Profiling partial programs in Linux

Question

I have a program in which significant amount of time is spent loading and saving data. Now I want to know how much time each function is taking in terms of percentage of the total running time. However, I want to exclude the time taken by loading and saving functions from the total time considered by the profiler. Is there any way to do so using gprof or any other popular profiler?

That's what `gprof` is actually good at (provided you have no recursion), because it doesn't sample during I/O. — Mike Dunlavey, Jul 08 '11 at 02:10

score 12 · Accepted Answer · answered Jul 07 '11 at 21:53

12

Similarly you can use

valgrind --tool=callgrind --collect-atstart=no --toggle-collect=<function>

Other options to look at:

--instr-atstart    # to avoid runtime overhead while not profiling

To get instructionlevel stats:

--collect-jumps=yes
--dump-instr=yes

Alternatively you can 'remote control' it on the fly: callgrind_control or annotate your source code (IIRC also with branch predictions stats): callgrind_annotate.

The excellent tool kcachegrind is a marvellous visualization/navigation tool. I can hardly recommend it enough:

answered Jul 07 '11 at 21:53

sehe

374,641
47
450
633

1

+1 Would give more if I could. `valgrind` and `kcachegrind` are an amazing pair! – Michael Mior Jul 07 '11 at 21:54
I appreciate your answer, but I'm in a hurry at the moment. Don't want to learn new profilers at the moment. – MetallicPriest Jul 08 '11 at 10:27

score 5 · Answer 2 · answered Jul 07 '11 at 21:46

5

I would consider using something more modern than gprof, such as OProfile. When generating a report using opreport you can use the --exclude-symbols option to exclude functions you are not interested in.

See the OProfile webpage for more details; however for a quick start guide see the OProfile docs page.

answered Jul 07 '11 at 21:46

DaveR

9,540
3
39
58

But OProfile is a system wide profiler. I don't think it gives very accurate results for individual process profiling. – MetallicPriest Jul 07 '11 at 21:57
Yes, OProfile has the ability to do system-wide profiling; but you can filter it to give data for a single application binary or process (it can tag all data it collects with the process it came from). – DaveR Jul 07 '11 at 22:02
It's pretty accurate in my experience. – static_rtti Jul 07 '11 at 22:29
I'm in a hurry at the moment so it would be good if some simple solution in gprof exists. – MetallicPriest Jul 08 '11 at 10:28

score 2 · Answer 3 · answered Jul 20 '11 at 18:00

Zoom from RotateRight offers a system-wide time profile for Linux. If your code spends a lot of time in i/o, then that time won't show up in a time profile of the CPUs. Alternatively, if you want to account for time spent in i/o, try the "thread time profile".

score 0 · Answer 4 · answered Jul 07 '11 at 21:53

for a simple, basic solution, you might want log data to a csv file.

e.g. Format [functionKey,timeStamp\n]

... then load that up in Excel. Get the deltas, and then include or exclude based on if functions. Nothing fancy. On the upside, you could get some visualisations fairly cheaply.

Profiling partial programs in Linux

4 Answers4