From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Milian Wolff <milian.wolff@kdab.com>,
David Ahern <dsahern@gmail.com>,
Peter Zijlstra <peterz@infradead.org>,
Yao Jin <yao.jin@linux.intel.com>,
Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 06/15] perf report: Fall-back to function name comparison for -g srcline
Date: Wed, 25 Oct 2017 13:00:04 -0300 [thread overview]
Message-ID: <20171025160013.11136-7-acme@kernel.org> (raw)
In-Reply-To: <20171025160013.11136-1-acme@kernel.org>
From: Milian Wolff <milian.wolff@kdab.com>
When a callchain entry has no srcline available, we ended up comparing
the instruction pointer. I consider this to be not too useful. Rather, I
think we should group the entries by function name, which this patch
adds. For people who want to split the data on the IP boundary, using
`-g address` is the correct choice.
Before:
~~~~~
100.00% 38.86% [.] main
|
|--61.14%--main inlining.cpp:14
| std::norm<double> complex:664
| std::_Norm_helper<true>::_S_do_it<double> complex:654
| std::abs<double> complex:597
| std::__complex_abs complex:589
| |
| |--56.03%--hypot
| | |
| | |--8.45%--__hypot_finite
| | |
| | |--7.62%--__hypot_finite
| | |
| | |--2.29%--__hypot_finite
| | |
| | |--2.24%--__hypot_finite
| | |
| | |--2.06%--__hypot_finite
| | |
| | |--1.81%--__hypot_finite
...
~~~~~
After:
~~~~~
100.00% 38.86% [.] main
|
|--61.14%--main inlining.cpp:14
| std::norm<double> complex:664
| std::_Norm_helper<true>::_S_do_it<double> complex:654
| std::abs<double> complex:597
| std::__complex_abs complex:589
| |
| |--60.29%--hypot
| | |
| | --56.03%--__hypot_finite
| |
| --0.85%--cabs
~~~~~
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/20171009203310.17362-7-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/callchain.c | 20 ++++++++++++--------
1 file changed, 12 insertions(+), 8 deletions(-)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index e7ee794d1e5b..0f2ba493a7a3 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -645,11 +645,9 @@ enum match_result {
MATCH_GT,
};
-static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
- struct callchain_list *cnode)
+static enum match_result match_chain_strings(const char *left,
+ const char *right)
{
- const char *left = cnode->srcline;
- const char *right = node->srcline;
enum match_result ret = MATCH_EQ;
int cmp;
@@ -659,10 +657,8 @@ static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
cmp = 1;
else if (left && !right)
cmp = -1;
- else if (cnode->ip == node->ip)
- cmp = 0;
else
- cmp = (cnode->ip < node->ip) ? -1 : 1;
+ return MATCH_ERROR;
if (cmp != 0)
ret = cmp < 0 ? MATCH_LT : MATCH_GT;
@@ -679,10 +675,18 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
struct dso *right_dso = NULL;
if (callchain_param.key == CCKEY_SRCLINE) {
- enum match_result match = match_chain_srcline(node, cnode);
+ enum match_result match = match_chain_strings(cnode->srcline,
+ node->srcline);
+
+ /* if no srcline is available, fallback to symbol name */
+ if (match == MATCH_ERROR && cnode->ms.sym && node->sym)
+ match = match_chain_strings(cnode->ms.sym->name,
+ node->sym->name);
if (match != MATCH_ERROR)
return match;
+
+ /* otherwise fall-back to IP-based comparison below */
}
if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
--
2.13.6
next prev parent reply other threads:[~2017-10-25 16:00 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-25 15:59 [GIT PULL 00/15] perf/core inlining improvements Arnaldo Carvalho de Melo
2017-10-25 15:59 ` [PATCH 01/15] perf report: Remove code to handle inline frames from browsers Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 02/15] perf callchain: Store srcline in callchain_cursor_node Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 03/15] perf callchain: Refactor inline_list to operate on symbols Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 04/15] perf callchain: Refactor inline_list to store srcline string directly Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 05/15] perf callchain: Create real callchain entries for inlined frames Arnaldo Carvalho de Melo
2017-10-25 16:00 ` Arnaldo Carvalho de Melo [this message]
2017-10-25 16:00 ` [PATCH 07/15] perf callchain: Mark inlined frames in output by " (inlined)" suffix Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 08/15] perf script: Mark inlined frames and do not print DSO for them Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 09/15] perf callchain: Compare symbol name for inlined frames when matching Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 10/15] perf report: Compare symbol name for inlined frames when sorting Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 11/15] perf report: Properly handle branch count in match_chain() Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 12/15] perf report: Cache failed lookups of inlined frames Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 13/15] perf report: Cache srclines for callchain nodes Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 14/15] perf report: Use srcline from callchain for hist entries Arnaldo Carvalho de Melo
2017-10-25 16:00 ` [PATCH 15/15] perf util: Enable handling of inlined frames by default Arnaldo Carvalho de Melo
2017-10-25 17:10 ` [GIT PULL 00/15] perf/core inlining improvements Ingo Molnar
2017-10-26 9:03 ` Milian Wolff
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171025160013.11136-7-acme@kernel.org \
--to=acme@kernel.org \
--cc=acme@redhat.com \
--cc=dsahern@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=milian.wolff@kdab.com \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=yao.jin@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).