Storing parity information for data recovery

• US 7,516,354 B2
• Filed: 08/25/2004
• Issued: 04/07/2009
• Est. Priority Date: 08/25/2004
• Status: Active Grant

• Current Assignee: Western Digital Technologies Incorporated (Western Digital Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Nguyen, Lu, Cherian, Neena A.
• Primary Examiner(s): Baderman; Scott T.
• Assistant Examiner(s): SCHELL, JOSEPH O
• Application Number:
  US10/925,825
• Publication Number:
  US 20060047896A1
• Time in Patent Office: 1,686 Days
• Field of Search: 714/6, 711/114
• US Class Current: 714/6.24
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity

Abstract

Provided is a method in which data is received at the first storage unit. A first information unit, a second information unit, and a third information unit are generated, wherein the first information unit, the second information unit, and the third information unit each include a portion of the received data and computed parity data. The first information unit is stored in the first storage unit at the first site. The second information unit is distributed to the second storage unit at the second site for storage. The third information unit is distributed to the third storage unit at the third site for storage.

Claims

1. A method, comprising:

receiving data at a first storage unit;

generating a first information unit, a second information unit, and a third information unit, wherein the first information unit, the second information unit, and the third information unit each include a portion of the received data and computed parity data;

storing the first information unit in the first storage unit at a first site;

distributing the second information unit to a second storage unit at a second site for storage; and

distributing the third information unit to a third storage unit at a third site for storage, wherein a majority of the parity data is stored in the first storage unit.

2. The method of claim 1, wherein the first storage unit is coupled to a host that sends Input/Output requests to the first storage unit.

3. The method of claim 1, further comprising:

in response to a data loss at the first site, recovering the received data from the second information unit and the third information unit.

4. The method of claim 3, wherein a sum of a size of the first information unit, the second information unit, and the third information unit is less than two times the received data size.

5. The method of claim 4, wherein the first site, the second site, and the third site are separated from each other by a distance of over ten miles, and wherein the first information unit, the second information unit, and the third information unit are stored in different storage disk systems.

6. The method of claim 1, wherein the data is received at the first storage unit from a host, and wherein multi-pathing hardware is used to connect the host to the first, second, and third storage units.

7. The method of claim 1, wherein distributing the second and third information units is via write operations from the first storage unit to the second and third storage units.