Newsgroups: php.internals
Path: news.php.net
Xref: news.php.net php.internals:86477
Return-Path: <php@golemon.com>
Mailing-List: contact internals-help@lists.php.net; run by ezmlm
Delivered-To: mailing list internals@lists.php.net
Received: (qmail 2349 invoked from network); 3 Jun 2015 14:29:59 -0000
Received: from unknown (HELO lists.php.net) (127.0.0.1)
  by localhost with SMTP; 3 Jun 2015 14:29:59 -0000
Authentication-Results: pb1.pair.com header.from=php@golemon.com; sender-id=softfail
Authentication-Results: pb1.pair.com smtp.mail=php@golemon.com; spf=softfail; sender-id=softfail
Received-SPF: softfail (pb1.pair.com: domain golemon.com does not designate 209.85.216.179 as permitted sender)
X-PHP-List-Original-Sender: php@golemon.com
X-Host-Fingerprint: 209.85.216.179 mail-qc0-f179.google.com  
Received: from [209.85.216.179] ([209.85.216.179:33098] helo=mail-qc0-f179.google.com)
	by pb1.pair.com (ecelerity 2.1.1.9-wez r(12769M)) with ESMTP
	id 1A/70-32628-66F0F655 for <internals@lists.php.net>; Wed, 03 Jun 2015 10:29:59 -0400
Received: by qcmi9 with SMTP id i9so4603610qcm.0
        for <internals@lists.php.net>; Wed, 03 Jun 2015 07:29:55 -0700 (PDT)
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20130820;
        h=x-gm-message-state:content-type:mime-version:subject:from
         :in-reply-to:date:cc:content-transfer-encoding:message-id:references
         :to;
        bh=yOZZY0pb3WpDnWZpHpiMyqzDN8froO7pV5O4h3SmFgs=;
        b=OoTRgaMdkKIYINJR1Yqh21WjQhjGpBfg5tfm5kEg8b9MhiizgFRbGM+npmOJJAd3jI
         IDloOUBgohGcEgLrggQFGq7EutjO+7yVECH07fHTeqFuv0vMAZQhmt65RxNeGWnCBCmu
         D2V/K43zU3Jm1hhek9oDBFiCbuOqkDwxD5073aTIQrr179irs597ZcfwhmcXcQ4nCuWY
         FHMFVcxKTYKElc5XJgz2aCrsYP6ku2U2ZyuoIXo/IEFsVw9vFrkjyJGk3TfVHuBqB47t
         zyQlpSt5PyLNXHNXyRQo8GNnabWvUkPXYQGZUz1TvmjtHNk0K/l+dYpr0tqHo/Ep7Xvv
         LHgw==
X-Gm-Message-State: ALoCoQkXKSppHqrDgVBFFM6Nj1sQYlXWl5y66XnH3MsW+yF4Uf8knDvyCpUQGhaOxmS0S/KVE2r7
X-Received: by 10.140.21.134 with SMTP id 6mr35883945qgl.47.1433341795632;
        Wed, 03 Jun 2015 07:29:55 -0700 (PDT)
Received: from [10.0.1.137] (c-73-189-247-124.hsd1.ca.comcast.net. [73.189.247.124])
        by mx.google.com with ESMTPSA id z13sm445073qkg.44.2015.06.03.07.29.53
        (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128);
        Wed, 03 Jun 2015 07:29:54 -0700 (PDT)
Content-Type: text/plain;
	charset=utf-8
Mime-Version: 1.0 (1.0)
X-Mailer: iPhone Mail (12B466)
In-Reply-To: <CB6903CB-DAC6-45D6-A71F-79BA14DE7B99@php.net>
Date: Wed, 3 Jun 2015 07:29:51 -0700
Cc: "bishop@php.net" <bishop@php.net>,
 PHP internals <internals@lists.php.net>
Content-Transfer-Encoding: quoted-printable
Message-ID: <440717E2-B633-48FF-A629-DEC3E0D89B19@golemon.com>
References: <CAEYWF=4Gn=6OcPWc3w2k6G7DWrqaUfS4QdohjhiSG+2vH8euyg@mail.gmail.com> <CB6903CB-DAC6-45D6-A71F-79BA14DE7B99@php.net>
To: Michael Wallner <mike@php.net>
Subject: Re: [PHP-DEV] Method call overhead
From: php@golemon.com (Sara Golemon)


> On Jun 3, 2015, at 00:50, Michael Wallner <mike@php.net> wrote:
>=20
>>> On 03 06 2015, at 05:30, Bishop Bettini <bishop@php.net> wrote:
>>=20
>> My question though is on relative times.  Method call overhead is
>> consistently 50% to 150% over a direct call.  Is my experiment invalid, o=
r
>> is this overhead expected?  Is the overhead in the allocation,
>> deallocation, GC?
>=20
> I=E2=80=99suggest you use a tool like valgrind=E2=80=99s callgrind (and vi=
sualize with e.g. kcachegrind).
>=20
I'd also take variable function calling out of the picture (or at least, hav=
e it as a separate dimension).  Normal applications make pretty spare use of=
 variable functions (compared to actual direct calls), whereas your benchmar=
k uses them exclusively.  So you've explicitly chosen the most pessimistic p=
ath, and an unrepresentative one.

-Sara=