Network resiliency through memory health monitoring and proactive management

• US 9,825,827 B2
• Filed: 08/07/2014
• Issued: 11/21/2017
• Est. Priority Date: 08/07/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Andrade Costa, Carlos H., Cher, Chen-Yong, Park, Yoonho, Rosenburg, Bryan S., Ryu, Kyung D.
• Primary Examiner(s): CHANG, LI WU
• Application Number:
  US14/453,879
• Publication Number:
  US 20160042280A1
• Time in Patent Office: 1,202 Days
• Field of Search: None
• CPC Class Codes: H04L 41/0663 Performing the actions predefined by failover planning, e.g. switching to standby network elements
• CPC Class Codes: H04L 41/0668 by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 43/0817 by checking functioning

Abstract

A method for managing a network queue memory includes receiving sensor information about the network queue memory, predicting a memory failure in the network queue memory based on the sensor information, and outputting a notification through a plurality of nodes forming a network and using the network queue memory, the notification configuring communications between the nodes.

Claims

1. A method for managing a network queue memory comprising:

receiving sensor information about the network queue memory;

predicting a memory failure in the network queue memory based on the sensor information;

outputting a notification to a plurality of nodes forming a network, each of the nodes including a block of the network queue memory, the notification configuring routing of communications between the nodes;

outputting the notification to a network client executing software using the plurality of nodes and the network queue memory; and

causing, in response to the notification, the network client to configure a process layout defining a mapping of a plurality of program variables generated by the executing software of the network client to the nodes including the blocks of the network queue memory.

2. The method of claim 1, wherein the sensor information includes information about errors corrected in by one or more of the nodes including the blocks of the network queue memory.

3. The method of claim 1, wherein the sensor information includes information about errors along one or more links connecting the nodes forming the network.

4. The method of claim 1, wherein the sensor information includes an assessment of a degradation process affecting the network queue memory of one or more of the plurality of nodes.

5. The method of claim 1, further comprising collecting, by the plurality of nodes, the sensor information, wherein one or more of the plurality of nodes comprises a sensor.

6. The method of claim 1, wherein the notification configures the routing of the communications between the nodes to route at least one message to by-pass one or more of a node using a faulty link and the faulty link.

7. The method of claim 1, further comprising:

performing, by the network client, at least one maintenance task in response to the notification.

8. The method of claim 7, wherein the at least one maintenance task includes wear leveling among the nodes and among one or more links connecting the nodes and forming the network by routing the communications between the nodes using the one or more links.

9. A computer program product for managing a network queue memory, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

receiving sensor information about the network queue memory;

predicting a memory failure in the network queue memory based on the sensor information;

outputting a notification to a plurality of nodes forming a network, each of the nodes including a block of the network queue memory, the notification configuring routing of communications between the nodes;

outputting the notification to a network client executing software using the plurality of nodes and the network queue memory; and

causing, in response to the notification, the network client to configure a process layout defining a mapping of a plurality of program variables generated by the executing software of the network client to the nodes including the blocks of the network queue memory.

10. The computer program product of claim 9, wherein the sensor information includes information about errors corrected in by one or more of the nodes including the blocks of the network queue memory.

11. The computer program product of claim 9, wherein the sensor information includes information about errors along one or more links connecting the nodes forming the network.

12. The computer program product of claim 9, wherein the sensor information includes an assessment of a degradation process affecting the network queue memory of one or more of the plurality of nodes.

13. The computer program product of claim 9, further comprising collecting, by the plurality of nodes, the sensor information, wherein one or more of the plurality of nodes comprises a sensor.

14. The computer program product of claim 9, wherein the notification configures the routing of the communications between the nodes to route at least one message to by-pass one or more of a node using a faulty link and the faulty link.

15. The computer program product of claim 9, wherein the network client performs at least one maintenance task in response to the notification, wherein the at least one maintenance task includes wear leveling among the nodes and among one or more links connecting the nodes and forming the network by routing the communications between the nodes.

16. A system comprising:

a plurality of nodes, each of the nodes including a block of network queue memory, the plurality of nodes forming a network; and

a monitor connected to the network and configured to received sensor information from the plurality of nodes and predict one of a memory failure and a link failure in the network queue memory, wherein at least one link connects the plurality of nodes, and determine message routes among the plurality of nodes based on one of a predicted memory failure and a predicted link failure in the network queue memory,

wherein the monitor outputs a notification to a network client executing software using the plurality of nodes and the network queue memory and causes, in response to the notification, the network client to configure a process layout defining a mapping of a plurality of program variables generated by the executing software of the network client to the nodes including the blocks of the network queue memory.