From owner-freebsd-current@FreeBSD.ORG Tue Dec 1 10:25:37 2009 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 65640106570B for ; Tue, 1 Dec 2009 10:25:37 +0000 (UTC) (envelope-from matt.thyer@gmail.com) Received: from mail-bw0-f213.google.com (mail-bw0-f213.google.com [209.85.218.213]) by mx1.freebsd.org (Postfix) with ESMTP id E90E78FC22 for ; Tue, 1 Dec 2009 10:25:36 +0000 (UTC) Received: by bwz5 with SMTP id 5so3307670bwz.3 for ; Tue, 01 Dec 2009 02:25:35 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=Yjp4qmJzNnBzRUib7zAycrC1t2ysiYVGY3CDcdPBAMA=; b=VLOGnvaBUFTT/qMb3RN9ZHrnQSX1CiHg5VTlZtuRg5tkvWvyhAfpdeFnzFA40buKy1 FUY2j7KvpyfnleiHN7Pwf1SN1W7o4clLsfiZvUulRXvULAABKF+Lv6DajIvii1r1JKJa yzxcEC1Fl6ZktZ56a8N2/BnMs0mgxKMML9Dhk= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=xE+H8xkofP7MOQgSbx+JCnsnq5Nl8hEOE6ESvgfG4r/zzEbZ0xsN3ZrWjoh1PO82FQ qO7D6EEJ0PJLIom3vcuHMr7bYsM4i3/1+NlneCJNlcx4Izj2Ph+hSTfL4SHXsx1727IV zmIxdjQ/tHUg0PoFqEviMOMbaeBeyox6gQ8Yg= MIME-Version: 1.0 Received: by 10.204.152.154 with SMTP id g26mr5745392bkw.54.1259661741905; Tue, 01 Dec 2009 02:02:21 -0800 (PST) In-Reply-To: <200911301117.37950.naylor.b.david@gmail.com> References: <200911301117.37950.naylor.b.david@gmail.com> Date: Tue, 1 Dec 2009 20:32:21 +1030 Message-ID: From: Matt Thyer To: David Naylor Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-current@freebsd.org Subject: Re: FreeBSD 8.0 Performance (at Phoronix) X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 01 Dec 2009 10:25:37 -0000 2009/11/30 David Naylor : > HI, > > Phoronix recently published a comparative benchmark[1] for FreeBSD 7.2/8.= 0 > against Linux and OpenSolaris. =A0I would like to bring some of the good = and bad > to light (in the hopes that the developers with the correct expertise wil= l be > intrigued). > > The tests were performed with a 'standard' installation of FreeBSD on a L= enovo > ThinkPad T61. > > I've tried to eliminate tests who's performance is a result of compiler > differences and/or 3rd party applications and tests who's statistical > significance are not so strong (subjective guess). > > Improvements for FreeBSD 8.0 vs 7.2: > =A0- 7-Zip Compression (page 3) > =A0- Timed MAFFT Alignment (page 5) > =A0- GraphicsMagick (page 5) > =A0- Threaded IO (64MB Random Write - 32 threads) (page 7) > =A0- Threaded IO (64MB Read - 32 threads) (page 7) > > Regressions for FreeBSD 8.0 vs 7.2: > =A0- Gzip compressions of a 2GB file (page 3) > =A0- C-Ray (page 4) > =A0- Threaded IO (64MB Write - 4 threads) (page 7) > =A0- Threaded IO (64MB Write - 32 threads) (page 7) > > Poor performance relative to Linux and OpenSolaris > =A0- Threaded IO (especially random writes) (page 7) > =A0- OpenSSL (RSA 4096bit) (page 8) > =A0- PostMark (disk transaction) (page 8) > > It appears that threaded activity on UFS does not fair well against Linux= /ext4 > and OpenSolaris/ZFS. =A0Phoronix intends to do a comparative test against > FreeBSD and OpenSolaris on ZFS. > > Regards, > > David > > 1) > http://www.phoronix.com/scan.php?page=3Darticle&item=3Dfreebsd8_benchmark= s&num=3D1 > How much of the problem is due to FreeBSD staying with GCC 4.2.1 (due to the GPL v3 issue) compared with Linux using the latest GCC ? Is CLANG/LLVM expected to perform better ? How much is due to FreeBSD using an older Xorg ? (or is this not relevant to the benchmarks ?). A recent Phoronix article showed that Ubuntu 9.04 (I think) performed worse than Windows (7 I think) using the same open source software. Interestingly though, Windows binaries generally ran faster under Ubuntu using Wine than they did under Windows. This makes one think that GCC still has a long way to go compared to MS Visual Studio (or Wine has a lot less overhead than a full Windows system). Matthew