Application performance monitoring expert
AssigneeNetworks Associates Technology, Inc.
InventorsMike Moran, Tauras Liubinskas, Jack Goral
Life of this patent
Estimating the term…
Abstract
A system, method, and computer program product are provided for expert application performance analysis. An application is monitored. Performance data is gathered during the monitoring. A set of metrics is generated based on the performance data. A performance of the application is measured from at least one of a client perspective, a server perspective, and a network perspective using the metrics.
Claims19
A method for expert application performance analysis, comprising:
- receiving a set of enabled applications;
- monitoring a network for traffic related to the enabled applications;
- filtering performance data relating to the enabled applications from the network traffic;
- categorizing the performance data into flows;
- prioritizing the flows;
- processing the flows based on the priority;`
- generating a set of metrics in real time based on the processed flows;
- measuring a performance of the applications from a:
- client perspective,
- a server perspective, and
- a network perspective using the metrics;
- and
- performing threshold-based actions based on the metrics;
- wherein the performance data is gathered for transaction-oriented transactions, stream-oriented transactions, and throughput-oriented transactions;
- wherein the metrics generated for the transaction-oriented transactions include a command time per transaction, a response time per transaction, an elapsed time from a start of a command to a start of a response, an elapsed time from a start of a command to an end of a response, and a number of failures;
- wherein the metrics generated for the stream-oriented transactions include a type of service expected during setup, a type of service actually received, a number of transactions, a number of successful transactions, and a ratio for an accumulated time of disrupted service over transaction time;
- wherein the metrics generated for the throughput-oriented transactions include a number of transactions, a number of successful transactions, throughput calculations per transaction, byte rate during the transaction, and response size;
- and
- identifying application subtypes within the application;
- wherein flows of the performance data are prioritized;
- wherein multiple applications are monitored;
- wherein each of the applications is monitored simultaneously when in a flat mode;
- wherein each of the applications is monitored sequentially when in a roving mode;
- wherein the sequential monitoring is based on an allotted amount of time.
A system for expert application performance analysis capable of carrying out a method, the method comprising:
- receiving a set of enabled applications;
- monitoring a network for traffic related to the enabled applications;
- filtering performance data relating to the enabled applications from the network traffic;
- categorizing the performance data into flows;
- prioritizing the flows;
- processing the flows based on the priority;
- generating a set of metrics in real time based on the processed flows;
- measuring a performance of the applications from a:
- client perspective,
- a server perspective, and
- a network perspective using the metrics;
- and
- performing threshold-based actions based on the metrics;
- wherein the performance data is gathered for transaction-oriented transactions, stream-oriented transactions, and throughput-oriented transactions;
- wherein the metrics generated for the transaction-oriented transactions include a command time per transaction, a response time per transaction, an elapsed time from a start of a command to a start of a response, an elapsed time from a start of a command to an end of a response, and a number of failures;
- wherein the metrics generated for the stream-oriented transactions include a type of service expected during setup, a type of service actually received, a number of transactions, a number of successful transactions, and a ratio for an accumulated time of disrupted service over transaction time;
- wherein the metrics generated for the throughput-oriented transactions include a number of transactions, a number of successful transactions, throughput calculations per transaction, byte rate during the transaction, and response size;
- and
- identifying application subtypes within the application;
- wherein flows of the performance data are prioritized;
- wherein multiple applications are monitored;
- wherein each of the applications is monitored simultaneously when in a flat mode;
- wherein each of the applications is monitored sequentially when in a roving mode;
- wherein the sequential monitoring is based on an allotted amount of time.
A computer program product embodied on a computer readable medium for expert application performance analysis capable of carrying out a method, the method comprising:
- receiving a set of enabled applications;
- monitoring a network for traffic related to the enabled applications;
- filtering performance data relating to the enabled applications from the network traffic;
- categorizing the performance data into flows;
- prioritizing the flows;
- processing the flows based on the priority;
- generating a set of metrics in real time based on the processed flows;
- measuring a performance of the applications from a:
- client perspective,
- a server perspective, and
- a network perspective using the metrics;
- and
- performing threshold-based actions based on the metrics;
- wherein the performance data is gathered for transaction-oriented transactions, stream-oriented transactions, and throughput-oriented transactions;
- wherein the metrics generated for the transaction-oriented transactions include a command time per transaction, a response time per transaction, an elapsed time from a start of a command to a start of a response, an elapsed time from a start of a command to an end of a response, and a number of failures;
- wherein the metrics generated for the stream-oriented transactions include a type of service expected during setup, a type of service actually received, a number of transactions, a number of successful transactions, and a ratio for an accumulated time of disrupted service over transaction time;
- wherein the metrics generated for the throughput-oriented transactions include a number of transactions, a number of successful transactions, throughput calculations per transaction, byte rate during the transaction, and response size;
- and
- identifying application subtypes within the application;
- wherein flows of the performance data are prioritized;
- wherein multiple applications are monitored;
- wherein each of the applications is monitored simultaneously when in a flat mode;
- wherein each of the applications is monitored sequentially when in a roving mode;
- wherein the sequential monitoring is based on an allotted amount of time.
Dependencies are inferred from the claim text.