DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma;
	h=mime-version:date:message-id:subject:from:to:content-type;
	b=t0KzB6e6lfaVfAYRdTmUlUdwuWSYtqs9B4/B4HdpuQ+4+Uy/u18lGK5y3SBih7s7EF
	Q7p8sFEY+pEjbwAqYPoTxomogBssFmD3jLKFSO2/mP7WUvZtZNf06gidG2T2dsrftWv5
	QVj4nwcCGTTNcC+MMcDoyXECtuBsDZUiRm27g=
MIME-Version: 1.0
Date: Mon, 11 Jan 2010 12:24:43 -0500
Message-ID: <73a01bf21001110924u9d754dby96bdd14f78e2840d@mail.gmail.com>
Subject: cache false-sharing in lwlocks
From: Rayson Ho <raysonlogin@gmail.com>
To: pgsql-performance@postgresql.org
Content-Type: multipart/mixed; boundary=001485f778a826875d047ce6d0a9

--001485f778a826875d047ce6d0a9
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: quoted-printable

Hi,

LWLockPadded is either 16 or 32 bytes, so modern systems (e.g. Core2
or AMD Opteron [1]) with cacheline size of 64 bytes can get
false-sharing in lwlocks.

I changed LWLOCK_PADDED_SIZE in src/backend/storage/lmgr/lwlock.c to
64, and ran sysbench OLTP read-only benchmark, and got a slight
improvement in throughput:

Hardware: single-socket Core 2, quad-core, Q6600  @ 2.40GHz
Software: Linux 2.6.28-17, glibc 2.9, gcc 4.3.3

PostgreSQL: 8.5alpha3

sysbench parameters: sysbench --num-threads=3D4 --max-requests=3D0
--max-time=3D120 --oltp-read-only=3Don --test=3Doltp

original: 3227, 3243, 3243
after:     3256, 3255, 3253

So there is a speedup of 1.005 or what other people usually call it, a
0.5% improvement.

However, it's a single socket machine, so all the cache traffic does
not need to go off-chip. Can someone with a multi-socket machine help
me run some test so that we can get a better idea of how this change
(patch attached) performs in bigger systems??

Thanks,
Rayson

P.S. And I just googled and found similar discussions about padding
LWLOCK_PADDED_SIZE, but the previous work was done on an IBM POWER
system, and the benchmark used was apachebench. IMO, the setup was too
complex to measure a small performance improvement in PostgreSQL.

[1] Performance Guidelines for AMD Athlon=99 64 and AMD Opteron=99 ccNUMA
Multiprocessor Systems Application Note

--001485f778a826875d047ce6d0a9
Content-Type: text/plain; charset=US-ASCII; name="lwlock.patch.txt"
Content-Disposition: attachment; filename="lwlock.patch.txt"
Content-Transfer-Encoding: base64
X-Attachment-Id: f_g4biquk30
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--001485f778a826875d047ce6d0a9--