Jump to content

OProfile: Difference between revisions

From Wikipedia, the free encyclopedia
Content deleted Content added
Dougher (talk | contribs)
m add links, fix wording, fix capitalization
m per WP:HYPHEN, sub-subsection 3, points 3,4,5, replaced: commonly- → commonly using AWB (8564)
Line 34: Line 34:
[[Call graph]]s are supported only on x86 and ARM.
[[Call graph]]s are supported only on x86 and ARM.


In 2012 it was recognized by IBM's engineers as one of two most commonly-used [[Hardware performance counter|performance counter monitor]] profiling tools on Linux; the other was [[perf (Linux)|perf tool]].<ref>A. Zanella, R. Arnold. [http://www.ibm.com/developerworks/linux/library/l-evaluatelinuxonpower/ Evaluate performance for Linux on POWER. Analyze performance using Linux tools], 12 Jun 2012 // IBM DeveloperWorks Technical library</ref>
In 2012 it was recognized by IBM's engineers as one of two most commonly used [[Hardware performance counter|performance counter monitor]] profiling tools on Linux; the other was [[perf (Linux)|perf tool]].<ref>A. Zanella, R. Arnold. [http://www.ibm.com/developerworks/linux/library/l-evaluatelinuxonpower/ Evaluate performance for Linux on POWER. Analyze performance using Linux tools], 12 Jun 2012 // IBM DeveloperWorks Technical library</ref>


== User-space tools ==
== User-space tools ==

Revision as of 17:15, 25 November 2012

Original author(s)John Levon
Initial release2001
Written inC
Operating systemLinux
Platformcross-platform
Typeprofiler
LicenseGPL
Websitehttp://oprofile.sourceforge.net/news/

OProfile - system-wide statistical profiling tool for Linux. Written by John Levon in 2001 for Linux kernel version 2.4 after his M.Sc. project.[1] Consists of kernel module, user-space daemon and several user-space tools.

This tool is capable of profiling entire system or its parts, from interrupt routines or drivers, to user-space processes. It has low overhead.

Most portable mode of oprofile uses system timer to generate sampling interrupts (events). Less portable mode allows hardware performance counters to be used for sampling events generationed on several processor architectures. In Linux 2.2/2.4 only 32-bit x86 and IA64 are supported; in Linux 2.6 there is wider support: x86 (32 and 64 bit), DEC Alpha, MIPS, ARM, sparc64, ppc64, AVR32.

Call graphs are supported only on x86 and ARM.

In 2012 it was recognized by IBM's engineers as one of two most commonly used performance counter monitor profiling tools on Linux; the other was perf tool.[2]

User-space tools

'opcontrol' is used to start and stop the daemon, which collects profiling data. This data is periodically saved to the /var/lib/oprofile/samples directory.

'opreport' shows basic profiling data. 'opannotate' can produce annotated sources or assembly. 'opgprof' converts from oprofile data into gprof-compatible format.[3]

References

  1. ^ Interview: John Levon, 11 Nov 2001 // KernelTrap: "John Levon, the author of OProfile"
  2. ^ A. Zanella, R. Arnold. Evaluate performance for Linux on POWER. Analyze performance using Linux tools, 12 Jun 2012 // IBM DeveloperWorks Technical library
  3. ^ http://oprofile.sourceforge.net/doc/tools-overview.html

See also