public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: kan.liang@intel.com
Cc: linux-kernel@vger.kernel.org, ying.huang@intel.com, andi@firstfloor.org
Subject: Re: [PATCH 1/1] perf,tools: add time out to force stop endless mmap processing
Date: Thu, 11 Jun 2015 11:06:14 -0300	[thread overview]
Message-ID: <20150611140614.GC2696@kernel.org> (raw)
In-Reply-To: <1433922364-22580-1-git-send-email-kan.liang@intel.com>

Em Wed, Jun 10, 2015 at 03:46:04AM -0400, kan.liang@intel.com escreveu:
> perf top reads all threads' /proc/xxx/maps. If there is any threads
> which generating a keeping growing huge /proc/xxx/maps, perf will do
> infinite loop in perf_event__synthesize_mmap_events.
> This patch fixes this issue by adding a time out to force stop this kind
> of endless mmap processing.
> 
> Reported-by: Huang, Ying <ying.huang@intel.com>
> Signed-off-by: Kan Liang <kan.liang@intel.com>

So we will silently stop processing those events?

We will make progress, no doubt, but I think the user needs to be warned
about this situation, so that later on when/if samples for those maps
appear and don't get resolved at least we will know that this is the
reason.

- Arnaldo

> ---
>  tools/perf/util/event.c | 7 ++++++-
>  1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
> index 793b150..0df7f2a9 100644
> --- a/tools/perf/util/event.c
> +++ b/tools/perf/util/event.c
> @@ -213,6 +213,8 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
>  	return 0;
>  }
>  
> +#define MMAP_TIMEOUT	(50 * 1000000ULL)
> +
>  int perf_event__synthesize_mmap_events(struct perf_tool *tool,
>  				       union perf_event *event,
>  				       pid_t pid, pid_t tgid,
> @@ -222,6 +224,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
>  {
>  	char filename[PATH_MAX];
>  	FILE *fp;
> +	unsigned long long t;
>  	int rc = 0;
>  
>  	if (machine__is_default_guest(machine))
> @@ -240,6 +243,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
>  	}
>  
>  	event->header.type = PERF_RECORD_MMAP2;
> +	t = rdclock();
>  
>  	while (1) {
>  		char bf[BUFSIZ];
> @@ -250,7 +254,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
>  		size_t size;
>  		ssize_t n;
>  
> -		if (fgets(bf, sizeof(bf), fp) == NULL)
> +		if ((fgets(bf, sizeof(bf), fp) == NULL) ||
> +		    ((rdclock() - t) > MMAP_TIMEOUT))
>  			break;
>  
>  		/* ensure null termination since stack will be reused. */
> -- 
> 1.8.3.1

  reply	other threads:[~2015-06-11 14:06 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-10  7:46 [PATCH 1/1] perf,tools: add time out to force stop endless mmap processing kan.liang
2015-06-11 14:06 ` Arnaldo Carvalho de Melo [this message]
2015-06-11 14:27   ` Liang, Kan
2015-06-11 15:37     ` Arnaldo Carvalho de Melo
2015-06-11 15:21   ` David Ahern
2015-06-11 18:47     ` Andi Kleen
2015-06-12  0:33       ` David Ahern
2015-06-12 14:42         ` Liang, Kan
2015-06-12 15:41           ` David Ahern
2015-06-12 17:05             ` Liang, Kan
2015-06-12 17:28               ` David Ahern
2015-06-12 18:19                 ` Liang, Kan
2015-06-12 19:29                   ` David Ahern
2015-06-12 19:45                     ` Andi Kleen
2015-06-12 20:39                     ` Liang, Kan
2015-06-12 20:52                       ` David Ahern
2015-06-12 22:41                         ` Liang, Kan
2015-06-13  4:07                           ` David Ahern
2015-06-13 14:59                             ` Liang, Kan
2015-06-13  4:24                       ` David Ahern
2015-06-13 15:06                         ` Liang, Kan
2015-06-16 15:11                         ` Arnaldo Carvalho de Melo
2015-06-16 15:44                           ` Andi Kleen
2015-06-16 15:57                           ` David Ahern
2015-06-16 16:42                           ` Liang, Kan
2015-06-16 18:08                             ` Arnaldo Carvalho de Melo

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=20150611140614.GC2696@kernel.org \
    --to=acme@kernel.org \
    --cc=andi@firstfloor.org \
    --cc=kan.liang@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ying.huang@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