From: Frederic Weisbecker <fweisbec@gmail.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@elte.hu>, LKML <linux-kernel@vger.kernel.org>,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Mike Galbraith <efault@gmx.de>, Paul Mackerras <paulus@samba.org>
Subject: [PATCH 6/3] perfcounter: Substract the buffer size field from the event record size
Date: Mon, 10 Aug 2009 16:11:32 +0200 [thread overview]
Message-ID: <20090810141129.GA5124@nowhere> (raw)
In-Reply-To: <1249909585.17467.135.camel@twins>
On Mon, Aug 10, 2009 at 03:06:25PM +0200, Peter Zijlstra wrote:
> > I'll do the alignment right in the end, just before inserting the entry
> > in the output. That will be more easy. I'll zeroe the rest in the same time.
>
> OK.
Actually I shouldn't, the alignment should be computed early, taking the
field size into account.
That's not a problem though, I've just substracted the u32 field once
I found the final aligned size.
See below:
---
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Mon, 10 Aug 2009 15:56:46 +0200
Subject: [PATCH 6/3] perfcounter: Substract the buffer size field from the event record size
We compute the perf raw sample size by aligning the raw ftrace event
size plus the buffer size field itself. We do that instead of aligning
only the perf raw sample size, so that we might economize some in some
cases.
But this buffer size field is not stored in the perf raw sample, we
must then substract its size from the buffer once we computed the
alignment unless we may get a useless u32 field in the buffer.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
include/trace/ftrace.h | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletions(-)
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 4dc1a60..f98ff56 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -639,7 +639,12 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
* pc = preempt_count();
*
* __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- * __entry_size = __data_size + sizeof(*entry);
+ *
+ * // Below we want to get the aligned size by taking into account
+ * // the u32 field that will later store the buffer size
+ * __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ * sizeof(u64));
+ * __entry_size -= sizeof(u32);
*
* do {
* char raw_data[__entry_size]; <- allocate our sample in the stack
@@ -689,6 +694,7 @@ static void ftrace_profile_##call(proto) \
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
sizeof(u64)); \
+ __entry_size -= sizeof(u32); \
\
do { \
char raw_data[__entry_size]; \
--
1.6.2.3
next prev parent reply other threads:[~2009-08-10 14:11 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-08 2:26 [PATCH 1/4] perf tools: callchain: Warn only once in empty node detection Frederic Weisbecker
2009-08-08 2:26 ` [PATCH 1/3] perfcounter: Initialize tracepoint record before any use Frederic Weisbecker
2009-08-08 2:30 ` Frederic Weisbecker
2009-08-10 9:27 ` [PATCH 4/3] perf_counter: Correct PERF_SAMPLE_RAW output Peter Zijlstra
2009-08-10 9:36 ` [tip:perfcounters/urgent] " tip-bot for Peter Zijlstra
2009-08-10 9:48 ` [PATCH 4/3] " Frederic Weisbecker
2009-08-10 12:57 ` Frederic Weisbecker
2009-08-10 13:06 ` Peter Zijlstra
2009-08-10 14:11 ` Frederic Weisbecker [this message]
2009-08-10 14:13 ` [PATCH 6/3] perfcounter: Substract the buffer size field from the event record size Peter Zijlstra
2009-08-10 14:21 ` [tip:perfcounters/urgent] perf_counter: Subtract " tip-bot for Frederic Weisbecker
2009-08-10 9:27 ` [PATCH 5/3] perf_counter: Require CAP_SYS_ADMIN for raw tracepoint data Peter Zijlstra
2009-08-10 9:36 ` [tip:perfcounters/urgent] " tip-bot for Peter Zijlstra
2009-08-08 2:26 ` [PATCH 2/4] perf tools: callchain: Ignore empty callchains Frederic Weisbecker
2009-08-08 2:26 ` [PATCH 2/3] perfcounter: Generalize the tracepoint sampling to generic sampling Frederic Weisbecker
2009-08-08 11:52 ` [tip:perfcounters/core] perf_counter: Fix tracepoint sampling to be part of " tip-bot for Frederic Weisbecker
2009-08-09 11:10 ` tip-bot for Frederic Weisbecker
2009-08-08 2:26 ` [PATCH 3/4] perf tools: callchain: Default display callchain from report if recorded with -g Frederic Weisbecker
2009-08-08 2:26 ` [PATCH 3/3] perfcounter: Align ftrace events raw samples to 8 bytes Frederic Weisbecker
2009-08-08 11:52 ` [tip:perfcounters/core] perf_counter: Fix ftrace events raw samples to be aligned " tip-bot for Frederic Weisbecker
2009-08-10 7:13 ` [PATCH 3/3] perfcounter: Align ftrace events raw samples " Peter Zijlstra
2009-08-10 7:32 ` Frederic Weisbecker
2009-08-10 14:38 ` [PATCH 7/3] perfcounter: Zeroe dead bytes from ftrace raw samples size alignment Frederic Weisbecker
2009-08-10 18:01 ` [tip:perfcounters/urgent] perf_counter: Zero " tip-bot for Frederic Weisbecker
2009-08-08 2:26 ` [PATCH 4/4] perf tools: callchain: Display amount of ignored chains in fractal mode Frederic Weisbecker
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=20090810141129.GA5124@nowhere \
--to=fweisbec@gmail.com \
--cc=acme@redhat.com \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
/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