This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
[Bug testsuite/18577] on rhel7, listing_mode_sanity.exp always gets a failure when doing 'stap -l **'
- From: "dsmith at redhat dot com" <sourceware-bugzilla at sourceware dot org>
- To: systemtap at sourceware dot org
- Date: Wed, 24 Jun 2015 17:17:59 +0000
- Subject: [Bug testsuite/18577] on rhel7, listing_mode_sanity.exp always gets a failure when doing 'stap -l **'
- Auto-submitted: auto-generated
- References: <bug-18577-6586 at http dot sourceware dot org/bugzilla/>
https://sourceware.org/bugzilla/show_bug.cgi?id=18577
--- Comment #2 from David Smith <dsmith at redhat dot com> ---
So, I compiled everything with '-pg' to enable profiling with grpof. Running
"stap -l '**'" took ~2.5 hours with profiling enabled. Here's the top of the
gprof output:
====
Flat profile:
Each sample counts as 0.01 seconds.
% cumulative self self total
time seconds seconds calls s/call s/call name
49.45 250.48 250.48 120081098 0.00 0.00 levenshtein(std::string
const&, std::string const&)
22.85 366.22 115.74 21077 0.01 0.02
levenshtein_suggest(std::string const&, std::set<std::string,
std::less<std::string>, std::allocator<std::string> > const&, unsigned int,
unsigned int)
7.19 402.66 36.44 1 36.44 43.34
semantic_pass_conditions(systemtap_session&)
====
It looks like we need to look at how we are using the levenshtein functions
(which suggest alternatives), since between the 2 functions they took ~72% of
the execution time.
--
You are receiving this mail because:
You are the assignee for the bug.