From: Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com>
To: Jin Yao <yao.jin@linux.intel.com>
Cc: jolsa@kernel.org, peterz@infradead.org, mingo@redhat.com,
alexander.shishkin@linux.intel.com, Linux-kernel@vger.kernel.org,
ak@linux.intel.com, kan.liang@intel.com, yao.jin@intel.com
Subject: Re: [PATCH v6 5/7] perf diff: Link same basic blocks among different data
Date: Tue, 2 Jul 2019 13:20:00 -0300 [thread overview]
Message-ID: <20190702162000.GL15462@kernel.org> (raw)
In-Reply-To: <20190702161739.GK15462@kernel.org>
Em Tue, Jul 02, 2019 at 01:17:39PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Fri, Jun 28, 2019 at 05:23:02PM +0800, Jin Yao escreveu:
> > The target is to compare the performance difference (cycles
> > diff) for the same basic blocks in different data files.
> >
> > The same basic block means same function, same start address
> > and same end address. This patch finds the same basic blocks
> > from different data files and link them together and resort
> > by the cycles diff.
> >
> > v3:
> > ---
> > The block stuffs are maintained by new structure 'block_hist',
> > so this patch is update accordingly.
> >
> > v2:
> > ---
> > Since now the basic block hists is changed to per symbol,
> > the patch only links the basic block hists for the same
> > symbol in different data files.
> >
> > Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
> > ---
> > tools/perf/builtin-diff.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 90 insertions(+)
> >
> > diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
> > index 83b8c0f..823f162 100644
> > --- a/tools/perf/builtin-diff.c
> > +++ b/tools/perf/builtin-diff.c
> > @@ -641,6 +641,85 @@ static int process_block_per_sym(struct hist_entry *he)
> > return 0;
> > }
> >
> > +static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
> > +{
> > + struct block_info *bi_a = a->block_info;
> > + struct block_info *bi_b = b->block_info;
> > + int cmp;
> > +
> > + if (!bi_a->sym || !bi_b->sym)
> > + return -1;
> > +
> > + if (bi_a->sym->name && bi_b->sym->name) {
> > + cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
> > + if ((!cmp) && (bi_a->start == bi_b->start) &&
> > + (bi_a->end == bi_b->end)) {
> > + return 0;
> > + }
>
>
> builtin-diff.c:658:17: error: address of array 'bi_a->sym->name' will always evaluate to 'true' [-Werror,-Wpointer-bool-conversion]
> if (bi_a->sym->name && bi_b->sym->name) {
> ~~~~~~~~~~~^~~~ ~~
> builtin-diff.c:658:36: error: address of array 'bi_b->sym->name' will always evaluate to 'true' [-Werror,-Wpointer-bool-conversion]
> if (bi_a->sym->name && bi_b->sym->name) {
>
> Because:
>
> struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
> {
> size_t namelen = strlen(name) + 1;
> struct symbol *sym = calloc(1, (symbol_conf.priv_size +
> sizeof(*sym) + namelen));
>
>
> So it will be at least a strlen(sym->name) == 0, i.e. we can use it
> without checking anything.
>
> I'm chanign it to do the cmp straight away
i.e. I added this on top of this patch:
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 823f162b0060..fafb7b3f58fb 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -650,13 +650,10 @@ static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
if (!bi_a->sym || !bi_b->sym)
return -1;
- if (bi_a->sym->name && bi_b->sym->name) {
- cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
- if ((!cmp) && (bi_a->start == bi_b->start) &&
- (bi_a->end == bi_b->end)) {
- return 0;
- }
- }
+ cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
+
+ if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
+ return 0;
return -1;
}
next prev parent reply other threads:[~2019-07-02 16:20 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-28 9:22 [PATCH v6 0/7] perf diff: diff cycles at basic block level Jin Yao
2019-06-28 8:02 ` Jiri Olsa
2019-07-02 15:51 ` Arnaldo Carvalho de Melo
2019-06-28 9:22 ` [PATCH v6 1/7] perf util: Create block_info structure Jin Yao
2019-07-03 14:32 ` [tip:perf/core] perf symbol: " tip-bot for Jin Yao
2019-06-28 9:22 ` [PATCH v6 2/7] perf util: Add block_info in hist_entry Jin Yao
2019-07-03 14:33 ` [tip:perf/core] perf hists: " tip-bot for Jin Yao
2019-06-28 9:23 ` [PATCH v6 3/7] perf diff: Check if all data files with branch stacks Jin Yao
2019-07-03 14:34 ` [tip:perf/core] " tip-bot for Jin Yao
2019-06-28 9:23 ` [PATCH v6 4/7] perf diff: Use hists to manage basic blocks per symbol Jin Yao
2019-07-03 14:35 ` [tip:perf/core] " tip-bot for Jin Yao
2019-06-28 9:23 ` [PATCH v6 5/7] perf diff: Link same basic blocks among different data Jin Yao
2019-07-02 16:17 ` Arnaldo Carvalho de Melo
2019-07-02 16:20 ` Arnaldo Carvalho de Melo [this message]
2019-07-03 1:07 ` Jin, Yao
2019-07-03 14:35 ` [tip:perf/core] " tip-bot for Jin Yao
2019-06-28 9:23 ` [PATCH v6 6/7] perf diff: Print the basic block cycles diff Jin Yao
2019-07-03 14:36 ` [tip:perf/core] " tip-bot for Jin Yao
2019-06-28 9:23 ` [PATCH v6 7/7] perf diff: Documentation -c cycles option Jin Yao
2019-07-03 14:37 ` [tip:perf/core] " tip-bot for Jin Yao
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=20190702162000.GL15462@kernel.org \
--to=arnaldo.melo@gmail.com \
--cc=Linux-kernel@vger.kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@intel.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=yao.jin@intel.com \
--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