This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: pfaults.stp
- From: William Cohen <wcohen at redhat dot com>
- To: "Paddie O'Brien" <paddieobrien at gmail dot com>
- Cc: systemtap at sourceware dot org
- Date: Thu, 05 Sep 2013 11:11:15 -0400
- Subject: Re: pfaults.stp
- Authentication-results: sourceware.org; auth=none
- References: <CAOK12DY46FmPB8mWWpR25TbEw+bVZJBRo9-YHmFQYdoZ29Gxrg at mail dot gmail dot com>
On 09/04/2013 05:14 PM, Paddie O'Brien wrote:
> Hi,
>
> I'm running a simple program and attempting to use examples/memory/pfaults.stp
> to see the page faults it generates. The program runs but pfaults.stp
> stays quiet
> every time (even the first). I know I'm missing something stupid but...
>
> Shouldn't I see something?!
>
> Thanks,
> Paddie
>
Hi Paddie,
On Fedora 19 running on an x86_64 machine I just ran the example and I got the expected output like:
$ stap pfaults.stp
...
18974551:2368:0x7f6e429bf000:w:minor:11
18974610:2368:0x7f6e429c0000:w:minor:1
18974671:2368:0x7f6e429c1000:w:minor:1
18974743:2368:0x7f6e429c2000:w:minor:11
18974801:2368:0x7f6e429c3000:w:minor:1
18974858:2368:0x7f6e429c4000:w:minor:0
18974920:2368:0x7f6e429c5000:w:minor:1
You might also do "stap -v pfaults.stp" to see if is just taking a while to get the instrumentation started. On a machine that everything has been running a while you might not get much output. Did you try to start a new program to trigger some page faults? You can check that you are getting some page faults doing something like:
$ /usr/bin/time calc
/usr/bin/time: cannot run calc: No such file or directory
0.00user 0.00system 0:00.00elapsed 0%CPU (0avgtext+0avgdata 248maxresident)k
0inputs+0outputs (0major+49minor)pagefaults 0swaps
Could you provide a bit more information about the environment you are running things in as listed on https://sourceware.org/systemtap/wiki/HowToReportBugs?
-Will