From carlsonj@phorcys.east.sun.com Thu Aug 2 12:26:53 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72JQqMY026690 for ; Thu, 2 Aug 2007 12:26:53 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l72JOZHr029351; Thu, 2 Aug 2007 20:24:37 +0100 (BST) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM500009V8Z1N00@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 12:24:35 -0700 (PDT) Received: from phorcys.east.sun.com ([129.148.174.143]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM500J8RV8YEW50@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 12:24:34 -0700 (PDT) Received: from phorcys.east.sun.com (localhost [127.0.0.1]) by phorcys.east.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72JOYG6001918; Thu, 02 Aug 2007 15:24:34 -0400 (EDT) Received: (from carlsonj@localhost) by phorcys.east.sun.com (8.14.1+Sun/8.14.1/Submit) id l72JOYee001915; Thu, 02 Aug 2007 15:24:34 -0400 (EDT) Date: Thu, 02 Aug 2007 15:24:34 -0400 From: James Carlson Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <200708021902.l72J2fAR021784@zion.eng.sun.com> To: Matthew Ahrens Cc: PSARC-ext@sun.com, zfs-team@sun.com Message-id: <18098.12146.191123.179282@gargle.gargle.HOWL> MIME-version: 1.0 X-Mailer: VM 7.01 under Emacs 21.3.1 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> Status: RO Content-Length: 1370 Matthew Ahrens writes: > This project delivers the following executable perl script: > /usr/benchmarks/filebench/filebench Not mentioned here is that this seems to establish a precedent for a directory called /usr/benchmarks, with subdirectories for each benchmark. It seems to be akin to /usr/demo/ (is that right?), but the semantics are somewhat unclear, as it seems unlikely that anyone would deliver more than handful of executables in any directory, and likely that it's just a single file per directory. Are there other things that might fit here? Future plans? An update to filesystem(5) to describe this new hierarchy would be helpful. > User Commands filebench(1) > > NAME > filebench - framework of workloads to measure and compare > filesystem performance Nit: since it's on a non-default path, I think this man page should include the full path. Would it make sense to have a new subsection (say, 1BENCH) to collect these man pages together? Otherwise, I think it seems a little odd to have things in section 1 that aren't going directly into /usr/bin. -- James Carlson, Solaris Networking Sun Microsystems / 1 Network Drive 71.232W Vox +1 781 442 2084 MS UBUR02-212 / Burlington MA 01803-2757 42.496N Fax +1 781 442 1677 From eric.kustarz@sun.com Thu Aug 2 13:28:35 2007 Received: from newsunmail1brm.central.sun.com (newsunmail1brm.Central.Sun.COM [129.147.62.245]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72KSZv9028498 for ; Thu, 2 Aug 2007 13:28:35 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by newsunmail1brm.central.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l72KQGeR026921; Thu, 2 Aug 2007 14:26:17 -0600 (MDT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM50060JY3UOM00@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 13:26:18 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM500FJLY3TQP70@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 13:26:17 -0700 (PDT) Received: from [129.146.229.211] (dhcp-umpk17-229-211.SFBay.Sun.COM [129.146.229.211]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72KQHUx464724; Thu, 02 Aug 2007 13:26:17 -0700 (PDT) Date: Thu, 02 Aug 2007 13:26:10 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18098.12146.191123.179282@gargle.gargle.HOWL> To: James Carlson Cc: Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com, filebench-team@sun.com Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> Status: RO Content-Length: 1718 On Aug 2, 2007, at 12:24 PM, James Carlson wrote: > Matthew Ahrens writes: >> This project delivers the following executable perl script: >> /usr/benchmarks/filebench/filebench > > Not mentioned here is that this seems to establish a precedent for a > directory called /usr/benchmarks, with subdirectories for each > benchmark. Correct. > > It seems to be akin to /usr/demo/ (is that right?), but the semantics > are somewhat unclear, as it seems unlikely that anyone would deliver > more than handful of executables in any directory, and likely that > it's just a single file per directory. > > Are there other things that might fit here? Future plans? Yep. One thing we're definitely planning on adding to /usr/ benchmarks is libMicro. Bart mentioned that he would like more than just a single executable in the libmicro directory. Something like: /usr/benchmarks/libmicro/libmicro (executable) /usr/benchmarks/libmicro/README /usr/benchmarks/libmicro/libmicro.tar.gz > > An update to filesystem(5) to describe this new hierarchy would be > helpful. Ah yes, thanks for pointing that out. > >> User Commands filebench >> (1) >> >> NAME >> filebench - framework of workloads to measure and compare >> filesystem performance > > Nit: since it's on a non-default path, I think this man page should > include the full path. Sure thing. > > Would it make sense to have a new subsection (say, 1BENCH) to collect > these man pages together? Otherwise, I think it seems a little odd to > have things in section 1 that aren't going directly into /usr/bin. Whatever the ARC/manpage experts think is the right way is a-ok with me. eric From carlsonj@phorcys.east.sun.com Thu Aug 2 13:40:25 2007 Received: from newsunmail1brm.central.sun.com (newsunmail1brm.Central.Sun.COM [129.147.62.245]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72KePBw028763 for ; Thu, 2 Aug 2007 13:40:25 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by newsunmail1brm.central.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l72Kc7Nk030431; Thu, 2 Aug 2007 14:38:07 -0600 (MDT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM500305YNLJ200@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 13:38:09 -0700 (PDT) Received: from phorcys.east.sun.com ([129.148.174.143]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM500JGOYNKES90@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 13:38:08 -0700 (PDT) Received: from phorcys.east.sun.com (localhost [127.0.0.1]) by phorcys.east.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72Kc8qm002138; Thu, 02 Aug 2007 16:38:08 -0400 (EDT) Received: (from carlsonj@localhost) by phorcys.east.sun.com (8.14.1+Sun/8.14.1/Submit) id l72Kc8ie002135; Thu, 02 Aug 2007 16:38:08 -0400 (EDT) Date: Thu, 02 Aug 2007 16:38:08 -0400 From: James Carlson Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: To: eric kustarz Cc: Matthew Ahrens , PSARC-ext@Sun.COM, zfs-team@Sun.COM, filebench-team@Sun.COM Message-id: <18098.16560.37467.576659@gargle.gargle.HOWL> MIME-version: 1.0 X-Mailer: VM 7.01 under Emacs 21.3.1 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> Status: RO Content-Length: 1524 eric kustarz writes: > Bart mentioned that he would like more than just a single executable > in the libmicro directory. Something like: > /usr/benchmarks/libmicro/libmicro (executable) > /usr/benchmarks/libmicro/README > /usr/benchmarks/libmicro/libmicro.tar.gz If there's a reasonable man page, what would be in the README? I'm really hesitant to ask what's in that tar.gz file. That doesn't look like a way to deliver packaged software. :-/ If there's a good case to be made that directories would be needed here, then I'm ok with it, but I don't quite see anything that establishes that case. That's particularly true given that the "extra" stuff is tucked neatly away in /usr/lib/ where it won't hurt anyone. Perhaps a more complete explanation of /usr/benchmarks would help. > > Would it make sense to have a new subsection (say, 1BENCH) to collect > > these man pages together? Otherwise, I think it seems a little odd to > > have things in section 1 that aren't going directly into /usr/bin. > > Whatever the ARC/manpage experts think is the right way is a-ok with me. Given that it's a segregated collection of software, I think a segregated set of man pages makes some sense. It'll need a new /usr/man/man.cf entry, and should likely have some sort brief Intro(1BENCH) page. -- James Carlson, Solaris Networking Sun Microsystems / 1 Network Drive 71.232W Vox +1 781 442 2084 MS UBUR02-212 / Burlington MA 01803-2757 42.496N Fax +1 781 442 1677 From jek3@sun.com Thu Aug 2 13:49:42 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72KnfFw029156 for ; Thu, 2 Aug 2007 13:49:42 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l72KlNAD011912; Thu, 2 Aug 2007 21:47:25 +0100 (BST) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM500729Z2ZEI00@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 14:47:23 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM50032CZ2XT230@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 14:47:22 -0600 (MDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72KlKCF468493; Thu, 02 Aug 2007 13:47:21 -0700 (PDT) Date: Thu, 02 Aug 2007 10:44:48 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18098.12146.191123.179282@gargle.gargle.HOWL> To: James Carlson Cc: Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com Message-id: <46B24240.1010301@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 2557 James Carlson wrote: > Matthew Ahrens writes: > >> This project delivers the following executable perl script: >> /usr/benchmarks/filebench/filebench >> > > Not mentioned here is that this seems to establish a precedent for a > directory called /usr/benchmarks, with subdirectories for each > benchmark. > > It seems to be akin to /usr/demo/ (is that right?), but the semantics > are somewhat unclear, as it seems unlikely that anyone would deliver > more than handful of executables in any directory, and likely that > it's just a single file per directory. > > Are there other things that might fit here? Future plans? > > An update to filesystem(5) to describe this new hierarchy would be > helpful. > > >> User Commands filebench(1) >> >> NAME >> filebench - framework of workloads to measure and compare >> filesystem performance >> > > Nit: since it's on a non-default path, I think this man page should > include the full path. > > Would it make sense to have a new subsection (say, 1BENCH) to collect > these man pages together? Otherwise, I think it seems a little odd to > have things in section 1 that aren't going directly into /usr/bin. > Not to pick on "Filebench", but it seems like we are throwing everything, including the kitchen sink, into Solaris. If we had a distribution repository (like Ubuntu/Debian), we would just make it available in the repository, and be done with it. Hopefully, we (Sun and/or OpenSolaris and/or "The State which can not be named") will have such a repository at some time. But alas, we don't have such a repository. We have a couple of "Meta-Clusters", which fit into each other like "Russian Dolls". Placing this in the "Developer Cluster" (rarely used) places it into the "ALL" bundle and ends up a lot of places. It doesn't seem appropriate to push back against Filebench, because we don't have "repository" today. Can we do something (in OpenSolaris) to track which new items are clearly items which would not be included in "standard" bundles? Classifying this as Uncommitted goes a long way to make this feasible. Should I be concerned about more than that? Maybe this is only a *real* concern for something "Committed", but "repository appropriate"? Comments? Oh yea, a real observation on this proposal: Why not Volatile? Benchmarks are often enhanced on a whim and sometime those whims can be incompatible. What is the value (in this rare case) of more stability. - jek3 From danek.duvall@sun.com Thu Aug 2 13:53:44 2007 Received: from newsunmail1brm.central.sun.com (newsunmail1brm.Central.Sun.COM [129.147.62.245]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72KriJZ029237 for ; Thu, 2 Aug 2007 13:53:44 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by newsunmail1brm.central.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l72KpR3J035218; Thu, 2 Aug 2007 14:51:27 -0600 (MDT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM500901Z9P2B00@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 13:51:25 -0700 (PDT) Received: from sfbaymail1sca.SFBay.Sun.COM ([129.145.154.35]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM500FPJZ9PQV80@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 13:51:25 -0700 (PDT) Received: from zruty.sfbay.sun.com (zruty.SFBay.Sun.COM [129.146.168.40]) by sfbaymail1sca.SFBay.Sun.COM (8.13.6+Sun/8.13.6/ENSMAIL,v2.2) with ESMTP id l72KpPRb003686; Thu, 02 Aug 2007 13:51:25 -0700 (PDT) Received: from zruty.sfbay.sun.com (localhost [127.0.0.1]) by zruty.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72KoNIe003033; Thu, 02 Aug 2007 13:50:23 -0700 (PDT) Received: (from dduvall@localhost) by zruty.sfbay.sun.com (8.14.1+Sun/8.14.1/Submit) id l72KoNC2003032; Thu, 02 Aug 2007 13:50:23 -0700 (PDT) Date: Thu, 02 Aug 2007 13:50:23 -0700 From: Danek Duvall Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18098.16560.37467.576659@gargle.gargle.HOWL> To: eric kustarz Cc: zfs-team@sun.com, PSARC-ext@sun.com, filebench-team@sun.com, Matthew Ahrens Message-id: <20070802205023.GB1833@zruty.sfbay.sun.com> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT Content-disposition: inline X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> User-Agent: Mutt/1.5.16 (2007-06-27) Status: RO Content-Length: 305 On Thu, Aug 02, 2007 at 04:38:08PM -0400, James Carlson wrote: > Given that it's a segregated collection of software, Is there a good reason that it be segregated? I guess it'll be nice that the man page will be found without path-twiddling, but why not just have the executable(s) in /usr/bin? Danek From carlsonj@phorcys.east.sun.com Thu Aug 2 13:59:46 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72Kxj3P029582 for ; Thu, 2 Aug 2007 13:59:45 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l72KvKSE016013; Fri, 3 Aug 2007 04:57:28 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM500403ZJRIA00@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 13:57:27 -0700 (PDT) Received: from phorcys.east.sun.com ([129.148.174.143]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM500JI1ZJQEOB0@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 13:57:27 -0700 (PDT) Received: from phorcys.east.sun.com (localhost [127.0.0.1]) by phorcys.east.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72KvQ03002215; Thu, 02 Aug 2007 16:57:26 -0400 (EDT) Received: (from carlsonj@localhost) by phorcys.east.sun.com (8.14.1+Sun/8.14.1/Submit) id l72KvQVT002212; Thu, 02 Aug 2007 16:57:26 -0400 (EDT) Date: Thu, 02 Aug 2007 16:57:26 -0400 From: James Carlson Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B24240.1010301@sun.com> To: Joseph Kowalski Cc: Matthew Ahrens , PSARC-ext@Sun.COM, zfs-team@Sun.COM Message-id: <18098.17718.809239.421164@gargle.gargle.HOWL> MIME-version: 1.0 X-Mailer: VM 7.01 under Emacs 21.3.1 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> Status: RO Content-Length: 1922 Joseph Kowalski writes: > Not to pick on "Filebench", but it seems like we are throwing > everything, including > the kitchen sink, into Solaris. If we had a distribution repository > (like Ubuntu/Debian), > we would just make it available in the repository, and be done with it. Even if we had such a repository, it would not change this case very much. We'd need some place to install that software on the system when fetched from the repository. There are two distinct variables here, and I don't think we should tie them together. The two are the installed location of the software on the system (when the package is opened), and the groupings of packages into logical units for a repository. This case specifies the former, but doesn't specify the latter, and I'm not so sure that the case would necessarily be different even if the latter part were rewhacked radically. Perhaps your argument should be that this belongs in /usr/bin or /usr/sbin instead. I'm unsure that it does. If you choose to install a benchmarking tool from the repository, do you want it showing up in every user's path? If so, why? > Can we do something (in OpenSolaris) to track which new items are > clearly items > which would not be included in "standard" bundles? Classifying this as > Uncommitted > goes a long way to make this feasible. Should I be concerned about more > than that? > Maybe this is only a *real* concern for something "Committed", but > "repository > appropriate"? I think the right way to go about doing this would be to ask about the intended Cluster and Metacluster (if any) for the SUNWfilebench package. Go ahead and get as detailed as you want on that question. ;-} -- James Carlson, Solaris Networking Sun Microsystems / 1 Network Drive 71.232W Vox +1 781 442 2084 MS UBUR02-212 / Burlington MA 01803-2757 42.496N Fax +1 781 442 1677 From jek3@sun.com Thu Aug 2 14:00:11 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72L0A71029633 for ; Thu, 2 Aug 2007 14:00:10 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l72KvnGs016118; Fri, 3 Aug 2007 04:57:53 +0800 (SGT) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM500801ZKE0400@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 14:57:50 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM50038CZKDSZ40@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 14:57:50 -0600 (MDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72KvirD470481; Thu, 02 Aug 2007 13:57:44 -0700 (PDT) Date: Thu, 02 Aug 2007 10:55:11 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <20070802205023.GB1833@zruty.sfbay.sun.com> To: Danek Duvall Cc: eric kustarz , zfs-team@sun.com, PSARC-ext@sun.com, filebench-team@sun.com, Matthew Ahrens Message-id: <46B244AF.8060600@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <20070802205023.GB1833@zruty.sfbay.sun.com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 651 Danek Duvall wrote: > On Thu, Aug 02, 2007 at 04:38:08PM -0400, James Carlson wrote: > > >> Given that it's a segregated collection of software, >> > > Is there a good reason that it be segregated? I guess it'll be nice that > the man page will be found without path-twiddling, but why not just have > the executable(s) in /usr/bin? > > Danek > I'd **guess** that the potential of name-conflicts between benchmarks is pretty high. I think I've seen objects called "report" in more benchmarks than not, and a lot of benchmarks don't have a single object to control everything. That said, I'd like the project team to say more. - jek3 From jek3@sun.com Thu Aug 2 14:14:18 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72LEHoc029921 for ; Thu, 2 Aug 2007 14:14:18 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l72LC0sY022005; Thu, 2 Aug 2007 22:12:01 +0100 (BST) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600501080DM00@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 14:12:00 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600J1F080EWB0@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 14:12:00 -0700 (PDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72LBxHq474306; Thu, 02 Aug 2007 14:11:59 -0700 (PDT) Date: Thu, 02 Aug 2007 11:09:26 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18098.17718.809239.421164@gargle.gargle.HOWL> To: James Carlson Cc: Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com Message-id: <46B24806.70201@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 2574 James Carlson wrote: > Joseph Kowalski writes: > >> Not to pick on "Filebench", but it seems like we are throwing >> everything, including >> the kitchen sink, into Solaris. If we had a distribution repository >> (like Ubuntu/Debian), >> we would just make it available in the repository, and be done with it. >> > > Even if we had such a repository, it would not change this case very > much. We'd need some place to install that software on the system > when fetched from the repository. > > There are two distinct variables here, and I don't think we should tie > them together. The two are the installed location of the software on > the system (when the package is opened), and the groupings of packages > into logical units for a repository. > > This case specifies the former, but doesn't specify the latter, and > I'm not so sure that the case would necessarily be different even if > the latter part were rewhacked radically. > Hummm, PSARC is lax about this, but other ARCs are more concerned about the name of the packages - SUNWfoobar - than PSARC. Sometimes we do show interest. I don't think SAC says anything about what Meta-Cluster the packages end up in. I would like to think it is a Marketing/Management concern, but I have a bad feeling that this isn't anybody's concern, and this just happens. If there was control of the Meta-Clusters, one check-box should be "none". So yes, I agree with your assesment of FileBench. I'm just pointing out a general "hole" in our broader processes which are being stressed by the influx of FOSS. > Perhaps your argument should be that this belongs in /usr/bin or > /usr/sbin instead. I'm unsure that it does. If you choose to install > a benchmarking tool from the repository, do you want it showing up in > every user's path? If so, why? > No. I think this specific case needs to resolve the "to bin or not to bin" question, independently of an repository concerns. >> Can we do something (in OpenSolaris) to track which new items are >> clearly items >> which would not be included in "standard" bundles? Classifying this as >> Uncommitted >> goes a long way to make this feasible. Should I be concerned about more >> than that? >> Maybe this is only a *real* concern for something "Committed", but >> "repository >> appropriate"? >> > > I think the right way to go about doing this would be to ask about the > intended Cluster and Metacluster (if any) for the SUNWfilebench > package. Go ahead and get as detailed as you want on that question. > ;-} > :-) - jek3 From jek3@sun.com Thu Aug 2 14:28:08 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72LS7xT000039 for ; Thu, 2 Aug 2007 14:28:08 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l72LPTjx027146; Fri, 3 Aug 2007 05:25:48 +0800 (SGT) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM60091N0UXI000@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 15:25:45 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM60032U0UWSV50@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 15:25:44 -0600 (MDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l72LPhpG476367; Thu, 02 Aug 2007 14:25:43 -0700 (PDT) Date: Thu, 02 Aug 2007 11:23:11 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B24806.70201@sun.com> To: Joseph Kowalski Cc: James Carlson , Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com Message-id: <46B24B3F.2030804@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B24806.70201@sun.com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 780 Joseph Kowalski wrote: > James Carlson wrote: ... > >> Perhaps your argument should be that this belongs in /usr/bin or >> /usr/sbin instead. I'm unsure that it does. If you choose to install >> a benchmarking tool from the repository, do you want it showing up in >> every user's path? If so, why? >> > No. I think this specific case needs to resolve the "to bin or not to > bin" question, > independently of an repository concerns. Talking to myself (replying to myself), I think this "benchmark" has to carry the burden of defining the semantics and "expectations" of a /usr/benchmark (or whatever) directory. Others seem to have taken up that gautlet, so I thought I'd sit back awhile and read what they had to say. (Yes, this is my less-evil twin :-) ) - jek3 From Artem.Kachitchkin@sun.com Thu Aug 2 16:26:36 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l72NQZs9003153 for ; Thu, 2 Aug 2007 16:26:35 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l72NODtr008133; Fri, 3 Aug 2007 07:24:19 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM6001036CILU00@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 16:24:18 -0700 (PDT) Received: from sca-es-mail-2.sun.com ([192.18.43.133]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM6001QU6CH7H10@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 16:24:17 -0700 (PDT) Received: from fe-sfbay-10.sun.com ([192.18.43.129]) by sca-es-mail-2.sun.com (8.13.7+Sun/8.12.9) with ESMTP id l72NOHsl010446; Thu, 02 Aug 2007 16:24:17 -0700 (PDT) Received: from conversion-daemon.fe-sfbay-10.sun.com by fe-sfbay-10.sun.com (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) id <0JM600G016BHKZ00@fe-sfbay-10.sun.com> (original mail from Artem.Kachitchkin@Sun.COM); Thu, 02 Aug 2007 16:24:17 -0700 (PDT) Received: from [192.168.1.100] ([75.6.236.174]) by fe-sfbay-10.sun.com (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) with ESMTPSA id <0JM6000IF6C41NE0@fe-sfbay-10.sun.com>; Thu, 02 Aug 2007 16:24:04 -0700 (PDT) Date: Thu, 02 Aug 2007 16:23:52 -0700 From: Artem Kachitchkine Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B24B3F.2030804@sun.com> Sender: Artem.Kachitchkin@sun.com To: Joseph Kowalski Cc: James Carlson , Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com Message-id: <46B26788.2020402@sun.com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B24806.70201@sun.com> <46B24B3F.2030804@sun.com> User-Agent: Mozilla/5.0 Gecko/20040113 Status: RO Content-Length: 442 FWIW (likely not much), this reminds of the 'games' class of applications, hinted at in the Filesystem Hierarchy Standard, which was adopted in LSB. /usr/games/ binaries /usr/share/games/ static data /usr/lib/games/ shared libs /var/games/ high scores The 'benchmarks' class and its layout appear intuitively similar to that, except games have their own man page section 6 (shared with demos in Solaris). -Artem From Eric.Kustarz@Sun.COM Thu Aug 2 17:13:52 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l730DpTr003905 for ; Thu, 2 Aug 2007 17:13:52 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l730BIqa024571; Fri, 3 Aug 2007 08:11:31 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM60051H8J6X200@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 17:11:30 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM60046Q8J64I80@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 17:11:30 -0700 (PDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l730BT9n502049; Thu, 02 Aug 2007 17:11:29 -0700 (PDT) Date: Thu, 02 Aug 2007 17:11:21 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18098.16560.37467.576659@gargle.gargle.HOWL> To: James Carlson Cc: Matthew Ahrens , PSARC-ext@Sun.COM, "zfs-team@sun.com" , filebench-team@Sun.COM, Michael Pogue , Bart Smaalders Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> Status: RO Content-Length: 1725 On Aug 2, 2007, at 1:38 PM, James Carlson wrote: > eric kustarz writes: >> Bart mentioned that he would like more than just a single executable >> in the libmicro directory. Something like: >> /usr/benchmarks/libmicro/libmicro (executable) >> /usr/benchmarks/libmicro/README >> /usr/benchmarks/libmicro/libmicro.tar.gz > > If there's a reasonable man page, what would be in the README? > > I'm really hesitant to ask what's in that tar.gz file. That doesn't > look like a way to deliver packaged software. :-/ > > If there's a good case to be made that directories would be needed > here, then I'm ok with it, but I don't quite see anything that > establishes that case. That's particularly true given that the > "extra" stuff is tucked neatly away in /usr/lib/ where it won't hurt > anyone. > > Perhaps a more complete explanation of /usr/benchmarks would help. Sure thing. If we allow benchmarks to have their own directory (such as /usr/benchmarks/libmicro/), then we can allow that benchmark to do what it wants in that directory. This would make porting much easier, less mangling of the source. It turns out that in filebench there is just a simple #define that specifies where everything under /usr/lib/filebench lives. So moving from platform to platform will be easy (if /usr/lib/filebench is not an option). Other benchmarks may have harder issues when having to place the main executable (if there only is one) in /usr/benchmarks, and the rest of their private files in /usr/lib/. Bart can comment on his plans for having a real directory for libMicro to utilize. Having /usr/benchmarks essentially be /usr/benchmarks/bin seemed overly restrictive. eric From eric.kustarz@sun.com Thu Aug 2 17:24:54 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l730OsJk004064 for ; Thu, 2 Aug 2007 17:24:54 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l730MY2L019384; Fri, 3 Aug 2007 01:22:35 +0100 (BST) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600K0D91M5B00@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 18:22:34 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600JE191KTN00@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 18:22:32 -0600 (MDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l730MWka503712; Thu, 02 Aug 2007 17:22:32 -0700 (PDT) Date: Thu, 02 Aug 2007 17:22:24 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B24240.1010301@sun.com> To: Joseph Kowalski Cc: James Carlson , Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com, filebench-team@sun.com Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> Status: RO Content-Length: 960 On Aug 2, 2007, at 1:44 PM, Joseph Kowalski wrote: > > Oh yea, a real observation on this proposal: > > Why not Volatile? Benchmarks are often enhanced on a whim and > sometime > those whims can be incompatible. What is the value (in this > rare case) of more > stability. > > - jek3 > This is in regards to the Location in the "Interfaces" sections, correct? 3. Interfaces /usr/benchmarks/filebench/filebench Location: Committed Invocation: Uncommitted Human-readable output: Not an Interface /usr/share/man/man1/filebench.1 Location Uncommitted So if we classify this as "Volatile" then we can change whatever /usr/ benchmarks/filebench/filebench does in an incompatible manner with previous versions? But if we go with "Committed", then we cannot? Yes, i've read: http://www.opensolaris.org/os/community/arc/policies/interface-taxonomy/ but i'd like clarification :) eric From David.Comay@sun.com Thu Aug 2 17:39:57 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l730duAD004461 for ; Thu, 2 Aug 2007 17:39:57 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l730bU3Y003119; Fri, 3 Aug 2007 08:37:37 +0800 (SGT) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600K0L9QLZA00@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 18:37:33 -0600 (MDT) Received: from izimbra.SFBay.Sun.COM ([129.146.226.141]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600JMB9QKTF10@brm-avmta-1.central.sun.com>; Thu, 02 Aug 2007 18:37:32 -0600 (MDT) Received: from localhost (localhost [127.0.0.1]) by izimbra.SFBay.Sun.COM (8.14.1+Sun/8.14.1) with ESMTP id l730bRlO101640; Thu, 02 Aug 2007 17:37:28 -0700 (PDT) Date: Thu, 02 Aug 2007 17:37:27 -0700 (PDT) From: David.Comay@sun.com Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B24240.1010301@sun.com> Sender: comay@izimbra.sfbay.sun.com To: Joseph Kowalski Cc: James Carlson , zfs-team@sun.com, PSARC-ext@sun.com, Matthew Ahrens Message-id: MIME-version: 1.0 Content-type: TEXT/PLAIN; charset=US-ASCII; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> Status: RO Content-Length: 651 > Can we do something (in OpenSolaris) to track which new items are > clearly items > which would not be included in "standard" bundles? Classifying this as > Uncommitted > goes a long way to make this feasible. Should I be concerned about more > than that? > Maybe this is only a *real* concern for something "Committed", but > "repository > appropriate"? Some of this discussion has been taking place on the indiana-discuss@opensolaris.org making list. The current thinking is that there will be a CD installation that provides a (supported) core from which you can then access one or more network repositories that contain other packages. dsc From eric.kustarz@sun.com Thu Aug 2 19:39:27 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l732dQ45006046 for ; Thu, 2 Aug 2007 19:39:26 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l732b3eb001854; Fri, 3 Aug 2007 03:37:06 +0100 (BST) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600G01F9SYN00@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 19:37:04 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.63]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM6005EDF9RI280@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 19:37:03 -0700 (PDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l732b37M517062; Thu, 02 Aug 2007 19:37:03 -0700 (PDT) Date: Thu, 02 Aug 2007 19:36:55 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B244AF.8060600@sun.com> To: Joseph Kowalski Cc: Danek Duvall , zfs-team@sun.com, PSARC-ext@sun.com, filebench-team@sun.com, Matthew Ahrens , Bart Smaalders , Michael Pogue Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <20070802205023.GB1833@zruty.sfbay.sun.com> <46B244AF.8060600@sun.com> Status: RO Content-Length: 1123 On Aug 2, 2007, at 1:55 PM, Joseph Kowalski wrote: > Danek Duvall wrote: >> On Thu, Aug 02, 2007 at 04:38:08PM -0400, James Carlson wrote: >> >> >>> Given that it's a segregated collection of software, >>> >> >> Is there a good reason that it be segregated? I guess it'll be >> nice that >> the man page will be found without path-twiddling, but why not >> just have >> the executable(s) in /usr/bin? >> >> Danek >> > I'd **guess** that the potential of name-conflicts between > benchmarks is pretty > high. I think I've seen objects called "report" in more benchmarks > than not, and > a lot of benchmarks don't have a single object to control everything. > > That said, I'd like the project team to say more. > We had originally planned on putting the executable 'filebench' in / usr/bin. After talking to Bart and Michael, we decided to go with / usr/benchmarks. This would give us a clear way of delivering reliable (compiled correctly) and meaningful benchmarks to our users. I think its a big win to have users go to /usr/benchmarks instead of www.google.com to do performance analysis. eric From jek3@sun.com Thu Aug 2 20:25:27 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l733PQF3006586 for ; Thu, 2 Aug 2007 20:25:26 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l733Mwps001158; Fri, 3 Aug 2007 11:23:06 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600101HEF8J00@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 20:23:03 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600GUUHEFIH90@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 20:23:03 -0700 (PDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l733N2mr521557; Thu, 02 Aug 2007 20:23:02 -0700 (PDT) Date: Thu, 02 Aug 2007 17:20:30 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: To: eric kustarz Cc: James Carlson , Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com, filebench-team@sun.com Message-id: <46B29EFE.2060701@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 2302 eric kustarz wrote: > > On Aug 2, 2007, at 1:44 PM, Joseph Kowalski wrote: >> >> Oh yea, a real observation on this proposal: >> >> Why not Volatile? Benchmarks are often enhanced on a whim and >> sometime >> those whims can be incompatible. What is the value (in this rare >> case) of more >> stability. >> >> - jek3 >> > > This is in regards to the Location in the "Interfaces" sections, correct? No. Actually for the "Invokation: Uncommitted" line seems more like it. > 3. Interfaces > > /usr/benchmarks/filebench/filebench > Location: Committed > Invocation: Uncommitted > Human-readable output: Not an Interface The fact you used "Not an Interface" shows that you read the taxonomy. :-) > /usr/share/man/man1/filebench.1 > Location Uncommitted > > So if we classify this as "Volatile" then we can change whatever > /usr/benchmarks/filebench/filebench does in an incompatible manner > with previous versions? > > But if we go with "Committed", then we cannot? > > Yes, i've read: > http://www.opensolaris.org/os/community/arc/policies/interface-taxonomy/ > but i'd like clarification :) > > eric I can't get too wrapped up between Committed/Uncommitted for "Location". Uncommitted makes it a little easier to remove it completely. We would probably be smoking something if were to just move its location (which is why we gotta get it right). What I'm not seeing why we should do anything to make this harder to just suck in the latest version. Who cares if a benchmark is incompatable with its previous version? Anybody who understands benchmarks even a little bit, they have to always cite the benchmark version. I know this kinda goes against our DNA, but I think being newer is better than stable for benchmarks. We usually don't cite a stability level for a man page. Its kinda recursive anyway, after all, the man page is the thing which tells us what the stabilities are. :-) So, my *suggestion* is: 3. Interfaces /usr/benchmarks/filebench/filebench Location: Committed (but Uncommitted also seems OK.) Invocation: Volatile Human-readable output: Not an Interface (but Volatile can also be used) Others may feel differently. - jek3 From jek3@sun.com Thu Aug 2 20:27:41 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l733Re76006600 for ; Thu, 2 Aug 2007 20:27:40 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l733PKiA002384; Fri, 3 Aug 2007 11:25:20 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600101HI7CM00@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 20:25:20 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600GBTHI7II90@nwk-avmta-2.sfbay.sun.com>; Thu, 02 Aug 2007 20:25:19 -0700 (PDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l733PIoW522163; Thu, 02 Aug 2007 20:25:18 -0700 (PDT) Date: Thu, 02 Aug 2007 17:22:46 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: To: David.Comay@sun.com Cc: James Carlson , zfs-team@sun.com, PSARC-ext@sun.com, Matthew Ahrens Message-id: <46B29F86.1000705@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 847 David.Comay@sun.com wrote: >> Can we do something (in OpenSolaris) to track which new items are >> clearly items >> which would not be included in "standard" bundles? Classifying this as >> Uncommitted >> goes a long way to make this feasible. Should I be concerned about more >> than that? >> Maybe this is only a *real* concern for something "Committed", but >> "repository >> appropriate"? > > Some of this discussion has been taking place on the > indiana-discuss@opensolaris.org making list. The current thinking is > that there will be a CD installation that provides a (supported) core > from which you can then access one or more network repositories that > contain other packages. > > dsc Right, but this is probably at least 6 months a way, probably significantly longer. I'm probing around what we might do in the interim. - jek3 From John.Plocher@Sun.COM Thu Aug 2 21:11:08 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l734B7jV007100 for ; Thu, 2 Aug 2007 21:11:08 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l7348k5p016976; Fri, 3 Aug 2007 12:08:51 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM60030FJIOZD00@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 21:08:48 -0700 (PDT) Received: from sca-es-mail-2.sun.com ([192.18.43.133]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM6005FQJIJI2B0@nwk-avmta-1.sfbay.Sun.COM>; Thu, 02 Aug 2007 21:08:47 -0700 (PDT) Received: from fe-sfbay-09.sun.com ([192.18.43.129]) by sca-es-mail-2.sun.com (8.13.7+Sun/8.12.9) with ESMTP id l7348hd6024388; Thu, 02 Aug 2007 21:08:43 -0700 (PDT) Received: from conversion-daemon.fe-sfbay-09.sun.com by fe-sfbay-09.sun.com (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) id <0JM600401JGL1P00@fe-sfbay-09.sun.com> (original mail from John.Plocher@Sun.COM); Thu, 02 Aug 2007 21:08:43 -0700 (PDT) Received: from [192.168.168.4] ([66.166.204.98]) by fe-sfbay-09.sun.com (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) with ESMTPSA id <0JM60077BJIIXYA0@fe-sfbay-09.sun.com>; Thu, 02 Aug 2007 21:08:43 -0700 (PDT) Date: Thu, 02 Aug 2007 21:08:41 -0700 From: John Plocher Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18098.17718.809239.421164@gargle.gargle.HOWL> Sender: John.Plocher@Sun.COM To: James Carlson Cc: Joseph Kowalski , zfs-team@Sun.COM, PSARC-ext@Sun.COM, Matthew Ahrens Message-id: <46B2AA49.4060106@Sun.Com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> User-Agent: Thunderbird 1.5.0.12 (Macintosh/20070509) Status: RO Content-Length: 585 James Carlson wrote: > Joseph Kowalski writes: >> ... > Perhaps your argument should be that this belongs in /usr/bin or > /usr/sbin instead. > Why shouldn't this all go under /usr/demo (for optional demo programs and their data) or under /opt (add on application programs)? This *certainly* is not stuff that A) belongs in $PATH for everyone, B) is a core part of the OS, and C) is special enough to carve out a new namespace under /usr This seems to me to be a poster child for /opt/benchmarks/filebench or even /opt/filebench. -1 to /usr/benchmarks. -John From Jeff.Bonwick@sun.com Fri Aug 3 00:30:44 2007 Received: from newsunmail1brm.central.sun.com (newsunmail1brm.Central.Sun.COM [129.147.62.245]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l737UicV009717 for ; Fri, 3 Aug 2007 00:30:44 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by newsunmail1brm.central.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l737SNMx051288; Fri, 3 Aug 2007 01:28:26 -0600 (MDT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600M1FSRDHG00@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 00:28:25 -0700 (PDT) Received: from engmail3mpk.sfbay.Sun.COM ([129.146.11.26]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600L16SRD8R60@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 00:28:25 -0700 (PDT) Received: from zion.eng.sun.com (zion.SFBay.Sun.COM [129.146.17.75]) by engmail3mpk.sfbay.Sun.COM (8.13.6+Sun/8.13.6/ENSMAIL,v2.2) with ESMTP id l737SOLD020020; Fri, 03 Aug 2007 00:28:24 -0700 (PDT) Received: from zion.eng.sun.com (localhost [127.0.0.1]) by zion.eng.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l737SOOX023220; Fri, 03 Aug 2007 00:28:24 -0700 (PDT) Received: (from bonwick@localhost) by zion.eng.sun.com (8.14.1+Sun/8.14.1/Submit) id l737SOVE023219; Fri, 03 Aug 2007 00:28:24 -0700 (PDT) Date: Fri, 03 Aug 2007 00:28:24 -0700 From: Jeff Bonwick Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B2AA49.4060106@Sun.Com> To: John Plocher Cc: James Carlson , Joseph Kowalski , zfs-team@sun.com, PSARC-ext@sun.com, Matthew Ahrens Message-id: <20070803072824.GC22964@eng.sun.com> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT Content-disposition: inline X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> X-Authentication-warning: zion.eng.sun.com: bonwick set sender to Jeff.Bonwick@sun.com using -f User-Agent: Mutt/1.5.14 (2007-02-12) Status: RO Content-Length: 1276 Does it matter? I mean, big picture, is it even worthy of discussion? VMware's long-term goal is to become an application platform that obsoletes all existing operating systems. (Did you know they're currently developing JVM, Rails, etc that run natively on ESX?) Linux is trying to eradicate our developer community. Intel and AMD are trying to make SPARC completely irrelevant. And we're arguing about /usr/benchmarks vs. /opt/benchmarks? I'm all for defending architectural purity when there's some fundamental principle at stake. If there's one here, please enlighten me. Jeff On Thu, Aug 02, 2007 at 09:08:41PM -0700, John Plocher wrote: > James Carlson wrote: > >Joseph Kowalski writes: > >>... > >Perhaps your argument should be that this belongs in /usr/bin or > >/usr/sbin instead. > > > > Why shouldn't this all go under /usr/demo (for optional > demo programs and their data) or under /opt (add on > application programs)? > > This *certainly* is not stuff that > A) belongs in $PATH for everyone, > B) is a core part of the OS, and > C) is special enough to carve out a new namespace under /usr > > This seems to me to be a poster child for /opt/benchmarks/filebench > or even /opt/filebench. > > -1 to /usr/benchmarks. > > -John > > From Darren.Moffat@sun.com Fri Aug 3 02:51:50 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l739pnXN011635 for ; Fri, 3 Aug 2007 02:51:49 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l739nTe5011787; Fri, 3 Aug 2007 10:49:30 +0100 (BST) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600C01ZAI1F00@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 02:49:30 -0700 (PDT) Received: from gmp-ea-fw-1.sun.com ([129.156.42.5]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM600AEEZAGBW20@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 02:49:30 -0700 (PDT) Received: from d1-emea-09.sun.com (d1-emea-09.sun.com [192.18.2.119]) by gmp-ea-fw-1.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l739nSvq019746; Fri, 03 Aug 2007 09:49:28 +0000 (GMT) Received: from conversion-daemon.d1-emea-09.sun.com by d1-emea-09.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JM600H01ZA4IG00@d1-emea-09.sun.com> (original mail from Darren.Moffat@Sun.COM); Fri, 03 Aug 2007 10:49:28 +0100 (BST) Received: from [129.156.173.21] by d1-emea-09.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JM6003D3ZAFKC30@d1-emea-09.sun.com>; Fri, 03 Aug 2007 10:49:28 +0100 (BST) Date: Fri, 03 Aug 2007 10:49:27 +0100 From: Darren J Moffat Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: Sender: Darren.Moffat@sun.com To: eric kustarz Cc: James Carlson , Matthew Ahrens , psarc-ext@sun.com, "zfs-team@sun.com" , filebench-team@sun.com, Michael Pogue , Bart Smaalders Message-id: <46B2FA27.1040804@Sun.COM> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> User-Agent: Thunderbird 2.0.0.0 (X11/20070605) Status: RO Content-Length: 685 eric kustarz wrote: > Sure thing. If we allow benchmarks to have their own directory (such as > /usr/benchmarks/libmicro/), then we can allow that benchmark to do what > it wants in that directory. This would make porting much easier, less > mangling of the source. > > It turns out that in filebench there is just a simple #define that > specifies where everything under /usr/lib/filebench lives. So moving > from platform to platform will be easy (if /usr/lib/filebench is not an > option). Specifically for filebench is there are reason to spread it around with parts in /usr/benchmarks/ and parts in /usr/lib ? I don't yet see any value in that. -- Darren J Moffat From Darren.Moffat@sun.com Fri Aug 3 02:54:39 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l739sc9B012008 for ; Fri, 3 Aug 2007 02:54:39 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l739qH3j010328; Fri, 3 Aug 2007 17:52:21 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM600I0BZF89K00@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 02:52:20 -0700 (PDT) Received: from gmp-ea-fw-1.sun.com ([129.156.42.6]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM6008UMZF6RQB0@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 02:52:19 -0700 (PDT) Received: from d1-emea-09.sun.com ([192.18.2.119]) by gmp-ea-fw-1.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l739qIh1010153; Fri, 03 Aug 2007 09:52:18 +0000 (GMT) Received: from conversion-daemon.d1-emea-09.sun.com by d1-emea-09.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JM600H01ZA4IG00@d1-emea-09.sun.com> (original mail from Darren.Moffat@Sun.COM); Fri, 03 Aug 2007 10:52:18 +0100 (BST) Received: from [129.156.173.21] by d1-emea-09.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JM6003DPZF5KC30@d1-emea-09.sun.com>; Fri, 03 Aug 2007 10:52:18 +0100 (BST) Date: Fri, 03 Aug 2007 10:52:17 +0100 From: Darren J Moffat Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B2AA49.4060106@Sun.Com> Sender: Darren.Moffat@sun.com To: John Plocher Cc: James Carlson , Joseph Kowalski , zfs-team@sun.com, psarc-ext@sun.com, Matthew Ahrens Message-id: <46B2FAD1.506@Sun.COM> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> User-Agent: Thunderbird 2.0.0.0 (X11/20070605) Status: RO Content-Length: 586 John Plocher wrote: > James Carlson wrote: >> Joseph Kowalski writes: >>> ... >> Perhaps your argument should be that this belongs in /usr/bin or >> /usr/sbin instead. > > Why shouldn't this all go under /usr/demo (for optional > demo programs and their data) or under /opt (add on > application programs)? Not in /opt because it is part of the WOS. /opt is really only appropriate for unbundled software - yes I know we have some legacy small stuff in there but it is purely legacy stuff now and /opt is almost pristine on a fresh install like it should be. -- Darren J Moffat From eric.kustarz@sun.com Fri Aug 3 08:42:00 2007 Received: from sunmail3mpk.sfbay.sun.com (sunmail3mpk.SFBay.Sun.COM [129.146.11.52]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73Fg09b017204 for ; Fri, 3 Aug 2007 08:42:00 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail3mpk.sfbay.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73Fdh7f029132; Fri, 3 Aug 2007 08:39:43 -0700 (PDT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM700K0DFI7B400@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 08:39:43 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.63]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700ELJFI6OS30@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 08:39:42 -0700 (PDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73FdfEt589231; Fri, 03 Aug 2007 08:39:42 -0700 (PDT) Date: Fri, 03 Aug 2007 08:39:35 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B29EFE.2060701@sun.com> To: Joseph Kowalski Cc: James Carlson , Matthew Ahrens , PSARC-ext@sun.com, zfs-team@sun.com, filebench-team@sun.com Message-id: <6862E68A-8ECD-4DAA-8E88-CEA5405C3B76@sun.com> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <46B29EFE.2060701@sun.com> Status: RO Content-Length: 511 On Aug 2, 2007, at 8:20 PM, Joseph Kowalski wrote: > > So, my *suggestion* is: > > 3. Interfaces > > /usr/benchmarks/filebench/filebench > Location: Committed (but > Uncommitted also seems OK.) > Invocation: Volatile > Human-readable output: Not an Interface (but Volatile can > also be used) > > Others may feel differently. > > - jek3 > Thanks for the taxonomy breakdown. Given your input, I very much agree with this suggestion. eric From Eric.Kustarz@sun.com Fri Aug 3 09:05:41 2007 Received: from sunmail2sca.sfbay.sun.com (sunmail2sca.SFBay.Sun.COM [129.145.155.234]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73G5fON017799 for ; Fri, 3 Aug 2007 09:05:41 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail2sca.sfbay.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73G3FK5002879; Fri, 3 Aug 2007 09:03:22 -0700 (PDT) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM70081FGLIMV00@brm-avmta-1.central.sun.com>; Fri, 03 Aug 2007 10:03:18 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM7005RPGLHT170@brm-avmta-1.central.sun.com>; Fri, 03 Aug 2007 10:03:17 -0600 (MDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73G3GUi594163; Fri, 03 Aug 2007 09:03:16 -0700 (PDT) Date: Fri, 03 Aug 2007 09:03:09 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B2FA27.1040804@Sun.COM> To: Darren J Moffat Cc: James Carlson , Matthew Ahrens , psarc-ext@sun.com, "zfs-team@sun.com" , filebench-team@sun.com, Michael Pogue , Bart Smaalders Message-id: <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> Status: RO Content-Length: 1384 On Aug 3, 2007, at 2:49 AM, Darren J Moffat wrote: > eric kustarz wrote: >> Sure thing. If we allow benchmarks to have their own directory >> (such as /usr/benchmarks/libmicro/), then we can allow that >> benchmark to do what it wants in that directory. This would make >> porting much easier, less mangling of the source. >> It turns out that in filebench there is just a simple #define that >> specifies where everything under /usr/lib/filebench lives. So >> moving from platform to platform will be easy (if /usr/lib/ >> filebench is not an option). > > Specifically for filebench is there are reason to spread it around > with parts in /usr/benchmarks/ and parts in /usr/lib ? I don't yet > see any value in that. > Having to use /usr/lib was historical (back when we had /usr/bin/ filebench). If others would like, i can certainly put everything in /usr/ benchmarks/filebench. That might be a nice precedent to set for the / usr/benchmarks directory. We would then have the following executables: /usr/benchmarks/filebench/bin/filebench (executable perl script) /usr/benchmarks/filebench/bin/go_filebench (isaexec link) /usr/benchmarks/filebench/bin/{i386,amd64,sparcv9}/go_filebench (executable binary) And the following subdirectories: /usr/benchmarks/filebench/config /usr/benchmarks/filebench/scripts /usr/benchmarks/filebench/workloads eric From Darren.Moffat@sun.com Fri Aug 3 09:13:13 2007 Received: from sunmail3mpk.sfbay.sun.com (sunmail3mpk.SFBay.Sun.COM [129.146.11.52]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73GDDvM017904 for ; Fri, 3 Aug 2007 09:13:13 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail3mpk.sfbay.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73GAvpR008236; Fri, 3 Aug 2007 09:10:57 -0700 (PDT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM70000FGY93N00@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 09:10:57 -0700 (PDT) Received: from gmp-ea-fw-1.sun.com ([129.156.42.5]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700EU3GY7ON50@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 09:10:56 -0700 (PDT) Received: from d1-emea-09.sun.com (d1-emea-09.sun.com [192.18.2.119]) by gmp-ea-fw-1.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l73GAsH8027279; Fri, 03 Aug 2007 16:10:54 +0000 (GMT) Received: from conversion-daemon.d1-emea-09.sun.com by d1-emea-09.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JM700K01GVG6300@d1-emea-09.sun.com> (original mail from Darren.Moffat@Sun.COM); Fri, 03 Aug 2007 17:10:54 +0100 (BST) Received: from [129.156.173.21] by d1-emea-09.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JM700BD4GY67Y10@d1-emea-09.sun.com>; Fri, 03 Aug 2007 17:10:54 +0100 (BST) Date: Fri, 03 Aug 2007 17:10:54 +0100 From: Darren J Moffat Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> Sender: Darren.Moffat@sun.com To: eric kustarz Cc: James Carlson , Matthew Ahrens , psarc-ext@sun.com, "zfs-team@sun.com" , filebench-team@sun.com, Michael Pogue , Bart Smaalders Message-id: <46B3538E.7050406@Sun.COM> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> User-Agent: Thunderbird 2.0.0.0 (X11/20070605) Status: RO Content-Length: 1108 eric kustarz wrote: > > On Aug 3, 2007, at 2:49 AM, Darren J Moffat wrote: > >> eric kustarz wrote: >>> Sure thing. If we allow benchmarks to have their own directory (such >>> as /usr/benchmarks/libmicro/), then we can allow that benchmark to do >>> what it wants in that directory. This would make porting much >>> easier, less mangling of the source. >>> It turns out that in filebench there is just a simple #define that >>> specifies where everything under /usr/lib/filebench lives. So moving >>> from platform to platform will be easy (if /usr/lib/filebench is not >>> an option). >> >> Specifically for filebench is there are reason to spread it around >> with parts in /usr/benchmarks/ and parts in /usr/lib ? I don't yet >> see any value in that. >> > > Having to use /usr/lib was historical (back when we had > /usr/bin/filebench). > > If others would like, i can certainly put everything in > /usr/benchmarks/filebench. That might be a nice precedent to set for > the /usr/benchmarks directory. That seems like a good precedent to me for /usr/benchmarks/ -- Darren J Moffat From John.Plocher@Sun.COM Fri Aug 3 10:13:05 2007 Received: from sunmail3mpk.sfbay.sun.com (sunmail3mpk.SFBay.Sun.COM [129.146.11.52]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73HD5Of019271 for ; Fri, 3 Aug 2007 10:13:05 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail3mpk.sfbay.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73HAmYM023530; Fri, 3 Aug 2007 10:10:49 -0700 (PDT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM700L0PJQ0C500@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 10:10:48 -0700 (PDT) Received: from sca-es-mail-2.sun.com ([192.18.43.133]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700I1RJQ0J950@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 10:10:48 -0700 (PDT) Received: from fe-sfbay-10.sun.com ([192.18.43.129]) by sca-es-mail-2.sun.com (8.13.7+Sun/8.12.9) with ESMTP id l73HAlMB022108; Fri, 03 Aug 2007 10:10:47 -0700 (PDT) Received: from conversion-daemon.fe-sfbay-10.sun.com by fe-sfbay-10.sun.com (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) id <0JM700J01JMHZC00@fe-sfbay-10.sun.com> (original mail from John.Plocher@Sun.COM); Fri, 03 Aug 2007 10:10:47 -0700 (PDT) Received: from [192.168.168.4] ([66.166.204.98]) by fe-sfbay-10.sun.com (Sun Java System Messaging Server 6.2-8.04 (built Feb 28 2007)) with ESMTPSA id <0JM70092WJPYGZ40@fe-sfbay-10.sun.com>; Fri, 03 Aug 2007 10:10:47 -0700 (PDT) Date: Fri, 03 Aug 2007 10:10:46 -0700 From: John Plocher Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B2FAD1.506@Sun.COM> Sender: John.Plocher@Sun.COM To: Darren J Moffat Cc: James Carlson , Joseph Kowalski , zfs-team@Sun.COM, PSARC-ext@Sun.COM, Matthew Ahrens Message-id: <46B36196.8070109@Sun.Com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> <46B2FAD1.506@Sun.COM> User-Agent: Thunderbird 1.5.0.12 (Macintosh/20070509) Status: RO Content-Length: 1425 Darren J Moffat wrote: > Not in /opt because it is part of the WOS. /opt is really only > appropriate for unbundled software - yes I know we have some legacy Remember, "In the WOS" != "delivered by Sun" or even "written or championed or used by engineers who work in Sun's kernel engineering group". The architectural principle is one of distributed development and reasonable management of our component abstractions. Sure, we could simply dump everything into "the WOS" and be done with it - except that doing so effectively forces all those objects to be constrained by the same one-size-fits-all boundary conditions of the WOS - delivery schedule, release taxonomy, etc. Maybe a better question to ask is "what consolidation will this be delivered into?" I'm asserting that "ON" is a particularly bad answer because these benchmarks are only tenuously related to the implementation details of ON. A better answer would be "SFW" or even "its own unbundled consolidation, delivered via the new repository". > small stuff in there but it is purely legacy stuff now and /opt is > almost pristine on a fresh install like it should be. Don't forget that a Solaris install installs much more than the WOS; your assertion that Sun delivered things should not go into /opt is only true for core OS related things - and, IMHO, benchmarks are on the fuzzy edge of really being optional, unbundled things. -John From carlsonj@phorcys.east.sun.com Fri Aug 3 10:20:19 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73HKIpa019290 for ; Fri, 3 Aug 2007 10:20:18 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73HHvJB018872; Fri, 3 Aug 2007 18:17:57 +0100 (BST) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM70060XK1WOE00@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 10:17:56 -0700 (PDT) Received: from phorcys.east.sun.com ([129.148.174.143]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700E1RK1VOSA0@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 10:17:56 -0700 (PDT) Received: from phorcys.east.sun.com (localhost [127.0.0.1]) by phorcys.east.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73HHvOm004743; Fri, 03 Aug 2007 13:17:57 -0400 (EDT) Received: (from carlsonj@localhost) by phorcys.east.sun.com (8.14.1+Sun/8.14.1/Submit) id l73HHv98004740; Fri, 03 Aug 2007 13:17:57 -0400 (EDT) Date: Fri, 03 Aug 2007 13:17:57 -0400 From: James Carlson Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <20070803072824.GC22964@eng.sun.com> To: Jeff Bonwick Cc: John Plocher , Joseph Kowalski , zfs-team@Sun.COM, PSARC-ext@Sun.COM, Matthew Ahrens Message-id: <18099.25413.11558.900550@gargle.gargle.HOWL> MIME-version: 1.0 X-Mailer: VM 7.01 under Emacs 21.3.1 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> <20070803072824.GC22964@eng.sun.com> Status: RO Content-Length: 1472 Jeff Bonwick writes: > I'm all for defending architectural purity when there's some > fundamental principle at stake. If there's one here, please > enlighten me. How about dumping all applications in /usr or just the root directory itself? Flatten it all out, and there's no need for discussion at all. The discussion isn't really about "purity." It's about avoiding clutter that ends up confusing users and making it _harder_ for them to locate what they want. As examples, /usr/sfw and /usr/ccs were clutter. They were unexpected and made things harder to find. Real users thought that Sun shipped the system without a functioning 'make' utility and without common open source software. I'm not sure whether /usr/benchmarks will eventually be seen as more of the same -- it may be. One of the unfortunate things about benchmark programs is that, despite the unstable output, people just love to wrap them up with ribbons and bows (see SunVTS and HCTS for two examples; there are many others), and thus become dependent on the location. That means we end up with this nailed down once we make the decision. So, yes, there is a reason to discuss this rather than just doing "whatever" because we're facing VMware or some other monster. -- James Carlson, Solaris Networking Sun Microsystems / 1 Network Drive 71.232W Vox +1 781 442 2084 MS UBUR02-212 / Burlington MA 01803-2757 42.496N Fax +1 781 442 1677 From jek3@Sun.COM Fri Aug 3 11:13:34 2007 Received: from sunmail2sca.sfbay.sun.com (sunmail2sca.SFBay.Sun.COM [129.145.155.234]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73IDY6E020841 for ; Fri, 3 Aug 2007 11:13:34 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail2sca.sfbay.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73IBEo4007096; Fri, 3 Aug 2007 11:11:17 -0700 (PDT) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM700G0LMISB100@brm-avmta-1.central.sun.com>; Fri, 03 Aug 2007 12:11:16 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700BK3MIQYO50@brm-avmta-1.central.sun.com>; Fri, 03 Aug 2007 12:11:14 -0600 (MDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73IBC8K618454; Fri, 03 Aug 2007 11:11:13 -0700 (PDT) Date: Fri, 03 Aug 2007 08:08:38 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <20070803072824.GC22964@eng.sun.com> To: Jeff Bonwick Cc: John Plocher , James Carlson , zfs-team@Sun.COM, PSARC-ext@Sun.COM, Matthew Ahrens Message-id: <46B36F26.50309@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> <20070803072824.GC22964@eng.sun.com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 1336 Jeff Bonwick wrote: > Does it matter? I mean, big picture, is it even worthy of discussion? > > VMware's long-term goal is to become an application platform that > obsoletes all existing operating systems. (Did you know they're > currently developing JVM, Rails, etc that run natively on ESX?) > Linux is trying to eradicate our developer community. Intel and > AMD are trying to make SPARC completely irrelevant. And we're > arguing about /usr/benchmarks vs. /opt/benchmarks? > > I'm all for defending architectural purity when there's some > fundamental principle at stake. If there's one here, please > enlighten me. > > Jeff > To me, the issue is namespace preservation. Benchmarks seem to not have unique names in many instances. Sure, we can just wait until we run into this problem, but by then, it will a 10x harder problem to deal with. So, I think this is actually about saving money. FRAM oil filters ran an ad for many years with the tag line: of "You can pay me now (for the filter) or of pay me later (an overhaul)". You get the idea. The only significant issue is "to bin, or not to bin". I the choice is "not to bin", then somebody needs to make a choice as to where. If its a new place, there should be a semantic definition of the new place. This should take a couple of hours to accomplish. - jek3 From jek3@sun.com Fri Aug 3 11:23:44 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73INhPY021279 for ; Fri, 3 Aug 2007 11:23:43 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l73ILJSm018026; Sat, 4 Aug 2007 02:21:21 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM70020RMZI4500@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 11:21:18 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.63]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700IERMZHJH90@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 11:21:17 -0700 (PDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73ILGqX621335; Fri, 03 Aug 2007 11:21:17 -0700 (PDT) Date: Fri, 03 Aug 2007 08:18:42 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <20070803072824.GC22964@eng.sun.com> To: Jeff Bonwick Cc: John Plocher , James Carlson , zfs-team@sun.com, PSARC-ext@sun.com, Matthew Ahrens Message-id: <46B37182.8020601@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> <20070803072824.GC22964@eng.sun.com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 410 Jeff Bonwick wrote: > Does it matter? I mean, big picture, is it even worthy of discussion? > Then again, if Jeff had quoted my posting about a general class of components which "repository appropriate, while not ideal for release", I'd probably have to agree with his "focus" message. We can (and probably should) just wait for any issues until such a repository exists. Sorry for the noise. - jek3 From carlsonj@phorcys.east.sun.com Fri Aug 3 11:23:48 2007 Received: from newsunmail1brm.central.sun.com (newsunmail1brm.Central.Sun.COM [129.147.62.245]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73INlk5021291 for ; Fri, 3 Aug 2007 11:23:48 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by newsunmail1brm.central.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73ILRf9035476; Fri, 3 Aug 2007 12:21:27 -0600 (MDT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM700D03MZT0T00@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 11:21:29 -0700 (PDT) Received: from phorcys.east.sun.com ([129.148.174.143]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM700E6SMZOOKD0@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 11:21:24 -0700 (PDT) Received: from phorcys.east.sun.com (localhost [127.0.0.1]) by phorcys.east.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73ILPSq005302; Fri, 03 Aug 2007 14:21:25 -0400 (EDT) Received: (from carlsonj@localhost) by phorcys.east.sun.com (8.14.1+Sun/8.14.1/Submit) id l73ILPtm005299; Fri, 03 Aug 2007 14:21:25 -0400 (EDT) Date: Fri, 03 Aug 2007 14:21:25 -0400 From: James Carlson Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> To: eric kustarz Cc: Darren J Moffat , Matthew Ahrens , filebench-team@sun.com, "zfs-team@sun.com" , Michael Pogue , psarc-ext@sun.com Message-id: <18099.29221.761226.853538@gargle.gargle.HOWL> MIME-version: 1.0 X-Mailer: VM 7.01 under Emacs 21.3.1 Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> Status: RO Content-Length: 965 eric kustarz writes: > We would then have the following executables: > /usr/benchmarks/filebench/bin/filebench (executable perl script) > /usr/benchmarks/filebench/bin/go_filebench (isaexec link) > /usr/benchmarks/filebench/bin/{i386,amd64,sparcv9}/go_filebench > (executable binary) Whew. That's quite wordy, but if it works for you, it's ok by me. It was the mix of /usr/benchmarks/ and /usr/lib/ that I found confusing. If it's like /usr/games or /usr/ucb, then binaries alone should go in /usr/benchmarks and the rest belongs in /usr/lib as you had it. If it's like /usr/demos, then just directories belong there. I'm not sure how clear the answer will be to users, but that's the clarification I was looking for. -- James Carlson, Solaris Networking Sun Microsystems / 1 Network Drive 71.232W Vox +1 781 442 2084 MS UBUR02-212 / Burlington MA 01803-2757 42.496N Fax +1 781 442 1677 From Eric.Kustarz@sun.com Fri Aug 3 12:42:41 2007 Received: from newsunmail1brm.central.sun.com (newsunmail1brm.Central.Sun.COM [129.147.62.245]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73Jge0l022803 for ; Fri, 3 Aug 2007 12:42:40 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by newsunmail1brm.central.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73JeGCS058709; Fri, 3 Aug 2007 13:40:19 -0600 (MDT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM70041NQN8XS00@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 12:40:20 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM7004R7QN7MI00@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 12:40:19 -0700 (PDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73JeFaX632812; Fri, 03 Aug 2007 12:40:15 -0700 (PDT) Date: Fri, 03 Aug 2007 12:40:09 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <18099.29221.761226.853538@gargle.gargle.HOWL> To: James Carlson Cc: Darren J Moffat , Matthew Ahrens , filebench-team@sun.com, zfs-team@sun.com, Michael Pogue , psarc-ext@sun.com, Bart Smaalders Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> <18099.29221.761226.853538@gargle.gargle.HOWL> Status: RO Content-Length: 1271 On Aug 3, 2007, at 11:21 AM, James Carlson wrote: > eric kustarz writes: >> We would then have the following executables: >> /usr/benchmarks/filebench/bin/filebench (executable perl script) >> /usr/benchmarks/filebench/bin/go_filebench (isaexec link) >> /usr/benchmarks/filebench/bin/{i386,amd64,sparcv9}/go_filebench >> (executable binary) > > Whew. > > That's quite wordy, but if it works for you, it's ok by me. Just have to put /usr/benchmarks/filebench/bin in your PATH :) > > It was the mix of /usr/benchmarks/ and /usr/lib/ that I > found confusing. If it's like /usr/games or /usr/ucb, then binaries > alone should go in /usr/benchmarks and the rest belongs in /usr/lib as > you had it. If it's like /usr/demos, then just directories belong > there. > > I'm not sure how clear the answer will be to users, but that's the > clarification I was looking for. Cool. Yeah there's basically two routes we can go (the so-called "to bin or not to bin"): 1) /usr/bin/filebench (with private files in /usr/lib/filebench) 2) everything under /usr/benchmarks/filebench Michael and Bart were very strong advocates of /usr/benchmarks (looking to the future). Seems like a reasonable thing to me. I'll update the PSARC case and send it out. eric From jek3@Sun.COM Fri Aug 3 13:58:07 2007 Received: from sunmail3mpk.sfbay.sun.com (sunmail3mpk.SFBay.Sun.COM [129.146.11.52]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l73Kw7UY025307 for ; Fri, 3 Aug 2007 13:58:07 -0700 (PDT) Received: from nwk-avmta-2.sfbay.sun.com (nwk-avmta-2.SFBay.Sun.COM [129.145.155.6]) by sunmail3mpk.sfbay.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l73Ktkhw020220; Fri, 3 Aug 2007 13:55:47 -0700 (PDT) Received: from pmxchannel-daemon.nwk-avmta-2.sfbay.sun.com by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM700801U4YTC00@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 13:55:46 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-2.sfbay.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM7004YHU4YMK30@nwk-avmta-2.sfbay.sun.com>; Fri, 03 Aug 2007 13:55:46 -0700 (PDT) Received: from [129.150.12.124] (vpn-129-150-12-124.SFBay.Sun.COM [129.150.12.124]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l73KteOf642457; Fri, 03 Aug 2007 13:55:41 -0700 (PDT) Date: Fri, 03 Aug 2007 10:53:07 -1000 From: Joseph Kowalski Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <46B36196.8070109@Sun.Com> To: John Plocher Cc: Darren J Moffat , James Carlson , zfs-team@Sun.COM, PSARC-ext@Sun.COM, Matthew Ahrens Message-id: <46B395B3.4070106@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <46B24240.1010301@sun.com> <18098.17718.809239.421164@gargle.gargle.HOWL> <46B2AA49.4060106@Sun.Com> <46B2FAD1.506@Sun.COM> <46B36196.8070109@Sun.Com> User-Agent: Thunderbird 1.5.0.5 (X11/20060925) Status: RO Content-Length: 610 John Plocher wrote: > Don't forget that a Solaris install installs much more than the WOS; > your assertion that Sun delivered things should not go into /opt > is only true for core OS related things - and, IMHO, benchmarks are > on the fuzzy edge of really being optional, unbundled things. > > -John Yes, other consolidations than ON also drop turds in /opt. They (like ON) should stop that. Other products (not bundled) often do usr /opt. This is a good thing. So some customer sites export /opt. Sorta like Sun's "/use/dist". I don't know if this is still common, but it used to be common. - jek3 From eric.kustarz@sun.com Fri Aug 3 17:10:54 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l740Ar7s029484 for ; Fri, 3 Aug 2007 17:10:53 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l7408QCH019572; Sat, 4 Aug 2007 08:08:28 +0800 (SGT) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JM800L11322OS00@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 17:08:26 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.63]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JM800FNI320LYC0@nwk-avmta-1.sfbay.Sun.COM>; Fri, 03 Aug 2007 17:08:24 -0700 (PDT) Received: from [192.168.1.4] (vpn-129-150-18-50.SFBay.Sun.COM [129.150.18.50]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l7408NHx673262; Fri, 03 Aug 2007 17:08:23 -0700 (PDT) Date: Fri, 03 Aug 2007 17:08:18 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: To: eric kustarz Cc: James Carlson , Darren J Moffat , Matthew Ahrens , filebench-team@sun.com, zfs-team@sun.com, Michael Pogue , psarc-ext@sun.com, Bart Smaalders Message-id: <98AF6779-E2FA-4234-8AE6-9C50E51224B0@sun.com> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> <18099.29221.761226.853538@gargle.gargle.HOWL> Status: RO Content-Length: 8043 Here's the updated case. eric 1. Introduction 1.1. Project/Component Working Name: Add FileBench into Solaris 1.2. Name of Document Author/Supplier: Author: Eric Kustarz 1.3 Date of This Document: Aug 3, 2007 4. Technical Description 1. Summary This project integrates filebench into Solaris. This project requests patch release binding. 2. Background FileBench is a framework of file system workloads for measuring and comparing file system performance. It runs under a variety of platforms, and is licensed under CDDL. More information is available at: http://www.opensolaris.org/os/community/performance/filebench/ http://www.solarisinternals.com/wiki/index.php/FileBench 3. Details /usr/benchmarks is a new directory for delivering benchmarks into (Open)Solaris. Each benchmark will have its own directory within /usr/benchmarks. For example, FileBench related files will be located in the directory /usr/benchmarks/filebench and libMicro related files will be located in the directory /usr/benchmarks/libmicro. This project delivers the following executable perl script: /usr/benchmarks/filebench/bin/filebench Additionial private implementation files will be delivered into /usr/benchmarks/filebench and are listed below: /usr/benchmarks/filebench/bin/go_filebench /usr/benchmarks/filebench/bin/{i386,amd64,sparcv9}/go_filebench /usr/benchmarks/filebench/config/fileio.prof /usr/benchmarks/filebench/config/filemacro.prof /usr/benchmarks/filebench/config/filemicro.prof /usr/benchmarks/filebench/config/generic.func /usr/benchmarks/filebench/config/seqread.prof /usr/benchmarks/filebench/scripts/filebench_compare /usr/benchmarks/filebench/scripts/fs_flush /usr/benchmarks/filebench/workloads/bringover.f /usr/benchmarks/filebench/workloads/copyfiles.f /usr/benchmarks/filebench/workloads/createfiles.f /usr/benchmarks/filebench/workloads/deletefiles.f /usr/benchmarks/filebench/workloads/filemicro_create.f /usr/benchmarks/filebench/workloads/filemicro_createfiles.f /usr/benchmarks/filebench/workloads/filemicro_createrand.f /usr/benchmarks/filebench/workloads/filemicro_delete.f /usr/benchmarks/filebench/workloads/filemicro_rread.f /usr/benchmarks/filebench/workloads/filemicro_rwrite.f /usr/benchmarks/filebench/workloads/filemicro_rwritedsync.f /usr/benchmarks/filebench/workloads/filemicro_rwritefsync.f /usr/benchmarks/filebench/workloads/filemicro_seqread.f /usr/benchmarks/filebench/workloads/filemicro_seqwrite.f /usr/benchmarks/filebench/workloads/filemicro_seqwriterand.f /usr/benchmarks/filebench/workloads/filemicro_writefsync.f /usr/benchmarks/filebench/workloads/fileserver.f /usr/benchmarks/filebench/workloads/mongo.f /usr/benchmarks/filebench/workloads/multistreamread.f /usr/benchmarks/filebench/workloads/multistreamreaddirect.f /usr/benchmarks/filebench/workloads/multistreamwrite.f /usr/benchmarks/filebench/workloads/multistreamwritedirect.f /usr/benchmarks/filebench/workloads/oltp.f /usr/benchmarks/filebench/workloads/randomread.f /usr/benchmarks/filebench/workloads/randomrw.f /usr/benchmarks/filebench/workloads/randomwrite.f /usr/benchmarks/filebench/workloads/singlestreamread.f /usr/benchmarks/filebench/workloads/singlestreamreaddirect.f /usr/benchmarks/filebench/workloads/singlestreamwrite.f /usr/benchmarks/filebench/workloads/singlestreamwritedirect.f /usr/benchmarks/filebench/workloads/tpcso.f /usr/benchmarks/filebench/workloads/varmail.f /usr/benchmarks/filebench/workloads/webproxy.f /usr/benchmarks/filebench/workloads/webserver.f All relevant files will be delivered in a new single package: SUNWfilebench. 3. Interfaces /usr/benchmarks/filebench/bin/filebench Location: Uncommited Invocation: Volatile Human-readable output: Not an Interface /usr/share/man/man1bench/filebench.1bench Location Uncommited 4. Bug/RFE Numbers 6581098 FileBench should be included in Solaris 5. References http://www.opensolaris.org/os/community/performance/filebench/ http://www.solarisinternals.com/wiki/index.php/FileBench 6. Manpages 6.1 filebench manpage User Commands filebench (1BENCH) NAME /usr/benchmarks/filebench/bin/filebench - framework of workloads to measure and compare filesystem performance SYNOPSIS filebench profile filebench -c stats_dir... DESCRIPTION The filebench command runs workloads in order to measure and compare filesystem performance. 'profile' is the name of the configuration file ending in '.prof'. The configuration file specifies what workloads to run, what parameters to run with, the directory path to operate on, and the directory path to store the results. Full documentation can be found at: http://www.opensolaris.org/os/community/performance/filebench/ OPTIONS -c stats_dir... Generates a HTML file ('index.html') that is a comparison of the specified directories. EXAMPLES Example 1 Running the multi-stream sequential read workload The following command runs the workloads described in the configuration file named 'sqread.prof'. # filebench sqread Example 2 Comparing multiple runs The following command compares the results of two previous runs. This assumes the results from the two previous runs were located in the directories: /stats/wombat-zfs-noel-Jun_27_2007-15h_45m_33s and /stats/wombat-ufs-noel-Jun_27_2007-15h_52m_11s. This command will generate a HTML file named 'index.html' in your current working directory. # filebench -c /stats/wombat-zfs-noel-Jun_27_2007-15h_45m_33s \ /stats/wombat-ufs-noel-Jun_27_2007-15h_52m_11s EXIT STATUS The following exit values are returned: 0 The run was successfull. 1 An error was detected. 2 Invalid command line options were specified. ATTRIBUTES See attributes(5) for descriptions of the following attri- butes: System Administration Commands filebench (1BENCH) ____________________________________________________________ | ATTRIBUTE TYPE | ATTRIBUTE VALUE | |_____________________________|_____________________________| | Availability | SUNWfilebench | |_____________________________|_____________________________| | Interface Stability | Uncommitted | |_____________________________|_____________________________| SEE ALSO attributes(5) 6.2 filesystem(5) manpage update /usr/aset Directory for Automated Security Enhancement Tools (ASET) programs and files. + /usr/benchmarks + Directory for benchmarks. /usr/bin Platform-dependent, user-invoked executables. These are commands users expect to be run as part of their normal $PATH. For executables that are different on a 64-bit system than on a 32-bit system, a wrapper that selects the appropriate executable is placed here. See isaexec(3C). An approved installation location for bun- dled Solaris software. The analogous location for add-on system software or for applications is /opt/packagename/bin. From eric.kustarz@sun.com Wed Aug 15 16:43:22 2007 Received: from sunmail4.Singapore.Sun.COM (sunmail4.Singapore.Sun.COM [129.158.71.19]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l7FNhLc3028866 for ; Wed, 15 Aug 2007 16:43:22 -0700 (PDT) Received: from brm-avmta-1.central.sun.com (brm-avmta-1.Central.Sun.COM [129.147.4.11]) by sunmail4.Singapore.Sun.COM (8.13.4+Sun/8.13.3/ENSMAIL,v2.2) with ESMTP id l7FNegoG013835; Thu, 16 Aug 2007 07:40:50 +0800 (SGT) Received: from pmxchannel-daemon.brm-avmta-1.central.sun.com by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JMU0040T9S0OH00@brm-avmta-1.central.sun.com>; Wed, 15 Aug 2007 17:40:48 -0600 (MDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.63]) by brm-avmta-1.central.sun.com (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JMU0031O9RZPR50@brm-avmta-1.central.sun.com>; Wed, 15 Aug 2007 17:40:48 -0600 (MDT) Received: from [192.168.1.4] (vpn-129-150-20-40.SFBay.Sun.COM [129.150.20.40]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l7FNelDF936129; Wed, 15 Aug 2007 16:40:47 -0700 (PDT) Date: Wed, 15 Aug 2007 16:40:29 -0700 From: eric kustarz Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <98AF6779-E2FA-4234-8AE6-9C50E51224B0@sun.com> To: psarc-ext@sun.com Cc: Matthew Ahrens , filebench-team@sun.com, zfs-team@sun.com, Michael Pogue , Bart Smaalders Message-id: <10F0CFA8-9EFA-404E-9DB8-BD042B3A6B42@sun.com> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; charset=US-ASCII; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> <18099.29221.761226.853538@gargle.gargle.HOWL> <98AF6779-E2FA-4234-8AE6-9C50E51224B0@sun.com> Status: RO Content-Length: 60 This case was approved during today's PSARC meeting. eric From david.brittle@sun.com Thu Aug 16 09:13:58 2007 Received: from sunmail5.uk.sun.com (sunmail5.UK.Sun.COM [129.156.85.165]) by sac.sfbay.sun.com (8.13.8+Sun/8.13.8) with ESMTP id l7GGDvv4021907 for ; Thu, 16 Aug 2007 09:13:58 -0700 (PDT) Received: from nwk-avmta-1.SFBay.Sun.COM (nwk-avmta-1.SFBay.Sun.COM [129.146.11.74]) by sunmail5.uk.sun.com (8.13.7+Sun/8.13.7/ENSMAIL,v2.2) with ESMTP id l7GGBMR4024494; Thu, 16 Aug 2007 17:11:27 +0100 (BST) Received: from pmxchannel-daemon.nwk-avmta-1.sfbay.Sun.COM by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) id <0JMV00013JN02E00@nwk-avmta-1.sfbay.Sun.COM>; Thu, 16 Aug 2007 09:11:24 -0700 (PDT) Received: from jurassic-x4600.sfbay.sun.com ([129.146.17.59]) by nwk-avmta-1.sfbay.Sun.COM (Sun Java System Messaging Server 6.2-3.04 (built Jul 15 2005)) with ESMTP id <0JMV008F6JN0FPC0@nwk-avmta-1.sfbay.Sun.COM>; Thu, 16 Aug 2007 09:11:24 -0700 (PDT) Received: from [129.146.11.147] (sr1-jurassic-04.SFBay.Sun.COM [129.146.11.147]) by jurassic-x4600.sfbay.sun.com (8.14.1+Sun/8.14.1) with ESMTP id l7GGBODL142966; Thu, 16 Aug 2007 09:11:24 -0700 (PDT) Date: Thu, 16 Aug 2007 09:11:24 -0700 From: brittle Subject: Re: Filebench [PSARC/2007/448 FastTrack timeout 08/16/2007] In-reply-to: <10F0CFA8-9EFA-404E-9DB8-BD042B3A6B42@sun.com> To: eric kustarz Cc: psarc-ext@sun.com, Matthew Ahrens , filebench-team@sun.com, zfs-team@sun.com, Michael Pogue , Bart Smaalders Reply-to: david.brittle@sun.com Message-id: <46C4772C.4040204@sun.com> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-PMX-Version: 5.2.0.264296 References: <200708021902.l72J2fAR021784@zion.eng.sun.com> <18098.12146.191123.179282@gargle.gargle.HOWL> <18098.16560.37467.576659@gargle.gargle.HOWL> <46B2FA27.1040804@Sun.COM> <5E14F1C7-7062-4C4C-BA62-021EE08BC410@Sun.COM> <18099.29221.761226.853538@gargle.gargle.HOWL> <98AF6779-E2FA-4234-8AE6-9C50E51224B0@sun.com> <10F0CFA8-9EFA-404E-9DB8-BD042B3A6B42@sun.com> User-Agent: Thunderbird 1.5 (X11/20060113) Status: RO Content-Length: 162 Eric - thanks for all the hard work driving this forward - Yahoo! Dave eric kustarz wrote: > This case was approved during today's PSARC meeting. > > eric >