Maintenance of free resource information in a distributed system

• US 6,820,122 B1
• Filed: 01/10/2000
• Issued: 11/16/2004
• Est. Priority Date: 07/11/1997
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Mandler, Benjamin, Haskin, Roger Lee, Wyllie, James Christopher, Schmuck, Frank Bernhard
• Primary Examiner(s): Donaghue, Larry D.
• Application Number:
  US09/480,446
• Time in Patent Office: 1,772 Days
• Field of Search: 709/226, 707/8-10, 707/205
• US Class Current: 709/226
• CPC Class Codes: G06F 16/1858 Parallel file systems, i.e. file systems supporting multiple processors
• CPC Class Codes: G06F 9/52 Program synchronisation; Mutual exclusion, e.g. by means of semaphores
• CPC Class Codes: Y10S 707/99953 Recoverability
• CPC Class Codes: Y10S 707/99956 File allocation

Abstract

A method for managing a shared resource that is allocated among nodes in a distributed computing system includes receiving periodic reports from the nodes regarding their respective allocations of the resource. Responsive to the periodic reports, an approximate amount of the resource that is free for further allocation is determined. Typically, the shared resource is a data storage resource, such as a plurality of disks linked to the nodes by a network, which disks are commonly accessible to multiple ones of the nodes.

Claims

1. A method for managing a shared resource that is allocated among nodes in a distributed computing system, the method comprising:

selecting one of the nodes to serve as a coordinating node;

receiving periodic reports at the coordinating node from the other nodes regarding their respective allocations of the resource, independently of any scanning of the other nodes by the coordinating node; and

responsive to the periodic reports, determining at the coordinating node an approximate amount of the resource that is free for further allocation.

2. A method according to claim 1, wherein the shared resource comprises data storage, and wherein determining the approximate amount of the resource that is free comprises determining an approximate amount of free storage capacity.

3. A method according to claim 2, wherein the data storage comprises a plurality of disks linked to the nodes by a network, which disks are commonly accessible to multiple ones of the nodes.

4. A method according to claim 3, wherein access by the nodes to the disks is controlled using a shared disk file system.

5. A method according to claim 2, wherein receiving the periodic reports comprises receiving information from the nodes based on an allocation map of data storage regions respectively controlled by the nodes.

6. A method according to claim 5, wherein determining the approximate amount of the resource that is free comprises finding, responsive to the periodic reports, one or more regions having sufficient free storage space to meet a storage need of one of the nodes, and comprising advising the node of the one or more regions.

7. A method according to claim 5, wherein determining the approximate amount of the resource that is free comprises determining the number of free storage blocks in the regions respectively controlled by the nodes.

8. A method according to claim 7, wherein determining the approximate amount of the resource that is free comprises determining an exact initial number of the free storage blocks, and then updating the number approximately responsive to the periodic reports.

9. A method according to claim 1, wherein receiving the periodic reports comprises receiving the reports at predetermined intervals.

10. A method according to claim 1, wherein receiving the periodic reports comprises receiving the reports at intervals that vary from one node to another in the system.

11. A method according to claim 10, wherein receiving the reports at the intervals that vary comprises receiving the reports from at least one of the nodes with a frequency responsive to a measure of allocation activity by the at least one of the nodes.

12. A method according to claim 1, wherein receiving the periodic reports comprises receiving a report with a timestamp, and wherein determining the approximate amount of the resource that is free comprises ignoring a report having an outdated timestamp.

13. A method according to claim 1, wherein determining the approximate amount of the resource that is free comprises compiling free resource information from the periodic reports to calculate a total amount of the resource that is free.

14. A method according to claim 1, wherein the coordinating node reports the approximate amount of the resource that is free to the other nodes.

15. Apparatus for managing a shared resource that is allocated among nodes in a distributed computing system, comprising a processor, which is configured to communicate with the nodes in the distributed computing system so as to receive periodic reports from the nodes regarding their respective allocations of the resource independently of any scanning of the other nodes by the processor, and responsive to the periodic reports, to determine an approximate amount of the resource that is free for further allocation.

16. A distributed computing system, comprising:

a plurality of processors, configured to serve as nodes of the system;

a communication network, linking the processors; and

a shared resource, accessible by the nodes via the network,

wherein one of the nodes is selected to act as a coordinating node, and

wherein the other nodes periodically report on their respective allocations of the resource independently of any scanning of the other nodes by the coordinating node, and

wherein the coordinating node is adapted, responsive to the reported allocations, to determine an approximate amount of the resource that is free for further allocation.

17. A system according to claim 16, wherein the shared resource comprises a data storage resource, and wherein the coordinating node determines an approximate amount of free data storage capacity.

18. A system according to claim 17, wherein the data storage resource comprises a plurality of disks linked to the nodes by a network, which disks are commonly accessible to multiple ones of the nodes.

19. A system according to claim 18, wherein access by the nodes to the disks is controlled using a shared disk file system.

20. A system according to claim 17, wherein the coordinating node is adapted to receive information from the nodes based on an allocation map of data storage regions respectively controlled by the nodes.

21. A system according to claim 20, wherein the coordinating node determines, based on the reported allocations, the number of free storage blocks in the region respectively controlled by the nodes.

22. A system according to claim 21, wherein the coordinating node initially determines an exact number of the free storage blocks, and then updates the number approximately responsive to the periodic reports.

23. A system according to claim 16, wherein the coordinating node compiles free resource information from the periodic reports to calculate a total amount of the resource that is free.

24. A system according to claim 16, wherein the coordinating node reports the approximate amount of the resource that is free to the other nodes.

25. A computer software product, comprising a computer-readable medium in which program instructions are stored, which instructions, when read by a computer in a distributed computing system in which a shared resource is allocated among multiple nodes, cause the computer to receive periodic reports from the nodes regarding their respective allocations of the resource independently of any scanning of the other nodes by the computer, and responsive to the periodic reports, to determine an approximate amount of the resource that is free for further allocation.

26. A product according to claim 25, wherein the shared resource comprises a data storage resource, and wherein the program instructions cause the computer to determine an approximate amount of free data storage capacity.

27. A product according to claim 26, wherein the data storage resource comprises a plurality of disks linked to the nodes by a network, which disks are commonly accessible to multiple ones of the nodes.

28. A product according to claim 27, wherein the computer program instructions are run by the computer in conjunction with a shared disk file system, which controls access by the nodes to the disks.

29. A product according to claim 25, wherein the instructions further cause the computer to report the approximate amount of the resource that is free to the nodes.

30. A method for managing a shared resource that is allocated among nodes in a distributed computing system, the method comprising:

receiving periodic reports from the nodes, at intervals that vary from one node to another in the system, regarding their respective allocations of the shared resource; and

responsive to the periodic reports, determining an approximate amount of the shared resource that is free for further allocation.

31. A method according to claim 30, wherein receiving the reports at the intervals that vary comprises receiving the reports from at least one of the nodes with a frequency responsive to a measure of allocation activity by the at least one of the nodes.