System and method to efficiently identify bad components in a multi-node system utilizing multiple node topologies
The exemplary embodiments of the present invention provide a method for efficiently identifying the bad component(s) in a multi-node system. The method includes assigning a unique ID to each of a plurality of nodes on the multi-node system, generating test statistics from a test on a plurality of nodes, and comparing the test statistics for the plurality of nodes against a first topology to generate a first number of clusters of bad nodes. The method further includes comparing the test statistics for the plurality of nodes against a second topology to generate a second number of clusters of bad nodes, and identifying the bad nodes by comparing the cluster sizes to a topology threshold.
1. A method for efficiently identifying the bad component(s) in a multi-node system embodied in a computer program product for execution on an instruction processing system, comprising a tangible storage medium readable by the instruction processing system and storing instructions for execution by the instruction processing system for performing the method comprising:
assigning a unique ID to each of a plurality of nodes on the multi-node system;
generating test statistics from a test on a plurality of nodes;
comparing the test statistics for the plurality of nodes against a first topology to generate a first number of clusters of bad nodes;
comparing the test statistics for the plurality of nodes against a second topology to generate a second number of clusters of bad nodes; and
identifying the bad nodes by comparing the cluster sizes to a topology threshold.
2. The method in claim 1 , wherein the comparing the test statistics for the plurality of nodes further comprises utilizing a clustering algorithm to identify a cluster of bad nodes.
3. The method of claim 2 , wherein the clustering algorithm is a k-means algorithm.
4. The method in claim 1 , wherein the generating test statistics further comprises utilizing data integrity to identify a cluster of bad nodes.
5. The method of claim 1 , wherein the generating test statistics further comprises utilizing execution time to identify a cluster of bad nodes.
6. The method of claim 1 , wherein the generating test statistics further comprises utilizing temperature to identify a cluster of bad nodes.
7. The method of claim 1 , wherein the first topology is based upon physical connections and the second topology is based upon logical connections.
8. A system for efficiently identifying the bad component(s) in a multi-node system, comprising:
a tangible storage medium readable by an instruction processing system and storing instructions for execution by the instruction processing system;
an assigning module that assigns a unique ID to each of a plurality of nodes on the multi-node system;
a test module that generates test statistics from a test on a plurality of nodes;
a first topology analysis module that compares the test statistics for the plurality of nodes against a first topology to generate a first number of clusters of bad nodes;
a second topology analysis module that compares the test statistics for the plurality of nodes against a second topology to generate a second number of clusters of bad nodes; and
a bad node identification module that identifies the bad nodes by comparing the cluster sizes to a topology threshold.
9. The system of claim 8 , wherein the bad node identification module further comprises utilizing a clustering algorithm to identify a cluster of bad nodes.
10. The system of claim 9 , wherein the clustering algorithm is a k-means algorithm.
11. The system of claim 8 , wherein the test module further comprises utilizing data integrity to identify a cluster of bad nodes.
12. The system of claim 8 , wherein the test module further comprises utilizing execution time to identify a cluster of bad nodes.
13. The system of claim 8 , wherein the test module further comprises utilizing temperature to identify a cluster of bad nodes.
14. The system of claim 8 , wherein the first topology is based upon physical connections and the second topology is based upon logical connections.
15. A computer program product for efficiently identifying the bad component(s) in a multi-node system, the computer program product comprising:
a tangible non-transitory storage medium readable by a computer system and storing instructions for execution by the computer system for performing a method comprising:
assigning a unique ID to each of a plurality of nodes on the multi-node system;
generating test statistics from a test on a plurality of nodes;
comparing the test statistics for the plurality of nodes against a first topology to generate a first number of clusters of bad nodes;
comparing the test statistics for the plurality of nodes against a second topology to generate a second number of clusters of bad nodes; and
identifying the bad nodes by comparing the cluster sizes to a topology threshold.
16. The computer program product of claim 15 , further comprising:
utilizing a clustering algorithm to identify a cluster of bad nodes.
17. The computer program product of claim 16 , wherein the clustering algorithm is a k-means algorithm.
18. The computer program product of claim 15 , further comprising:
utilizing data integrity to identify a cluster of bad nodes.
19. The computer program product of claim 15 , further comprising:
utilizing execution time to identify a cluster of bad nodes.
20. The computer program product of claim 15 , wherein the first topology is based upon physical connections and the second topology is based upon logical connections.