Received: from sencha.khimov.ru ([89.223.109.22]) by linuxtogo.org with esmtp (Exim 4.72) (envelope-from ) id 1RI2YX-0005Lu-U6 for openembedded-devel@lists.openembedded.org; Sun, 23 Oct 2011 20:13:58 +0200 Received: from [93.100.16.104] (helo=mate.hex) by sencha.khimov.ru with esmtpsa (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.69) (envelope-from ) id 1RI2CG-0003c8-Us for openembedded-devel@lists.openembedded.org; Sun, 23 Oct 2011 21:51:01 +0400 From: Roman Khimov To: openembedded-devel@lists.openembedded.org Date: Sun, 23 Oct 2011 21:50:43 +0400 User-Agent: KMail/1.13.6 (Linux/2.6.37.6-0.7-desktop; KDE/4.6.0; x86_64; ; ) References: <4E9C93AB.7090705@telia.com> <4E9CA882.7080107@gmail.com> <4E9D16AD.7040403@telia.com> In-Reply-To: <4E9D16AD.7040403@telia.com> MIME-Version: 1.0 Message-Id: <201110232150.53072.roman@khimov.ru> Subject: Re: Performance measurement: Building openembedded-core with and without overclocking on C-i7 2600K X-BeenThere: openembedded-devel@lists.openembedded.org X-Mailman-Version: 2.1.11 Precedence: list Reply-To: openembedded-devel@lists.openembedded.org List-Id: Using the OpenEmbedded metadata to build Distributions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 23 Oct 2011 18:13:58 -0000 X-Groupsio-MsgNum: 34988 Content-Type: multipart/signed; boundary="nextPart1890086.Wi8TAq8cAK"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit --nextPart1890086.Wi8TAq8cAK Content-Type: Text/Plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable =D0=92 =D1=81=D0=BE=D0=BE=D0=B1=D1=89=D0=B5=D0=BD=D0=B8=D0=B8 =D0=BE=D1=82 = 18 =D0=BE=D0=BA=D1=82=D1=8F=D0=B1=D1=80=D1=8F 2011 10:03:25 =D0=B0=D0=B2=D1= =82=D0=BE=D1=80 Ulf Samuelsson =D0=BD=D0=B0=D0=BF=D0=B8=D1=81=D0=B0=D0=BB: > Also what happens if it it built on a fast SSD, or even a RAMdisk? Our main build server has two Xeons X5670 with 96 GB of RAM. It's running 2= 4=C3=977=20 cyclicly doing clean isolated builds of all our OE projects (currently five= ).=20 "Isolated" means that the the actual build is done inside a container (LXC)= =20 with no network available at all, that is a requirement for all our builds,= to=20 be able to take one tarball of sources, one tarball of OE tree and build th= e=20 project somewhere in a nuclear bunker. The system is configured in such way that container is located on tmpfs (wi= th=20 size of 50 GB). The most complex build takes about hour and a half on this= =20 system occupying about 45 GB of space in a ramdisk. So today I tried to get some RAM vs. Linux cache statistics and switched th= is=20 mount point over to newly created 60 GB LVM partition with ext4 on RAID0 ar= ray=20 consisting of two SAS 15K drives. The system made builds for three projects is this configuration and I see n= o=20 difference at all, usual 1-2 minutes deviation. Granted, the system has qui= te=20 powerful disks (RAID array gives about 380 MB/sec on hdparm) and things mig= ht=20 be a little different on plain SATA drives, but frankly I'd expected to see= =20 the difference anyway since there are lots of small files involved in a bui= ld. Maybe I should try to further degrade the disk system by creating some=20 encrypted volume inside LVM, but still from what I see Linux caching and=20 buffering works good enough, just give it as much RAM as you can. But then also what you'll get from RAM or disk or even CPU upgrade depends = on=20 what type of build you have. Upgrading developers build servers from pair o= f=20 4-core Opterons (don't remember exact model) with 8 GB of RAM to pair of Xe= ons=20 E5620 with 24 GB of RAM with comparable disks gave about 20-30% of build ti= me=20 reduction for one project and 50% for another. But that builds are not=20 isolated and use icecc cluster with all build servers available to the=20 cluster, maybe that helps also in our situation. =2D-=20 http://roman.khimov.ru mailto: roman@khimov.ru gpg --keyserver hkp://subkeys.pgp.net --recv-keys 0xE5E055C3 --nextPart1890086.Wi8TAq8cAK Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part. -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.16 (GNU/Linux) iEYEABECAAYFAk6kU/wACgkQXJ70z+XgVcPFDQCeMNhg7MSge+lFHhxucss8uvU/ SWUAn11yB9uqhao7lg5h5f6Vql+xaQEB =27gp -----END PGP SIGNATURE----- --nextPart1890086.Wi8TAq8cAK--