Performance Co-Pilot (PCP) is a framework and set of services for supporting system-level performance monitoring and performance management. It provides a unifying abstraction for all of the interesting performance data in a system, and allows client applications to easily retrieve and process any subset of that data using a single API. A client-server architecture allows multiple clients to monitor the same host, and a single client to monitor multiple hosts. Archive logging and replay are integrated so that a client application can use the same API to process real-time data from a host or historical data from an archive.
TAU (Tuning and Analysis Utilities) is a set of tools for analyzing the performance of C, C++, Fortran and Java programs. It collects much more information than is available through prof or gprof, the standard Unix utilities, including per-process, per-thread, and per-host information, inclusive and exclusive function times, profiling groups that allow you to organize data collection, access to hardware counters on some systems, per-class and per-instance information, the ability to separate data for each template instantiation, start/stop timers for profiling arbitrary sections of code, and support for collection of statistics on user-defined events.
coNCePTuaL is a domain-specific programming language for rapidly generating programs that measure the performance and/or test the correctness of networks and network protocol layers. A few lines of coNCePTuaL code can produce programs that would take significantly more effort to write in a conventional programming language.
PootyPedia is a tool to track which hardware is in use by a software project. PootyPedia consists of a client program which finds the hardware and prepares it for reporting and a server program which tracks all the reports and keeps them organized in a database and generates reports from them.
FunkLoad is a functional and load Web tester whose main use cases are functional testing of Web projects (and thus regression testing as well), performance testing, load testing (such as volume testing or longevity testing), and stress testing. It can also be used to write Web agents to script any Web repetitive task.
Python Tracer lets you see your Python program's execution as a tree of function invocations, each tree node exposing the real time and CPU time (user/sys) of that call. The project consists of two main components: a Python tracer that can run your Python programs (much like "cProfile" and friends), and a GTK+ based GUI that can show the trace results. It uses a tiny auxiliary library (graphfile) to allow append-only writing and reading static DAGs directly from a file without reading it whole into memory at any stage.
namebench finds the best DNS servers to use for your machine, benchmarks them, and outputs pretty graphs to tell you why they are optimal. It supports multiple data sources such as Alexa, your browser history, or tcpdump replays in order to generate the most relevant and individualized recommendation.