Open Source Linux Profiling Software

The goal of the project is now to develop a user library called libpfm4 to help setup performance events for use with the perf_events Linux kernel interface. The development of the perfmon kernel subsystem, libpfm and pfmon has now stopped.

OProfile is a low-overhead, transparent profiler for Linux, capable of instruction-grain profiling of all processes, shared libraries, the kernel and device drivers, via the hardware performance counters.

cloc (Count Lines Of Code) counts, and computes differences of, comment lines, blank lines, and physical lines of source code in many programming languages. cloc is now being developed at https://github.com/AlDanial/cloc

(Diver is in the process of being moved to GitHub. Please find us at https://github.com/thechiselgroup/Diver. Support requests & messages sent here may never be seen.) Dynamic Interactive Views For Reverse Engineering. Div/er is a set of Eclipse Plugins that aid developers in understanding software. It uses dynamic analysis and reverse engineering to offer views and filters that aid comprehension and discovery.

ebizzy is designed to generate a workload resembling common web application server workloads. It is highly threaded, has a large in-memory working set, and allocates and deallocates memory frequently.

This benchmark suite is intend as a tool for the research community. It consists of a set of open source, real world applications with non-trivial memory loads.

GPerftools (formerly Google Performance Tools) is a collection of a high-performance multi-threaded malloc() implementation, plus some pretty nifty performance analysis tools useful for creating more robust applications. These tools can be especially useful when developing multi-threaded applications in C++ with templates. Among these tools are TCMalloc, a thread-friendly heap-checker, heap-profiler and cpu-profiler.

py-spy is a sampling profiler for Python programs. It lets you visualize what your Python program is spending time on without restarting the program or modifying the code in any way. py-spy is extremely low overhead: it is written in Rust for speed and doesn't run in the same process as the profiled Python program. This means py-spy is safe to use against production Python code. py-spy works from the command line and takes either the PID of the program you want to sample from or the command line of the python program you want to run. py-spy has three subcommands record, top and dump. py-spy supports recording profiles to a file using the record command. Top shows a live view of what functions are taking the most time in your python program, similar to the Unix top command.

KCachegrind visualizes traces generated by profiling, including a tree map and a call graph visualization of the calls happening. It's designed to be fast for very large programs like KDE applications.

Jensor is a light-weight, low-overhead Java Profiler built using Java BCI. Jensor provides innovative analysis modules like JVM Replay, Pattern Analysis and Tagging Engine for technical as well as business analysis based on the same underlying data.

TimeDoctor is a tool to visualize execution traces of tasks, queues, cache behavior, etc. While originally targeting embedded media processors and includes specific features for analyzing audio/video streaming applications it has wider applicability.

Cinemagoer is a Python package useful to retrieve and manage the data of the IMDb movie database about movies, people, characters and companies. Platform-independent, it can retrieve data from both the IMDb's web server and a local copy of the whole db.

SLOCCount is an easy-to-use tool that counts Source Lines of Code (SLOC). It auto-determines the language(s) (inc. C, C++, Ada, Assembly, shell, COBOL, C#, Fortran, Haskell, Java, LISP/Scheme, Perl, PHP, Python, Ruby, SQL). It also estimates cost & time.

Library for dynamic tuning of program parameters for best performance of program.

Java exception extractor. This utility will parse all files (either plain text or bzipped) and tries to search for various exceptions. It then tries to match exceptions against grouping rules (regexps). It is also able to group unrecognised exceptions.

"It's not a tool, which fixes a problem, but the fool using it!" (Jörg Stryk) The M7 bunch of scripts should help the EXPERIENCED Troubleshooter to quickly identify bottlenecks and to develop/implement appropriate solutions. "With great power comes great responsibility" (Uncle Ben)

Warning: Older projects may have to be compiled with -DDEBUG_NEW_CONFIG_HAVE_DEPRECATED Debug_New offers the possibility of debugging memoryleaks, not only (note the "not only"; that's just one of its functions) in a <report-memory-leaks-on-shutdown> kind of way, but implemented using memory-states. - Cross platform + Cross compiler support (only utilizes the preprocessor and template-voodoo-magic for c++) - Supports C and C++ - Supports gcc and g++ - Supports pthread and any posix platform - Multithreading is supported. - Easy to use and install (just include the header and link the source). - Easily debug memory-leaks. - Easily debug dangling pointers. - Easily debug deallocation method correctness. - Easily debug array index errors (when writing past the end). - Easily profile memory usage and track down memory hawks. - Click-And-Goto-Source support for Visual Studio. - Integrated compatibility for new, new[], delete, delete[], malloc, calloc, realloc, free

A very simple implementation of C++ keyword sizeof for Java 5+. Developers can use it to know the real size of objects in memory.

Madmap is a tool to help analyze java heap dumps. New in v1.1 it supports hprof ascii and now binary dumps collected with jmap. It helps find memory leaks by showing the live set and automatically calculating which objects retain the most heap size.

ParTools allows the interactive analysis of a C program execution profile and data dependencies to facilitate the discovery and selection of suitable parallelization candidates in a manual parallelization process. The flow does not assume any specific parallelization technique, thus it can be broadly applied. The original (serial) C source is automatically annotated to trace the execution profile and data dependencies at run-time. The annotated program is then executed using a significant (but small) data set selected by the developer. The data collected is cross-referenced with the original source and can be interactively analyzed graphically to determine the best parallelization candidates and techniques.

Callgraph visualization for the VerySleepy profiler.

SPE is a python IDE with auto indentation&completion,call tips,syntax coloring&highlighting,uml viewer,class explorer,source index,todo list,pycrust shell,file browsers,drag&drop,Blender support.Spe ships with wxGlade,PyChecker and Kiki.

.Net Memory Profiler is a single C# class that builds a tree of specified object's fields, their sub-fields and so on up to primitive types. And in the "Quick Watch" window of the Visual Studio you will be able to see the memory usage by each of those fields. For more details see screenshots.

Developer tool for automatic runtime tracing software errors with various resources. Number of resources virtually unlimited.

FunctionCheck is a profiler for C/C++ programs, based on gcc V4.6.3+. Features are flat profile, cycles detection, call-graph, MIN/MAX time in functions, memory profiling, profiling control at execution...