count of blocks involved in the access request;

persistently storing a record indicating whether particular logical block addresses have been accessed since creation;

in response to detecting a condition that requires an operation that writes to a logical block address using data previously placed at that logical block address, consulting the persistently stored record as to whether the logical block address has been previously accessed; and

skipping the operation when the logical block address has been previously accessed.

2. The method of claim 1, wherein the persistent record is stored in one or more reserved sectors of at least one disk drive in an array.

3. The method of claim 1, wherein the persistent record is stored in non-volatile memory of the controller.

4. The method of claim 1, wherein the operation comprises a rebuild operation.

5. The method of claim 1, wherein the operation comprise a capacity expansion operation.

6. The method of claim 1, wherein the operation comprises a data migration operation.

7. The method of claim 1, wherein the act of skipping can be selectively disabled.

8. The method of claim 1, wherein the record indicates whether any of a particular range of block addresses has been previously written.

9. The method of claim 1, wherein the record indicates whether any of a particular range of block addresses has been previously read.

10. The method of claim 1, further comprising:

defining a plurality of zones, wherein each zone comprises a range of logical block addresses;

determining from the logical block address and count information associated with a storage access request, the identity of zones affected by the storage access request; and

setting a bit in the persistent record corresponding to the identified zone before completing the storage access request.

11. A storage controller comprising:

mechanisms for handling storage access operations that specify one or more logical block addresses;

mechanisms for accessing metadata indicating groups of logical block addresses that have been previously accessed and comprising;

a shift register operable to shift the at least one logical block address by a predetermined number of bits based on the size of a logical volume to which the storage access operations apply; and

a decoder operable on a predetermined number of the most significant bits of the shifted logical block address to generate a bit map indicating a range of logical block addresses including the at least one logical block address specified by the storage access operation; and

,

mechanisms for skipping selected storage access operations when the selected storage access operations operate on a logical block address that has been previously accessed.

12. The storage controller of claim 11, wherein the storage access operation comprises a write operation and the mechanism for accessing metadata further comprise:

processes for updating the metadata to indicate that the write operation has accessed a range of logical block addresses including the logical block address specified in the write operation.

13. The storage controller of claim 11, wherein the storage access operation comprises a read operation and the mechanism for accessing metadata further comprise:

processes for updating the metadata to indicate that the read operation has accessed a range of logical block addresses including the logical block address specified in the read operation.

14. The storage controller of claim 11, wherein the mechanisms for accessing metadata further comprise:

mechanisms for reading metadata stored persistently in reserved sectors of a physical disk drive.

15. The storage controller of claim 11, wherein the storage controller further comprises non-volatile memory and the mechanisms for accessing metadata further comprise:

mechanisms for reading metadata stored persistently in the non-volatile memory.

16. The storage controller of claim 11, further comprising processes for selectively disabling the mechanisms for skipping.

17. The storage controller of claim 11, further comprising a mechanism for logically combining the map with the metadata to produce updated metadata.

18. A method of operating a storage controller comprising:

defining a plurality of zones, wherein each zone comprises a range of logical block addresses;

receiving data access requests containing a logical block address and a count of blocks involved in the access request;

determining from the logical block address and count information associated with a storage access request, the identity of zones affected by the storage access request; and

,

setting a bit in the persistent record corresponding to the identified zone before completing the storage access request.