git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / Atom feed
From: Carlo Arenas <carenas@gmail.com>
To: "René Scharfe" <l.s.r@web.de>
Cc: git@vger.kernel.org, gitster@pobox.com,
	johannes.schindelin@gmx.de, avarab@gmail.com,
	michal.kiedrowicz@gmail.com
Subject: Re: [RFC PATCH v3 2/3] grep: make PCRE2 aware of custom allocator
Date: Thu, 8 Aug 2019 05:38:11 -0700
Message-ID: <CAPUEspi2vu=7uLU19c-wcW+ji63gyeO7poAwS5_7ZhTiBWSxjg@mail.gmail.com> (raw)
In-Reply-To: <f6056e0c-fe7f-30b3-c2d7-bba2b44d6888@web.de>

On Thu, Aug 8, 2019 at 12:07 AM René Scharfe <l.s.r@web.de> wrote:
>
> Am 08.08.19 um 04:35 schrieb Carlo Arenas:
> > On Wed, Aug 7, 2019 at 6:03 AM René Scharfe <l.s.r@web.de> wrote:
> >>
> >> Am 07.08.19 um 11:49 schrieb Carlo Arenas:
> >>> was hoping will perform better but it seems that testing can be done
> >>> only in windows
> >>
> >> nedmalloc works on other platforms as well.
> >
> > I meant[1] it works reliably enough to be useful for performance testing.
>
> You mentioned being concerned about performance several times and I
> wondered why each time.  I'd expect no measurable difference between
> using a custom global context and the internal one of PCRE2 -- setting
> two function pointers surely can't take very long, can it?  But
> measuring is better than guessing, of course.

setting the allocator is not a concern, but using it; it requires an
extra indirect function call which is usually not very friendly to
caches in our speculative execution CPU world.  our implementation
also adds the wrapper call overhead, but in this case it is just the
"cost of doing business" with PCRE2.

compilers had gotten a lot better since (mainly because of C++ and the
need for it with virtual methods) but I would rather measure.

> > goes without saying that the fact that I am using a virtualbox with 2
> > CPUs running Debian 10 on top of macOS (a macbook pro with 4 cores)
> > and the test uses by default 8 threads, doesn't help,
>
> nedmalloc is supposed to run on macOS as well.

the last version has some "fix miscompilations in macOS" fixes that
might be relevant, and the version we have in tree says it works in
the 32-bit version which latest macOS versions are working hard to
deprecate (can't even build for it anymore), eitherway trying to run
with a nedmalloc enabled git in macOS is not fun.

> > with the only relevant line (for my code) being 7820.19 where it would
> > seem it performs almost the same (eventhough just adding NED made it
> > initially worst)
> >
> > note though that the fact there are 20% swings in parts of the code
> > that hasn't changed
> > or that where explicitly #ifdef out of my code changes doesn't give me
> > much confidence, but since the windows guys seem to be using NED by
> > default, I am hoping it works better there.
>
> These measurement results are quite noisy, so I wouldn't trust them too
> much.  nedmalloc being slower than the one from a recent glibc version
> is not very surprising given this statement from its home page,
> https://www.nedprod.com/programs/portable/nedmalloc/:
>
>    "Windows 7, Linux 3.x, FreeBSD 8, Mac OS X 10.6 all contain
>     state-of-the-art allocators and no third party allocator is
>     likely to significantly improve on them in real world results"
>
> In particular I don't think that these results justify coupling the use
> of nedmalloc to the choice of using a custom global context for PCRE2.

neither did I either, the only reason I am holding on fully enabling
NED with PCRE2 in my series is just because I wan't to make sure we
have identified the bug correctly and we are fixing it (specially
since I can't reproduce it, and therefore neither debug it)

sorry for not making that clear enough, and as I said before, if we
keep seeing segfaults even after v4 then we will have to do that or I
might need to do a quick run to the nearest microsoft store hoping for
a distracted rep, instead.

> I'd expect:
> - Without USE_NED_ALLOCATOR: xmalloc() should be used for all
>   allocations, including for PCRE2.  Some special exceptions use
>   malloc(3) directly, but for most uses we want the consistent
>   out-of-memory handling that xmalloc() brings.

that is already in v4 and would expect to carry it forward.  this is
also what I had in mind when I said we will need some fixes on top of
Dscho version if we give up with these.

> - With USE_NED_ALLOCATOR: malloc() and xmalloc() use nedmalloc
>   behind the scenes and free() is similarly overridden, so all
>   allocations are affected.
> - If USE_NED_ALLOCATOR performs worse than the system allocator on
>   some system then it's the problem of those that turn on that flag.
>
> Makes sense?

completely, but note also that Dscho version would make the
performance impacts of using a custom allocator (if any) affect
everyone using PCRE2.

Carlo

  reply	other threads:[~2019-08-08 12:38 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-05 11:51 [PATCH 0/1] Fix a problem with PCRE2 and nedmalloc, found via Azure Pipelines Johannes Schindelin via GitGitGadget
2019-08-05 11:51 ` [PATCH 1/1] pcre2: allow overriding the system allocator Johannes Schindelin via GitGitGadget
2019-08-05 16:19   ` Carlo Arenas
2019-08-05 16:27     ` Carlo Arenas
2019-08-05 19:32       ` Johannes Schindelin
2019-08-05 19:26     ` Johannes Schindelin
2019-08-05 21:53     ` Junio C Hamano
2019-08-06  6:24       ` Carlo Arenas
2019-08-06  8:50       ` [PATCH 0/3] grep: no leaks (WIP) Carlo Marcelo Arenas Belón
2019-08-06  8:50         ` [PATCH 1/3] grep: make PCRE1 aware of custom allocator Carlo Marcelo Arenas Belón
2019-08-08 13:54           ` Johannes Schindelin
2019-08-08 15:19             ` Carlo Arenas
2019-08-06  8:50         ` [PATCH 2/3] grep: make PCRE2 " Carlo Marcelo Arenas Belón
2019-08-08 13:56           ` Johannes Schindelin
2019-08-08 14:32             ` Carlo Arenas
2019-08-06  8:50         ` [PATCH 3/3] grep: avoid leak of chartables in PCRE2 Carlo Marcelo Arenas Belón
2019-08-06 16:36         ` [RFC PATCH v3 0/3] grep: no leaks or crashes (windows testing needed) Carlo Marcelo Arenas Belón
2019-08-06 16:36           ` [RFC PATCH v3 1/3] grep: make PCRE1 aware of custom allocator Carlo Marcelo Arenas Belón
2019-08-06 16:36           ` [RFC PATCH v3 2/3] grep: make PCRE2 " Carlo Marcelo Arenas Belón
2019-08-07  5:38             ` René Scharfe
2019-08-07  9:49               ` Carlo Arenas
2019-08-07 13:02                 ` René Scharfe
2019-08-07 13:08                   ` [PATCH 1/2] nedmalloc: do assignments only after the declaration section René Scharfe
2019-08-07 13:09                   ` [PATCH 2/2] nedmalloc: avoid compiler warning about unused value René Scharfe
2019-08-08  2:35                   ` [RFC PATCH v3 2/3] grep: make PCRE2 aware of custom allocator Carlo Arenas
2019-08-08  7:07                     ` René Scharfe
2019-08-08 12:38                       ` Carlo Arenas [this message]
2019-08-08 14:29                         ` René Scharfe
2019-08-08 20:18                           ` Johannes Schindelin
2019-08-07 18:15                 ` Junio C Hamano
2019-08-06 16:36           ` [RFC PATCH v3 3/3] grep: avoid leak of chartables in PCRE2 Carlo Marcelo Arenas Belón
2019-08-06 16:48           ` [RFC PATCH v3 0/3] grep: no leaks or crashes (windows testing needed) Junio C Hamano
2019-08-07 21:39           ` [RFC PATCH v4 " Carlo Marcelo Arenas Belón
2019-08-07 21:39             ` [RFC PATCH v4 1/3] grep: make PCRE1 aware of custom allocator Carlo Marcelo Arenas Belón
2019-08-07 21:39             ` [RFC PATCH v4 2/3] grep: make PCRE2 " Carlo Marcelo Arenas Belón
2019-08-07 22:28               ` Junio C Hamano
2019-08-07 21:39             ` [RFC PATCH v4 3/3] grep: avoid leak of chartables in PCRE2 Carlo Marcelo Arenas Belón
2019-08-09  3:02             ` [RFC PATCH v5 0/3] grep: almost no more leaks, hopefully no crashes Carlo Marcelo Arenas Belón
2019-08-09  3:02               ` [RFC PATCH v5 1/3] grep: make PCRE1 aware of custom allocator Carlo Marcelo Arenas Belón
2019-08-09  3:02               ` [RFC PATCH v5 2/3] grep: make PCRE2 " Carlo Marcelo Arenas Belón
2019-08-27  9:07                 ` Johannes Schindelin
2019-08-27 11:51                   ` Carlo Arenas
2019-10-03  5:02                     ` Junio C Hamano
2019-10-03  8:08                       ` Johannes Schindelin
2019-10-03 11:17                         ` Carlo Arenas
2019-10-03 18:23                           ` Johannes Schindelin
2019-10-03 22:57                           ` Junio C Hamano
2019-08-09  3:02               ` [RFC PATCH v5 3/3] grep: avoid leak of chartables in PCRE2 Carlo Marcelo Arenas Belón
2019-08-09 11:24               ` [RFC PATCH v5 0/3] grep: almost no more leaks, hopefully no crashes Carlo Arenas
2019-08-09 17:01                 ` René Scharfe
2019-08-09 17:46                   ` Junio C Hamano
2019-08-09 21:26                   ` Johannes Schindelin
2019-08-10  3:03                     ` [PATCH] SQUASH Carlo Marcelo Arenas Belón
2019-08-10  7:57                       ` René Scharfe
2019-08-10  8:42                         ` Carlo Arenas
2019-08-10 19:47                           ` René Scharfe
2019-08-12  7:35                             ` Carlo Arenas
2019-08-12 12:14                               ` René Scharfe
2019-08-12 12:28                                 ` Carlo Arenas
2019-08-10 13:57                       ` Johannes Schindelin
2019-08-10  3:05                     ` [RFC PATCH v5 0/3] grep: almost no more leaks, hopefully no crashes Carlo Arenas
2019-08-10  7:56                       ` René Scharfe
2019-08-10 12:40                         ` Carlo Arenas
2019-08-10 21:16                           ` René Scharfe
2019-08-08 20:21           ` [RFC PATCH v3 0/3] grep: no leaks or crashes (windows testing needed) Johannes Schindelin
2019-08-09  6:52             ` Carlo Arenas
2019-08-09 21:13               ` Johannes Schindelin

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

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAPUEspi2vu=7uLU19c-wcW+ji63gyeO7poAwS5_7ZhTiBWSxjg@mail.gmail.com' \
    --to=carenas@gmail.com \
    --cc=avarab@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=johannes.schindelin@gmx.de \
    --cc=l.s.r@web.de \
    --cc=michal.kiedrowicz@gmail.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

git@vger.kernel.org list mirror (unofficial, one of many)

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 git git/ https://public-inbox.org/git \
		git@vger.kernel.org
	public-inbox-index git

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.io/gmane.comp.version-control.git
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for the project(s) associated with this inbox:

	https://80x24.org/mirrors/git.git

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git