linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Andi Kleen <ak@linux.intel.com>
Cc: jolsa@kernel.org, linux-perf-users@vger.kernel.org
Subject: Re: [PATCH] perf lzma: Quieten lzma warning
Date: Wed, 16 Nov 2022 14:03:05 -0300	[thread overview]
Message-ID: <Y3UXySfyfzj49Pai@kernel.org> (raw)
In-Reply-To: <20221004190615.998656-1-ak@linux.intel.com>

Em Tue, Oct 04, 2022 at 12:06:15PM -0700, Andi Kleen escreveu:
> On my Fedora system which is missing some modules I always get a long flood
> of
> 
> lzma: fopen failed on /usr/lib/modules/5.3.9-300.fc31.x86_64/kernel/sound/pci/hda/snd-hda-codec.ko.xz: 'No such file or directory'
> lzma: fopen failed on /usr/lib/modules/5.16.7-200.fc35.x86_64/kernel/sound/pci/hda/snd-hda-intel.ko.xz: 'No such file or directory'
> lzma: fopen failed on /usr/lib/modules/5.1.11-200.fc29.x86_64/kernel/drivers/vhost/vhost_net.ko.xz: 'No such file or directory'
> 
> for each use of "perf list".
> 
> Disable the message.
> 
> Also I'm not sure why it's looking at the modules of each kernel, not
> just the running one, but that's a different problem.

So using:

[root@five ~]# perf probe -x ~/bin/perf -L lzma_decompress_to_file | head -20
<lzma_decompress_to_file@/var/home/acme/git/perf/tools/perf/util/lzma.c:0>
      0  int lzma_decompress_to_file(const char *input, int output_fd)
         {
      2  	lzma_action action = LZMA_RUN;
         	lzma_stream strm   = LZMA_STREAM_INIT;
      4  	lzma_ret ret;
         	int err = -1;
         
         	u8 buf_in[BUFSIZE];
         	u8 buf_out[BUFSIZE];
         	FILE *infile;
         
         	infile = fopen(input, "rb");
     12  	if (!infile) {
     13  		pr_err("lzma: fopen failed on %s: '%s'\n",
         		       input, strerror(errno));
     15  		return -1;
         	}
         
     18  	ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED);
[root@five ~]#

And:

[root@five ~]# perf probe -x ~/bin/perf lzma_decompress_to_file
Added new event:
  probe_perf:lzma_decompress_to_file (on lzma_decompress_to_file in /var/home/acme/bin/perf)

You can now use it in all perf tools, such as:

	perf record -e probe_perf:lzma_decompress_to_file -aR sleep 1

[root@five ~]#
[root@five ~]# perf record -e probe_perf:lzma_decompress_to_file/max-stack=16/ perf list syscalls:sys_enter_open*
[ perf record: Woken up 1 times to write data ]

[ perf record: Captured and wrote 0.119 MB perf.data (625 samples) ]

[root@five ~]#
[root@five ~]#
[root@five ~]# perf report --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 625  of event 'probe_perf:lzma_decompress_to_file'
# Event count (approx.): 625
#
# Children      Self  Trace output
# ........  ........  ............
#
   100.00%   100.00%  (5c53b0)
            |
            ---__libc_start_call_main
               main
               run_builtin
               cmd_list
               print_sdt_events
               build_id_cache__list_all
               filename__read_build_id
               lzma_decompress_to_file



#
# (Tip: Limit to show entries above 5% only: perf report --percent-limit 5)
#
[root@five ~]#


Seems like it is trying to find SDT events in everything that is in
~/.debug :-\ I'll try to continue this later, sidetracked now.

- Arnaldo
 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> ---
>  tools/perf/util/lzma.c | 5 +----
>  1 file changed, 1 insertion(+), 4 deletions(-)
> 
> diff --git a/tools/perf/util/lzma.c b/tools/perf/util/lzma.c
> index 51424cdc3b68..ef0520c82245 100644
> --- a/tools/perf/util/lzma.c
> +++ b/tools/perf/util/lzma.c
> @@ -44,11 +44,8 @@ int lzma_decompress_to_file(const char *input, int output_fd)
>  	FILE *infile;
>  
>  	infile = fopen(input, "rb");
> -	if (!infile) {
> -		pr_err("lzma: fopen failed on %s: '%s'\n",
> -		       input, strerror(errno));
> +	if (!infile)
>  		return -1;
> -	}
>  
>  	ret = lzma_stream_decoder(&strm, UINT64_MAX, LZMA_CONCATENATED);
>  	if (ret != LZMA_OK) {
> -- 
> 2.37.2

-- 

- Arnaldo

      parent reply	other threads:[~2022-11-16 17:03 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-04 19:06 [PATCH] perf lzma: Quieten lzma warning Andi Kleen
2022-10-17 12:36 ` Arnaldo Carvalho de Melo
2022-11-16 17:03 ` Arnaldo Carvalho de Melo [this message]

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=Y3UXySfyfzj49Pai@kernel.org \
    --to=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=jolsa@kernel.org \
    --cc=linux-perf-users@vger.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;
as well as URLs for NNTP newsgroup(s).