From owner-freebsd-stable Thu Feb 17 5:10:40 2000 Delivered-To: freebsd-stable@freebsd.org Received: from morpheus.skynet.be (morpheus.skynet.be [195.238.2.39]) by hub.freebsd.org (Postfix) with ESMTP id 8D65F37B6CC for ; Thu, 17 Feb 2000 05:10:35 -0800 (PST) (envelope-from blk@skynet.be) Received: from [195.238.1.121] (brad.techos.skynet.be [195.238.1.121]) by morpheus.skynet.be (Postfix) with ESMTP id C6005CBB3 for ; Thu, 17 Feb 2000 14:10:30 +0100 (MET) Mime-Version: 1.0 X-Sender: blk@pop.skynet.be Message-Id: In-Reply-To: References: Date: Thu, 17 Feb 2000 14:10:04 +0100 To: freebsd-stable@FreeBSD.ORG From: Brad Knowles Subject: Re: Initial performance testing w/ postmark & softupdates... Content-Type: text/plain; charset="us-ascii" ; format="flowed" Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG At 1:22 PM +0100 2000/2/17, Brad Knowles wrote: > I'm going to be doing my own memory-based filesystem checks, to get > an idea of what the real upper bound of performance is on this hardware. > I'll let you know more as I do it myself. Just got my own memory-based filesystem (MFS) numbers with the same FreeBSD 3.4-STABLE machine. Let's compare these to the NetApp TMPFS, NetApp NFS/F630, and +SOFT: Test 1: 1000 files & 50,000 transactions MFS TMPFS NFS/F630 +SOFT ------ ----- -------- ------- TPS 1724 2000 253 458 Read 5488.64 4880 799.91 1495.04 Write 5611.52 7330 817.89 1525.76 Test 2: 20,000 files & 50,000 transactions MFS TMPFS NFS/F630 +SOFT ------ ----- -------- ------- TPS 228 438 176 142 Read 504.14 663.64 383.41 318.81 Write 913.29 1530 694.58 577.55 Test 3: 20,000 files & 100,000 transactions UFS TMPFS NFS/F630 +SOFT ------ ----- -------- ------- TPS 228 335 169 139 Read 606.47 613.03 446.69 379.79 Write 838.31 1160 617.45 524.98 Test 4: 20,000 files/100 subdirectories & 100,000 transactions MFS TMPFS NFS/F630 +SOFT ------ ----- -------- ------- TPS 1333 86 Read 3471.36 237.10 Write 4802.56 327.75 TPS = Transactions Per Second Read = Data read per second (in kilobytes) Write = Data written per second (in kilobytes) Hmm. That sure makes me wonder what the *HECK* they were using for their TMPFS tests! That said, notice that performance on MFS goes up *dramatically* when you use subdirectories, implying that directory search overhead at those kinds of speeds is quite significant. Also note that their TMPFS and their NFS/F630 tests slowed down between test #2 and test #3, while my MFS test hardly changed at all (reads were a bit faster, and writes were slightly slower). -- These are my opinions and should not be taken as official Skynet policy _________________________________________________________________________ |o| Brad Knowles, Belgacom Skynet NV/SA |o| |o| Systems Architect, Mail/News/FTP/Proxy Admin Rue Col. Bourg, 124 |o| |o| Phone/Fax: +32-2-706.13.11/726.93.11 B-1140 Brussels |o| |o| http://www.skynet.be Belgium |o| \/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/ Unix is like a wigwam -- no Gates, no Windows, and an Apache inside. Unix is very user-friendly. It's just picky who its friends are. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message