linux-trace-devel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: "Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>
Cc: linux-trace-devel@vger.kernel.org
Subject: [PATCH] trace-cmd: Adjust host_trace_info structure to be better packed
Date: Thu, 5 Mar 2020 12:46:55 -0500	[thread overview]
Message-ID: <20200305124655.0738a585@gandalf.local.home> (raw)
In-Reply-To: <20200304091220.30936-8-tz.stoyanov@gmail.com>


From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>

Move the unsigned long long trace_id out from between the boolean
sync_enable and the int ts_samples_count, which removes the gap in the
structure, making the structure size drop from 32 bytes to 24, as displayed
by pahole.

Before:

struct host_trace_info {
        _Bool                      sync_enable;          /*     0     1 */

        /* XXX 7 bytes hole, try to pack */

        long long unsigned int     trace_id;             /*     8     8 */
        int                        ts_samples_count;     /*    16     4 */

        /* XXX 4 bytes hole, try to pack */

        struct ts_offset_sample * ts_samples;            /*    24     8 */

        /* size: 32, cachelines: 1, members: 4 */
        /* sum members: 21, holes: 2, sum holes: 11 */
        /* last cacheline: 32 bytes */
};

After:

struct host_trace_info {
        long long unsigned int     trace_id;             /*     0     8 */
        _Bool                      sync_enable;          /*     8     1 */

        /* XXX 3 bytes hole, try to pack */

        int                        ts_samples_count;     /*    12     4 */
        struct ts_offset_sample * ts_samples;            /*    16     8 */

        /* size: 24, cachelines: 1, members: 4 */
        /* sum members: 21, holes: 1, sum holes: 3 */
        /* last cacheline: 24 bytes */
};

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---

This is why I'm picky on ordering of fields in data structures.
I'm sure there's many more places we can update here.

-- Steve


 lib/trace-cmd/trace-input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 2f0274d9..a1241f4b 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -83,8 +83,8 @@ struct ts_offset_sample {
 };
 
 struct host_trace_info {
-	bool			sync_enable;
 	unsigned long long	trace_id;
+	bool			sync_enable;
 	int			ts_samples_count;
 	struct ts_offset_sample	*ts_samples;
 };
-- 
2.20.1


  reply	other threads:[~2020-03-05 17:46 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-04  9:12 [PATCH v22 00/13] Timestamp synchronization of host - guest tracing session Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 01/13] trace-cmd: Find and store pids of tasks, which run virtual CPUs of given VM Tzvetomir Stoyanov (VMware)
2020-03-04 21:09   ` Steven Rostedt
2020-03-04  9:12 ` [PATCH v22 02/13] trace-cmd: Implement new API tracecmd_add_option_v() Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 03/13] trace-cmd: Add new API to generate a unique ID of the tracing session Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 04/13] trace-cmd: Store the session tracing ID in the trace.dat file Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 05/13] trace-cmd: Add definitions of htonll() and ntohll() Tzvetomir Stoyanov (VMware)
2020-03-05 15:48   ` [PATCH] trace-cmd: Make functions in trace-write-local.h inline Steven Rostedt
2020-03-04  9:12 ` [PATCH v22 06/13] trace-cmd: Exchange tracing IDs between host and guest Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 07/13] trace-cmd: Implement new option in trace.dat file: TRACECMD_OPTION_TIME_SHIFT Tzvetomir Stoyanov (VMware)
2020-03-05 17:46   ` Steven Rostedt [this message]
2020-03-04  9:12 ` [PATCH v22 08/13] trace-cmd: Add guest information in host's trace.dat file Tzvetomir Stoyanov (VMware)
2020-03-05 18:44   ` [PATCH] trace-cmd: Make name and cpu_pid into const pointers to tracecmd_get_guest_cpumap() Steven Rostedt
2020-03-04  9:12 ` [PATCH v22 09/13] trace-cmd: Add host trace clock as guest trace argument Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 10/13] trace-cmd: Refactor few trace-cmd internal functions Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 11/13] trace-cmd: Basic infrastructure for host - guest timestamp synchronization Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 12/13] trace-cmd: [POC] PTP-like algorithm " Tzvetomir Stoyanov (VMware)
2020-03-04  9:12 ` [PATCH v22 13/13] trace-cmd: Debug scripts for " Tzvetomir Stoyanov (VMware)

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=20200305124655.0738a585@gandalf.local.home \
    --to=rostedt@goodmis.org \
    --cc=linux-trace-devel@vger.kernel.org \
    --cc=tz.stoyanov@gmail.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).