Abstract: Systems and methods are provided that determine the actual amount of time a processor consumes in executing a code portion. The actual execution time of a code portion may be accurately determined by taking into consideration context switches and/or overhead time corresponding to the code portion. Determining the actual execution time of a code portion may include recording context switches and time values that occur during the execution of the code portion. This information along with overhead measurements may be used to generate the actual execution time of a code portion, as will be described in more detail below. For example, the switched-out intervals resulting from the context switches and the overhead time associated with the time measurements may be subtracted from the elapsed time to produce the actual execution time of a code portion.

Abstract: A system for displaying performance test information for software. The system includes a graphical user interface that displays information in a format to allow ready identification of performance problems and their causes. The interface includes a timeline view depicting activity levels during the execution of a program under test. Events during a sub-range of times during the program execution may be displayed with information revealing interactions of threads making up the program. Additional information may be displayed in a further display fields, including textual information. Much of the displayed information is represented graphically, allowing a performance engineer to quickly identify areas of the program to investigate further.

Abstract: Analyzing usage patterns of resources by various execution contexts (such as threads) may be difficult due to the volume of information that may be involved. A profiling technique may focus on the detection of resource requests that result in a resource conflict, e.g., a request for access to a resource that is exclusively in use by another resource. The profiling may then involve identifying the user action associated with the execution context that caused the resource conflict (e.g., via a stack walk) and the resource utilized, measuring the delay in the fulfillment of the request, and recording the information in a resource conflict log. The resource requests that are captured and recorded in this manner may be constrained to the information that is helpful in identifying performance bottlenecks and usage patterns, which may lead to redesigned applications of greater performance while interfacing with execution contexts, and vice versa.