PERFORMING DIAGNOSTIC TESTS IN A DATA CENTER

• US 20140122931A1
• Filed: 08/13/2013
• Published: 05/01/2014
• Est. Priority Date: 10/25/2012
• Status: Abandoned Application

• Current Assignee: Lenovo Enterprise Solutions (Singapore) Pte., Ltd. (Lenovo Group Ltd.)
• Original Assignee: International Business Machines Corporation
• Inventors: DEVALE, SANTOSH, JOSHI, RAJAT Y., KULKARNI, VISHAL, SAINATH, VENKATESH
• Application Number:
  US13/965,749
• Publication Number:
  US 20140122931A1
• Time in Patent Office: Days
• US Class Current: 714/37
• CPC Class Codes: G06F 11/0709 in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
• CPC Class Codes: G06F 11/0784 Routing of error reports, e.g. with a specific transmission path or data flow
• CPC Class Codes: G06F 11/2268 Logging of test results
• CPC Class Codes: G06F 11/2294 by remote test
• CPC Class Codes: G06F 11/34 Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment

Abstract

Diagnostic tests are performed in a data center that includes servers of various types and a management console, where each server provides an error log in a format specific to the type of the server. The management console receives an error log indicating an error produced by a hardware component, parses the error log into an error notification that describes the error and a type of the hardware component, and provides the error notification to other servers. Each of the other servers determines whether the server includes a hardware component of the same type, and if so, performs one or more diagnostic tests on the hardware component and reports results of the diagnostic tests to the management console.

Claims

1. A method of performing diagnostic tests in a data center, the data center comprising a plurality of servers and a management console, the plurality of servers comprising two or more different types of servers, each server configured to report errors to the management console in an error log format specific to the type of the server reporting the error log, the method comprising:

receiving, by the management console from an error generating server, an error log indicating an error produced by a hardware component of the error generating server;

parsing, by the management console, the error log into an error notification, the error notification including information describing the error and a type of the hardware component producing the error in the error generating server; and

providing, by the management console to a plurality of other servers, the error notification.

2. The method of claim 1 further comprising:

for each of the other servers receiving the error notification;

determining, by the other server, whether the server includes a hardware component having the same hardware component type included in the error notification;

if the other server includes a hardware component having the same hardware component type included in the error notification;

performing, by the other server, one or more diagnostic tests on the hardware component of the server; and

reporting, by the other server, results of the diagnostic tests to the management console.

3. The method of claim 2 wherein:

the error log further comprises one or more test cases executed on the error generating server prior to the hardware component of the error generating server producing the error;

parsing the error log into an error notification further comprises inserting, in the error notification, the test cases; and

performing, by the other server, one or more diagnostic tests on the hardware component of the server further comprises performing the diagnostic tests in accordance with the test cases.

4. The method of claim 2 further comprising maintaining, by the management console for each error log, a history of diagnostic test results received from servers of the data center.

5. The method of claim 1 further comprising operating the other server to avoid producing the error associated with the error notification if the other server includes a hardware component having the same hardware component type included in the error notification.

6. The method of claim 5 wherein operating the other server to avoid producing the error associated with the error notification further comprises employing redundancy techniques in the other server to avoid the error.

7. The method of claim 5 wherein the error log indicates information on a pattern of usage of the hardware component causing the error;

wherein the other server is operated to avoid producing the error by avoiding the pattern of usage indicated in the error log.

8. The method of claim 1 wherein receiving an error log further comprises receiving, from a plurality of servers in the data center, an error log, each of the error logs indicating a same type of hardware component producing the error, and the method further comprises:

upon receiving greater than a predefined number of error logs indicating the same type of hardware component, adding, by the management console to a hardware component blacklist, the type of hardware component indicated in the error logs; and

providing the hardware component blacklist to the plurality of servers in the data center.

9. The method of claim 1 wherein:

receiving an error log further comprises receiving, from a plurality of servers in the data center, an error log indicating a same type of hardware component producing the error; and

providing the error notification to the plurality of other servers further comprises providing only one error notification to each of the other servers.

10-20. -20. (canceled)