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.

(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.

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

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.

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.

An implementation of the Open Group's Application Response Measurement (ARM) Version 4 standard. The ARM standard describes a means of breaking an application down into it's constituent transactions, and measuring response time across multiple tiers.

COMPAS J2EE is a non-intrusive performance instrumentation and monitoring toolkit for J2EE. It uses adaptive monitoring to automatically adjust the target coverage. COMPAS is completely portable across J2EE application servers and OSs.

Open|SpeedShop is an open source multi platform Linux performance tool which is targeted to support performance analysis of applications running on both single node and large scale IA64, IA32, EM64T, AMD64, PPC, Blue Gene, ARM and Cray platforms.

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.

LightProfiler – application for performance analysis of the Oracle databases. It generates detailed resource profile for extended SQL trace files (10046 event), containing information about consuming of response time (by events, by cursors, etc.), data files usage, error analysis (SQL, PL/SQL) and much more. Also it contain tools for additional processing of trace files (extract session data, splitting files) and for management of database's sessions (disconnecting, tracing, monitor parameters, blocking locks, events and etc.)

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.

Lack of Progress Bar (Lopb) is an Eclipse plugin that tracks how long developers wait for file check-ins/outs, code compilation, publishing apps to a web server, and other IDE background jobs to complete. Read more at http://lopb.org

bcov is a code coverage tool similar to gcov. Unlike gcov, it does not require recompiling the project for coverage. Coverage is determined by using temporary breakpoints, which causes minimal overhead. gcov produces a lcov style coverge report.

The fastest malloc we've seen; works particularly well with threads and STL. Also: thread-friendly heap-checker, heap-profiler, and cpu-profiler.

Glassbox is an automated troubleshooting and monitoring agent for Java apps that diagnoses common problems with one-click. Drop in a .war file from http://www.glassbox.com and find out what's wrong with your existing web apps, without any code chang

JRat is the Java Runtime Analysis Toolkit. Its purpose is to enable developers to better understand the runtime behavior of their Java programs. The term behavior includes, but is not limited to performance profiling.

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

FProfiler is a Java Profiler using log4j. Its very fast because it inserts the needed instructions into the byte-code of the class. It can be used to find "Hotspots" in Java programs, libs and servlet environments simply every Java class.

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...

Stand alone Java application used simulate a memory leak in order to generate profile signatures. The application has the ability to generate system (CPU) load in order to observe profile signature changes.

The Performance Inspector package contains a suite of performance analysis tools for Linux, Windows, AIX, and zOS with an emphasis on Java profiling.

Java agent which recognizes "flows" as unique sequences of instrumented method calls. Runtime statistics are collected for the dynamically detected flows during snapshot interval. The instrumented methods may be set either manually via UI or automatically in drill down mode. The automatic drill down mode effectively instruments classes generated by frameworks like Hibernate, Rhino, etc.