qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Alex Bennée" <alex.bennee@linaro.org>
To: Richard Henderson <rth@twiddle.net>
Cc: qemu-devel@nongnu.org, Anthony Liguori <aliguori@amazon.com>,
	batuzovk@ispras.ru
Subject: Re: [Qemu-devel] [PATCH] tcg: add ability to dump /tmp/perf-<pid>.map files
Date: Mon, 14 Jul 2014 14:53:30 +0100	[thread overview]
Message-ID: <8761j0xcxt.fsf@linaro.org> (raw)
In-Reply-To: <53C01667.4010003@twiddle.net>


Richard Henderson writes:

> On 07/11/2014 09:43 AM, Alex Bennée wrote:
>> +/* if I could put this in a header easily.... */
>> +void tb_enable_perfmap(void);
>
> How about next to tb_flush in exec/exec-all.h?

Including exec/exec-all.h trips up some sort of include prevention
magic:

  CC    vl.o
In file included from vl.c:82:0:
/home/alex/lsrc/qemu/qemu.git/include/exec/exec-all.h:75:28: error: attempt to use poisoned "CPUArchState"
 void gen_intermediate_code(CPUArchState *env, struct TranslationBlock *tb);
                            ^
>> +
>> +void tb_enable_perfmap(void) {
>
> Watch the { placement.
>
>> +    gchar * map_file = g_strdup_printf("/tmp/perf-%d.map", getpid());
>> +    tb_perfmap = fopen(map_file, "w");
>> +    g_free(map_file);
>> +}
>
> And speaking of tb_flush, ought there be some marker in the perf file to reset
> things?  Otherwise you're just going to wind up with garbage if you let the
> guest run long enough.
>
> Of course, I have no idea how to link the flush with a timestamp that allows
> one to selectively choose which section of the perf file one uses...

The perf JIT format isn't really that smart so currently I'm not sure
how it would deal with it. Currently I suspect the best solution is
"don't do that then" :-/

>
>
> r~

-- 
Alex Bennée

  reply	other threads:[~2014-07-14 13:54 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-11 16:43 [Qemu-devel] [PATCH] tcg: add ability to dump /tmp/perf-<pid>.map files Alex Bennée
2014-07-11 16:52 ` Richard Henderson
2014-07-14 13:53   ` Alex Bennée [this message]
  -- strict thread matches above, loose matches on Subject: below --
2014-07-15 11:34 Alex Bennée

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=8761j0xcxt.fsf@linaro.org \
    --to=alex.bennee@linaro.org \
    --cc=aliguori@amazon.com \
    --cc=batuzovk@ispras.ru \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    /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).