Failure recovery in a parallel-processing database system

• US 8,676,843 B2
• Filed: 11/14/2002
• Issued: 03/18/2014
• Est. Priority Date: 11/14/2002
• Status: Active Grant

• Current Assignee: LexisNexis Risk Data Management, Inc. (RELX PLC)
• Original Assignee: LexisNexis Risk Data Management, Inc. (RELX PLC)
• Inventors: Bayliss, David, Chapman, Richard, Smith, Jake, Poulsen, Ole, Halliday, Gavin, Hicks, Nigel
• Primary Examiner(s): Kim, Paul
• Application Number:
  US10/293,475
• Publication Number:
  US 20040098371A1
• Time in Patent Office: 4,142 Days
• Field of Search: 707/202, 707/782, 707/781, 707/769, 714/10
• US Class Current: 707/782
• CPC Class Codes: G06F 11/203 using migration
• CPC Class Codes: G06F 11/2035 without idle spare hardware
• CPC Class Codes: G06F 11/2038 with a single idle spare processing component
• CPC Class Codes: G06F 16/2471 Distributed queries
• CPC Class Codes: G06F 2201/80 Database-specific techniques

Abstract

A system and method for failure recovery in a multiple processing node system are described herein. Each node can be adapted to store a backup copy of its database portion and/or results to disk storage or memory of at least one other node. In the event of a failure of a node, the replacement node can be adapted to transfer or copy the backup copy of the database portion of the failed node from the failed node'"'"'s neighbors to the replacement node'"'"'s disk storage or memory in between database operations. Before the transfer or copy of the backup copy is completed, the replacement node can be adapted to perform database operations in part on the portion of the backup copy the replacement node has already received and in part on the backup copy stored at the neighboring node(s).

Claims

1. A method for recovering from a failure of a processing node, the method comprising:

storing, prior to failure of a first processing node of a plurality of interconnected processing nodes, a database portion of the first processing node on a second processing node of the plurality of processing nodes;

replacing the first processing node with a third processing node of the plurality of processing nodes when the first processing node fails;

copying the database portion of the first processing node from the second processing node to the third processing node between database operations performed by the second processing node and the third processing node;

performing, by the third processing node, database operations using the database portion of the first processing node stored on the second processing node during the copying of the database portion of the first processing node from the second processing node to the third processing node; and

performing, by the third processing node, database operations using the database portion of the first processing node stored at the third processing node when the copying of the database portion from the second processing node to the third processing node is completed.

2. The method of claim 1, further comprising storing a database portion of a fourth node of the plurality of processing nodes on the third processing node.

3. The method of claim 2, further comprising storing a database portion of the second processing node on a fifth processing node of the plurality of processing nodes.

4. The method of claim 1, further comprising storing a database portion of the second processing node on a fourth processing node of the plurality of processing nodes.

5. The method of claim 1, further comprising:

storing, prior to failure of the first processing node, results of at least one database operation performed by the first processing node on the database portion at the first processing node on the second processing node; and

copying, after failure of the first processing node, the results from the second processing node to the third processing node between database operations performed by the second processing node and the third processing node.

6. The method of claim 1, further comprising:

storing, prior to failure of the first processing node, the database portion on a fourth processing node;

replacing the first node with a third processing node of the plurality of processing nodes when the first processing node fails;

copying, after failure of the first processing node and the second processing node, the database portion from the fourth processing node to the third processing node between database operations performed by the third processing node and the fourth processing node;

performing, by the third processing node, database operations on the database portion stored on the fourth processing node until the copying of the database portion from the fourth processing node to the third processing node is completed; and

performing, by the third processing node, database operations on the database portion stored at the third processing node when the copying of the database portion from the fourth processing node to the third processing node is completed.

7. The method of claim 6, further comprising:

storing, prior to failure of the first processing node, results of at least one database operation performed by the first processing node on the database portion at the first processing node on both the second processing node and a fourth processing node; and

copying, after failure of the first processing node and second processing node, the results stored on the fourth processing node to the third processing node between database operations performed by the third processing node and the fourth processing node.

8. A database management system for failover recovery, the system comprising:

a first processing node storing a first database portion and configured to perform at least one database operation on the first database portion;

a second processing node operably connected to the first processing node and storing a second database portion and configured to perform the at least one database operation on the second database portion, and wherein prior to a failure of the first processing node, the first database portion is stored on the second processing node; and

a third processing node operably connected to the second processing node and configured to;

perform at least one database operation using the first database portion after the first processing node fails; and

copy the first database portion from the second node between database operations performed by the second processing node and the third processing node;

wherein the third processing node performs database operations using the first database portion stored on the second processing node until the copying of the first database portion from the second processing node to the third processing node is completed; and

wherein the third processing node performs database operations using the first database portion stored at the third processing node when the copying of the first database portion from the second processing node to the third processing node is completed.

9. The system of claim 8, further comprising a fourth processing node operably connected to the first processing node, and wherein the first processing node is further adapted to store the first database portion on the fourth processing node.

10. The system of claim 8, further comprising a fourth processing node operably connected to the second processing node, and wherein the second processing node is further adapted to store the second database portion on the fourth processing node.

11. The system of claim 8, wherein:

the first processing node is further adapted to store, prior to failure of the first processing node, results of at least one database operation using the first database portion on the second processing node; and

the third processing node is further adapted to copy, after failure of the first processing node, the results from the second processing node between database operations performed by the second processing node and the third processing node.

12. The system of claim 8, wherein each processing node includes:

a processor;

memory; and

a first disk storage for storing a database portion used by the processing node to perform at least one database operation.

13. The system of claim 12, wherein each processing node includes a second disk storage for storing a copy of a database portion of another processing node.

14. The system of claim 8, wherein an alert is generated upon the occurrence of a failover condition.