Tim Bird at 17:45, 25 January 2011

2011-01-25T17:45:31Z

Tim Bird: Created page with "; Summary: Work on performance utilities for ARM/MIPS ; Proposer: Holger Hans Peter Freyther == Description == Linux has gained great performance utilities in recent years. The..."

2011-01-25T17:43:37Z

Created page with "; Summary: Work on performance utilities for ARM/MIPS ; Proposer: Holger Hans Peter Freyther == Description == Linux has gained great performance utilities in recent years. The..."

New page

; Summary: Work on performance utilities for ARM/MIPS

; Proposer: Holger Hans Peter Freyther

== Description ==
Linux has gained great performance utilities in recent years. These include
OProfile, SystemTap with utrace, perf for the CPU usage. For doing memory
analysis GNU Libc provides the LD_PRELOADable memusagestat, and GNOME has the
memprof utility to look into the allocations.

The story for ARM and MIPS is not as good. In general the tools that require a
backtrace from userspace to be really useful (memprof, oprofile, perf) will
not work well as GCC with -O2 compiles without frame pointers. The oprofile
backtrace support for ARM requires the frame pointers for userspace, MIPS has
no backtrace support for Oprofile at all. Most distributions (Poky/Yocto,
Debian, Ubuntu, Fedora, MeeGo) build their software without frame pointers
making good performance analysis painful as one needs to recompile them.

There are multiple work items here that could be of interest:

* Make utrace work on ARM by implementing user_regset support and provide
integration with Poky/Yocto.

* Enable backtrace generation without the need of frame pointers by looking
at the stack and finding old program counters.

* Provide Oprofile backtrace support on MIPS. In the first version with the
frame-pointer, later with the same approach taken on ARM.

* Allow GNOME memprof to run over a socket and provide a client/server
interface to remotely analyze an application.

* Add ARM backtrace support to GNOME memprof.

* Add MIPS backtrace support to GNOME memprof.

== Scope ==
[utrace]
* The ptrace/user_regset implementation and testing (that ptrace and gdb
still work, specially for VFP, iwmmx and other co-processors) should be
about two weeks. After this the utrace patch should be selectable for ARM.
* There is likely another week for review, redoing the patch for upstream
inclusion.
* The addition of Systemtap/utrace the to yocto kernel and poky buildsystem
is less than a day of work.

[ARM oprofile]
* A heuristic needs to be implemented to detect the previous frames. One
can look at libunwind and gdb to see their criteria for the heuristic and
implement it for the kernel. A working patch ready for upstream should be
creatable within 10 days, the feasibility to see if such a heuristic is
applicable for the kernel can be done with less than a day.

[MIPS oprofile]
* The first part to add basic backtrace support should be done within three
days of work. For the heuristic it might be more difficult (just like in
ARM) to get it right for LE/BE systems, different ABIs.

[memprof]
* Client/Server work should take less than a week.
* MIPS/ARM backtrace support each should not take more than a day each.

== Contractor Candidates ==
I would be interested in working on some/all of these items myself.

== Related work ==
* SystemTap - http://sourceware.org/systemtap/
* Oprofiler - http://oprofile.sf.net
* GNOME memprof - http://git.gnome.org/browse/memprof/

** utrace/ARM - http://osdir.com/ml/linux.kernel.utrace/2008-03/msg00012.html

== Comments ==

[[Category:Project proposals 2011]]

@@ Line 19: / Line 19: @@
 There are multiple work items here that could be of interest:
-* Make utrace work on ARM by implementing user_regset support and provide
+* Make utrace work on ARM by implementing user_regset support and provide integration with Poky/Yocto.
-  integration with Poky/Yocto.
+* Enable backtrace generation without the need of frame pointers by looking at the stack and finding old program counters.
 * Provide Oprofile backtrace support on MIPS. In the first version with the frame-pointer, later with the same approach taken on ARM.
-* Enable backtrace generation without the need of frame pointers by looking
+* Allow GNOME memprof to run over a socket and provide a client/server interface to remotely analyze an application.
-  at the stack and finding old program counters.
-−
 * Provide Oprofile backtrace support on MIPS. In the first version with the
-  frame-pointer, later with the same approach taken on ARM.
-−
 * Allow GNOME memprof to run over a socket and provide a client/server
-  interface to remotely analyze an application.
-−
 * Add ARM backtrace support to GNOME memprof.
 * Add MIPS backtrace support to GNOME memprof.
@@ Line 38: / Line 29: @@
 == Scope ==
 [utrace]
-  * The ptrace/user_regset implementation and testing (that ptrace and gdb
+* The ptrace/user_regset implementation and testing (that ptrace and gdb still work, specially for VFP, iwmmx and other co-processors) should be about two weeks. After this the utrace patch should be selectable for ARM.
-    still work, specially for VFP, iwmmx and other co-processors) should be
+* There is likely another week for review, redoing the patch for upstream inclusion.
-    about two weeks. After this the utrace patch should be selectable for ARM.
+* The addition of Systemtap/utrace the to  yocto kernel and poky buildsystem is less than a day of work.
-  * There is likely another week for review, redoing the patch for upstream
-    inclusion.
-  * The addition of Systemtap/utrace the to  yocto kernel and poky buildsystem
-    is less than a day of work.
-−
 [ARM oprofile]
-   * A heuristic needs to be implemented to detect the previous frames. One
+* A heuristic needs to be implemented to detect the previous frames. One can look at libunwind and gdb to see their criteria for the heuristic and implement it for the kernel. A working patch ready for upstream should be creatable within 10 days, the feasibility to see if such a heuristic is applicable for the kernel can be done with less than a day.
-     can look at libunwind and gdb to see their criteria for the heuristic and
-     implement it for the kernel. A working patch ready for upstream should be
-     creatable within 10 days, the feasibility to see if such a heuristic is
-     applicable for the kernel can be done with less than a day.
 [MIPS oprofile]
-   * The first part to add basic backtrace support should be done within three
+* The first part to add basic backtrace support should be done within three days of work. For the heuristic it might be more difficult (just like in ARM) to get it right for LE/BE systems, different ABIs.
-     days of work. For the heuristic it might be more difficult (just like in
-     ARM) to get it right for LE/BE systems, different ABIs.
 [memprof]
-   * Client/Server work should take less than a week.
+* Client/Server work should take less than a week.
-   * MIPS/ARM backtrace support each should not take more than a day each.
+* MIPS/ARM backtrace support each should not take more than a day each.
-−
 == Contractor Candidates ==
@@ Line 71: / Line 50: @@
 * Oprofiler     - http://oprofile.sf.net
 * GNOME memprof - http://git.gnome.org/browse/memprof/
 * utrace/ARM   - http://osdir.com/ml/linux.kernel.utrace/2008-03/msg00012.html
-** utrace/ARM   - http://osdir.com/ml/linux.kernel.utrace/2008-03/msg00012.html
 == Comments ==
 [[Category:Project proposals 2011]]

Work on performance utilities for ARM/MIPS - Revision history

Tim Bird at 17:45, 25 January 2011

Tim Bird: Created page with "; Summary: Work on performance utilities for ARM/MIPS ; Proposer: Holger Hans Peter Freyther == Description == Linux has gained great performance utilities in recent years. The..."