linux-kernel - Re: [PATCH 2/2] perf callchain: Use global caching provided by libunwind

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 24 Sep 2014 15:45:57 +0200
From:	Jean Pihet <jean.pihet@...aro.org>
To:	Namhyung Kim <namhyung@...nel.org>
Cc:	Arun Sharma <asharma@...com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Ingo Molnar <mingo@...nel.org>,
	Paul Mackerras <paulus@...ba.org>,
	Namhyung Kim <namhyung.kim@....com>,
	LKML <linux-kernel@...r.kernel.org>, Jiri Olsa <jolsa@...hat.com>
Subject: Re: [PATCH 2/2] perf callchain: Use global caching provided by libunwind

Hi!

Here are the test results on ARMv7 for the 2 patches. The speedup is
about x2.1 for identical unwinding output data.

'perf record --call-graph dwarf -- stress --cpu 2 --io 2 --vm 2
--timeout 10s' generates a 365 MB perf.data file.

time perf.orig report --sort symbol --call-graph --stdio 2&>1 > /dev/null
average on 3 runs
real    36.736
user   14.79
sys    21.91

time perf.libunwind.speedup report --sort symbol --call-graph --stdio
2&>1 > /dev/null
average on 3 runs
real    17.41        x2.11
user     6.42        x2.3
sys    10.97        x2

So the patches definitely speedup the unwinding.
FWIW: Acked-by: Jean Pihet <jean.pihet@...aro.org>

For info unwinding using libdw is about 5x faster:
time perf.libdw.speedup report --sort symbol --call-graph --stdio 2&>1
> /dev/null
real    0m3.484s
user    0m2.360s
sys    0m1.070s

Thanks,
Jean

On 24 September 2014 04:24, Namhyung Kim <namhyung@...nel.org> wrote:
> Hi Arun,
>
> On Tue, 23 Sep 2014 14:01:22 +0000, Arun Sharma wrote:
>> On 9/23/14, 12:00 PM, Namhyung Kim wrote:
>>
>>> +    unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
>>
>> The result is a bit surprising for me. In micro benchmarking (eg:
>> Lperf-simple), the per-thread policy is generally faster because it
>> doesn't involve locking.
>>
>> libunwind/tests/Lperf-simple
>> unw_getcontext : cold avg=  109.673 nsec, warm avg=   28.610 nsec
>> unw_init_local : cold avg=  259.876 nsec, warm avg=    9.537 nsec
>> no cache        : unw_step : 1st= 3258.387 min= 2922.331 avg= 3002.384 nsec
>> global cache    : unw_step : 1st= 1192.093 min=  960.486 avg=  982.208 nsec
>> per-thread cache: unw_step : 1st=  429.153 min=  113.533 avg=  121.762 nsec
>
> Yes, per-thread policy is faster than global caching policy.  Below is my
> test result.  Note that I already run this several times before to
> remove an effect that file contents loaded in page cache.
>
>  Performance counter stats for
>    'perf report -i /home/namhyung/tmp/perf-testing/perf.data.kbuild.dwarf --stdio' (3 runs):
>
>                                  UNW_CACHE_NONE         UNW_CACHE_GLOBAL     UNW_CACHE_PER_THREAD
>   -----------------------------------------------------------------------------------------------
>   task-clock (msec)                14298.911947              7112.171928              6913.244797
>   context-switches                        1,507                      762                      742
>   cpu-migrations                              1                        2                        1
>   page-faults                         2,924,889                1,101,380                1,101,380
>   cycles                         53,895,784,665           26,798,627,423           26,070,728,349
>   stalled-cycles-frontend        24,472,506,687           12,577,760,746           12,435,320,081
>   stalled-cycles-backend         17,550,483,726            9,075,054,009            9,035,478,957
>   instructions                   73,544,039,490           34,352,889,707           33,283,120,736
>   branches                       14,969,890,371            7,139,469,848            6,926,994,151
>   branch-misses                     193,852,116              100,455,431               99,757,213
>   time elapsed                     14.905719730              7.455597356              7.242275972
>
>
>>
>> I can see how the global policy would involve less memory allocation
>> because of shared data structures. Curious about the reason for the
>> speedup (specifically if libunwind should change the defaults for the
>> non-local unwinding case).
>
> I don't see much difference between global and per-thread caching for
> remote unwind (besides rs_cache->lock you mentioned).  Also I'm curious
> that how rs_new() is protected from concurrent accesses in per-thread
> caching.  That's why I chose the global caching - yeah, it probably
> doesn't matter to a single thread, but... :)
>
> Thanks
> Namhyung
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/