Method and apparatus for mapping and identifying the root causes of performance problems in network-based services

• US 7,779,101 B1
• Filed: 06/27/2006
• Issued: 08/17/2010
• Est. Priority Date: 06/27/2006
• Status: Active Grant

• Current Assignee: Emc IP Holding Company LLC (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Ohsie, David, Zahavi, William, Artzi, Amanuel Ronen, Kuhhirte, William
• Primary Examiner(s): Jacobs; Lashonda T
• Application Number:
  US11/475,774
• Time in Patent Office: 1,512 Days
• Field of Search: 709/223, 709/224, 709/203, 709/217, 709/219
• US Class Current: 709/223
• CPC Class Codes: G06F 11/3006 where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems multiprogramming arrangements G06F9/46; allocation of resources G06F9/50
• 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
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/87 Monitoring of transactions

Abstract

A method, apparatus and computer-program product for mapping and identifying root causes of performance problems in network based services, wherein the service is composed of applications and transactions, is disclosed. The method comprises the steps of establishing a performance objective value, and a threshold value therefrom, for selected ones of the transactions for each of the applications, wherein the aggregate of the performance objective values insures a known service performance, monitoring a measure of performance for each of the selected transactions, generating an indication for each of the performance measures that exceeds a corresponding threshold value and determining the cause of the degradation by correlating the transactions generating the indication with the elements executing the transaction.

Claims

1. A method for determining the cause of a degradation of a service provided over a network composed of a plurality of hardware and software elements, the service including a plurality of applications each including at least one transaction, the transactions being executed by selected ones of the hardware and software elements, the method executing without user interaction, the method comprising:

obtaining a service level objective (SLO) corresponding to a set of service level objective for service on a network;

establishing, in one or more computers, a performance objective value, and a threshold value therefrom, for selected ones of the transactions for each of the applications, wherein the aggregate of the performance objective values insures a known service performance;

wherein exceeding the threshold value indicates a potential error condition associated with the SLO;

monitoring, in the one or more computers, a measure of performance for each of the selected transactions;

generating, in the one or more computers, a computer readable indication for each of the performance measures that exceeds a corresponding threshold value;

associating a respective relationship between each of the transactions and each of the elements executing the transaction; and

determining a match between the generated indications using the respective relationships associated with each of the elements executing the transaction; and

determining, in the one or more computers in response to each generated computer readable indication of a performance measure exceeding a corresponding threshold value, the cause of the degradation by correlating the transactions generating the indication with the elements executing the transaction before the SLO is violated.

2. The method as recited in claim 1, wherein the performance objective value is determined as a function of a time to process an input and an arrival rate of inputs.

3. The method as recited in claim 1, wherein the threshold value is determined based on a desired factor of the performance objective value.

4. The method as recited in claim 1, wherein the associated relationship is selected from the group consisting of:

fixed value and probabilistic value.

5. The method as recited in claim 1, further comprising the step of:

associating each of the selected transactions with at least one of the network elements.

6. An apparatus for determining the cause of a degradation of a service provided over a network composed of a plurality of hardware and software elements, the service including a plurality of applications each including at least one transaction, the transactions being executed by selected ones of the hardware and software elements, the apparatus comprising:

a processor in communication with a memory, the processor executing software instructions, without user interaction, to execute the steps of;

establishing, in one or more computers, a performance objective value, and a threshold value therefrom, for selected ones of the transactions for each of the applications, wherein the aggregate of the performance objective values insures a known service performance;

wherein exceeding the threshold value indicates a potential error condition associated with the SLO;

monitoring, in the one or more computers, a measure of performance for each of the selected transactions;

generating, in the one or more computers, a computer readable indication for each of the performance measures that exceeds a corresponding threshold value;

associating a respective relationship between each of the transactions and each of the elements executing the transaction; and

determining a match between the generated indications using the respective relationships associated with each of the elements executing the transaction; and

determining, in the one or more computers in response to each generated indication of a performance measure exceeding a corresponding threshold value, the cause of the degradation by correlating the transactions generating the indication with the elements executing the transaction before the SLO is violated.

7. The apparatus as recited in claim 6, wherein the performance objective value is determined as a function of a time to process an input and an arrival rate of inputs.

8. The apparatus as recited in claim 6, wherein the threshold value is determined based on a desired factor of the performance objective value.

9. The apparatus as recited in claim 6, wherein the assigned value is selected from the group consisting of:

fixed value and probabilistic value.

10. The apparatus as recited in claim 6, wherein the processor further executing software instruction for executing the step of:

associating each of the transactions with at least one of the network elements.

11. A computer-program product for determining the cause of a degradation of a service provided over a network composed of a plurality of hardware and software elements, the service including a plurality of applications each including at least one transaction, the transactions being executed by selected ones of the hardware and software elements, the computer-program product providing instruction to a processor to execute the steps, without user interaction, of:

establishing, in one or more computers, a performance objective value, and a threshold value therefrom, for selected ones of the transactions for each of the applications, wherein the aggregate of the performance objective values insures a known service performance;

wherein exceeding the threshold value indicates a potential error condition associated with the SLO;

monitoring, in the one or more computers, a measure of performance for each of the selected transactions;

generating, in the one or more computers, a computer readable indication for each of the performance measures that exceeds a corresponding threshold value;

associating a respective relationship between each of the transactions and each of the elements executing the transaction; and

determining a match between the generated indications using the respective relationships associated with each of the elements executing the transaction; and

determining, in the one or more computers in response to each generated computer readable indication of a performance measure exceeding a corresponding threshold value, the cause of the degradation by correlating the transactions generating the computer readable indication with the elements executing the transaction before the SLO is violated.

12. The computer-program product as recited in claim 11, wherein the performance objective value is determined as a function of a time to process an input and an arrival rate of inputs.

13. The computer-program product as recited in claim 11, wherein the threshold value is determined based on a desired factor of the performance objective value.

14. The computer-program product as recited in claim 11, wherein the assigned value is selected from the group consisting of:

fixed value and probabilistic value.

15. The computer-program product as recited in claim 11, providing further instruction to the processor to execute the step of:

associating each of the transactions with at least one of the network elements.