mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Wangnan (F)" <wangnan0@huawei.com>
To: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>,
	<linux-kernel@vger.kernel.org>, <kan.liang@intel.com>,
	<acme@kernel.org>, <kernel-team@lge.com>
Subject: Re: [PATCH 1/2] perf mmap: Fix perf backward recording
Date: Wed, 1 Nov 2017 20:56:32 +0800	[thread overview]
Message-ID: <4eeabf43-4de0-467c-04b0-85217040b036@huawei.com> (raw)
In-Reply-To: <20171101123957.GA27215@krava>



On 2017/11/1 20:39, Jiri Olsa wrote:
> On Wed, Nov 01, 2017 at 08:10:49PM +0800, Wangnan (F) wrote:
>
> SNIP
>
>>>>> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
>>>>> index c6c891e154a6..27ebe355e794 100644
>>>>> --- a/tools/perf/util/evlist.c
>>>>> +++ b/tools/perf/util/evlist.c
>>>>> @@ -838,6 +838,11 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
>>>>>                    if (*output == -1) {
>>>>>                            *output = fd;
>>>>> +                       if (evsel->attr.write_backward)
>>>>> +                               mp->prot = PROT_READ;
>>>>> +                       else
>>>>> +                               mp->prot = PROT_READ | PROT_WRITE;
>>>>> +
>>>> If evlist->overwrite is true, PROT_WRITE should be unset even if
>>>> write_backward is
>>>> not set. If you want to delay the setting of mp->prot, you need to consider
>>>> both evlist->overwrite and evsel->attr.write_backward.
>>> I thought evsel->attr.write_backward should be set when
>>> evlist->overwrite is set.  Do you mean following case?
>>>
>>>     perf record --overwrite -e 'cycles/no-overwrite/'
>>>
>> No. evlist->overwrite is unrelated to '--overwrite'. This is why I
>> said the concept of 'overwrite' and 'backward' is ambiguous.
>>
>> perf record never sets 'evlist->overwrite'. What '--overwrite' actually
>> does is setting write_backward. Some testcases needs overwrite evlist.
> did not check deeply, but so why can't we do the below?
>
> jirka
>
>
> ---
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index f4d9fc54b382..4643c487bd29 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -300,7 +300,7 @@ static int record__mmap_evlist(struct record *rec,
>   	struct record_opts *opts = &rec->opts;
>   	char msg[512];
>   
> -	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
> +	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, opts->overwrite,
>   				 opts->auxtrace_mmap_pages,
>   				 opts->auxtrace_snapshot_mode) < 0) {

perf_evlist__mmap_ex's overwrite argument is used to control evlist->mmap.

Consider Namhyung's example:

   perf record --overwrite -e 'cycles/no-overwrite/'

In this case both evlist->mmap and evlist->backward_mmap would be set to overwrite.
'cycles' will be put into evlist->mmap, so it will be set to overwrite incorrectly.

Patch 2/2 clarifies these concepts. What we want is the flight recorder mode,
not only a read only ring buffer. Even flight recorder mode is selected, we can
still have a normal ring buffer which keep output data.

Thank you.

  reply	other threads:[~2017-11-01 12:57 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-01  5:53 [PATCH 0/2] perf record: Fix --overwrite and clarify concepts Wang Nan
2017-11-01  5:53 ` [PATCH 1/2] perf mmap: Fix perf backward recording Wang Nan
2017-11-01  9:49   ` Namhyung Kim
2017-11-01 10:32     ` Wangnan (F)
2017-11-01 12:00       ` Namhyung Kim
2017-11-01 12:10         ` Wangnan (F)
2017-11-01 12:39           ` Jiri Olsa
2017-11-01 12:56             ` Wangnan (F) [this message]
2017-11-02 15:12               ` Jiri Olsa
2017-11-01 13:57           ` Liang, Kan
2017-11-01 16:12             ` Wangnan (F)
2017-11-01 16:22               ` Liang, Kan
2017-11-02  5:34                 ` Namhyung Kim
2017-11-02 13:25                   ` Liang, Kan
2017-11-02 14:59                     ` Jiri Olsa
2017-11-01  5:53 ` [PATCH 2/2] perf record: Replace 'overwrite' by 'flightrecorder' for better naming Wang Nan
2017-11-01 10:03   ` Namhyung Kim
2017-11-01 10:17     ` Wangnan (F)
2017-11-01 12:03       ` Namhyung Kim
2017-11-01 13:26   ` Liang, Kan
2017-11-01 14:05     ` Wangnan (F)
2017-11-01 14:22       ` Liang, Kan
2017-11-01 14:44         ` Wangnan (F)
2017-11-01 15:04           ` Liang, Kan
2017-11-01 16:00             ` Wangnan (F)
2017-11-01 16:13               ` Liang, Kan

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=4eeabf43-4de0-467c-04b0-85217040b036@huawei.com \
    --to=wangnan0@huawei.com \
    --cc=acme@kernel.org \
    --cc=jolsa@redhat.com \
    --cc=kan.liang@intel.com \
    --cc=kernel-team@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=namhyung@kernel.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

all inboxes | Powered by JetHome®