Newsgroups: php.internals
Path: news.php.net
Xref: news.php.net php.internals:88959
Mailing-List: contact internals-help@lists.php.net; run by ezmlm
Received-SPF: pass (pb1.pair.com: domain hotmail.com designates 65.55.111.91 as permitted sender)
Message-ID: <BLU437-SMTP80680F918D469D1EC111A0E2210@phx.gbl>
Content-Type: multipart/alternative;
	boundary="Apple-Mail=_8FCB8C1D-0E21-4748-ABDE-637C8539AA77"
MIME-Version: 1.0 (Mac OS X Mail 9.0 \(3094\))
In-Reply-To: <CA+9eiLuDJf9z5Lh0_Ca8VphmoDHC=ZkNZm=j6ytg0Bvswo_V_A@mail.gmail.com>
Date: Wed, 28 Oct 2015 07:11:31 +0100
CC: Xinchen Hui <xinchen.h@zend.com>,
 Nikita Popov <nikita.ppv@gmail.com>,
 PHP Internals <internals@lists.php.net>
References: <CA+9eiLuVkwpTzfzJpNG_REgF=v31nWdY6BDcN8kp5oTz2eg+DA@mail.gmail.com> <CA+9eiLuDJf9z5Lh0_Ca8VphmoDHC=ZkNZm=j6ytg0Bvswo_V_A@mail.gmail.com>
To: Dmitry Stogov <dmitry@zend.com>
Subject: Re: Speed up fetching of class entries for self:: parent:: and static:: (Bob's idea)
From: bobwei9@hotmail.com (Bob Weinand)

--Apple-Mail=_8FCB8C1D-0E21-4748-ABDE-637C8539AA77
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain; charset="utf-8"


> Am 28.10.2015 um 05:20 schrieb Dmitry Stogov <dmitry@zend.com>:
> What is the general impression from the patch?
> Should we commit it (with minor fixes and/or additional =
optimisations)?
> Bob, do you see performance improvement on your app?
>=20
> Thanks. Dmitry.
>=20
> On Oct 27, 2015 4:14 PM, "Dmitry Stogov" <dmitry@zend.com =
<mailto:dmitry@zend.com>> wrote:
> Hi,
>=20
> Please take a look: https://github.com/php/php-src/pull/1604 =
<https://github.com/php/php-src/pull/1604>
> The speed improvement on real-life is insignificant.
> VM size is increased by 10KB.
>=20
> I don't have a strong opinion, if this should go into master or not.
>=20
> Thanks. Dmitry.

In general I like the patch, if only for the reason that it splits up =
the monster zend_fetch_var_address_helper actually was into two =
helpers=E2=80=A6

I benchmarked https://github.com/amphp/aerys/blob/master/lib/HPack.php =
with the following code:

// Two example request headers from RFC 7541
$data1 =3D hex2bin(str_replace(" ", "", "8286 8441 8cf1 e3c2 e5f2 3a6b =
a0ab 90f4 ff"));
$data2 =3D hex2bin(str_replace(" ", "", "8286 84be 5886 a8eb 1064 =
9cbf"));

for ($i =3D 0; $i < 1e5; $i++) {
    $obj =3D new HPack;
    $obj->decode($data1);
    $obj->decode($data2);
}

and got 6.27 vs. 6.01 seconds (4%). With the one or other optimization =
(like mentioned in PR: not doing a zend_fetch_class() on each call, =
maybe more), it'll be probably even more.

(I realize there's a lot overhead, but that's because I try to have a =
not too synthetic benchmark; but at least these methods are the =
bottleneck of most HTTP/2 traffic in this server app, so, if I can speed =
these up, it will be significant.)

Bob=

--Apple-Mail=_8FCB8C1D-0E21-4748-ABDE-637C8539AA77--