Investigation of performance bottlenecks occurring during execution of software applications

A non-transitory machine-readable medium storing one or more sequences of instructions, wherein execution of said one or more instructions by one or more processors contained in a digital processing system causes the digital processing system to perform the actions of:

• examining data representing a plurality of super-sequences to identify a respective frequency of occurrence of a plurality of sub-sequences within said plurality of super-sequences,
• wherein each super-sequence and sub-sequence represents a corresponding sequence of invocation of modules during execution of a software application, wherein each module in the corresponding sequence is determined to have invoked the next module in the corresponding sequence during execution of said software application, wherein each corresponding sequence contains at least two different modules;
• identifying a set of long sub-sequences based on both of said identified frequencies and respective length of each of said plurality of sub-sequences;
• and
• notifying a user that said set of long sub-sequences for examination of any performance bottlenecks during execution of said software application.

A digital processing system for aiding investigation of performance bottlenecks occurring during execution of software applications, the digital processing system comprising:

• a memory storing executable software instructions;
• one or more processors to execute said software instructions, which cause said digital processing system to perform the actions of:
• examining data representing a plurality of super-sequences to identify a respective frequency of occurrence of a plurality of sub-sequences within said plurality of super-sequences,
• wherein each super-sequence and sub-sequence represents a corresponding sequence of invocation of modules during execution of a software application, wherein each module in the corresponding sequence is determined to have invoked the next module in the corresponding sequence during execution of said software application, wherein each corresponding sequence contains at least two different modules;
• identifying a set of long sub-sequences based on both of said identified frequencies and respective length of each of said plurality of sub-sequences;
• and
• notifying a user that said set of long sub-sequences for examination of any performance bottlenecks during execution of said software application.

A method of aiding investigation of performance bottlenecks occurring during execution of software applications, said method comprising:

• examining data representing a plurality of super-sequences to identify a respective frequency of occurrence of a plurality of sub-sequences within said plurality of super-sequences,
• wherein each super-sequence and sub-sequence represents a corresponding sequence of invocation of modules during execution of a software application, wherein each module in the corresponding sequence is determined to have invoked the next module in the corresponding sequence during execution of said software application, wherein each corresponding sequence contains at least two different modules;
• identifying a set of long sub-sequences based on both of said identified frequencies and respective length of each of said plurality of sub-sequences;
• and
• notifying a user that said set of long sub-sequences for examination of any performance bottlenecks during execution of said software application.