From owner-freebsd-performance@freebsd.org Wed Nov 18 21:13:15 2015 Return-Path: Delivered-To: freebsd-performance@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 132AFA32D8A for ; Wed, 18 Nov 2015 21:13:15 +0000 (UTC) (envelope-from dan@langille.org) Received: from clavin1.langille.org (clavin.langille.org [162.208.116.86]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client CN "clavin.langille.org", Issuer "StartCom Class 2 Primary Intermediate Server CA" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id C22E71DDE; Wed, 18 Nov 2015 21:13:14 +0000 (UTC) (envelope-from dan@langille.org) Received: from (clavin1.int.langille.org (clavin1.int.unixathome.org [10.4.7.7]) (Authenticated sender: hidden) with ESMTPSA id 7813F4BE ; Wed, 18 Nov 2015 21:13:00 +0000 (UTC) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 9.1 \(3096.5\)) Subject: Re: Measuring ZFS configuration differences From: Dan Langille In-Reply-To: Date: Wed, 18 Nov 2015 16:12:55 -0500 Cc: freebsd-performance@freebsd.org Content-Transfer-Encoding: quoted-printable Message-Id: References: <8B37FEDC-218A-4071-8CB7-48361BB72B1D@langille.org> <14A0EA61-6545-42BB-910E-62C752D4396C@langille.org> To: Marcelo Araujo X-Mailer: Apple Mail (2.3096.5) X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 18 Nov 2015 21:13:15 -0000 > On Nov 17, 2015, at 9:31 PM, Marcelo Araujo = wrote: >=20 > 2015-11-18 10:23 GMT+08:00 Dan Langille : >=20 >>=20 >>> On Nov 17, 2015, at 8:46 PM, Marcelo Araujo = >> wrote: >>>=20 >>> 2015-11-18 3:14 GMT+08:00 Dan Langille : >>>=20 >>>>=20 >>>> On Nov 12, 2015, at 1:30 AM, Marcelo Araujo = >>>> wrote: >>>>=20 >>>>=20 >>>>=20 >>>> 2015-11-12 6:34 GMT+08:00 Dan Langille : >>>>=20 >>>>> On Oct 12, 2015, at 1:00 PM, Dan Langille = wrote: >>>>>>=20 >>>>>> Following up on the discussions during EuroBSDCon 2015 = (Stockholm) >>>>> during the FreeBSD Developer >>>>>> Summit regarding various ZFS configuration settings, I write to = start >>>>> our implementation phase now that some >>>>>> usual suspects have joined the list. >>>>>>=20 >>>>>> re https://wiki.freebsd.org/201510DevSummit/Performance >>>>>>=20 >>>>>> I think the first order of business is granting access rights to = the >>>>> server (varm) in question: >>>>>>=20 >>>>>> http://dan.langille.org/2015/07/19/varm/ >>>>>>=20 >>>>>> During the workshop, mention was made of serial access. I can = arrange >>>>> that. >>>>>>=20 >>>>>> The server has IPMI, however, my first thought: >>>>>>=20 >>>>>> 1 - connect a USB-serial cable to varm & link that to another = server >> in >>>>> my rack. >>>>>=20 >>>>> Marcelo: At EuroBSDCon, was it you who mentioned a particular >>>>> configuration for the test machine which made >>>>> it easy to configure and run tests? Was it PXE booting or = something? >>>>>=20 >>>>>> 2 - create a jail in that server and give it access to that = serial >>>>> connection >>>>>> 3 - redirect incoming port XYZ to that jail via a public-key-only = ssh >>>>> connection >>>>>> 4 - give people access >>>>>>=20 >>>>>> Any suggestions? >>>>>=20 >>>>> =E2=80=94 >>>>> Dan Langille >>>>> http://langille.org/ >>>>>=20 >>>>>=20 >>>> Hello Dan, >>>>=20 >>>> Yes, was me :) >>>>=20 >>>> I mention about zopkio test framework. >>>> I gave a presentation last weekend at PyCon Hong Kong about it. >>>>=20 >>>> Here is my slides: >>>>=20 >> = http://www.slideshare.net/araujobsd/functional-and-scale-performance-tests= -using-zopkio >>>>=20 >>>> The good of Zopkio is, we can write tests at once and run it as = much as >> we >>>> want in different machines. Also Zopkio depends of Naarad, that can >> parse a >>>> CSV file and create metrics and SLA over those metrics, plot graphs = and >> so >>>> on. Pretty nice tool!!! >>>>=20 >>>> I'm wondering if we could start to test something and maybe show it = at >>>> AsiaBSDCon and BSDCon(Canada) next year? What do you think? >>>> What I need right now would be a list of tests that we want to = perform >> as >>>> well as what parameters we would like to take as metrics to = compare.\ >>>>=20 >>>>=20 >>>> For tests, we can start with this list: >>>> https://github.com/dlangille/zfs_benchmarks/issues >>>>=20 >>>> We can start as soon as I figure out how to provide access to the >>>> testers. See above re serial connection. >>>>=20 >>>> I want to provide access, but I want to keep access restricted to = only >>>> this box and not to the rest of my home LAN. I plan to do this via = a >>>> VLAN. >>>>=20 >>>> I could fire up a Rasperberry Pi and allow ssh into that. Will = that be >>>> enough >>>> power for what you need to do? >>>>=20 >>>>=20 >>> First of all, thanks to share the tests cases. >>>=20 >>> If I use zopkio, the best would be access SSH direct to the target >> machine >>> where I need to run the tests. For zopkio, I need to have my SSH KEY = on >> the >>> target machine. >>=20 >> I am OK with this. >>=20 >>> As I don't know your network, maybe what you could do is: Via >> RasperBerry, >>> forward the SSH to the target machine, I will pass-through via your >>> RasperBerry where you can control the access for the rest of your = LAN. >>>=20 >>> Another approach could be, two different subnets and a firewall. Or = as >> you >>> said, VLANS. >>=20 >> I will be doing VLANS, which have yet to be set up. >>=20 >> The target system will have ZFS pools can be configured for different >> tests (i.e. raidz2 vs raidz3). >> This will involve gpart etc because the drives & pools will need to = be >> 'wiped' between different test >> runs. >>=20 >> I seem to recall someone suggesting PXE boot and configuring the = system >> remotely. Does anyone >> recall that? That aspect of the discussion was not recorded: >> https://wiki.freebsd.org/201510DevSummit/Performance >>=20 >>=20 > Bapt@ mentioned that, this is the way how we are doing in another = project. > But in my point of view, it is not a must for our case! >=20 > The PXE wold be good if we try to test different of OS flavors, or = build > different images. OK. The only thing holding us back is: - adding the air filters to the case - moving to the new switch with the new VLANs It's now a matter of time. =E2=80=94=20 Dan Langille http://langille.org/