Methods and systems for migrating network resources to improve network utilization

• US 10,212,099 B2
• Filed: 09/11/2015
• Issued: 02/19/2019
• Est. Priority Date: 01/29/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Krishnamurthy, Rajaram B.
• Primary Examiner(s): Sison, June Y
• Assistant Examiner(s): Cooney, Adam A
• Application Number:
  US14/852,390
• Publication Number:
  US 20160006671A1
• Time in Patent Office: 1,257 Days
• Field of Search: 709226
• CPC Class Codes: G06F 9/5088 involving task migration
• CPC Class Codes: G06F 9/526 Mutual exclusion algorithms
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 47/823 Prediction of resource usage
• CPC Class Codes: H04L 47/83 based on usage prediction

Abstract

A method and system are disclosed for migrating network resources to improve network utilization, for use in a multi-node network wherein nodes of the network share network resources. The method comprises the steps of identifying a group of nodes that share one of the network resources, and identifying one of the nodes satisfying a specified condition based on at least one defined access latency metric. The shared resource is moved to the identified one of the nodes to reduce overall access latency to access the shared resource by said group of nodes. One embodiment of the invention provides a method and system to synchronize tasks in a distributed computation using network attached devices (NADs). A second embodiment of the invention provides a method and system to reduce lock latency and network traffic by migrating lock managers to coupling facility locations closest to nodes seeking resource access.

Claims

1. A method of migrating a lock manager in a computer network to improve network utilization, for use in a computer network comprising a first group of computers located in a first datacenter, and a second group of computers located in a second datacenter, and wherein the first group of computers access resources owned by the second group of computers, and a lock manager manages access to the resources, the method comprising:

for each computer of a plurality of computers of the first group of computers, determining an associated aggregate access latency time, based on at least one defined access latency metric, indicating an aggregate latency time for requests from all the computers of the first group of computers, in aggregate, to reach the each computer of the plurality of computers;

identifying one of the computers from the first group of computers based on the aggregate access latency times; and

moving the lock manager from the second data center to a location in the first data center based on the identified one of the computers from the first group of computers.

2. The method according to claim 1, wherein:

the first group of computers are connected together by a first coupling facility;

the second group of computers are connected together by a second coupling facility; and

the moving step includes the step of moving the lock manager from the second coupling facility to the first coupling facility.

3. The method according to claim 2, wherein the first group of computers access the lock manager on the second coupling facility for access to the resources of the second group of computers in the second datacenter, and the lock manager is moved from the second datacenter to the first datacenter if the only accesses of the lock manager are by the first group of computers.

4. The method according to claim 1, wherein:

the determining includes, for each computer of the plurality of computers, determining an amount of time, based on the at least one defined access latency metric, needed for the requests from each computer of the first group of computers to reach the each computer of the plurality of computers, and summing the amounts of time for the requests from all of the computers of the first group of computers to obtain an associated total access latency time for the each computer of the plurality of computers; and

the identifying includes identifying the one of the computers based on the associated total access latency times obtained for the plurality of computers.

5. The method according to claim 4, wherein the identifying includes identifying the one of the computers having a minimum of the associated total access latency times.

6. The method according to claim 1, wherein:

the aggregate access latency time is based on the distance between each computer of the first group of computers and each computer of the plurality of computers, as measured according to a defined distance metric.

7. The method according to claim 1, further comprising:

after moving the lock manager to the location in the first datacenter, directing requests from the first group of computers in the first datacenter for the lock manager to the identified one of the computers to reduce overall aggregate access latency time for the requests from the first group of computers to reach the lock manager.

8. The method according to claim 1, wherein the moving step includes:

moving the lock manager from a home computer to the identified one of the computers; and

the home computer forwarding requests for the lock manager to the identified one of the computers.

9. The method according to claim 8, wherein the moving the lock manager from the home computer includes:

the home computer keeping track of a number of accesses to the lock manager;

when the lock manager is accessed a given number of times, the home computer moving the lock manager to the identified one of the computers; and

providing the home computer with a resource mapping table to identify a resource id, a current resource owner, a resource manager location and a list of requesting computers.

10. The method according to claim 8, wherein the moving the lock manager from the home computer includes using the home computer to move the lock manager to the identified one of the computers.

11. A system for migrating a lock manager in a computer network to improve network utilization, for use in a computer network comprising a first group of computers located in a first datacenter, and a second group of computers located in a second datacenter, and wherein the first group of computers access resources owned by the second group of computers, and a lock manager manages access to the resources, the system comprising:

a memory for storing data; and

one or more processor units connected to the memory for receiving data from and transmitting, data to the memory, the one or more processing units configured for (i) for each of a plurality of computers of the first group of computers, determining an associated aggregate access latency time, based on at least one defined access latency metric, indicating an aggregate latency time for requests from the computers of the first group of computers, in aggregate, to reach the each computer of the plurality of computers, (ii) identifying one of the computers from the first group of computers based on the aggregate access latency times, and (iii) moving the lock manager from the second data center to a location in the first data center based on the identified one of the computers from the first group of computers.

12. The system according to claim 11, wherein:

the first group of computers are connected together by a first coupling facility;

the second group of computers are connected together by a second coupling facility; and

the moving step includes the step of moving the lock manager from the second coupling facility to the first coupling facility.

13. The system according to claim 12, wherein the first group of computers access the lock manager on the second coupling facility for access to the resources of the second group of computers in the second datacenter, and the lock manager is moved from the second datacenter to the first datacenter if the only accesses of the lock manager are by the first group of computers.

14. The system according to claim 11, wherein:

the determining includes, for each computer of the plurality of computers, determining an amount of time, based on the at least one defined access latency metric, needed for the requests from each computer of the first group of computers to reach the each computer of the plurality of computers, and summing the amounts of time for the requests from all of the computers of the first group of computers to obtain an associated total access latency time for the each computer of the plurality of computers; and

the identifying includes identifying the one of the computers based on the associated total access latency times obtained for the plurality of computers.

15. The system according to claim 14, wherein the identifying includes identifying the one of the computers having the minimum of the associated total access latency times.

16. An article of manufacture comprising a program storage device readable by computer, tangibly embodying a program of instructions executable by the computer to perform a method for migrating a lock manager to improve network utilization, for use in a multi-node network comprising a first group of computers located in a first datacenter and a second group of computers located in a second datacenter, and wherein computers of the network share network resources and a lock manager manages access to the resources, the method comprising:

for each of a plurality of computers of the first group of computers, determining an associated aggregate access latency time, based on at least one defined access latency metric, indicating an aggregate latency time for requests from all the computers of the first group of computers, in aggregate, to reach the each computer of the plurality of computers;

identifying one of the computers from the first group of computers based on the aggregate access latency times; and

moving the lock manager from the second data center to a location in the first data center based on the identified one of the computers from the first group of computers.

17. The article of manufacture according to claim 16, wherein:

the first group of computers are connected together by a first coupling facility;

the second group of computers are connected together by a second coupling facility; and

the moving step includes the step of moving the lock manager from the second coupling facility to the first coupling facility.

18. The article of manufacture according to claim 17, wherein the first group of computers access the lock manager on the second coupling facility for access to the resources of the second group of computers in the second datacenter, and the lock manager is moved from the second datacenter to the first datacenter if the only accesses of the lock manager are by the first group of computers.

19. The article of manufacture according to claim 16, wherein:

the determining includes, for each computer of the plurality of computers, determining an amount of time, based on the at least one defined access latency metric, needed for the requests from each of the computers of said first group of computers to reach the each of the computers of the plurality of computers, and summing said amounts of time for the requests from all of the computers of the first group of computers to obtain an associated total access latency time for the each computer of the plurality of computers; and

the identifying includes identifying the one of the computers based on the associated total access latency times obtained for the plurality of computers.

20. The article of manufacture according to claim 19, wherein the identifying includes identifying the one of the computers having a minimum of the associated total access latency times.