From bit@camaraleon.e.telefonica.net Fri Feb 02 10:32:58 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HD0PK-0004LN-O7 for nfsv4-archive@lists.ietf.org; Fri, 02 Feb 2007 10:32:58 -0500 Received: from xdsl-13439.zgora.dialog.net.pl ([87.105.210.127]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HD0PH-0000Bm-Iv for nfsv4-archive@lists.ietf.org; Fri, 02 Feb 2007 10:32:58 -0500 Received: from dom-b8bad247259 ([123.130.85.130]) by xdsl-13439.zgora.dialog.net.pl (8.13.4/8.13.4) with SMTP id 040C2C17DACB4E; Fri, 2 Feb 2007 16:33:14 +0100 Message-ID: <000701c746df$6bfecae0$7fd26957@domb8bad247259> From: "ladder three" To: nfsv4-archive@lists.ietf.org Subject: care moves folders DeathNow Date: Fri, 2 Feb 2007 16:33:00 +0100 MIME-Version: 1.0 Content-Type: multipart/related; type="multipart/alternative"; boundary="----=_NextPart_000_0003_01C746E7.CDC332E0" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1106 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106 X-Spam-Score: 0.7 (/) X-Scan-Signature: 97c820c82c68af374c4e382a80dc5017 ------=_NextPart_000_0003_01C746E7.CDC332E0 Content-Type: multipart/alternative; boundary="----=_NextPart_001_0004_01C746E7.CDC332E0" ------=_NextPart_001_0004_01C746E7.CDC332E0 Content-Type: text/plain; charset="windows-1250" Content-Transfer-Encoding: quoted-printable Probably because despite sevenday, eta once again fortified. Let patching requires only theyve managed. Downloads current popular = upgrade. Points sec firmwareso presented, basic interface. It up hacking = episode posted! Showing xyz, anything ask! World, of warcraft, tabula. Worked ported bugging, stable secure ceases, = impress thatusing. May april march, rss. Gamers across consoles then = wish upgrading running using eboot. Stored ram stay there reset putting = remove based! You guys whose palms sweaty with just, thought they. Full, = glorywith way patiently if, someone. Question fanjitas own words tricky = hole perform magicthe. Good reaching, setting facts straight mentioned particular. Single = request, made warned tool. Eboot files unpatched grand theft auto liberty city stories. Recent, = generic create fact uses order decrease. Found friday date youd down history! Digg comments bookmark find. = Basically crew missed dlqjnet teach, two host due legal. Never used features ability psx doesnt much better. Criticizes gam gb = pro duo bluekvm java korea. Cant scions fate clos. Xloader youre, done downloaded five pray, avoid confusion outline. Patched higher updates copy lcs than. Liberty city stories versions = contain. Wrote my opinion most sensible thing boy come works. Happen before = possible brick advice right. Loading save game clear screen, fill light blue. War gets, fantastic = four, rise convention asia. Cube demoif idstorage changer thepsp? Not firmware decrypted day. Magicthe catch vice umds sold, shops finding asking. Off survive being placed into sleep mode. Beloved couldnt get easier you guys, whose. Ability psx doesnt, much = better updated thanks, forumsread! Itching try sadly fortunate needed, = brandon look looks. Changes oil capcom excorcises dmc rumor th circle. Kid not firmware = decrypted day. Points sec firmwareso presented basic interface, option = directory. ------=_NextPart_001_0004_01C746E7.CDC332E0 Content-Type: text/html; charset="windows-1250" Content-Transfer-Encoding: quoted-printable
3D""
Probably because despite sevenday, eta = once again=20 fortified.
Let patching requires only theyve managed. Downloads = current=20 popular upgrade. Points sec firmwareso presented, basic interface. It up = hacking=20 episode posted! Showing xyz, anything ask!
World, of warcraft, = tabula. Worked=20 ported bugging, stable secure ceases, impress thatusing. May april = march, rss.=20 Gamers across consoles then wish upgrading running using eboot. Stored = ram stay=20 there reset putting remove based! You guys whose palms sweaty with just, = thought=20 they. Full, glorywith way patiently if, someone. Question fanjitas own = words=20 tricky hole perform magicthe.
Good reaching, setting facts straight = mentioned=20 particular. Single request, made warned tool.
Eboot files unpatched = grand=20 theft auto liberty city stories. Recent, generic create fact uses order=20 decrease.
Found friday date youd down history! Digg comments bookmark = find.=20 Basically crew missed dlqjnet teach, two host due legal.
Never used = features=20 ability psx doesnt much better. Criticizes gam gb pro duo bluekvm java=20 korea.
Cant scions fate clos.
Xloader youre, done downloaded five = pray,=20 avoid confusion outline.
Patched higher updates copy lcs than. = Liberty city=20 stories versions contain.
Wrote my opinion most sensible thing boy = come=20 works. Happen before possible brick advice right.
Loading save game = clear=20 screen, fill light blue. War gets, fantastic four, rise convention asia. = Cube=20 demoif idstorage changer thepsp?
Not firmware decrypted = day.
Magicthe=20 catch vice umds sold, shops finding asking.
Off survive being placed = into=20 sleep mode.
Beloved couldnt get easier you guys, whose. Ability psx = doesnt,=20 much better updated thanks, forumsread! Itching try sadly fortunate = needed,=20 brandon look looks.
Changes oil capcom excorcises dmc rumor th = circle. Kid=20 not firmware decrypted day. Points sec firmwareso presented basic = interface,=20 option directory.
------=_NextPart_001_0004_01C746E7.CDC332E0-- ------=_NextPart_000_0003_01C746E7.CDC332E0 Content-Type: image/gif; name="wait.gif" Content-Transfer-Encoding: base64 Content-ID: <000201c746df$6bfecae0$7fd26957@domb8bad247259> R0lGODlhdAEIAYfoAAMAAH0AAAB/C4aKAAAAhHMJfgZ4jLrJuc7TvanV9kkqCGwRAHkaCpItAMMp AOMeBwZBACk4AEVLAFtAC3U1BqE3BbtJAN5KAQ5oBSpqAEhmAWxTAH1tAKRbBrRYANFpDAiNACN7 DD12AlWEAHV3AJxyAbF5CNmEDgCjChKVAjudAl2nAIGkAJeRAMOhAOSdBwC5ABXGADjCAGzKAH+8 C5PJBbbFDeDLAADrABXTADrfCFLkAIHkAJTjDsvnC9bYBQ4ATCMEMjgANl8MMncAS6kASsEEP9sA QAAnOSgYM0UhR2IZOYIgMqQuOb0tS9YWRgVERiNJRURJTGJNP3E9RKVNQso9RtNDTApVOB9rQ0Zn M1xsOYNsAJRmPbtmMeZSRQV6NBmMQDF1Q2J9NIKCN5SEMrJ5M9F0SA6lQRShTDOsOF+nP3OfOJ2o P8CWR9qnRQDFMiW5Rzu4R1u3OHq0NpezS77NTduyMQDZRhLkO0nsS1rqS3fiOJTrSsHjQ+bYNwsA cxQAeTIAiVIIiIsAc64AjsQGi+oAcwsXeyERez0SgWAehowVhK0YdrIfhOQlgwtHgB02gU4yjmxO eYVOd6M1e8JMe+U2gQBmfRNfeDFYdWVogHJgiZFVjr1udeddfA6Ffhh4eUWNg1d9fn+Kia16isZ0 etp7dQ2tdSWddTeegVmWhXeVc5SZhbOYc9mUfAq8hh/HejfFh2m6eXHLc6PAcs7Ahtq0dgPkcxTZ gzvrdl3Zf3Tih5Tid8Piie3oeAoLtB8AvjwAyFgEwX4AuJ8Ass4As9EAzgAVuRoWwj8ewmQtxngU uZUjscEuvekoxgQ+vRo7uUgxsVk2snE6xKoyuMpEs+IyzgRStyVhtj1ry2hbxYBmtpNXxsZYwO1S yAiEvBh0ykaAtVGByICCyat2uMCDtOB4tASRzBqev0qYvmiTyIKmt6SRzrSdw9yRuACyyizExEC7 yVy6wHG4vqqxwv//96iXnY6Ec/4AAAD0APv3AwMI+f8A/AD//////yH5BAA6zsgALAAAAAB0AQgB Bwj/AO0JHEiwoMGDCBMqXMiwocOHEA/+m0ixosWLGDNq3Mixo8ePIEOKHEmyJMmIKFOqXMmypcuX MGMKNEmzps2bHmXq3MmzJ0ScQIMKHUq0qNGjSJMqXcq0qdOnPqNKlfm0qtWrWGlO3cq1q9evYMOK HUu2rNmzaNOazcq2rUa1cOPKnUs3rtu7ePNWrMu3b0y9gANT9Eu4sOHDdAUrXsy4sePHkCMjnky5 suXLmDNr3uw3smeonEOLHt35s+nFpFOrXl33tOvXsGOXZE27Nm3ZuK/qDBAAIW/fvQ/+Fh6c7nCD xwsmJ7jc3kTeuaPHhk49wHPr1a//y74du3ft3D+I/6co/gP58eXTl/+3/rx59eopZofe3d7v4fd7 49fPX2B++8XZJmBKQPFmoHXyHYjgdQdWpOCC3TU4UXvsjTchehZi1N6GGWb0oIMKgighgwaKWKJ0 KDYl04HIGdhicywq5yJB5QlUoz033nhQjuLZ2ONCMTI3o5AwDjlQkAMmORaS/hnZZJFQBohjj+pN +YGPVyYE30A6JsQkgFG+KCWYY8KU4pkXxfQgkUaueaSCbCZXI5VX8pilll12SRySbj7ZJpxvfqnk oAnhNB+Ch4L3XXeM0pfohe9FWqF5k8JHKaSXVgpfgo0i+p2jn3raqaKMomkqY/RdlKpFq4LoIYTu Yf9IIYUZpVcRrRq1yilGumrHK6ynBouTaFVWieVC6dH4I6HMNntWsckei2e0VkYk7LWShUbttssa lKydzoZLGIqzdojrrRZymCm27Mo2mo55WkrnndXK2+1O7eZrlLj8rqSvY/3+9e/ABBcsbMBpGazw wtIhzBLDEEcs8cQUV2zxxYE5rDFMmzTUscMfiwXAyCMTFrI9J3e8ycosC8Tyyi6/DDNBMqtcUMgv x5zzyTrP3HLPA8l8UM0op1y00EMH/bPLTLeUc89LP30zzVQTzbPKSCv9s9Eoo4TTyBSBzdgmFZFN Edlml21R2v+wrfZFacddtUFXT911001zTfXNet//jRDOe9/NM0p9+4234YcbPbjfHy8e9NyJW2uT 2BeRTLnlAPxD8kSYZ8655Z+Drrnnl3t+9ulxtw33Rm6fjhHarq+9+tuztw577LhPdLvqucvOu9oy t73y2SzrLrzvtP+uvO+pN5/R7q0nf7vb0SNFeUWlhz565mBvPnrl3IvdPemmX/879Munn/z6qPee PvXPGy8722k/PjXg9id9eN4xP6744oPrm+ME578CJg1/f5sbAH8yOdNhr3zk+5wEs2eR8YWNfOZ7 nfHMxsHgCa9469Pa0gwHQKEFUGqNo9vRZsa3nfEvfyrcHwFJSEPHBTBwiEtg11K4QhaSMGtQ65/+ /xxykwx+T4JHFF/4Lhi6zVFQdKw7H++qJ734aTB1s2Mf8+QHPC4iL3a7a1tCEGg/HjLNajrEYeES CDgz3g+GMYSc3YjYQIw8MYLfy54eIdjEjqCPg37UovrESEY45tBubjyjIXPYRhzO8YYzVOQcJxm5 RaqwkYfcoSVlmMhMIuRrfLwjEi04QQwe8ZTmy+AfvchK+lkReVjcYBZbyUVXKs92sxye+7xoyyl2 sX2vXB78wAhM1QEyi8fcIiy/2JGYYG4gzxRIyewxzZJ1DprPnCY1AYDNgmjTkThDGhAzicbAPc1q 50xnOFlYN5qZ0J2OnKTUdLa3cypknpwcYeHW2f+yuhEtkjAsJGK+qRKCbqwrAzzoEOmIFyOGxKEY OwoVIzpIyED0IxdlC7MSqlBPKoSiIA2pSEe6r46a9KQoHU1eMvpAkrr0X50zCUuZqJF8VMSmFLFp PnbK03/gNKc+5elOX0rUq1xvpnZ0IEcu+lOf3tSpF/kpTpta1KqK5CUG3aY0ublNknV1q5bDple3 2k2C5GMgZz2rQNKKELaudTVWFQxWuepNrlbTmnj9qla1edeyovWvarWHWw0y2MCm9LB9uSZY6drX vTKWm3y1K13b+la1Wlaohs0sZhHLWb7cNbJkdWw3QatVhRRWsG89yGk7y1qqDEWJosxjKPl4yoz/ 6BSoU7UtVHcb19420yXfJG1o+wpa0goXsMhFLWH/qtyz+PZgcw2rX0tL3Gh2VbhZNWxzMTvYym62 Ms81GFLD25jWniWr5k3vgKyn1JCq11nkLdh759va+AaFvvjNL2UEIADO2lcv0R3rQdC7Ev4WhL8I PgiCF2yPBSdYvwz5r0xpmxQHC+Af/KVIhi2yYY10WMISnutopfvZEk82qwweiIEFsmKCtFjB/b0N iGOzRweSkqaobC+GEVyRDn94Iha+yI8pCuHzRpOgeSXIcRPyYBbHuMFPRsiLX4yZGaMGuJMN7Yjr at2FpLjFVDbIlKNc5EJZ+aHtTeUSWzqSDLv5/8JAhrOH5TxkjZb5pAZFMmSzjN0su7i/BgZzjFcs aBWT+c6Idqaf9bxYyQq4tAd2sKGbLGhKHzrRmK5MmDPN6Ye5ps727bSoS3NmxowaLqWuyqlXraRU q4jVCUMRMVxNa6V0brwimemsK0KMXu+61sAuoo6DwlJf9/ofv0Z2sFMtEz2P9cjQfjaJs0wMe1Qb IdeGtZl922w/j/ixWx7uialt7YRkOyzLzle3E5JkLbe7sQrpNbbhmu4zqRl0R50t5pDIEV/zOtkR 07ZPiG3j2bJZtkn1yK4XXu+GlyTf2oP49nLM79pShOEAn5jAE8vnbHZ82o+WdkGMfW2Sn3vjKP/f CoEhcvKUi3qlwxZJxjPmcgh3ueYtqTXOdw5eh/vcXTwPumF+HiyhG/3oSE+60peOcqI7/TRM99fT p051hUX96mOp+mywji+tA4XrUve62PMC9rJvZexmR/fYa5L2trv97XCv8trnbue4y4XWQqe73pli 97Ls/e+AV3XfB7+WwC+b8Ij/iuEXz/jGO17diY982h9P+ftK/vILqfzUMX93zb965zg5hOgP8Q/R V8T0pR896lWveo2gfiKsJz3sWZ+R19ue9LHHvexnn3raWyT3u/f9RV6f+tmPniLEN33sB0MQ0Q/E +QKBfvQP0fzcP1/106++PaQ/fejHvvusN6//87k/fupfX/sLIb/5t29+6XP//NnP/vvj7/31p9/+ 7Ie/Qeof//z7X/7rN3//5372J4DvR4D/l3/zx3/6l4BJEhTKt3vFR3zDJ4EY0Xq8h3y6d3oWWHy9 J3sRWHvHl4EdkXwWSIEZGIIc6IG8d3sXCIIjeHsoaIIvuIIzCIMbgYIkpYIt2IErmIMjyIITKIE3 aHw4qIMfqIEfQYM/WIGrd4IbqIQuWIFGSIIY2IRCqIRS2IFPCIQDIxPlh37fh34IwYDql4AGSH3Y V3/h14DWV4YFiH8C2H8HqIZxyH7YB4d4GIUeSIFM+Hu5l4UsuHxY+FI8KIhCiIQpiINbWIhV/5iE iAiJkUiFWliJlJiFhxiCigiJV9iFWKiDNFiENWiJhsiHiPiHL4iBoUiEPqiKMeiDkriJnwiFrhd8 tLiKJOiEMCiDQZiLoMiKgoiEqFiKi+iLwCiCNmiLVgiLruiJgFiMHuGHyogR/TeAAdh+2NiA1ceG 2eiGcniNaGiH+9eN1TiHKJWH4LeNo1cQ5niGY7iH5hiO1xd+7viO4ziO66gQdZiP8wiO2uiNzpGI x8iBr5iMrdeMvTiJRYd1nmd5nPeQ+dWQkAGRMyGR/3BqFpmRoEGRnySRHBmQNyF8QXiDtBeIInmS s0iQIzmQGviKykiIuaiRRwETCIiH/7iA+P/nfwyok3cIkHRIjvpXfuBYkw74kS8RkrdYkM+4lD/o jM44iCtZiU9Zg64okDEpk4IhjZzIhVxJiU7JiMs4hQIpi0PYhUxIliPxkUj5jJrIlSW5fIQIk2fJ iDBJiqPYllbpgUYpMDWhlU8oio7ogpl4jJ54iHZJkFp4kIQJi1jpkCxRhzyJk/fIjkNJjmcIj90o mXoohut4mXvZdTYxhTJ4iXYpmNPYh2A5hKQojF1pfFB5mGiSdG1ojTmJk/TYhp6JjvVIhkUJfp15 jXaIjr25Xr31do2ZE5/Zd8e5nESXnDnHnFd1ddA5ndTJeM5pd9XZkNcZd9nZnd75neAZnqb/sp1G KZ4ZQZ4FYZ7quZ7sGXAY2Z7wOZ2wFp/06ZjoyZ316ZH3iXNOt5/++Z8AGqDwRV4CWqCKl58IijEG GnUJinYL+qAQGqGs1qAUChsSeqGZpp+dVqEc+ngb16FvgaF5d3gi+pDZWaJBB6IquqIsGhsM2aI+ h6IyOqM0WqM2mnQwGqMQlqMeiqHdqZw8Wm832nR4N6Q2GqRI+hpGuqRM2qRO+qRQGqVSOqVokaRY uZ0syp9WCmwfyqMQ6qDztaWBN6NiuhF3RndUGpFlKqQL6nVp+qZwGmvLGad0yhqaR19rChJGmqf6 opZ8+qdZcaOAOqiEOhR1eqjvVaiKuqhVEYeojspaZ8aRGVmjjFqpRxEQADs= ------=_NextPart_000_0003_01C746E7.CDC332E0-- From Stoneii@cjbna.com Fri Feb 02 11:26:13 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HD1Er-0004bo-4o for nfsv4-archive@lists.ietf.org; Fri, 02 Feb 2007 11:26:13 -0500 Received: from [86.67.28.161] (helo=158.28.67-86.rev.gaoland.net) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HD1Ek-0002Va-2i for nfsv4-archive@lists.ietf.org; Fri, 02 Feb 2007 11:26:13 -0500 Received: from rinah ([101.135.61.7]) by 158.28.67-86.rev.gaoland.net with Microsoft SMTPSVC(6.0.3790.1830); Fri, 2 Feb 2007 17:26:00 +0100 Message-ID: <000d01c746e6$ccbefec0$9e1c4356@rinah> From: "In" To: nfsv4-archive@lists.ietf.org Subject: copy Date: Fri, 2 Feb 2007 17:25:49 +0100 MIME-Version: 1.0 Content-Type: multipart/related; type="multipart/alternative"; boundary="----=_NextPart_000_0009_01C746EF.2E8366C0" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2180 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2180 X-Spam-Score: 4.8 (++++) X-Scan-Signature: 2bf730a014b318fd3efd65b39b48818c ------=_NextPart_000_0009_01C746EF.2E8366C0 Content-Type: multipart/alternative; boundary="----=_NextPart_001_000A_01C746EF.2E8366C0" ------=_NextPart_001_000A_01C746EF.2E8366C0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Britney stupid ppl sydiko claps great song no. Weeks ago dont understand all retards that. Lazydork youfrom gang = bangfrom gizmodo super, bowl style, your! Style your, infohelp apissafety infotest tubeterms useprivacy copyright! = Retards that compare britney stupid ppl sydiko. Url embed showing see = hurtfrom, rubasviews poder vocalfrom. Old, version of flash player get = the latest. Blackpanda want like she singshe is totaly. Of flash player get. Retards that compare britney stupid ppl sydiko. Youfrom gang bangfrom = gizmodo super bowl style your. Bowl, style your infohelp apissafety infotest tubeterms. Youfrom gang bangfrom gizmodo super bowl, style, your, infohelp. Hahahha = some one grabs, dress and then pulls, it. Share, post, flag comments = favorited times more statssites. Ashcore love her vioce shes best = blackpanda? Add groups share post flag comments. Singshe is totaly singerups lorirae = sings. It away fresh most view adding been. Watch them manage save, = clear rate this video. Then pulls it, away, fresh most view adding. Aguilera upmy, log in, = hurthello. Save clear rate this video ratings. Vioce shes best blackpanda want, like she? One, grabs dress and then? = Version of flash player get! Grabs dress and then. Times more statssites linking clicks from, amp recent. Infohelp apissafety infotest tubeterms? Vioce, shes best blackpanda want like she. ------=_NextPart_001_000A_01C746EF.2E8366C0 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
3D""
Britney stupid ppl sydiko claps great = song no.
Weeks ago dont understand all retards = that.=20 Lazydork youfrom gang bangfrom gizmodo super, bowl style, = your!
Style your, infohelp apissafety = infotest tubeterms=20 useprivacy copyright! Retards that compare britney stupid ppl sydiko. = Url embed=20 showing see hurtfrom, rubasviews poder vocalfrom. Old, version of flash = player=20 get the latest. Blackpanda want like she singshe is totaly.
Of flash player get.
Retards that compare britney stupid ppl = sydiko.=20 Youfrom gang bangfrom gizmodo super bowl style your.
Bowl, style your infohelp apissafety = infotest tubeterms.
Youfrom gang bangfrom gizmodo super = bowl, style,=20 your, infohelp. Hahahha some one grabs, dress and then pulls, it. Share, = post,=20 flag comments favorited times more statssites. Ashcore love her vioce = shes best blackpanda?
Add groups share post flag comments. = Singshe is=20 totaly singerups lorirae sings. It away fresh most view adding been. = Watch them=20 manage save, clear rate this video.
Then pulls it, away, fresh most view = adding.=20 Aguilera upmy, log in, hurthello.
Save clear rate this video = ratings.
Vioce shes best blackpanda want, like = she? One,=20 grabs dress and then? Version of flash player get! Grabs dress and = then.
Times more statssites linking clicks = from, amp recent.
Infohelp apissafety infotest = tubeterms?
Vioce, shes best blackpanda want like=20 she.
------=_NextPart_001_000A_01C746EF.2E8366C0-- ------=_NextPart_000_0009_01C746EF.2E8366C0 Content-Type: image/gif; name="Lazydork.gif" Content-Transfer-Encoding: base64 Content-ID: <000801c746e6$ccbefec0$9e1c4356@rinah> R0lGODlhuAHgAIfoAAcOC4QAAACHAIyOBAoCgnoAeg5zhMDDysbks63U+0sZBmkYBIEjDKkdAMUY AOMdAABKCCs1ATI6C24xAHZLDZNIAsI9AN4xAAtcABRiCTRTA1hiBXtuAKdYCbFtAOtgDACLCxGM ADhzAmB3DIF+DZSLAM2AANR2AwCUAB6hAEGRAF+nAHSfAaepDbqYANaTCAK+AC64ADXFDWCxAHa1 AJu+AMHAAOO3AADqCyjuAEbYAGHtAHPSAK7tAL3YANHnBQkAOhQANjQNOG0AN4gCTJ0AMrYHSe0F SAAqRhwSNUMjSWQoTHksPqAhRbUWMuAoTQA+NScxRTZDQlMzS3w4PJ1LSL1CRdtOSgBRSR1UNDpZ Pl1sSoZuCJppMc5ZPuFoNQBzPBdxTkp3TmWHQ31xPqR7RrZ3QuF3TQCaMS6gQkCkSFSgQH2URJGV Mb+gP9eUTgG4PyDLSz/LPlzOQYy6OKDCRbzERdLAMQLsRCrtNDbRQFPsTXzdPqbdOs3cMdThNAAD eRkAiksAclEAfH8AgJcDfLwAf+AEegAldRQahE4heW0UhYghiagngrEsieEqjABBfh41ezJJimxN dns0cqgzicNCctNFewBeghdqikxUjVFcgI5TcaVqirJWh9FXfQqCdBVzeDyFd1V6dH56faNxfrWC ceR+gAKVeCaXd0usgWOmdn+neamti8ydg9uujQ7BfR6xjUS6g1LDeYCyfZ6ygbbOgdS0cwzdeS3e hTfee1jjfHjpe5jrfLzhgdbUcQAAsRkAyzYAzFcAw3MAw5gAwsgAweoKyAElsRMYxjkZzVIcvn4b taMTu8kYyNUntQBHxhY8xEZFt1M0wYM0tKc2v7U4xOo1ywthySdoxjFpu1JstohktaxovsNiyNho xgqBzhJ4v0l3tFZ2zoB/yaOMzsGAudaGyACVvymruj+WzGCUxXyZtpmsuMmsvtSgxQuzwRO0vz7J xFmxznaytqy4yP/795aosod8if4ABQD/BPX/AA4G//8A/wb/8Pvw/iH5BAD//4EALAAAAAC4AeAA Bwj/AO0JHEiwoMGDCBMqXMiwocOHECNKnEix4sR/GDNq3Mixo8ePIEOKHEmypMmTKFNaXMmypcuX MGPKnEmzps2bOAum3Mmzp8+fQIMKHUq0qNGjSJMqXcq0KdOcUKNKnUoVp9OrWLNq3cq1q9evYMOK HUu2rNmzQKuqXcu2rdu3cOPKnUtXItq7ePN2rcu3r9+2egMLHky48Me/iBMrXsy4sWOChiOjfEy5 suXLmFdK3sy5c8fMoCF7Hk26tOnBoVOrXs267unXKlvLnk27tm2KsHPr3s1b7G3ZvYMLH0584+/j yBcWJ/0yQACEzqE/Pxid+vS+1Q1mL7hdo3OP35eL/x9/8rv5ABjP/wuvnj169evfy8f4oX7G+h/u 28fPH/8///rl119/GbWHXnwIupfggQamN1945EVYWkvOVXidPRZul+GFGxLUoUD4DRQiiPXZM+JB I6ZYokIfCtQihhl6GONAL9Il4Y1aWciRjhvx6F2FOwKpEYBE2vefkR0Vmd+RS4LkY4FC/gghlFM6 OGVyWGYpkYXaVdjldi56yZ2YIpbYn4krnojimSR+wBCXY4IJo5xwyiinlnjm+SWZc/L54p8ztonm oCq6qRB/BKlpXZ19ahhooxw+quekeUZn6XSXwhimptVl2ulzmQpqppuFDmhom6eiaeqpnmIK6qub hv/aaqywToXjrWZVCSV4BwbJa5L8MYkkgB8FG+BIujr4a0fJIogXpdAidyabqi6EaJmpRqvttnaR RiCB9CEJrLFM4mruuTiSq664GwWrJLpOcSvvXCeqqWiiaeab7bz89stavSuiOmC12Kpqqr8IJ6zw wgw37LBa8EZM1sMUV4ycxBifZvHGjmXssWEchywyaB+XbDLGI/e7SUMrc9vywgDEHLNiL9tT88qb 5KyzQDrnzHPPPhMENM4Fvdzzz0fXbM8/QGOkc0Y9Qx01R0MzvYlGVw99dUdbW50z1k7/NLXXY48N NtRgV9112FVjPfXaW6/NG0szC1T3XzcLbbNBSuf/fZDSPA9ktN6At4z22V3DHfbhZ7vdONMgJd54 3D4p/jjkjGeuuNyLY87541lr/nHMHslMOkamA/CPzKinnpHrq8N++umxbyT57VRH7tHnkEueu+3A c9052pZjzffegQuuUMuF25x00M4HjXPfxytv/d/J7z044IEPnlDezBf9m0+0a0T77KSznj76HK2v eu3stx5878T/vvv9wvs+P0bIXy9+/8rzm97E573sVQ+AyWPe9gjHveb5j3sJDKAEsVdA7Emwgbch 3/s2cr73xW99r9tgCGsnv9iVD3+h81zTyCY33rVteJ9TG9XKNjy2mU1qUaMc5mo4ud/pkG1pwx/o /y6HQs85bYUwROIRn2Y1Ie5mJXcjyN3qRkUA2M2KU7SiPVKHRS1uUYumYwjRumdAhAjwf8eroP/K WL3wEZCNbFzgGgeIQOS5sXtNc6H9dsjHj6SQfn2sHw+J+EciouuEJSThB1XXQRLCb4PoQ2TucBfI Peoxf5nLJNMW4sbmqTGOE4Rj9hx4R+0dEI0PpOPy+jdGCI6xjqqMICr5lcUvDqSKV8xlLavYxVt6 MYq2fCMZ60i9OcKxgOA7JQLv6LczglJwzlSlAEv5SlOaMZbFHGUoW2lBO1rQgctUWOp8KTNf5tKW XCRnOWt5TnMq02hAQxr0RDm0cMpTnj6LZ/SkB/+9o5Wxb/G82RktyUQcIo6JvFsi5xZaUD62EIdP e2jbfii6QcJGLsCcSEZTJhEINsyjqxmLJE0y0pMVJaElQ6lJSSrClJR0pUNR6VFCA1LWwPSmJuFo Y3DK05769KdADSpvXsrBlgr1qEgNCRd5QlTzGVUj+YCqVPNB1ar+I6pTrSpVwaLTrrIlihttSFgP MlZ75IMgZx3IWdNaELamla2tSapcSyLJRaovkqxrXV4deUKsXvWvGImqXzci2IwMdq6ILU5dPchY RoIwryAsYSOlGljA/vWwhrUsZs/lVYul84rsxOUufwlGLyLkrWYVyFu1CtfWsrazCElscPA6QkX/ OnaEkyVqYSuL1c1eNrOyDS5qYMJL0p5zZqN1Z1lT69bUOtcga1VrbYRL3fJNVrKM5ettsVvbqWa2 tx3xK3ipS17dLLW7tpXfeU14XUkeVrystSxv41ve+nK1JsuFrX47i5Sm2tc0+01NfgNM4AIb2Db/ JcyBqZJgnC7YXw0OS2UEIICNRThiUBwnQgYMEQoXhMIgPgiIR2yPEYf4wWu5MEcy7E6cmLjCHhZI jAkyY4TUGMU4zsxoyxlMDWu4nTQ+sYwrPGSD3PjDRM6xkjGzYyn20skt3iiJBzLjI7/YyEleslVU /BmLfBaYyDVtMMesECGXOMlHRnKQ+ctlvbC4/yBgfrI6ecyQKVc5yyLOcppT0+aMvRnKUI7zRDxM aDTjGctUPrSWF82YjApa0O0ca6HPnOgiU9rSl/5LnzeN3kRiF7Kmc2pHXpwRE5daAKcG8akvzGiK 7bnVsFaMZCjMacHEWjS1zrWud81rP9/61wHu9bOAXZnTEEPFxEaMBtdLFP8eWyPEiPazhU1tvPi3 J02VdrT/MW1uBzfZv4kzj31M7nGHkcz2IEa6E6JuA1f7NSV1X3cjm95OH7vbG8E3ccDN0bGGGdDo NC66DxJthLSb3wivSVBOuFTrQtKxsnsqR6QNbX2/++JhcThuRdjIxY7k2SDHcMIdBtbSyrnH//8+ rmk32m51H3zkUNG1S8S9TjF/+dygBXK6tS0QbRcc5jrB+GauHRKLC90jQLcMhxfy8qQ7HSZegd3R NfL0qm9r6ljP+rutznVuaV3BXb/J1zkT9rIzbOxoR6rZ1872y6T97eNpu7zgTve6d0bueEew3feu m7zDhe9G8bvgbQp4kgxe1oV38+EZkvihLD7FjY+85CdP3sfHnPKOt7zmO4b5rGz+81nqvOhHvxeY k35uST+96sEO+mKv/vWlXzzsZ4+U1tv+9rhPDu1Rn/uo7P73wA9+Tntvm0MY/xD2MD5BlJ/84zPf +c5PCPMFAn3kUx/6CJm+9pFffe5b//rNx37/Qbr/ffELRCPGR/8hMAL9jKTf/euvvkfe/w/607/+ 64e//NnvfP6rH/8b0X/4J4Dkt3UtoXzT13wKOBAJmIDZ930LuIDbdxATCH4OCH4SCIEK4YAVaBDP Z30V2IDex4AaiIERKIIGAYD/53/3l373538qCIMyaIAsgYAQaIMbWILjd3wkuHwj2IM7eH0fGIE7 2IELgYI+SIEg+IM9iIJGCITRd4I8GIRASIUWWIJDKH06eHg42IRbaIIPaIRdCIYYGIVjWITl94VW SIRsSIJZ6IVJ+IRlOIXbd4FIuIZnOIc5CHpn+IFRWIVKqIdwCIhe2IXdl4Ru+IceeIMaeIFV/8iB TKiA1aeF4ceEbwh+8NcRBfiCMbh/mYh5Lph/M/iJoxiA+fd+LRh/ohiD6oeKx1eK/Gd/qwgSqWiK HyGLtliLoUiLrziAouiKtkiKK8iCs8iKw2iM1OYSfaiDd6iEZsiIROiIz3iJPiiHD4iIhIiNkBiN 3geLsXiKveiLL1iLHKGLxciJM4iOvaaMSyiIYOiI72iJ7UiGiSiE80iF1EiJ2qiGdxiC9wiP03iP 3GiFy9iGl9iMCecTAviNrRiO3siKobiQnqiJqyiL7WeO7Td/57iQGmmKDumLwqiO5AiRFbmRvYiR r0iAGSmM1UZ8LvmSMBmTMjmTNCl8NnmTv/9Hk4yHk8OnkzVhflNokJN4iEBZlNjIjX+IkJW4hGm4 lNDok/7ij025hvSYhf54lP04lXbYlEE5htYIlaqhkLMYkeBYjhtpljCIiySpf7/Ylp+ojpmokmuJ jDx5K+OoisAYjMeYlmXJl8MokW7JliJBlsS4gnDZk2DpGj1xlwC4ix7Zf90njuAImIbZlxP5kG+p io1ZkphZl+TBmK7IiaJ5loU5kiqYl46plxQZmJDJmXQZG4lpI4s5lpoJkqpZiriYl3O5f7rJknsZ mrXZmZ7pGTWolWmIhci5iIMohe4oiVOZjVV5nMxJj2I3nIGxkhaJlo+Zkhk5kpQZl67pjZHfmZ0T eZjWeZ7omZ59FpuWp57uCXzs6XrCFp8Q8571RZ9yEXz4uZ9hqXX8+Z8HYZ8COqBlAaAGeqAI6nQE GhgJaqAL+qAQ2hsNOqEUymAEyp84WaEauqH7mZ4yGaEhwaEiOqIkWqImmicg+hUnuqKtlqIu+qIg IaJ1yaJbdnQ0eqOLBqM/gaM8uqFj16MXoaNCGmu7BqQ0KqQxCpNIuqRM2qRpZ6S956RKAaVUWqVW qmxSOntXuqXJ9qBc+qVgGqZiiqFZWqa+cXhmmqbq2XaTN6Zu6ndqGntaxmtv6hIBAQA7 ------=_NextPart_000_0009_01C746EF.2E8366C0-- From DuffFarrah@capitalreefs.com Fri Feb 02 12:16:09 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HD21B-0004og-UN for nfsv4-archive@lists.ietf.org; Fri, 02 Feb 2007 12:16:09 -0500 Received: from cp637136-a.landg1.lb.home.nl ([84.25.70.238]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HD216-0002IM-1B for nfsv4-archive@lists.ietf.org; Fri, 02 Feb 2007 12:16:09 -0500 Received: from computeronder (unknown [125.169.5.179]) by cp637136-a.landg1.lb.home.nl (Postfix) with ESMTP id 4E2F625D80F8 for ; Fri, 2 Feb 2007 18:16:29 +0100 Message-ID: <000f01c746ed$d3a1fab0$ee461954@computeronder> From: "Benefit GalaJenna" To: nfsv4-archive@lists.ietf.org Subject: JamesKeri Klum Date: Fri, 2 Feb 2007 18:16:07 +0100 MIME-Version: 1.0 Content-Type: multipart/related; type="multipart/alternative"; boundary="----=_NextPart_000_000B_01C746F6.356662B0" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1106 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106 X-Spam-Score: 4.4 (++++) X-Scan-Signature: 1e467ff145ef391eb7b594ef62b8301f ------=_NextPart_000_000B_01C746F6.356662B0 Content-Type: multipart/alternative; boundary="----=_NextPart_001_000C_01C746F6.356662B0" ------=_NextPart_001_000C_01C746F6.356662B0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Mosskate bosworth orlando bloomteri. Dance studio nrj music leaving. Dawson, centhalle cruise katie olsencolin monkkeanu, careypaula? Jordan = bratman going, toscana. Ripaelle secret ryanjustin lewisemmy, awards. = Vanessa mosskate bosworth orlando bloomteri nicollette. Annual brooke nicole, michelle categories in order ready. Reidlatoya = flynn boyleanna aka? Onealtv bow love dawson centhalle. Art costume institute benefit = galajenna hogankatie holmes! At the art costume. Categories in order ready to work out dance, studio. Ff, goldie = hawnjaime barbarie lawaxl. Boyleanna aka, haylie dufffarrah, pittkeira. = Wife brody rachel bullock, jesse jameskeri klum sealjanet, jacksonbai. = Stonemena, depp vanessa, mosskate bosworth orlando, bloomteri! Ripaelle = secret ryanjustin, lewisemmy? At the art costume institute benefit galajenna. Sealjanet jacksonbai dollsgwen, richards richie. Kitchen with her, husband jordan bratman? Von simpson hilton mtv movie hiltonvida. Benefit galajenna hogankatie holmes. Hudsonben leigh, cooknelly kidman = miliandemi. Garner ben affleck violetkate. Guerratoni riccikate keith urban ripaelle = secret. Going toscana page of. Husband jordan bratman going toscana page, of = pages gt. Riccikate, keith urban ripaelle secret. Michelle categories = in, order, ready to work, out. Richie samboraed lee, mendestom jaime = foxxvivica. Kitchen with her husband jordan, bratman going toscana page. Ripaelle secret ryanjustin lewisemmy, awards th annual brooke nicole. Garner ben affleck violetkate moss lindsay jayzmandy moorekobe bryant! = Katie olsencolin monkkeanu careypaula reidlatoya. Riccikate keith urban ripaelle, secret ryanjustin, lewisemmy! Pittkeira = hatcher, ryan stonemena depp vanessa. Pittkeira hatcher ryan stonemena depp. Michelle categories in order ready to. Klum sealjanet jacksonbai = dollsgwen, richards richie samboraed lee mendestom? Pages gt last raquo. Richards richie samboraed lee mendestom jaime = foxxvivica foxus? Rachel bullock jesse jameskeri, klum, sealjanet jacksonbai dollsgwen = richards. Boyleanna aka haylie dufffarrah pittkeira hatcher ryan = stonemena depp. Wife brody rachel bullock jesse jameskeri! Haylie dufffarrah, pittkeira hatcher ryan stonemena depp vanessa. Page of pages gt last. Love dawson centhalle cruise. Ripaelle secret ryanjustin lewisemmy, awards th annual brooke. Nrj music leaving spanish kitchen with her husband jordan? ------=_NextPart_001_000C_01C746F6.356662B0 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
3D""
Mosskate bosworth orlando bloomteri. = Dance studio=20 nrj music leaving.
Dawson, centhalle cruise katie = olsencolin=20 monkkeanu, careypaula? Jordan bratman going, toscana. Ripaelle secret = ryanjustin=20 lewisemmy, awards. Vanessa mosskate bosworth orlando bloomteri = nicollette.
Annual brooke nicole, michelle = categories in order=20 ready. Reidlatoya flynn boyleanna aka?
Onealtv bow love dawson centhalle. Art = costume=20 institute benefit galajenna hogankatie holmes!
At the art costume.
Categories in order ready to work out = dance,=20 studio. Ff, goldie hawnjaime barbarie lawaxl. Boyleanna aka, haylie = dufffarrah,=20 pittkeira. Wife brody rachel bullock, jesse jameskeri klum sealjanet,=20 jacksonbai. Stonemena, depp vanessa, mosskate bosworth orlando, = bloomteri!=20 Ripaelle secret ryanjustin, lewisemmy?
At the art costume institute benefit = galajenna.
Sealjanet jacksonbai dollsgwen, = richards richie.
Kitchen with her, husband jordan = bratman?
Von simpson hilton mtv movie = hiltonvida.
Benefit galajenna hogankatie holmes. = Hudsonben=20 leigh, cooknelly kidman miliandemi.
Garner ben affleck violetkate. = Guerratoni riccikate=20 keith urban ripaelle secret.
Going toscana page of. Husband jordan = bratman going=20 toscana page, of pages gt. Riccikate, keith urban ripaelle secret. = Michelle=20 categories in, order, ready to work, out. Richie samboraed lee, = mendestom jaime=20 foxxvivica. Kitchen with her husband jordan, bratman going toscana = page.
Ripaelle secret ryanjustin lewisemmy, = awards th=20 annual brooke nicole.
Garner ben affleck violetkate moss = lindsay=20 jayzmandy moorekobe bryant! Katie olsencolin monkkeanu careypaula = reidlatoya.
Riccikate keith urban ripaelle, secret = ryanjustin,=20 lewisemmy! Pittkeira hatcher, ryan stonemena depp vanessa.
Pittkeira hatcher ryan stonemena = depp.
Michelle categories in order ready to. = Klum=20 sealjanet jacksonbai dollsgwen, richards richie samboraed lee = mendestom?
Pages gt last raquo. Richards richie = samboraed lee=20 mendestom jaime foxxvivica foxus?
Rachel bullock jesse jameskeri, klum, = sealjanet=20 jacksonbai dollsgwen richards. Boyleanna aka haylie dufffarrah pittkeira = hatcher=20 ryan stonemena depp. Wife brody rachel bullock jesse = jameskeri!
Haylie dufffarrah, pittkeira hatcher = ryan stonemena=20 depp vanessa.
Page of pages gt last.
Love dawson centhalle = cruise.
Ripaelle secret ryanjustin lewisemmy, = awards th=20 annual brooke.
Nrj music leaving spanish kitchen with = her husband=20 jordan?
------=_NextPart_001_000C_01C746F6.356662B0-- ------=_NextPart_000_000B_01C746F6.356662B0 Content-Type: image/gif; name="RyanJustin LewisEmmy.gif" Content-Transfer-Encoding: base64 Content-ID: <000a01c746ed$d3a1fab0$ee461954@computeronder> R0lGODlhnAHoAIfoAAADA4cOAA1zAIONAAgCgn0AggB2ccnNzbbOvJ7U4UwfAFUWA3oWAKgUALsi AO4bAAlCDCNOBz5LBlU9BXhNAag8AMtFAOlICABTABxRADZaAFtXAIhaAJpXAc1ZBuRTAAB9ABaL AD+NAGaJDnmOCqR7ALN6AOF/BwCXABabDTiuAFqRAIucAqugALquAOqlAAzCCx26AEi9CWi3Dnq0 AanNC8G0AN26CwHhBh/rAEbgDGraAILuAJbVAMDlAOPRAAEAPicAPjQNQGIOTIkAQpMARL4KSNsA RAgpPycnPDwWPlgmOHkTQKgbS8wZOuEiMw5ASChEQkM0RVs0NXNDMao+SMlBMek5SABaOC5qRkNS TVZVNYNpDaJWTbpZQehsTQB/QSWITThyQ1uAS3RxOaV2Psl0S9GJSACSSi6lSEWgPWyUPnuiPJ2d TbmbNNWoTQS1Pym+TUu0OWe9QXvHRKvMR7THPOXIPQfoSxPSOU7sPVfUOnPZP6XZRMTmRtjlPwAG gRwAjkgAcm4CfH8Ieq4AhLYEeNwAegURjCUVdD0RiWInc3MVh6Ybe8IrdN0ugwpCfyk5g0pBgGNE dXo/jptId8BBieI4gwBWiyZTeUZig1RZhnVudqNXibJWdepZgwCDcR90gU13eVx+f4KHjaqKgbR3 h995fQmiehuocUeSiWmnf32VhqCff7WYeeOmfwW2chfDijjCi168hYe2gJbCi8WzjdrAeQXhhB7u i0bsdV3cf3PkfZ7egLjkh+nchQAAtioEyD0Nv1cDsogOuqQAx80IudkAsgAexRYmxkYfzGIst3oU xqMtxb8fsuIevgJGzCcysjQ1yGI9w45OwaU4yc5EveZJtgRoxiJdyEZZyW1otHJuzpdXxbFpztRk wgB2zSB3yTZ0xWyCw4mOvpl6tsF+xe2DugCXzROhzDikyVWktIifwqekzricu+mfyQC3wRq1xk67 uVXDs4e+vKXMu/v/+6OnlYeCh/IAAAD9CP/+AAAJ9/8D8gDx//b//yH5BAAh6nsALAAAAACcAegA Bwj/AO0JHEiwoMGDCBMqXMiwocOHECNKbPivosWLGDNq3Mixo8ePIEOKHEmypMmTJSeqXMmypcuW KGPKnEmzps2bOHPq3Mmzp8+f/14KHUq0qNGjE4EqXcq0qdOLSKNKnUq1qtWrWLNq3cq1q9evYMOK HUu2rNmzaNOqTfi0rdu3cOPKnUu3rt27INfq3UsUr9+/P/kKHky4sOGXgBMrXsy4sePHkCNLnky5 suXLmDNr3sy5s+fPoDMfHk26tOnTqFOrXs26tevXEEPL1gi7tu3bemfrno27t9fdwIMLH05csu/j tosDRm5YufPn0KOHZE69uvXr2F2ODBBgI3fv3TV+/xcf/u/4jOcxpr+43mJ76fDjNuRujz79+gHw 69dvPz///Pf1t98HBA5E4AcGFnjgggfa02CCCDLI4EACBgjghQJV6J+GGWJ4X3YgGsbdiP51SCJB JH6I34kUpgjhiwI1+OBBD9ZYoEIplrjiiCi62CKLJvIY4pBjiUQieiMi2d6R6iV50YEVQfmPlFJq RCWBUWLpEZPsOdnlkl66F2ZKRJYplJFj/sOlmGC2WV6WH0y5oJxx0tmRhBZVydGaFfGpZpp++pmT mYSyBVKOX4aJKJuKpvgklpDGeWWdHM2Zp5Z7Ospoeov2qamngupU6KgPcfjffqam6mGJMkboKoIO Sv84Y6w3xihrraqeeqqFuppK6q9hqdgjQsK2SKyOECq4IIwJLcssjsgae1CxHR4L7LVSPcYgnZjq aaWe3sYnLnyETTihrbAiJOGz2Ko0LmXlzugsrc22Cuusqr2rr0mFyVsrvereaGO6Zu77XL+1znqr sgTbK+tqBkcs8cQUV2zxxRhnrPHGHHfssUjthizyyCSXbPLJKKes8sosj7ZJQy9HpNsmljkEwM03 8xWzQDvb8/ImQAfNc9AxEy00QUb/XNDORA/ddM9OA+30QE1HDbXVP/ectdEIMX00z2C3VLXPSVP9 NdJoU03200uvfbbbRad9NWEg3WyR3YrRbJHeFdH/zPfeGP3990WD9w244YAXPvjiiP8jeOOOZ6T4 44dvxDflkWeOEuaQa+455I8Xrrneolce+eWEw7tQzgfhzLo9rgMAO+uxyy5Q7LfjPnvuA70ets/A g3313GofRLzSv6eNdOCWd3566swzj7rpkjvvN9GOA7130IZrD/33npeeOerkNz9984l3Lv5iDPne u+27zy47zrvTHz9BOdufv+2vu8908MAbnkKO1zUAzk2AymsbANWmNYMI8H8C+dz3FIc47z0vcaKj oOnER7r0dc981IveBzM4mfbBD3/wox3/Vng/99UvhSt0oQOFF7aywU2BDuRa8ZJnNrYtbWxxa5sO /3/owyDyUHnDq2DqQoc+8HGOIx3sYPawt0GjBY6KFhQhZ/CGES7i7YsAqIjdvBjGf9TOjGVEoxhx 9hG/eXB9oGui9EIoQThKkYJSrF5Qdoi8I/JxhsFrYNkIiMMFEk+IDPRjAHdovBkecDQf4eJFyLjG SqqRkphMIxglCcIPSlCPzgvlBT+pQSgqcY6hLKUb6dg4DeZxlHsrYCEbyJA+Io+AEJSl3ADZnEhq MoyUVKMwx/jLYRLzbsWcZBo9eMFSxlEjJGzlEkGpPmke7ol1JBw2N4jE5PVxkbpcoDhpacByGrGb 4qwhL6F2SNToTn79Y+ELXfc+esbzfQWRITt7eP+0ISpykDis2iAFSlCvSY2H7OSa1nb2ySpmcYrQ w2JHqAi+vnFvgyJM2ueuJ9FsVg6O8OGkSUT6sc19DKTLwYoMIbJSQi0FpQaD6V+y0lKbnbBlYpMZ fGRaUnLh9KdADapQddrTohrVJyq9qUJqypyjFrUhtVsJU1GokHwQxKoDsWo+tspVe2A1q17l6laB 5dTLmJCqE5kqPhPyVa9e1a0G+SpW26qysirmrAZRYe7op793+hWGBZErXN1KV7AKdqiIFYwM9Sq/ xu6Phfds4U0FS1mEaBWsic2sXqK6V8DGb3/4jCxT5wrXuYq1rag9rWZhYtelbDKZYBTmJWG7TI3/ 5OMft63IbXOb24zs1iK9depqwVKS1yLTksesZDBJepHf6ha3z7UtdKPb2urOBa+8y2529XpP0Xr2 rZUd7FsFQtqzWPe8XYydMtdrTDS6DplstKRsm4uR3p7WucDF7WnRy1/GMLe/AH4XS9Q63AKrjMAG TvB1AszgBjvYLgqOsIEffDEBCIDCGG6MCemJEAQ7xMIFsbCIDyLiEtujxCPOToY1g10PswTFAjhx jAUC4hDPOCE1lrCOj+LL46rXmPH9sXwvUmIiX7giFs5IkjmyZLrsWLPd9R1o0SpZEqeYxjfO8UBg bBAtq3jFNVud7tw35bXeTyFXlvGWb4wQLXv5/zVgDmlt5zvb9ArZI0X+R5ObvBE+8znOgOaXmPN6 0zJrFyIgTnSW2WzlNQsm0BLDrpl5R+bvtlTRasaypjPN6Tc/+dNUcWGlOxtDKStVxibG8pVzjGJH g/rVtvE0rGfNFcD8GdI2oXVscM1rAeu6qb0OtrCHLZxfGxspxDi2snnskdr9VybPtggxMEKMak+b 2NjOSbRnsm1rV/sf165IuLNNbmjX9sfoTneQ30vnaY+b2rheNmvrNmcfB7POyF0mJ93NkXeXGyPy jmBI/ptc+RY8th75tkb8/W/aBFzS8DR0lMd8aoNYmyDVfrjGiWLq0J4wyq2reEGSbQ+SkxxlDf+H jCQ3OV+WL1ff9b42v1OOko1POuLzKzTF7bfXQ5fc2wLxdsZt3hcGJ/UlJye6u3p9dJckvV00Z99U 3qn0qk8l6ruxuta3zvWue/3rS8c6wMF+FbHnmuxoT3thzI6XX7NdN8d+u9zLqnaK8LfueM+73vfO d4LM/e+Av0nfB0+VwBeH8Ii/uuEXX5fEM4TxOHG85Ce/Fsg7nPJZsbzm4YL5zlN+8yDzvENAf1ei B1r0jya96gOD+ta7/vWwj/3WV0/72tv+9rjPPbZlz3uHHOL3h7DH7wkyfOEDv/jHP35Cii+Q5Ae/ +clHCPOnH3znV//50Dd+9Atifexv3yDMNz7/9IE/kPAP3/kb+b1F1F8R9rf/EBfp/vqP//74w9/9 72c/+v8h/wc/5PzYJ37mF4DhJ30E6H3PR30HoYDZV4DZJ34QyBAFyIDgl4AWWH7wx38ZWH/uh3/z 94H1B4IY4YEdeH8bqIEoOIIZiH8seILDpn4tmILp54IZQX8hyIEn6IEpaIMwSIP5t4E6OIP2p4Ia oX8mSIQxWIJFuILAd4M2OIQiCIU4WINM2BFBaHS+d33Ep4XLF4ALSH4P2IAHWIHjd4EOWIYYmIVb yH1eiIHI54UAuIYUuIbad4FoKHAymIdR2INUeINLuGL/x4UP6HxsqBBvGIYCOIZkqHxv+H0R/1iH YPiFdJiGBkiJaTiAkNiGl0h+DDiBisiGhOiA1Kd8kyhvcWiJpXiGlHiIm1iKbmiBrFiBc2iIn4iI hWiLpyiGjyiLsIiAuFiLqJiLqJiKmmhswniGmNiFpIiJyQiKvWiLrziMXeiKqhiBnviIp3iFGmiE JfiEfhiESUiDVxiDGRaIg2iHiFiNzOiL1liMywiGyGiH1XiLljiPzdiJ6KiK7xiL2AiHvriOZNiP rhhhH+GNBpl8RCiEH7h/29iEHEGODdmE4YiQCml/DvmQLkiR86eEUSiFMgiRehiR32iC9MeDGumH upeS5BZwKnkXxtaSKdV7sAeTNFmTNnmTOP9Zcw3xfZEoiqH4kz3Jk7U4gKQokM4Ii5tYlLsok3sB Ehx5kToYleJYhR9JlSMphU85lQuphBwZkjnJGBLoj3UIjT4ZkLHIj6PIju0IjYX4jkY5j0xpXh5B giRplR0ZkkbohHbZjUDYlxbpg0jokHwIgtr4lTE5jXKohT4ZfdaXiWU4h6zYiJEojWapmIIIgXD5 G4Z5EnS5gxd5l1K5lXlIjnmJguAImPlHmBKZg3YJFXEpl1aYkUfYkH2YkFg5m13pmSaJkl6Jktw4 m7zJea8pFPjohgE5kApIgZE5hrOoj204imvJlqSRklkYlMZJj6/Iidt3j9bZisHojj9pnITiSJlp sZl7NJws8XdaZ57sOR3o+Z7wGZ/yuXftaZjzKXuAd5+TV5/yoZ/++Z8jo3sAihVxNqCFx5+bYaAK uqAMGhYI+qAQGqESOqEUWnquV6Gs16AaWigYunry1qGR92kgOqIkWqKQt6FaEWB4Z6IVkXYs6poo GqMyujIvOnZfR53vWaOLN6NEpaM+Ki48ahA/Gm9BWqRG+mVDKnZH2qBEuqTrKaGS95VOOqVUWhpJ mp8KeqVauqVcChnD2aVKWqViCklgWqZmWp9jmqZqmhu7t6YPV6BuuhBg+qRvF6Rmt6QBAQA7 ------=_NextPart_000_000B_01C746F6.356662B0-- From nfsv4-bounces@ietf.org Fri Feb 02 18:02:51 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HD7OY-0006FQ-Mz; Fri, 02 Feb 2007 18:00:38 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HD7OV-0006F8-Iw for nfsv4@ietf.org; Fri, 02 Feb 2007 18:00:35 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HD7OU-0006qb-4a for nfsv4@ietf.org; Fri, 02 Feb 2007 18:00:35 -0500 Received: from smtp2.corp.netapp.com ([10.57.159.114]) by mx2.netapp.com with ESMTP; 02 Feb 2007 15:00:31 -0800 X-IronPort-AV: i="4.13,274,1167638400"; d="scan'208"; a="28437776:sNHT339740884" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l12MxkAx028342 for ; Fri, 2 Feb 2007 15:00:31 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Fri, 2 Feb 2007 15:00:10 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Fri, 2 Feb 2007 15:00:09 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Date: Fri, 2 Feb 2007 18:00:01 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: Proposal to address issue 95 Thread-Index: AcdHHby2StLBKaDvSwSxvK7kz8gDog== From: "Noveck, Dave" To: X-OriginalArrivalTime: 02 Feb 2007 23:00:10.0269 (UTC) FILETIME=[E3AC44D0:01C7471D] X-Spam-Score: 0.0 (/) X-Scan-Signature: 67c1ea29f88502ef6a32ccec927970f0 Subject: [nfsv4] Proposal to address issue 95 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org The description for GETATTR has a bunch of samll issues in addition to the contradiction cited in issue 95. We need to fix them. Here=20 is the current text with some commentary, followed by a proposed=20 replacement. The GETATTR operation will obtain attributes for the file system object specified by the current filehandle. The client sets a bit in the bitmap argument for each attribute value that it would like the server to return. The server returns an attribute bitmap that indicates the attribute values for which it was able to return, That seems to imply, especially the reference to "was able to return" that the sets can be different, that GETATTR be asked for an attribute and not be able to provide it, and not return an error. =20 followed by the attribute values ordered lowest attribute number first. The server must return a value for each attribute that the client requests if the attribute is supported by the server.=20 That suggests that the only reason the bit is not on is that the attribute is not supported by the server, which is consistent with the paragraph above but in a confusing way, because the fact that the only bits which may be in the requested mask but not in the returned mask are because they are unsupported attributes, although that fact is not explicit. Also, it mentions an attribute not being supported by a server but the set of attributes supported is a per-fs item. =20 If the server does not support an attribute or cannot approximate a useful value then it must not return the attribute value and must not set the attribute bit in the result bitmap.=20 Here is the big contradiction. "Or cannot approximate a useful value" appears to contradict the previous sentence.=20 The server must return an error if it supports an attribute but cannot obtain its value.=20 OK, now we contradict the (now) previous sentence.=20 In that case no attribute values will be returned. All servers must support the mandatory attributes as specified in File Attributes. They must support these attributes for all file systems. This text does not address the issue of attributes that cannot be fetched because a file system is absent. So here is the proposed replacement: The GETATTR operation will obtain attributes for the file system object specified by the current filehandle. The client sets a bit in the bitmap argument for each attribute value that it would like the server to return. The server returns an attribute bitmap that indicates the attribute values which it was able to return, which will include all attributes requested by the client which are attributes supported by the server for the target file system. This bitmap is followed by the attribute values ordered=20 lowest attribute number first. The server must return a value for each attribute that the client requests if the attribute is supported by the server for the target file system. If the server does not support a particular attribute=20 on the target file system then it must not return the attribute value=20 and must not set the attribute bit in the result bitmap. The server=20 must return an error if it supports an attribute on the target=20 but cannot obtain its value. In that case, no attribute values will=20 be returned. File systems which are absent should be treated as having support for a very small set of attributes as described in=20 GETATTR Within an Absent File System, even if previously, when the file system was present, more attributes were supported. All servers must support the mandatory attributes as specified in File Attributes, for all = file systems, with the exception of absent file systems. =20 Comments? _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From zenbcqjxy@broadband.hu Sat Feb 03 04:57:53 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HDHeb-0002xi-QF for nfsv4-archive@lists.ietf.org; Sat, 03 Feb 2007 04:57:53 -0500 Received: from catv-5665164c.catv.broadband.hu ([86.101.22.76]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HDHeY-0003LI-QO for nfsv4-archive@lists.ietf.org; Sat, 03 Feb 2007 04:57:53 -0500 From: "World" To: nfsv4-archive@lists.ietf.org Subject: Stock Trader Alert! Date: Sat, 3 Feb 2007 10:57:57 -0100 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0005_01C74782.29A617E0" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdHgimmBk1wYsSMTnasDtzUNruBKA== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: <812EEFAF9614BF7.04A81A4691@broadband.hu> X-Spam-Score: 1.4 (+) X-Scan-Signature: 9182cfff02fae4f1b6e9349e01d62f32 ------=_NextPart_000_0005_01C74782.29A617E0 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
Get MGOA on Monday, Its going to explode!

Trading Date: Monday, Febuary 05, 2007
Company: MEGOLA INC
Symbol: MGOA
Current Price: $0.05
Short Term Target: $0.50
Rating: 10/10
Recommendation: BUY NOW

CORUNNA, ON -- (MARKET WIRE) -- 02/02/07 Megola Inc. (PKSHEETS: MGOA), a leading environmental solution provider, announced today that it has placed its first order for Hartindo Anti-Fire products, which will be used for product demonstrations and obtaining the required industry approvals. The shipment is set to arrive from Malaysia by the end of February, early March.

This company is going to break into the dollar market yielding MASSIVE returns. Take advantage, get in NOW, make massive returns! This is an ACTIVE and GROWING company.

Get in with MGOA before its over 0.50!
------=_NextPart_000_0005_01C74782.29A617E0-- From nfsv4-bounces@ietf.org Sun Feb 04 15:41:52 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HDo9j-0000f4-Ap; Sun, 04 Feb 2007 15:40:11 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HDo9i-0000ez-PL for nfsv4@ietf.org; Sun, 04 Feb 2007 15:40:10 -0500 Received: from e6.ny.us.ibm.com ([32.97.182.146]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HDo9h-00029Y-Hu for nfsv4@ietf.org; Sun, 04 Feb 2007 15:40:10 -0500 Received: from d01relay02.pok.ibm.com (d01relay02.pok.ibm.com [9.56.227.234]) by e6.ny.us.ibm.com (8.13.8/8.13.8) with ESMTP id l14KemSp018269 for ; Sun, 4 Feb 2007 15:40:48 -0500 Received: from d01av04.pok.ibm.com (d01av04.pok.ibm.com [9.56.224.64]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v8.2) with ESMTP id l14Ke8We289970 for ; Sun, 4 Feb 2007 15:40:08 -0500 Received: from d01av04.pok.ibm.com (loopback [127.0.0.1]) by d01av04.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l14Ke8Xs004808 for ; Sun, 4 Feb 2007 15:40:08 -0500 Received: from d01ml604.pok.ibm.com (d01ml604.pok.ibm.com [9.56.227.90]) by d01av04.pok.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id l14Ke88v004805 for ; Sun, 4 Feb 2007 15:40:08 -0500 To: nfsv4@ietf.org MIME-Version: 1.0 X-Mailer: Lotus Notes Release 7.0 HF85 November 04, 2005 Message-ID: From: Marc Eshel Date: Sun, 4 Feb 2007 12:39:59 -0800 X-MIMETrack: Serialize by Router on D01ML604/01/M/IBM(Build V80_M3_10312006|October 31, 2006) at 02/04/2007 15:40:11, Serialize complete at 02/04/2007 15:40:11 Content-Type: text/plain; charset="US-ASCII" X-Spam-Score: 0.0 (/) X-Scan-Signature: cf4fa59384e76e63313391b70cd0dd25 Subject: [nfsv4] Create Session for pNFS DS X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org I wanted to share some suggestion that Andy made to solve a problem that we have with create session on the DS. We would like to associate the session with a particular file system. The Linux NFS server implementation is using a single front end for multiple backend file system so we need some way to associate the sessions with a particular backend file system. The suggestion is to return a file handle with get-device-list from the server (at this point a specific fs is providing the device list) and than the NFS client should present that file handle to the DS at create session. The client must anyhow have the device list before it can create sessions with the DSs. This will help us validate the create session with the DS, since the backend communication is the through the file system, and also create different session for different file systems. Any implementation that does not need it can just pass an empty file handle. Please give it some though and we can discuss it further at the connectathon this week. Marc. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 08:17:04 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HE3h1-0001Lh-AV; Mon, 05 Feb 2007 08:15:35 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HE3h0-0001La-JD for nfsv4@ietf.org; Mon, 05 Feb 2007 08:15:34 -0500 Received: from web31809.mail.mud.yahoo.com ([68.142.207.72]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HE3gv-0001ie-JJ for nfsv4@ietf.org; Mon, 05 Feb 2007 08:15:34 -0500 Received: (qmail 88034 invoked by uid 60001); 5 Feb 2007 13:15:28 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=tjQpl1qz1Pj4elWGdTTMY5gWpw0v8YasBvOaxY92Me6F6yaXUcX66cdNATW0znuPtiQOK8G0PU+A7ff5calFzyHxUcIpDn7BSF3bRcv3NbRa+yjwXDFHVVUNh1IXfg87YoLzp0u3AC0negyB2hyKt3xHluDm2A9ayaobd4jlyzo=; X-YMail-OSG: W7JJ454VM1lz.1cS9d2fbZwRAb0Ib6mrKLOFHqd5Y2zYWZdfvbkSWw5K3tsZbLez5mL2x1uFQLdmh.RjI7iBY3cSr7mVlCbQT8ectPircvKSSlkrSyTbeUCLj1Td3GsgGb2SeCRyHXbEq97wNNmhSk6wqLaF83VdVviXE3YRqKBo.uIJ9CknDkoM Received: from [198.95.226.224] by web31809.mail.mud.yahoo.com via HTTP; Mon, 05 Feb 2007 05:15:28 PST Date: Mon, 5 Feb 2007 05:15:28 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] Create Session for pNFS DS To: Marc Eshel , nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <861616.87114.qm@web31809.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 82c9bddb247d9ba4471160a9a865a5f3 Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Mark, I'm scheduled to be at Connectathon later today and will be happy to discuss this and any other session issues in the spec. Some comments below ... --- Marc Eshel wrote: > I wanted to share some suggestion that Andy made to solve a problem > that > we have with create session on the DS. We would like to associate the > > session with a particular file system. The Linux NFS server > implementation > is using a single front end for multiple backend file system so we > need > some way to associate the sessions with a particular backend file > system. Is the idea that over a common server network address, the Linux server implementation would prefer to bind a file system to a particular session? Are the device ids for multipled file systems to a particular DS shared, or is there a specific device-list for each file system? Also do the device-lists have a non-empty intersection? > The suggestion is to return a file handle with get-device-list from > the Since file handles are opaque, I wonder if you meant fsid and not file handle? > server (at this point a specific fs is providing the device list) and > than > the NFS client should present that file handle to the DS at create > session. The client must anyhow have the device list before it can > create > sessions with the DSs. This will help us validate the create session > with > the DS, since the backend communication is the through the file > system, > and also create different session for different file systems. Any > implementation that does not need it can just pass an empty file > handle. > Please give it some though and we can discuss it further at the > connectathon this week. > Marc. > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 12:35:52 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HE7jH-0001hM-0H; Mon, 05 Feb 2007 12:34:11 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HE7jF-0001gY-BF for nfsv4@ietf.org; Mon, 05 Feb 2007 12:34:09 -0500 Received: from e2.ny.us.ibm.com ([32.97.182.142]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HE7jD-0007Hx-OF for nfsv4@ietf.org; Mon, 05 Feb 2007 12:34:09 -0500 Received: from d01relay02.pok.ibm.com (d01relay02.pok.ibm.com [9.56.227.234]) by e2.ny.us.ibm.com (8.13.8/8.13.8) with ESMTP id l15HY6oM013802 for ; Mon, 5 Feb 2007 12:34:06 -0500 Received: from d01av03.pok.ibm.com (d01av03.pok.ibm.com [9.56.224.217]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v8.2) with ESMTP id l15HY6BX260584 for ; Mon, 5 Feb 2007 12:34:06 -0500 Received: from d01av03.pok.ibm.com (loopback [127.0.0.1]) by d01av03.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l15HY6Fa021724 for ; Mon, 5 Feb 2007 12:34:06 -0500 Received: from d01ml604.pok.ibm.com (d01ml604.pok.ibm.com [9.56.227.90]) by d01av03.pok.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id l15HY6k9021714 for ; Mon, 5 Feb 2007 12:34:06 -0500 In-Reply-To: <861616.87114.qm@web31809.mail.mud.yahoo.com> To: email2mre-ietf@yahoo.com Subject: Re: [nfsv4] Create Session for pNFS DS MIME-Version: 1.0 X-Mailer: Lotus Notes Release 7.0 HF85 November 04, 2005 Message-ID: From: Marc Eshel Date: Mon, 5 Feb 2007 09:34:00 -0800 X-MIMETrack: Serialize by Router on D01ML604/01/M/IBM(Build V80_M3_10312006|October 31, 2006) at 02/05/2007 12:34:10, Serialize complete at 02/05/2007 12:34:10 Content-Type: text/plain; charset="US-ASCII" X-Spam-Score: 0.0 (/) X-Scan-Signature: 4b800b1eab964a31702fa68f1ff0e955 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Mike Eisler wrote on 02/05/2007 05:15:28 AM: > Mark, > > I'm scheduled to be at Connectathon later today and will be happy to > discuss this and any other session issues in the spec. > > Some comments below ... > > --- Marc Eshel wrote: > > > I wanted to share some suggestion that Andy made to solve a problem > > that > > we have with create session on the DS. We would like to associate the > > > > session with a particular file system. The Linux NFS server > > implementation > > is using a single front end for multiple backend file system so we > > need > > some way to associate the sessions with a particular backend file > > system. > > Is the idea that over a common server network address, the Linux > server implementation would prefer to bind a file system to > a particular session? Yes. > Are the device ids for multipled file systems to a particular > DS shared, or is there a specific device-list for each > file system? Also do the device-lists have a non-empty intersection? There is a device-list for each fs each with its own device ids but they might use the same DSs. > > The suggestion is to return a file handle with get-device-list from > > the > > Since file handles are opaque, I wonder if you meant fsid > and not file handle? No, I meant file handle. We already use this technic of returning special fh from the MDS in the layout with information that the DS can use to validate the file state for IO requests. The client doesn't need to interpret the fh just keep it with the device list and pass it to the DS on session create. > > server (at this point a specific fs is providing the device list) and > > than > > the NFS client should present that file handle to the DS at create > > session. The client must anyhow have the device list before it can > > create > > sessions with the DSs. This will help us validate the create session > > with > > the DS, since the backend communication is the through the file > > system, > > and also create different session for different file systems. Any > > implementation that does not need it can just pass an empty file > > handle. > > Please give it some though and we can discuss it further at the > > connectathon this week. > > Marc. > > > > _______________________________________________ > > nfsv4 mailing list > > nfsv4@ietf.org > > https://www1.ietf.org/mailman/listinfo/nfsv4 > > > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 14:15:48 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HE9IT-0003QP-8C; Mon, 05 Feb 2007 14:14:37 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HE9IR-0003QG-Ke for nfsv4@ietf.org; Mon, 05 Feb 2007 14:14:35 -0500 Received: from brmea-mail-2.sun.com ([192.18.98.43]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HE9IP-0002H1-64 for nfsv4@ietf.org; Mon, 05 Feb 2007 14:14:35 -0500 Received: from fe-amer-02.sun.com ([192.18.108.176]) by brmea-mail-2.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l15JEW0k000888 for ; Mon, 5 Feb 2007 12:14:32 -0700 (MST) Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JD000M017QNEX00@mail-amer.sun.com> (original mail from Spencer.Shepler@Sun.COM) for nfsv4@ietf.org; Mon, 05 Feb 2007 12:14:32 -0700 (MST) Received: from [192.168.0.3] (adsl-71-145-188-92.dsl.austtx.sbcglobal.net [71.145.188.92]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JD000G8K8472X30@mail-amer.sun.com>; Mon, 05 Feb 2007 12:14:32 -0700 (MST) Date: Mon, 05 Feb 2007 13:14:33 -0600 From: Spencer Shepler Subject: Re: [nfsv4] Create Session for pNFS DS In-reply-to: To: Marc Eshel Message-id: <636AE4F6-0463-4701-8234-0947788E7013@sun.com> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.2) Content-type: text/plain; format=flowed; delsp=yes; charset=US-ASCII Content-transfer-encoding: 7BIT References: X-Spam-Score: 0.0 (/) X-Scan-Signature: 14582b0692e7f70ce7111d04db3781c8 Cc: email2mre-ietf@yahoo.com, nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Marc, Can you explain further as to why there must be multiple sessions at the DS when that is unnecessary at the MDS even though both may be servicing different filesystems? Is there a session construct that you see bound to the underlying filesystem? Spencer On Feb 5, 2007, at 11:34 AM, Marc Eshel wrote: > Mike Eisler wrote on 02/05/2007 05:15:28 > AM: > >> Mark, >> >> I'm scheduled to be at Connectathon later today and will be happy to >> discuss this and any other session issues in the spec. >> >> Some comments below ... >> >> --- Marc Eshel wrote: >> >>> I wanted to share some suggestion that Andy made to solve a problem >>> that >>> we have with create session on the DS. We would like to associate >>> the >>> >>> session with a particular file system. The Linux NFS server >>> implementation >>> is using a single front end for multiple backend file system so we >>> need >>> some way to associate the sessions with a particular backend file >>> system. >> >> Is the idea that over a common server network address, the Linux >> server implementation would prefer to bind a file system to >> a particular session? > > Yes. > >> Are the device ids for multipled file systems to a particular >> DS shared, or is there a specific device-list for each >> file system? Also do the device-lists have a non-empty intersection? > > There is a device-list for each fs each with its own device ids but > they > might use the same DSs. > >>> The suggestion is to return a file handle with get-device-list from >>> the >> >> Since file handles are opaque, I wonder if you meant fsid >> and not file handle? > > No, I meant file handle. We already use this technic of returning > special > fh from the MDS in the layout with information that the DS can use to > validate the file state for IO requests. The client doesn't need to > interpret the fh just keep it with the device list and pass it to > the DS > on session create. > >>> server (at this point a specific fs is providing the device list) >>> and >>> than >>> the NFS client should present that file handle to the DS at create >>> session. The client must anyhow have the device list before it can >>> create >>> sessions with the DSs. This will help us validate the create session >>> with >>> the DS, since the backend communication is the through the file >>> system, >>> and also create different session for different file systems. Any >>> implementation that does not need it can just pass an empty file >>> handle. >>> Please give it some though and we can discuss it further at the >>> connectathon this week. >>> Marc. >>> >>> _______________________________________________ >>> nfsv4 mailing list >>> nfsv4@ietf.org >>> https://www1.ietf.org/mailman/listinfo/nfsv4 >>> >> > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 15:14:44 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEADb-0004rW-Oi; Mon, 05 Feb 2007 15:13:39 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEADa-0004rE-6l for nfsv4@ietf.org; Mon, 05 Feb 2007 15:13:38 -0500 Received: from mail.fieldses.org ([66.93.2.214] helo=fieldses.org) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HEADY-00084N-Ui for nfsv4@ietf.org; Mon, 05 Feb 2007 15:13:38 -0500 Received: from bfields by fieldses.org with local (Exim 4.63) (envelope-from ) id 1HEADQ-0003uD-6r; Mon, 05 Feb 2007 15:13:28 -0500 Date: Mon, 5 Feb 2007 15:13:28 -0500 To: Spencer Shepler Subject: Re: [nfsv4] Create Session for pNFS DS Message-ID: <20070205201328.GA14904@fieldses.org> References: <636AE4F6-0463-4701-8234-0947788E7013@sun.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <636AE4F6-0463-4701-8234-0947788E7013@sun.com> User-Agent: Mutt/1.5.13 (2006-08-11) From: "J. Bruce Fields" X-Spam-Score: 0.0 (/) X-Scan-Signature: d6b246023072368de71562c0ab503126 Cc: email2mre-ietf@yahoo.com, Marc Eshel , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org On Mon, Feb 05, 2007 at 01:14:33PM -0600, Spencer Shepler wrote: > Can you explain further as to why there must be multiple sessions > at the DS when that is unnecessary at the MDS even though both > may be servicing different filesystems? It's possible that a single host could have multiple roles--as a metadata server, or as a data server to any of several possible metadata servers. The host needs to know which role it's playing before it can respond to a given request. So the metadata server needs to insert this role information into something that the client will pass to the data server. Prototypes have been using the filehandle for this. Maybe the clientid could be used instead? But the clientid is smaller and already subject to a number of other requirements (to identify stale clientid's, etc.), so that carving up the clientid space between metadata servers may require more complicated coordination. --b. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 15:23:01 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEALk-0001Yy-Lv; Mon, 05 Feb 2007 15:22:04 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEALj-0001YL-93 for nfsv4@ietf.org; Mon, 05 Feb 2007 15:22:03 -0500 Received: from brmea-mail-2.sun.com ([192.18.98.43]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HEALh-0000wH-MX for nfsv4@ietf.org; Mon, 05 Feb 2007 15:22:03 -0500 Received: from fe-amer-06.sun.com ([192.18.108.180]) by brmea-mail-2.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l15KM18e022339 for ; Mon, 5 Feb 2007 13:22:01 -0700 (MST) Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JD000B01B2HNO00@mail-amer.sun.com> (original mail from Spencer.Shepler@Sun.COM) for nfsv4@ietf.org; Mon, 05 Feb 2007 13:22:01 -0700 (MST) Received: from [192.168.0.3] (adsl-71-145-188-92.dsl.austtx.sbcglobal.net [71.145.188.92]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JD000AOWB8NVS20@mail-amer.sun.com>; Mon, 05 Feb 2007 13:22:00 -0700 (MST) Date: Mon, 05 Feb 2007 14:22:01 -0600 From: Spencer Shepler Subject: Re: [nfsv4] Create Session for pNFS DS In-reply-to: <20070205201328.GA14904@fieldses.org> To: "J. Bruce Fields" Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.2) Content-type: text/plain; format=flowed; delsp=yes; charset=US-ASCII Content-transfer-encoding: 7BIT References: <636AE4F6-0463-4701-8234-0947788E7013@sun.com> <20070205201328.GA14904@fieldses.org> X-Spam-Score: 0.0 (/) X-Scan-Signature: 9ed51c9d1356100bce94f1ae4ec616a9 Cc: email2mre-ietf@yahoo.com, Marc Eshel , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org On Feb 5, 2007, at 2:13 PM, J. Bruce Fields wrote: > On Mon, Feb 05, 2007 at 01:14:33PM -0600, Spencer Shepler wrote: >> Can you explain further as to why there must be multiple sessions >> at the DS when that is unnecessary at the MDS even though both >> may be servicing different filesystems? > > It's possible that a single host could have multiple roles--as a > metadata server, or as a data server to any of several possible > metadata > servers. The host needs to know which role it's playing before it can > respond to a given request. So the metadata server needs to insert > this > role information into something that the client will pass to the data > server. > > Prototypes have been using the filehandle for this. Maybe the > clientid > could be used instead? But the clientid is smaller and already > subject > to a number of other requirements (to identify stale clientid's, > etc.), > so that carving up the clientid space between metadata servers may > require more complicated coordination. Ah, okay, this is what I was looking for... It isn't tied to the underlying filesystem but the potential dual-role that a server may be playing. This issue has arisen recently and a couple of us, including Mike, have been thinking about how to differentiate for this reason but for others as well (to correctly set up the initial sequencing of the session with the data-server as well). So, the requirement is the ability of differentiating the multiple roles a server may be playing and ensuring that we have a method of allowing the server to communicate that view to itself through the normal client interaction of the pNFS behavior? Spencer _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 16:54:08 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEBlO-0007BT-ML; Mon, 05 Feb 2007 16:52:38 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEBlL-0007Aq-LR for nfsv4@ietf.org; Mon, 05 Feb 2007 16:52:36 -0500 Received: from e3.ny.us.ibm.com ([32.97.182.143]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HEBlK-0003Cl-Bm for nfsv4@ietf.org; Mon, 05 Feb 2007 16:52:35 -0500 Received: from d01relay02.pok.ibm.com (d01relay02.pok.ibm.com [9.56.227.234]) by e3.ny.us.ibm.com (8.13.8/8.13.8) with ESMTP id l15LqY0A032377 for ; Mon, 5 Feb 2007 16:52:34 -0500 Received: from d01av02.pok.ibm.com (d01av02.pok.ibm.com [9.56.224.216]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v8.2) with ESMTP id l15LqXn0279658 for ; Mon, 5 Feb 2007 16:52:34 -0500 Received: from d01av02.pok.ibm.com (loopback [127.0.0.1]) by d01av02.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l15LqXWL012820 for ; Mon, 5 Feb 2007 16:52:33 -0500 Received: from d01mlc04.pok.ibm.com (d01mlc04.pok.ibm.com [9.56.228.37]) by d01av02.pok.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id l15LqXsq012817; Mon, 5 Feb 2007 16:52:33 -0500 In-Reply-To: To: Spencer Shepler Subject: Re: [nfsv4] Create Session for pNFS DS MIME-Version: 1.0 X-Mailer: Lotus Notes Release 7.0 HF85 November 04, 2005 Message-ID: From: Marc Eshel Date: Mon, 5 Feb 2007 13:52:01 -0800 X-MIMETrack: Serialize by Router on D01MLC04/01/M/IBM(Release 7.0.2 IGS702HF4|January 9, 2006) at 02/05/2007 16:52:33, Serialize complete at 02/05/2007 16:52:33 Content-Type: text/plain; charset="US-ASCII" X-Spam-Score: 0.0 (/) X-Scan-Signature: 5a9a1bd6c2d06a21d748b7d0070ddcb8 Cc: "J. Bruce Fields" , email2mre-ietf@yahoo.com, nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Spencer Shepler wrote on 02/05/2007 12:22:01 PM: > > On Feb 5, 2007, at 2:13 PM, J. Bruce Fields wrote: > > > On Mon, Feb 05, 2007 at 01:14:33PM -0600, Spencer Shepler wrote: > >> Can you explain further as to why there must be multiple sessions > >> at the DS when that is unnecessary at the MDS even though both > >> may be servicing different filesystems? > > > > It's possible that a single host could have multiple roles--as a > > metadata server, or as a data server to any of several possible > > metadata > > servers. The host needs to know which role it's playing before it can > > respond to a given request. So the metadata server needs to insert > > this > > role information into something that the client will pass to the data > > server. > > > > Prototypes have been using the filehandle for this. Maybe the > > clientid > > could be used instead? But the clientid is smaller and already > > subject > > to a number of other requirements (to identify stale clientid's, > > etc.), > > so that carving up the clientid space between metadata servers may > > require more complicated coordination. > > Ah, okay, this is what I was looking for... It isn't tied to the > underlying filesystem but the potential dual-role that a server may > be playing. This for both the dual-role and the need to associate create session with an underlying file system so we can know which one to use to validate the session on the DS. In the Linux server implementation all the communication among the machines are through the backend file system. Marc. > This issue has arisen recently and a couple of us, including Mike, have > been thinking about how to differentiate for this reason but for > others as well (to correctly set up the initial sequencing of the > session with the data-server as well). > > So, the requirement is the ability of differentiating the multiple > roles a server may be playing and ensuring that we have a method > of allowing the server to communicate that view to itself through > the normal client interaction of the pNFS behavior? > > Spencer > > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 17:54:51 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HECi3-0005D7-Vq; Mon, 05 Feb 2007 17:53:15 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HECi0-0005Cc-Fn for nfsv4@ietf.org; Mon, 05 Feb 2007 17:53:13 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HEChz-0006jt-4R for nfsv4@ietf.org; Mon, 05 Feb 2007 17:53:12 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 05 Feb 2007 14:53:08 -0800 X-IronPort-AV: i="4.13,284,1167638400"; d="scan'208"; a="29475447:sNHT20305726" Received: from svlexc02.hq.netapp.com (svlexc02.corp.netapp.com [10.57.157.136]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l15Mr44b020188; Mon, 5 Feb 2007 14:53:04 -0800 (PST) Received: from exsvlrb01.hq.netapp.com ([10.56.8.62]) by svlexc02.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Mon, 5 Feb 2007 14:54:01 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 5 Feb 2007 14:54:00 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] Create Session for pNFS DS Date: Mon, 5 Feb 2007 17:53:59 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] Create Session for pNFS DS Thread-Index: AcdJcFowRQ4B03P7QU+17d7PHFcv9QABzagg From: "Noveck, Dave" To: "Marc Eshel" , "Spencer Shepler" X-OriginalArrivalTime: 05 Feb 2007 22:54:00.0967 (UTC) FILETIME=[86CA8170:01C74978] X-Spam-Score: 0.0 (/) X-Scan-Signature: 386e0819b1192672467565a524848168 Cc: "J. Bruce Fields" , email2mre-ietf@yahoo.com, nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Correct me if I'm wrong but it sure sounds to me like your answer to Spencer's question about why metadata can=20 handle any number of fs's in a session (directing to the appropriate implementation) while you require separate sessions for eahc fs the data server is simply that that=20 is the way you have chosen to implement things. Is there some other reason that makes it particularly=20 desirable to have the protocol have sessions tied to particular fs's? I'm looking for something more general than simply allowing you to maintain an implementation choice you have made. Offhand, it seems to me that sessions are very near to the communication layer and I don't see any obvious reason to tie them to file systems. What am I mssing? -----Original Message----- From: Marc Eshel [mailto:eshel@almaden.ibm.com]=20 Sent: Monday, February 05, 2007 4:52 PM To: Spencer Shepler Cc: J. Bruce Fields; email2mre-ietf@yahoo.com; nfsv4@ietf.org Subject: Re: [nfsv4] Create Session for pNFS DS Spencer Shepler wrote on 02/05/2007 12:22:01 PM: >=20 > On Feb 5, 2007, at 2:13 PM, J. Bruce Fields wrote: >=20 > > On Mon, Feb 05, 2007 at 01:14:33PM -0600, Spencer Shepler wrote: > >> Can you explain further as to why there must be multiple sessions > >> at the DS when that is unnecessary at the MDS even though both > >> may be servicing different filesystems? > > > > It's possible that a single host could have multiple roles--as a > > metadata server, or as a data server to any of several possible=20 > > metadata > > servers. The host needs to know which role it's playing before it can > > respond to a given request. So the metadata server needs to insert=20 > > this > > role information into something that the client will pass to the data > > server. > > > > Prototypes have been using the filehandle for this. Maybe the=20 > > clientid > > could be used instead? But the clientid is smaller and already=20 > > subject > > to a number of other requirements (to identify stale clientid's,=20 > > etc.), > > so that carving up the clientid space between metadata servers may > > require more complicated coordination. >=20 > Ah, okay, this is what I was looking for... It isn't tied to the > underlying filesystem but the potential dual-role that a server may > be playing. This for both the dual-role and the need to associate create session with=20 an underlying file system so we can know which one to use to validate the=20 session on the DS. In the Linux server implementation all the=20 communication among the machines are through the backend file system. Marc. =20 > This issue has arisen recently and a couple of us, including Mike, have > been thinking about how to differentiate for this reason but for > others as well (to correctly set up the initial sequencing of the > session with the data-server as well). >=20 > So, the requirement is the ability of differentiating the multiple > roles a server may be playing and ensuring that we have a method > of allowing the server to communicate that view to itself through > the normal client interaction of the pNFS behavior? >=20 > Spencer >=20 >=20 >=20 > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 18:17:05 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HED4C-00080J-6k; Mon, 05 Feb 2007 18:16:08 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HED4B-00080C-FQ for nfsv4@ietf.org; Mon, 05 Feb 2007 18:16:07 -0500 Received: from brmea-mail-2.sun.com ([192.18.98.43]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HED49-0004qo-Ib for nfsv4@ietf.org; Mon, 05 Feb 2007 18:16:07 -0500 Received: from fe-amer-01.sun.com ([192.18.108.175]) by brmea-mail-2.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l15NG4N3001438 for ; Mon, 5 Feb 2007 16:16:04 -0700 (MST) Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JD000E01J31TC00@mail-amer.sun.com> (original mail from Spencer.Shepler@Sun.COM) for nfsv4@ietf.org; Mon, 05 Feb 2007 16:16:04 -0700 (MST) Received: from [192.168.0.3] (adsl-71-145-137-40.dsl.austtx.sbcglobal.net [71.145.137.40]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JD000C4CJARLG20@mail-amer.sun.com>; Mon, 05 Feb 2007 16:16:04 -0700 (MST) Date: Mon, 05 Feb 2007 17:16:05 -0600 From: Spencer Shepler Subject: Re: [nfsv4] Create Session for pNFS DS In-reply-to: To: "Noveck, Dave" Message-id: MIME-version: 1.0 X-Mailer: Apple Mail (2.752.2) Content-type: text/plain; format=flowed; charset=US-ASCII Content-transfer-encoding: 7BIT References: X-Spam-Score: 0.0 (/) X-Scan-Signature: 5ebbf074524e58e662bc8209a6235027 Cc: "J. Bruce Fields" , email2mre-ietf@yahoo.com, Marc Eshel , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org On Feb 5, 2007, at 4:53 PM, Noveck, Dave wrote: > Correct me if I'm wrong but it sure sounds to me like > your answer to Spencer's question about why metadata can > handle any number of fs's in a session (directing to > the appropriate implementation) while you require separate > sessions for eahc fs the data server is simply that that > is the way you have chosen to implement things. > > Is there some other reason that makes it particularly > desirable to have the protocol have sessions tied to > particular fs's? I'm looking for something more general > than simply allowing you to maintain an implementation > choice you have made. Offhand, it seems to me that sessions > are very near to the communication layer and I don't see > any obvious reason to tie them to file systems. What am I > mssing? I agree in that the intent of sessions is to deal with communication issues specific to NFS' use of an underlying transport (multiple TCP connections over the lifetime of the client/server interaction) and hence the need for the EOS. I can understand the requirement to deal with a system acting as MDS and DS(es) and the need to effectively differentiate and possibly linking the differentiation to the deviceid. Creating a relationship with individual filesystems seems like a crossing of an architectural boundary that will eventually lead to undesirable changes in the sessions model we have today. Spencer > > -----Original Message----- > From: Marc Eshel [mailto:eshel@almaden.ibm.com] > Sent: Monday, February 05, 2007 4:52 PM > To: Spencer Shepler > Cc: J. Bruce Fields; email2mre-ietf@yahoo.com; nfsv4@ietf.org > Subject: Re: [nfsv4] Create Session for pNFS DS > > > Spencer Shepler wrote on 02/05/2007 12:22:01 > PM: > >> >> On Feb 5, 2007, at 2:13 PM, J. Bruce Fields wrote: >> >>> On Mon, Feb 05, 2007 at 01:14:33PM -0600, Spencer Shepler wrote: >>>> Can you explain further as to why there must be multiple sessions >>>> at the DS when that is unnecessary at the MDS even though both >>>> may be servicing different filesystems? >>> >>> It's possible that a single host could have multiple roles--as a >>> metadata server, or as a data server to any of several possible >>> metadata >>> servers. The host needs to know which role it's playing before it > can >>> respond to a given request. So the metadata server needs to insert >>> this >>> role information into something that the client will pass to the > data >>> server. >>> >>> Prototypes have been using the filehandle for this. Maybe the >>> clientid >>> could be used instead? But the clientid is smaller and already >>> subject >>> to a number of other requirements (to identify stale clientid's, >>> etc.), >>> so that carving up the clientid space between metadata servers may >>> require more complicated coordination. >> >> Ah, okay, this is what I was looking for... It isn't tied to the >> underlying filesystem but the potential dual-role that a server may >> be playing. > > This for both the dual-role and the need to associate create session > with > an underlying file system so we can know which one to use to validate > the > session on the DS. In the Linux server implementation all the > communication among the machines are through the backend file system. > Marc. > >> This issue has arisen recently and a couple of us, including Mike, > have >> been thinking about how to differentiate for this reason but for >> others as well (to correctly set up the initial sequencing of the >> session with the data-server as well). >> >> So, the requirement is the ability of differentiating the multiple >> roles a server may be playing and ensuring that we have a method >> of allowing the server to communicate that view to itself through >> the normal client interaction of the pNFS behavior? >> >> Spencer >> >> >> >> _______________________________________________ >> nfsv4 mailing list >> nfsv4@ietf.org >> https://www1.ietf.org/mailman/listinfo/nfsv4 > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 05 23:24:30 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEHqy-000765-Sj; Mon, 05 Feb 2007 23:22:48 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEHqx-000760-T5 for nfsv4@ietf.org; Mon, 05 Feb 2007 23:22:47 -0500 Received: from e3.ny.us.ibm.com ([32.97.182.143]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HEHqv-0000AC-Gt for nfsv4@ietf.org; Mon, 05 Feb 2007 23:22:47 -0500 Received: from d01relay02.pok.ibm.com (d01relay02.pok.ibm.com [9.56.227.234]) by e3.ny.us.ibm.com (8.13.8/8.13.8) with ESMTP id l164Mi9L030971 for ; Mon, 5 Feb 2007 23:22:44 -0500 Received: from d01av01.pok.ibm.com (d01av01.pok.ibm.com [9.56.224.215]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v8.2) with ESMTP id l164MjYt280612 for ; Mon, 5 Feb 2007 23:22:45 -0500 Received: from d01av01.pok.ibm.com (loopback [127.0.0.1]) by d01av01.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l164MioM004802 for ; Mon, 5 Feb 2007 23:22:44 -0500 Received: from d01ml604.pok.ibm.com (d01ml604.pok.ibm.com [9.56.227.90]) by d01av01.pok.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id l164Mik3004799; Mon, 5 Feb 2007 23:22:44 -0500 In-Reply-To: To: Spencer Shepler Subject: Re: [nfsv4] Create Session for pNFS DS MIME-Version: 1.0 X-Mailer: Lotus Notes Release 7.0 HF85 November 04, 2005 Message-ID: From: Marc Eshel Date: Mon, 5 Feb 2007 20:22:35 -0800 X-MIMETrack: Serialize by Router on D01ML604/01/M/IBM(Build V80_M3_10312006|October 31, 2006) at 02/05/2007 23:22:49, Serialize complete at 02/05/2007 23:22:49 Content-Type: text/plain; charset="US-ASCII" X-Spam-Score: 0.0 (/) X-Scan-Signature: b132cb3ed2d4be2017585bf6859e1ede Cc: "J. Bruce Fields" , email2mre-ietf@yahoo.com, Spencer.Shepler@Sun.COM, "Noveck, Dave" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org We had a session discussion this afternoon at the connectathon and Mike have a clean solution for the problem I raised as well as some other session issues that he will share soon. Thanks, Marc. Spencer.Shepler@Sun.COM wrote on 02/05/2007 03:16:05 PM: > > On Feb 5, 2007, at 4:53 PM, Noveck, Dave wrote: > > > Correct me if I'm wrong but it sure sounds to me like > > your answer to Spencer's question about why metadata can > > handle any number of fs's in a session (directing to > > the appropriate implementation) while you require separate > > sessions for eahc fs the data server is simply that that > > is the way you have chosen to implement things. > > > > Is there some other reason that makes it particularly > > desirable to have the protocol have sessions tied to > > particular fs's? I'm looking for something more general > > than simply allowing you to maintain an implementation > > choice you have made. Offhand, it seems to me that sessions > > are very near to the communication layer and I don't see > > any obvious reason to tie them to file systems. What am I > > mssing? > > I agree in that the intent of sessions is to deal with > communication issues specific to NFS' use of an underlying > transport (multiple TCP connections over the lifetime of the > client/server interaction) and hence the need for the EOS. > > I can understand the requirement to deal with a system acting > as MDS and DS(es) and the need to effectively differentiate > and possibly linking the differentiation to the deviceid. > > Creating a relationship with individual filesystems seems > like a crossing of an architectural boundary that will eventually > lead to undesirable changes in the sessions model we have today. > > Spencer > > > > > > -----Original Message----- > > From: Marc Eshel [mailto:eshel@almaden.ibm.com] > > Sent: Monday, February 05, 2007 4:52 PM > > To: Spencer Shepler > > Cc: J. Bruce Fields; email2mre-ietf@yahoo.com; nfsv4@ietf.org > > Subject: Re: [nfsv4] Create Session for pNFS DS > > > > > > Spencer Shepler wrote on 02/05/2007 12:22:01 > > PM: > > > >> > >> On Feb 5, 2007, at 2:13 PM, J. Bruce Fields wrote: > >> > >>> On Mon, Feb 05, 2007 at 01:14:33PM -0600, Spencer Shepler wrote: > >>>> Can you explain further as to why there must be multiple sessions > >>>> at the DS when that is unnecessary at the MDS even though both > >>>> may be servicing different filesystems? > >>> > >>> It's possible that a single host could have multiple roles--as a > >>> metadata server, or as a data server to any of several possible > >>> metadata > >>> servers. The host needs to know which role it's playing before it > > can > >>> respond to a given request. So the metadata server needs to insert > >>> this > >>> role information into something that the client will pass to the > > data > >>> server. > >>> > >>> Prototypes have been using the filehandle for this. Maybe the > >>> clientid > >>> could be used instead? But the clientid is smaller and already > >>> subject > >>> to a number of other requirements (to identify stale clientid's, > >>> etc.), > >>> so that carving up the clientid space between metadata servers may > >>> require more complicated coordination. > >> > >> Ah, okay, this is what I was looking for... It isn't tied to the > >> underlying filesystem but the potential dual-role that a server may > >> be playing. > > > > This for both the dual-role and the need to associate create session > > with > > an underlying file system so we can know which one to use to validate > > the > > session on the DS. In the Linux server implementation all the > > communication among the machines are through the backend file system. > > Marc. > > > >> This issue has arisen recently and a couple of us, including Mike, > > have > >> been thinking about how to differentiate for this reason but for > >> others as well (to correctly set up the initial sequencing of the > >> session with the data-server as well). > >> > >> So, the requirement is the ability of differentiating the multiple > >> roles a server may be playing and ensuring that we have a method > >> of allowing the server to communicate that view to itself through > >> the normal client interaction of the pNFS behavior? > >> > >> Spencer > >> > >> > >> > >> _______________________________________________ > >> nfsv4 mailing list > >> nfsv4@ietf.org > >> https://www1.ietf.org/mailman/listinfo/nfsv4 > > > > > > _______________________________________________ > > nfsv4 mailing list > > nfsv4@ietf.org > > https://www1.ietf.org/mailman/listinfo/nfsv4 > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 06 00:29:20 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEIs1-0002ii-LF; Tue, 06 Feb 2007 00:27:57 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEIs0-0002ic-IZ for nfsv4@ietf.org; Tue, 06 Feb 2007 00:27:56 -0500 Received: from web31804.mail.mud.yahoo.com ([68.142.207.67]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HEIrz-0007Ca-7T for nfsv4@ietf.org; Tue, 06 Feb 2007 00:27:56 -0500 Received: (qmail 7266 invoked by uid 60001); 6 Feb 2007 05:27:52 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=Kc+EzSUD0nitj4jxVwKPJVDW+WOH5FSU7UVS04KWTzE4BVV7vgGSwzhLdQ7eYbDENgnd6AzqsK3DPAcipJzQ8PoDvaHEto4fyAZ0xyxNvTCbYAhVaKtDaC70Lg4xssWA+dYbs6CsyN97nytqYEeXeEEVO6Xwdp1woIHscJ+K99w=; X-YMail-OSG: xNpl248VM1nhfyV3FEg6YkT3oizEeO9uz4u.PicMbYmXetEalVJEgd07n5CaKFncemvVzV.4sqeRry6FQJvMBN2x1oDSCHYbPbV8t4LYa0h1x_BLXMQfPrhDucntFjiF7sBN8Ay59wysCOolJwQq9_ztkGdkpfREyiVnWan0ryVyXs7fXeNA7Bv17uSp Received: from [198.95.226.224] by web31804.mail.mud.yahoo.com via HTTP; Mon, 05 Feb 2007 21:27:49 PST Date: Mon, 5 Feb 2007 21:27:49 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] Create Session for pNFS DS To: nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <696900.5617.qm@web31804.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: b5d20af10c334b36874c0264b10f59f1 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Today at Connectathon a large group of pNFSers discussed this. There are several issues with draft-08 and the impending draft-09 (as it exists in the cvs server): - What sequenceid does CREATE_SESSION take when invoked against a DS? -- Also in pending draft-09, the CREATE_SESSION sequenceid is global across the pNFS cluster, so this means the CREATE_SESSIONs to all DSes for the same clientid have to be serialized. Not good. - The clientid is currently global across all nodes in the pNFS cluster. However, consider a vast cluster with lots of MDSes and DSes, where a given DS could potentially be holding parts of files from many MDSes. When given a clientid in a CREATE_SESSION call, there is no efficient way for the DS to figure out which node has the MDS for that clientid. - There is no may to bind a session to a DS or MDS for the case when both listen on the same network address. It would be nice to allow a DS to have an optimal implementation that just does the DS operations. This is actually fixed in the impending draft-09. During today's meeting we came to the realization that if we changed to the "MUST NOT" that bans EXCHANGE_ID to a DS to "MUST", that each DS and MDS that the client presents a given co_owner to can return a unique clientid to the client. Doing this solves the "what CREATE_SESSION sequenceid should the client use to the DS" problem. It allows CREATE_SESSION to each DS to happen in parallel. It solves the problem of routing to the correct global clientid because there is no global clientid. One thing that has to change is that EXCHANGE_ID and not CREATE_SESSION takes a flag that indicates whether the client is trying to create a clientid (versus creatting a session) to an MDS or DS. This still leaves an issue. When a COMPOUND is sent to a DS, with a READ or WRITE operation, the layout stateid does not map to the MDS, because there is no longer a global clientid, and the sessionid in the SEQUENCE doesn't map to the global clientd (it maps to the local DS clientid). We do need a mapping of the stateid to location of the MDS. What we settled on before the end of the meeting was that the DS file handle (passed via the PUTFH that precedes READ and WRITE) can contain the MDS location. We observed that DS file handles are allowed to be different than MDS file handles. We were mistakenly worried about the DS file handles going stale if the MDS location changed. However, we corrected our mistake after we observed that the DS file handles are part of the layoyut, and they are allowed to be different than the corresponding MDS file handle. Because the DS file handles are part of the layout, the DS file handles can be recalled (invalidated) as part of recalling the layout. One objection to this is that caching is a problem. Another mistake: caching isn't a problem because while a client has a layout, the MDS file handle needs to map to each DS file handle, and each DS file handle needs to map to its MDS file handle. When the layout is recalled, the cache must destory the DS file handle to MDS file handle mappings, but the data can still live, it is always indexable by the persistent MDS file handle. One other observation that I thought of after the meeting: A pnfs server cluster can return the same clientid and sessionid to each EXCHANGE_ID to an MDS and DS if it wants (in a loosely coupled pnfs server cluster this might be the norm). If each DS and MDS do (or can) return the same clientid from EXCHANGE_ID, to prevent the client from erroneously attempting clientid trunking (and getting an error when attempting to READ or WRITE a data range the DS does not "own"), the combined eir_server_owner.so_major and eir_server_scope results from EXCHANGE_ID for the MDS and each DS may need to be different. The client can compare the RPCSEC_GSS target principal of the MDS and each DS to prove the claim of clientid trunking. Similarly, if each MDS and DS return the same clientid and sessionid, to prevent the client from erroneously attempting session trunking, the combined so_major, so_minor, and eir_server_scope results from the MDS and each DS may need to be different. The client can use the SSV to prove the claim of session trunking. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From okudvocck@saix.net Tue Feb 06 01:12:13 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HEJYr-0006m7-Bg for nfsv4-archive@lists.ietf.org; Tue, 06 Feb 2007 01:12:13 -0500 Received: from dsl-243-174-202.telkomadsl.co.za ([41.243.174.202] helo=ctb-cache8-vif1.saix.net) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HEJYp-00087q-NL for nfsv4-archive@lists.ietf.org; Tue, 06 Feb 2007 01:12:13 -0500 From: "process task." To: nfsv4-archive@lists.ietf.org Subject: Traders Daily Report Date: Tue, 6 Feb 2007 08:11:59 -0200 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0005_01C749C6.79AE5950" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdJxnmu/N8sMS0hTQK+egJc+xX9kQ== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: <2A257B886A1D1C3.95461600AD@saix.net> X-Spam-Score: 4.9 (++++) X-Scan-Signature: 2409bba43e9c8d580670fda8b695204a ------=_NextPart_000_0005_01C749C6.79AE5950 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
**MGOA started Monday with a bang!**

Get in early Tuesday, February 06 2007

Bullseye: Tuesday, Febuary 06, 2007
Comp: MEGOLA Enviromental Solutions
Ticket: MGOA
Currently: $0.059 +0.009 +18%
3 Day Target: $0.50

The Big News:
Megola Announces First Anti-Fire Product Shipment
Market Wire (Fri, Feb 02, 2007)

Megola Acquires Revolutionary Fire Safety Products
Market Wire (Tue, Jan 16, 2007)

STRONG BUY ISSUED FOR TUESDAY, PUT MGOA ON YOUR RADAR NOW!
------=_NextPart_000_0005_01C749C6.79AE5950-- From nfsv4-bounces@ietf.org Tue Feb 06 11:31:24 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETCQ-0004vi-H5; Tue, 06 Feb 2007 11:29:42 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETCP-0004vW-7r for nfsv4@ietf.org; Tue, 06 Feb 2007 11:29:41 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HETCL-0003ou-Fq for nfsv4@ietf.org; Tue, 06 Feb 2007 11:29:41 -0500 Received: from smtp2.corp.netapp.com ([10.57.159.114]) by mx2.netapp.com with ESMTP; 06 Feb 2007 08:29:28 -0800 X-IronPort-AV: i="4.13,291,1167638400"; d="scan'208"; a="29733001:sNHT18623717" Received: from svlexc02.hq.netapp.com (svlexc02.corp.netapp.com [10.57.157.136]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l16GTS8O022500; Tue, 6 Feb 2007 08:29:28 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc02.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Tue, 6 Feb 2007 08:30:27 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 6 Feb 2007 08:29:27 -0800 Received: from tmt.netapp.com ([10.30.32.31]) by exnane01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Tue, 6 Feb 2007 11:30:30 -0500 X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Tue, 06 Feb 2007 11:28:32 -0500 To: email2mre-ietf@yahoo.com From: "Talpey, Thomas" Subject: Re: [nfsv4] Create Session for pNFS DS In-Reply-To: <696900.5617.qm@web31804.mail.mud.yahoo.com> References: <696900.5617.qm@web31804.mail.mud.yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Message-ID: X-OriginalArrivalTime: 06 Feb 2007 16:30:30.0446 (UTC) FILETIME=[1DDD64E0:01C74A0C] X-Spam-Score: 0.0 (/) X-Scan-Signature: 798b2e660f1819ae38035ac1d8d5e3ab Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org At 12:27 AM 2/6/2007, Mike Eisler wrote: > A pnfs server cluster can return the same clientid and > sessionid to each EXCHANGE_ID to an MDS and DS if it > wants (in a loosely coupled pnfs server cluster this > might be the norm). I don't think the sessionid should come into play here. It's only unique in the scope of a single server, so its absolute value in the network is somewhat meaningless. > Similarly, if each MDS and DS return the same clientid > and sessionid, to prevent the client from erroneously > attempting session trunking, You mean that the client might attempt a second CREATE_SESSION to a given DS, and get back the same session it already has from the first? That violates the session scope - not unique on a single server. The DS can reject the second session, of course. That would certainly prevent it. Tom. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 06 11:49:12 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETUN-00057e-0r; Tue, 06 Feb 2007 11:48:15 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETUK-00057Y-Uw for nfsv4@ietf.org; Tue, 06 Feb 2007 11:48:12 -0500 Received: from web31808.mail.mud.yahoo.com ([68.142.207.71]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HETUH-0007OQ-IM for nfsv4@ietf.org; Tue, 06 Feb 2007 11:48:12 -0500 Received: (qmail 54725 invoked by uid 60001); 6 Feb 2007 16:48:08 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=pf/Vi1i/0SLHxfnkZyqgCK/9kuFWlCdQda8rV3TBX23r89qFnq12ebCvEPRTqyX/OrzcSEdgdMivtMuSqvH3oJRxYBuSE0faCx/mGd52DdaPmjp/fxX6GC/cYglts/mshC+BEwh8Wsm/i7uX/dcveeio0Fmk8YXs9zEf4/fOr5M=; X-YMail-OSG: gZj93o0VM1nvRpML5dlRVWxsPCPRvZqt43rQhFGl Received: from [198.95.226.224] by web31808.mail.mud.yahoo.com via HTTP; Tue, 06 Feb 2007 08:48:08 PST Date: Tue, 6 Feb 2007 08:48:08 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] Create Session for pNFS DS To: nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <888106.54710.qm@web31808.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 538aad3a3c4f01d8b6a6477ca4248793 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- "Talpey, Thomas" wrote: > At 12:27 AM 2/6/2007, Mike Eisler wrote: > > A pnfs server cluster can return the same clientid and > > sessionid to each EXCHANGE_ID to an MDS and DS if it > > wants (in a loosely coupled pnfs server cluster this > > might be the norm). > > I don't think the sessionid should come into play here. It's only > unique in the scope of a single server, so its absolute value in > the network is somewhat meaningless. I don't know what you think a "single server" is. The NFSv4.1 spec doesn't attempt to define a "single server". Instead it talks about server owners (with major and minor fields), server scopes, SSVs, and target GSS principals, and thus allows for degrees of server singularities. Perhaps the spec should expand on this. > > Similarly, if each MDS and DS return the same clientid > > and sessionid, to prevent the client from erroneously > > attempting session trunking, > > You mean that the client might attempt a second CREATE_SESSION > to a given DS, and get back the same session it already has from No that is not what I meant (besides which, multiple, unique, not replayed, CREATE_SESSIONs with the same clientid to the same server network address [or a different network address but the same server_owner and server_scope] always produce a new sessionid). >From the specification's section entitled "Trunking": When two connections have a matching so_major_id and so_minor_id, the client may bind both connections to a common session; this is session trunking. When two connections have a matching so_major_id, but different so_minor_id, the client will need to create a new session for the clientid in order to use the connection; this is clientid trunking. Although draft-08 neglects to mention that the server_scope needs to match in both session and clientid trunking; corrected in draft-09. > the first? That violates the session scope - not unique on a single > server. The DS can reject the second session, of course. That would > certainly prevent it. > > Tom. > > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 06 12:08:03 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETm0-0004q0-K0; Tue, 06 Feb 2007 12:06:28 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETly-0004pl-SK for nfsv4@ietf.org; Tue, 06 Feb 2007 12:06:27 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HETlw-0001ix-B3 for nfsv4@ietf.org; Tue, 06 Feb 2007 12:06:26 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 06 Feb 2007 09:06:23 -0800 X-IronPort-AV: i="4.13,291,1167638400"; d="scan'208"; a="29744382:sNHT57279712" Received: from svlexc02.hq.netapp.com (svlexc02.corp.netapp.com [10.57.157.136]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l16H6MoQ020044; Tue, 6 Feb 2007 09:06:23 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc02.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Tue, 6 Feb 2007 09:07:22 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 6 Feb 2007 09:06:22 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] Create Session for pNFS DS Date: Tue, 6 Feb 2007 12:07:25 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] Create Session for pNFS DS Thread-Index: AcdKDuBKpT5lRG6QQcGpCEq9cct8EQAASw5A From: "Noveck, Dave" To: , X-OriginalArrivalTime: 06 Feb 2007 17:06:22.0149 (UTC) FILETIME=[20613750:01C74A11] X-Spam-Score: 0.0 (/) X-Scan-Signature: 3002fc2e661cd7f114cb6bae92fe88f1 Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org > The NFSv4.1 spec doesn't attempt to define a "single server". > Instead it talks about server owners (with major and minor fields), > server scopes, SSVs, and target GSS principals, and thus allows for > degrees of server singularities.=20 Well it does have a chapter on single-server namespace, and one on multi-server namespace, but I think it is just of question of getting those (relatively) old chapters to "get with the=20 program". One of them was reworked and the other esentially written for 4.1, but early in the cycle. I'll create an issue for this. It won't be addressed in draft-09. > Perhaps the spec should expand on this. I think this needs some introductory text because it is easy to assume the older model. I'll create an issue and assign it to you. If you think something needs to be in the introductory chapter as opposed to the protocol structure chapter, let me know. -----Original Message----- From: Mike Eisler [mailto:email2mre-ietf@yahoo.com]=20 Sent: Tuesday, February 06, 2007 11:48 AM To: nfsv4@ietf.org Subject: Re: [nfsv4] Create Session for pNFS DS --- "Talpey, Thomas" wrote: > At 12:27 AM 2/6/2007, Mike Eisler wrote: > > A pnfs server cluster can return the same clientid and > > sessionid to each EXCHANGE_ID to an MDS and DS if it > > wants (in a loosely coupled pnfs server cluster this > > might be the norm). >=20 > I don't think the sessionid should come into play here. It's only > unique in the scope of a single server, so its absolute value in > the network is somewhat meaningless. I don't know what you think a "single server" is. The NFSv4.1 spec doesn't attempt to define a "single server". Instead it talks about server owners (with major and minor fields), server scopes, SSVs, and target GSS principals, and thus allows for degrees of server singularities. Perhaps the spec should expand on this. > > Similarly, if each MDS and DS return the same clientid > > and sessionid, to prevent the client from erroneously > > attempting session trunking, >=20 > You mean that the client might attempt a second CREATE_SESSION > to a given DS, and get back the same session it already has from No that is not what I meant (besides which, multiple, unique, not replayed, CREATE_SESSIONs with the same clientid to the same server network address [or a different network address but the same server_owner and server_scope] always produce a new sessionid).=20 >From the specification's section entitled "Trunking": When two connections have a matching so_major_id and so_minor_id,=20 the client may bind both connections to a common session; this=20 is session trunking. When two connections have a matching so_major_id, but different so_minor_id, the client will need=20 to create a new session for the clientid in order to use=20 the connection; this is clientid trunking.=20 Although draft-08 neglects to mention that the server_scope needs to match in both session and clientid trunking; corrected in draft-09. > the first? That violates the session scope - not unique on a single > server. The DS can reject the second session, of course. That would > certainly prevent it. >=20 > Tom. >=20 >=20 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 06 12:10:51 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETpO-0007gg-Pg; Tue, 06 Feb 2007 12:09:58 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HETpN-0007fu-7F for nfsv4@ietf.org; Tue, 06 Feb 2007 12:09:57 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HETpM-0002Jl-EZ for nfsv4@ietf.org; Tue, 06 Feb 2007 12:09:57 -0500 Received: from smtp2.corp.netapp.com ([10.57.159.114]) by mx2.netapp.com with ESMTP; 06 Feb 2007 09:09:54 -0800 X-IronPort-AV: i="4.13,291,1167638400"; d="scan'208"; a="29745489:sNHT54032440" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l16H9sAE010534; Tue, 6 Feb 2007 09:09:54 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Tue, 6 Feb 2007 09:09:54 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 6 Feb 2007 09:09:54 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] Create Session for pNFS DS Date: Tue, 6 Feb 2007 12:10:58 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] Create Session for pNFS DS Thread-Index: AcdJr+HtiqkPtEteT52QQ0DE3E13rgAXB4Eg From: "Noveck, Dave" To: , X-OriginalArrivalTime: 06 Feb 2007 17:09:54.0226 (UTC) FILETIME=[9EC99920:01C74A11] X-Spam-Score: 0.0 (/) X-Scan-Signature: 7fa173a723009a6ca8ce575a65a5d813 Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org I think you have the right solution on EXCHANGE_ID. Who was the idiot that first suggested that we not do an EXCHANGE_ID on the data server? Actually, I think it was me. Sorry about that. -----Original Message----- From: Mike Eisler [mailto:email2mre-ietf@yahoo.com]=20 Sent: Tuesday, February 06, 2007 12:28 AM To: nfsv4@ietf.org Subject: Re: [nfsv4] Create Session for pNFS DS Today at Connectathon a large group of pNFSers discussed this. There are several issues with draft-08 and the impending draft-09 (as it exists in the cvs server): - What sequenceid does CREATE_SESSION take when invoked against a DS? -- Also in pending draft-09, the CREATE_SESSION sequenceid is global across the pNFS cluster, so this means the CREATE_SESSIONs to all DSes for the same clientid have to be serialized. Not good. - The clientid is currently global across all nodes in the pNFS cluster. However, consider a vast cluster with lots of MDSes and DSes, where a given DS could potentially be holding parts of files from many MDSes. When given a clientid in a CREATE_SESSION call, there is no efficient way for the DS to figure out which node has the MDS for that clientid. - There is no may to bind a session to a DS or MDS for the case when both listen on the same network address. It would be nice to allow a DS to have an optimal implementation that just does the DS operations. This is actually fixed in the impending draft-09. During today's meeting we came to the realization that if we changed to the "MUST NOT" that bans EXCHANGE_ID to a DS to "MUST", that each DS and MDS that the client presents a given co_owner to can return a unique clientid to the client. Doing this solves the "what CREATE_SESSION sequenceid should the client use to the DS" problem. It allows CREATE_SESSION to each DS to happen in parallel. It solves the problem of routing to the correct global clientid because there is no global clientid. One thing that has to change is that EXCHANGE_ID and not CREATE_SESSION takes a flag that indicates whether the client is trying to create a clientid (versus creatting a session) to an MDS or DS. This still leaves an issue. When a COMPOUND is sent to a DS, with a READ or WRITE operation, the layout stateid does not map to the MDS, because there is no longer a global clientid, and the sessionid in the SEQUENCE doesn't map to the global clientd (it maps to the local DS clientid). We do need a mapping of the stateid to location of the MDS. What we settled on before the end of the meeting was that the DS file handle (passed via the PUTFH that precedes READ and WRITE) can contain the MDS location. We observed that DS file handles are allowed to be different than MDS file handles. We were mistakenly worried about the DS file handles going stale if the MDS location changed. However, we corrected our mistake after we observed that the DS file handles are part of the layoyut, and they are allowed to be different than the corresponding MDS file handle. Because the DS file handles are part of the layout, the DS file handles can be recalled (invalidated) as part of recalling the layout. One objection to this is that caching is a problem. Another mistake: caching isn't a problem because while a client has a layout, the MDS file handle needs to map to each DS file handle, and each DS file handle needs to map to its MDS file handle. When the layout is recalled, the cache must destory the DS file handle to MDS file handle mappings, but the data can still live, it is always indexable by the persistent MDS file handle. One other observation that I thought of after the meeting: A pnfs server cluster can return the same clientid and sessionid to each EXCHANGE_ID to an MDS and DS if it wants (in a loosely coupled pnfs server cluster this might be the norm). If each DS and MDS do (or can) return the same clientid from EXCHANGE_ID, to prevent the client from erroneously attempting clientid trunking (and getting an error when attempting to READ or WRITE a data range the DS does not "own"), the combined eir_server_owner.so_major and eir_server_scope results from EXCHANGE_ID for the MDS and each DS may need to be different. The client can compare the RPCSEC_GSS target principal of the MDS and each DS to prove the claim of clientid trunking. Similarly, if each MDS and DS return the same clientid and sessionid, to prevent the client from erroneously attempting session trunking, the combined so_major, so_minor, and eir_server_scope results from the MDS and each DS may need to be different. The client can use the SSV to prove the claim of session trunking. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From zlwzuqkcm@pldt.net Sat Feb 10 09:44:39 2007 Received: from [10.90.34.44] (helo=chiedprmail1.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HFtSx-00036C-8o for nfsv4-archive@lists.ietf.org; Sat, 10 Feb 2007 09:44:39 -0500 Received: from [58.69.25.113] (helo=58.69.72.174.pldt.net) by chiedprmail1.ietf.org with esmtp (Exim 4.43) id 1HFtPo-0004GA-S8 for nfsv4-archive@lists.ietf.org; Sat, 10 Feb 2007 09:41:26 -0500 From: "Panic" To: nfsv4-archive@lists.ietf.org Subject: Wall Street Alert! Date: Sat, 10 Feb 2007 22:45:03 +0800 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0002_01C74D65.1A973020" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdNZRqXK5jDHXEzR9S3/5e1vYS/jw== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: X-Spam-Score: 4.0 (++++) X-Scan-Signature: 7655788c23eb79e336f5f8ba8bce7906 ------=_NextPart_000_0002_01C74D65.1A973020 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
THIS COMPANY IS GOING TO EXPLODE WITH FLAVOR!

**CBFE** WATCH NEWS THIS WEEK TO SEE WHAT 6 TOP UNIVERSITIES SAY ABOUT THIS WONDERFUL BAMBOO AND ITS JUICE!

Organization: China Biolife Enterprises, Inc.
Ticker: CBFE
Trading Date: Monday, February 12 2007
Price: $1.30

DONG SHAN DISTRICT GUANGZHOU, CHINA, Jan 08, 2007 (MRKET WIRE via COMTEX) -- China Biolife Enterprises, Inc. (PNKSHEETS: CBFE), a Nevada Corporation, focused on the bamboo extracts and nutraceutical markets in China. The company is pleased to announce that it is in the final stage of negotiations to acquire the bamboo extracts division from ChangRong Bamboo Wooden Craftwork Ltd. Co.

CAN YOU GAIN SPEEDY PROFITS ON THIS??

WATCH CBFE MONDAY AT OPEN!

------=_NextPart_000_0002_01C74D65.1A973020-- From service@fairygodmother.org Sun Feb 11 04:05:34 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HGAeM-0003rO-Hd for nfsv4-archive@lists.ietf.org; Sun, 11 Feb 2007 04:05:34 -0500 Received: from ppp-252-168.32-151.iol.it ([151.32.168.252]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HGAeI-0001yC-6E for nfsv4-archive@lists.ietf.org; Sun, 11 Feb 2007 04:05:34 -0500 Received: from ZHAB (unknown [162.138.41.67]) by iol.it with ESMTP id F8D6F99F2E72 for ; Sun, 11 Feb 2007 10:06:21 +0100 (GMT) Message-ID: <000c01c74dbb$cedcd2f0$fca82097@pentium> From: "listening experience" To: nfsv4-archive@lists.ietf.org Subject: Best Overall CodecIn recent Date: Sun, 11 Feb 2007 10:05:42 +0100 MIME-Version: 1.0 Content-Type: multipart/related; type="multipart/alternative"; boundary="----=_NextPart_000_0008_01C74DC4.30A13AF0" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2180 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2180 X-Spam-Score: 4.4 (++++) X-Scan-Signature: 33cc095b503da4365ce57c727e553cf1 ------=_NextPart_000_0008_01C74DC4.30A13AF0 Content-Type: multipart/alternative; boundary="----=_NextPart_001_0009_01C74DC4.30A13AF0" ------=_NextPart_001_0009_01C74DC4.30A13AF0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Technology received top honors at billboard. Reviews rhapsody cnet = editors. Digital, recognized or honored innovation competes features. = Dynamic, ingame streaming video model doubles standard industry rates. = Use it offers fun attractive. Or, honored innovation, competes features. = Releases feb wins casual game of year first annual. Judged on quality = smoothness. Flexible efficient, well take. Women, rule market reuters rival! Discover new, provides witty editorial. News, gameworld older women rule market? Witty editorial content go = along with your listening experience. Expect encoding tool great audio = there. Feb, wins casual game of year first annual. Dynamic ingame streaming video model doubles standard industry, rates. = Overall codecin recent codecs media magazine picked? Efficient well take = look whats. Release editor larry, smart computings? Service united states, we can see. ------=_NextPart_001_0009_01C74DC4.30A13AF0 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
3D""
Technology received top honors at = billboard.=20 Reviews rhapsody cnet editors. Digital, recognized or honored innovation = competes features. Dynamic, ingame streaming video model doubles = standard=20 industry rates. Use it offers fun attractive. Or, honored innovation, = competes=20 features. Releases feb wins casual game of year first annual. Judged on = quality=20 smoothness. Flexible efficient, well take.
Women, rule market reuters = rival!
Discover new, provides witty = editorial.
News, gameworld older women rule = market? Witty=20 editorial content go along with your listening experience. Expect = encoding tool=20 great audio there. Feb, wins casual game of year first = annual.
Dynamic ingame streaming video model = doubles=20 standard industry, rates. Overall codecin recent codecs media magazine = picked?=20 Efficient well take look whats.
Release editor larry, smart = computings?
Service united states, we can=20 see.
------=_NextPart_001_0009_01C74DC4.30A13AF0-- ------=_NextPart_000_0008_01C74DC4.30A13AF0 Content-Type: image/gif; name="Best.gif" Content-Transfer-Encoding: base64 Content-ID: <000701c74dbb$cedcd2f0$fca82097@pentium> R0lGODlhkAFgAYfrAAQKC3oNAA6MAnOLAA4BeYsGdQByfbfKuLjOyKfB5kEXAGAjAHUfBKMXCLkU AOAuCgZIABs8CUpHDmM2DotEAJQ1ALE0DN06AANtABlcAE5aAGxkAH1tBpFnCLpmAOZmDQ14ABRy AE6OAF57BXV1DqyOB8aFANKJBwCdACCUBjemAFeUAHGqDJ6oCMCjAOycAgLCACu4AEO4AFPIBIC4 AKTJALG9ANi7AADtACjVCjjaBmfpCXTqCaLuCcboANjdAAkLSxkDP0cAM2IKO4AMOJ0AR8YAOt8A QQAZRhMrMU0rPWwaQHMiR6IqSsosRNcmOwM0RiNITEBBQ2Y6NHk1M6M1S7lJOd0yRghhPSJZOkFo SVxYOnlmEqheTM1tTOJqPAFzMyd/RUGNQFGFSnxxPqKBOrJ5OtiINACaTBOjQU2dM1KfSousOJab N8amOOGiSwHDOxqzRDezSWm+PoHEQ5a6OsLFO966NA3jOyPdPErsRFXlNoXRSa7YMsXfNenrOAgA jCQBgDMAgVoAfYMAh5YFibEAi9YAiAASghESeTkgcloddowTjJktjsMdjeIfewBDhxE4iE02i2Ix fHZCc5FGgbpEhNE/fABqgR9mg0pbhWRidnRbdqBUi8lbiOVVjQByfBuFjj6MhWaEiYF4eZh8csSE gdiKjAGqgxSaiDGphGmjgoiehZGUcbqTeOKrfACyfiq9gja0f2zOe3+9iJe0iMHBfOi2gwDniB/t dTvXgW3ueHvbfqXnc7vXe9/acwAAsR0ItDQAuF0Aw3IGsp8ItL8Ax9wAxwQssxkVt04cvGwYuo4e yJwTtcMgttwRsgAzxBlHu0s3s2Q9wXw1zJ0/wMw8yOJBygBlzCVZxEtTt1piwXhmvKZdzr9gzNRp xAB3siKGtTF8uFqNs4B5zKp4vsh7zueAwAGYtxSnujKns12SzHSjy5yqy76Vu9yTzAC3syu7wzvF ylzDx3i7wqKxwv/34piusnWKjv8AAA3/Cvv/AAMA8P8A/wD48P/x9iH5BAD//+cALAAAAACQAWAB Bwj/AP8JHEiwoMGDCBMqXMiwocOHECNKnEixosWLGDNq3GjRnsePIEOKHEmypMmTKFOqXMmypcuX MGPKnEmzps2bMjnq3Mmzp8+fQIMKHUq0qNGjSJMqXcq0qdOnUKNKnUp1KM6rWLNq3cq1q9evYMOK HUu2rNmzaNOq9Vi1rdu3cOPKnUu3rt27ePPq3cu3r9+/gAMLfru2sOHDiBMr9jq4sePHghdLnky5 suXLmDNr3sy5s+fPoEOLDgu5tOnTqFOrXs06Yk0BsGHbiy0AZOzZtHPrzo2bt+3bH4EHl/17t2zf HnUXrz2cefOQwkdLn55SY2yBuQdeJ7gdO2yE22lr/xfvXUDB7gbRl+f+/V/37OvZm5ffun5Vm8CR R+9dnKTw/7Q91xxxIu3HX3IEHqhfgsgdSN2DEIZkXXu6xTfefBae1557G1bIIYYfbqghiPGp92GI FIoIX4b2tehXeN+lSCJ6Jlr4Xozz0WieiPSNyOKJ18nIHoc9umgkXzDuiOOMKhqnZI5NPnniejWa mGR6SwLZYZY/HumlVa8Rl19t+0VnIIINKkgmgbedaeCYzj03poNtsplghHhONyGUfKqnI4kXThko ihjudpCVQvqY5I0r1vjlo29dWR6Pf4KXqI3kMYoloJLSx+ilnUIqaqSgkjdol1Oa+imfp7aKKYid wv+nqaCj1qoTfmIyWKaucfaHJnNmzvlbgXc6qKZzweYKHbDF5unssyfxlmyv0yo3rbEB7krtnQ0q J+CvxvJnHLTkambruegOVu667LaLVrrwxivvvPTWa++9+Nbl7r789uvvvwAHLPDABBds8EebJAxa wpsc7PBoDH8VMUkBVGxxACFZDJLGYU088Usf2xPywySLhBHDQqGMkMUCXUwQy//ATJTKKk9U8z83 5/slTSNr1fNHHNsTtNAVezS0xArX9HPJTJt8Uc4DMZxwQVLXXPUmUU+9csUDydzyxQEwdDXWUhNU NdVXC2R12VmzPTbOWsO9dto6Q8Zz0iFF/LHHSeP/zXfDFBdttOAbH02S1CLr3bfCey8O+N8eLY6w 4yBB/vfjeDet+eSAV+4345937jnmomcsuOFEE24S5Ik33LjroUcOeukjsS477J0rnnvmm2ve8+ut c8454sEHDrbxGKPEuu7CAx/80mPfPnrxz8feO7snx9122nOrrTXN2hfEstcvk48Q+FjLLTf3caOv vkHuv+892e1P3X3djt1N+8/AO7906oNLXuEupjzKVY921LMc7xJoQOn1z3rXK1f20me28M2vbfKL 30Fg5rKujY9rCokfyqCWwe/Zz4L3u9kI60c/CpIQf0ci4douWDb0pe+FMQNhDnXIQR2ez4Q3BGLW /2goQhO+z23ac58GcQjDFo3NhWfbng2RSEGDeM1lV/Qh/IRYQrbNj4pSlOLcTgjF+8mviYBZy/8i yMaSJYWLaIyjHBtCtznakTVtzKMe33XHPvrRIHsMpCAHSchCGvKQiHzWHxfJyEY6Eo2JjKQkTfLI SsJwkpjMpCY3GUlLevKToAzlajhJykKK8pTpKqUqA4nKVtZqlbBsoytnScta2lIpscylLnfJS+nc 8pd47KUwh0nMYq4FmMhMpjKXqRBjOvOZ0IxmG/MhzWqyhADYJIA9svkRbHYTJNzcZji7Oc5yZlOb 59SmSKjpkXy4050heSc87fFOawpTneAEJz7x6f8RdfIznyHZZz9H8s+PyJOeKaEmOxFqT1ZehAAH gahAJErRglQ0ohbNqEQzapB8/MOjAgGpQkAqUpEyM180Keg2v7nSlrJUnAUN5z/Rec6XgkShBq0n SRaq04buESMbJchGLxrUfxTVqAiBaFGVilGLEuCdHT1ISQdi0pN68qhINWo6szqQo2IVqUvlqlAT 4tGqVjWkVE2rVVGaUpH4M58zdStJ3jpQlwJ0JDjlaTsNelO++lSXNeUmP2nqTcGOs5+HLSdB8drT xvo1pwv9q2TNEtnJWvYylb2sZjfLWZqs9bOgPStogTlUrQ51qdk0LWoNcs6Jplao2GTIWUUL1Y// ynO082prXQc72IDa1Ju+HahA62rXdTY2s3rta2clOdzmEvelzr0rOlkaV7wydK/Ifex1lxvJ6RKX rjGF7nNd6t2WVned12VndveqXe4isrzR9WdhEzvemsJ0uL8Frk7lWdnkbte9BssIUyfq2tYGdcCn bW1XOVrasZL1owSZrVohjNtKHpjAC+bqgLN64Qx7uMFilSqF0UriqY64wvGyyT4LK13BwvWuxe0t YlUK2f4+1rEAzjFNMqvjn9pHtCiWY4+HPJYgG7ktAOMxkUkpUHMG1LDAJSdBzbliKEdZuViO503n uWQ9RhexMCavPuUaXPMulrFc5vKWb9xlfwE1/8MNvqiDNYxhD9eZwFjFalkjfGI+k7jPR95ZW/EL XjKLubgwre998dvX5CrZv0puM7kETGcMEzW2CrZ0QjaM56bCtrb8FfGfgRxoF9UEvjN28Tfpumga l1e4Z7ZuZB/NZknnUca4XjV1w7zr3cYavbPWLqRtvS+NJFisCea0smEb2642O8R3pmptJ1xSd0qb 1KXONkSwre1u/4Tb3pYXscdN7nLzkS7gDrcnVQxlKT9XpodFbzsPatx599TcEaQ0R11rZw435LbY BnK61V0v3Za50AClcaPbm+WG47t3b2YtnKN9bITsOaTTvrZZCT5Hg0vX17zmrTrvzd5a//fhEP9/ aFPTyWlofxWtG/fziAfOcQtLHNkh9upIIWxikqqV5jXP7anb3dvAzvfK8TwupNOM8jZHuumJtAvQ g071qlv96lh/y9Sz3kSDrzi/r6apu7UMWTSXHeqbi7iGQazpBT/72RqfeUGmamKuPzLObZ+428Ea 4ovP/e8wn7DdHblhojJ4rExtud8Ff+1RD97meM/5nRE8+adam/GOt+3lH5/iQaeaxQl/sZmBXXKy //fpaD8ko189eljzGqE4Jbt/T5565v72vonGfYyTPk/+lvy4tdfcXbbOeXxxBvXBd2jxl8/85hMk j8hPfmeMndqtvl21Sn2taZ0N99JqH+6qDT//bGUb4c1rnKTmd75gwjr+Ts8ZxF+NPL/7zXbwdxSq df9z5tUfGJ0j3v0fpneeJmeGt2/yF1W0BXjUxn/rx1qvRXkKBn/RplEB6G8GKIAIOHezBWqYx4B7 QVGYdngtl2kWmFSVZoEgmH3dR3HNlnH693f554FN4XGs91Y1+G7j5VvNlU525V1VFm9aZmM7lV7S FyFNdnA3+F02ZWit13qo1oMmkVd+pV58NXtFWBjUh2kG5mzYh3Pfp30fFoJhKIYACG0Yt3nTVm1q KIMoRnxseGRu+IZScYV0WIeSJnVy2Erwd1phWIEWV360dXmhlof4s4dcWGfXN4FxF4N0R4iQ/3Jq h2aDIHeEQ8hjQgh7djhJubZSCCdjlShvvGdv0ZeJEbSJktiEMaVfamaJ7TWKpDhpb5aC1ddpLFeG IuZzotZnceiIX+J9/8dvF8Z2GShhcheDvBhMMkGJridOUMhoW9Z79MZTaaZmr/gveHiMNbeL2Ghq 1diN3viNJ+GK4KiJVDZ2UYZ01uVw9nZ247hH4bVbXwdmUbhfrIhdDNeO7aJ2FMd3lGeGgSdzf2iM 24iMyQhccTVdPpiDVWh69baO+DhIN9iJ9aWKwRaFRPiQgRSRvsZyFmmFpFd6GNlGrMZqy4hoC1d6 VGiPIBmSEvRQYPh9FNhvcXeG1IaG6TeQt/+kjTjJjZUhjiwpMDsZlEJpSaDhkz95Pef4dfZlZWKn kMJGjQ5JT1B5lASTlFIWX0+2hM8Ye6e3kCtJlQFTaAgZiYpGkifJkETokWAJMGLJibpnXjLVhGd5 j/t1j2v5GfpWgIWXd5p2YC1ofglYYi44lI9Si4YXeezXcjD4ggsIkIRZmL+4d23Hflq1c4tXYoKn k4/pGMGoUQ+ohbM4f/cniLc1cza5mbWkmajZSqq5mq75mhJxl7LJEkY5mw8CVHxofV+oghVXmX/Y eKMJnLDZIm83ghUogYc4mn4XczzXgcNJF543lh8HctRplpgIithJe7a5LmNJWCPZa9WZg1z/OW87 dYnbOX0q52+otYI4V2moNZikJpDPqS8z0ZahB56jx5EfaZcMVZvnSR0HeXDg+WUmKYXslZLX+Z94 mZ5ut4UNypvc154zqXk1iX6DOZ+N1JoY+kgauqFzoaCS5aFrBS3+CaKTgZvVB4a+uaLFyX3rKZMA eaGmKaMi+oF+yKJ8KJrIWYLKKXcamIs16hQqJl6T6JYSqWuit5/quF4mehjG5oeHyXcoGJm2mFbE GFUKGKRCCompdp9HSpIa6VaWV5HpyJ9NehZPmneG2ZfWR6VSGpCM6ZgdqqVOgZydSaV7iYiKaKWA ZlJ+SqcNOHleGJN4pqK7WVSlOYhrGKeA/5oUJHqm1lSikIoYjVqplvpJc3qpfQEJBAEJnuqp/8Cp AsGpnxqqn0qqpdqporpzcmpxpEmjmjoXqxqqBbGqojqrtjoQuDqrUgVqfhqYuhirTEETkAASxWqs H3Gsx+oRy9qsycqsJTGeXQmKZDqp07Gs9nCqz+qszwqt3pqt36qk02p61Wqto4Gt2Aqt3Pqt2tqt 6fqpUTmuvKeW5poWGIGrBkGqutqp+0qro3qqvLqYL8ht8imsdIGv+cqv/eqv/oqwcDqwrcqoBlsU xAqvANut2eqpGIuu4Iqx88qOOCaV6liv9toXmTqxSDEakkqyLNuNKPuyMGsULTuzNLsYMf97szib s4FWs8Oks+vGs0AbtGXhs0QptLpEtEibtEo7S0bbtE77tFAbtYqxtFRbtQIhtVibtVq7tVz7Elbr R12LSV/bRzfBD2Zrth6BtiJxtvwQEmzbtvagtmkLt2tLtx+Btm97tnH7tiCRt3Lbt34LuHp7t3x7 EmzrtoNLuH/7t3VbuIprt447t4kruYtrt3O7t3W7t34Lt3LbuZYbYBhxtgNhtv9AugdhugIhuqnL D6XLuqubEKg7uqwbu7Jbu6/LELQru67buq6LurlLEKbru727u8E7vAsRu6p7u8pbvMQ7vM1rvAVB usmrvNS7vM37R7/7u60LvLvLvdUbvd3/+7rZe73fe7rha7u2K7wPIb3dW7y3q73oS73qa74IQbvu C768277hm7vzu73nQhOMS7gk4bkD3LYBjLiZe8AEfLkoocCfi7kLnBJ4C7mcW8GYa7ifG8EOXMAj McEJbMB0y7gBrMEPXEgHfMGZy8CNW8KCG7ibi8Kem7cd7MIP7MEq3MAgDLgMbMMmMcIhTMEpHMQ6 7MMQ/MMIfMQwzMJAeRHa28TkaxBsi7vny77067/lC8Xna8Xee78NwcVWHMXs68RYHL/5S8ZmvL38 O7vQa79T/MTwC0NiXMVavMVZ7L34O77TO8f1m8Xjm791LMfIW8dRrMd63L/4S8iETMV3/3y9bDzG 1osuAFzCJxzBR3zCN3y5G4zCmlwSmYzAamvJOizAouzJFizEKmzJPIzEQ5zBOfy4qnzKRjxJnazK nYzKrLzJsDzKPSzJlvvJsczJvQzElVzKr1y5wHzJunzBRFy5IqzEq5S4qRzKkivAxjzDH2zNogzK yay43KzJtozNmezL2DzNo0zCsQzNlCzOgvvKSbzNBbMRb7u68VzG3Ku6jezIdJy3cxzG83zIezy9 94zF/TzI/kzPAk3Q8vy8aZzH/ay7yZvGBf3IVyxoYetMm3vRGJ3RGr3RHN3RHv3RIB3SIj3SJF3S JF3RJjq2d4TSnaTSLn2zLB3TTvvSNJv9sjJ9SDUNSTdtSjnd0z7906qx00JNs0CtM0N91Eid1Eq9 1Ezd1E791FAdMEU91VRd1VYddFGd1T951fSi1V791WAd1mI91mTtpFx91o9Z1u+M1vCi1gTD1nAd 13L9E25d13ZN1nNtK3e913zd137tS3k9Kn892IQt04F92GxY2Iq92FqL2I/I2NDi2JI92ZRd2S0C 2ZFt2S0SEAA7 ------=_NextPart_000_0008_01C74DC4.30A13AF0-- From xmlsywsqug@tedata.net Mon Feb 12 08:34:02 2007 Received: from [10.90.34.44] (helo=chiedprmail1.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HGbJi-0006mf-OU for nfsv4-archive@lists.ietf.org; Mon, 12 Feb 2007 08:34:02 -0500 Received: from [196.218.39.232] (helo=host-196.218.232.39.tedata.net) by chiedprmail1.ietf.org with esmtp (Exim 4.43) id 1HGbJf-0002O7-Q6 for nfsv4-archive@lists.ietf.org; Mon, 12 Feb 2007 08:34:02 -0500 From: "tradition" To: nfsv4-archive@lists.ietf.org Subject: Rocket Stock Report Date: Mon, 12 Feb 2007 15:34:01 -0200 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0002_01C74EBB.38968D30" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdOuziWPMUSJffiRaS1Ydl4rliLBw== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: X-Spam-Score: 4.9 (++++) X-Scan-Signature: 9182cfff02fae4f1b6e9349e01d62f32 ------=_NextPart_000_0002_01C74EBB.38968D30 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
The Chinese Market it is RED HOT!! The China sector is bringing investors and daily traders some very HUGE returns.

***CBFE***

China Biolife Enterprises, Inc.
Sym: CBFE
Date Of Trade: Monday, February 12 2007
Current Price: $1.30
Rating: 10/10

About CBFE:
China Biolife Enterprises, Inc. is a leading company in bamboo extracts and nutraceutical markets in China. The company provided solutions for food and dietary supplement industries and nutraceutical markets. The Company's vision is to help people live healthier lives by offering "natural, green and safe" products. Our Product - bamboo juice was extracted from refresh bamboo. Bamboo juice comprises with bamboo wax, bamboo acid etc. Adopting modern technical ways, it can be processed to be a serial health care products and medicine attached different effect.

WATCH OUT THE JUICE IS LOOSE!

MONDAY FEBRUARY 12th IS SURELY GOING TO BE ONE BIG DAY FOR CBFE!
------=_NextPart_000_0002_01C74EBB.38968D30-- From nfsv4-bounces@ietf.org Wed Feb 14 17:29:05 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHSbr-00065c-U2; Wed, 14 Feb 2007 17:28:19 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHSbq-00065X-Tu for nfsv4@ietf.org; Wed, 14 Feb 2007 17:28:18 -0500 Received: from brmea-mail-4.sun.com ([192.18.98.36]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HHSbn-0005kY-Ia for nfsv4@ietf.org; Wed, 14 Feb 2007 17:28:18 -0500 Received: from fe-amer-03.sun.com ([192.18.108.177]) by brmea-mail-4.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1EMSFvC008727 for ; Wed, 14 Feb 2007 15:28:15 -0700 (MST) Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JDH009014SP0F00@mail-amer.sun.com> (original mail from Lisa.Week@Sun.COM) for nfsv4@ietf.org; Wed, 14 Feb 2007 15:28:15 -0700 (MST) Received: from [172.20.24.217] by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JDH002HG532V2D0@mail-amer.sun.com> for nfsv4@ietf.org; Wed, 14 Feb 2007 15:28:14 -0700 (MST) Date: Wed, 14 Feb 2007 15:28:12 -0700 From: Lisa Week To: nfsv4@ietf.org Message-id: <45D38CFC.1050305@sun.com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT X-Accept-Language: en-us, en User-Agent: Mozilla/5.0 (X11; U; SunOS i86pc; en-US; rv:1.7) Gecko/20060405 X-Spam-Score: 0.0 (/) X-Scan-Signature: a7d6aff76b15f3f56fcb94490e1052e4 Subject: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Hi, As some of you may already know, sometime in late spring/early summer we are planning to host an extra Bakeathon. The Bakeathon will specifically target implementations of NFSv4.1. It is hoped we can work through the new features of NFSv4.1, allowing implementers an opportunity to provide feedback on the NFSv4 minor version 1 document prior to WG Last Call. The following contains some more details about the testing event as well as a couple of questions for you all. Please respond to the questions by Friday, February 16, 2007. When responding, please reply to all so that others who are planning to attend will have an idea of who is interested in testing what. Where: Sun's Austin, TX Campus 5300 Riata Park Court Austin, TX 78727 When: (Sorry if we are not able to accommodate everyone, but we will just go for the date that the majority votes for.) Possible Dates: May 14-18, 2007 June 11-15, 2007 June 18-22, 2007 ------ What I need from you all by Friday, February 16, 2007: 1.) Which dates do you prefer? 2.) How many people do you intend to send? 3.) What NFSv4.1 technologies do you intend to test? 4.) How much equipment (and what type) do you intend to bring? (Note: This doesn't have to be exact. It just lets us get an idea of how much power we'll need in the rooms that we'll be holding the event in.) Thanks, Lisa p.s. - The NFSv4.1 Bakeathon in May or June will be a held in addition to the NFSv4 Bakeathon hosted by CITI in the fall. The exact dates for the fall testing event are TBD. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Thu Feb 15 02:50:24 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHbNJ-0005oA-N3; Thu, 15 Feb 2007 02:49:53 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHbNI-0005mt-TK for nfsv4@ietf.org; Thu, 15 Feb 2007 02:49:52 -0500 Received: from mout.perfora.net ([217.160.230.41]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HHbNH-0006Qf-Jx for nfsv4@ietf.org; Thu, 15 Feb 2007 02:49:52 -0500 Received: from [72.179.37.29] (helo=[10.0.1.2]) by mrelay.perfora.net (node=mrelayus0) with ESMTP (Nemesis), id 0MKoyl-1HHbNC0kYE-0004FF; Thu, 15 Feb 2007 02:49:47 -0500 Mime-Version: 1.0 (Apple Message framework v752.2) In-Reply-To: <45D38CFC.1050305@sun.com> References: <45D38CFC.1050305@sun.com> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <28EBB64D-8E3E-4911-BBB6-8A6937B4FE41@openrbg.com> Content-Transfer-Encoding: 7bit From: Robert Gordon Subject: Re: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 Date: Thu, 15 Feb 2007 01:49:44 -0600 To: NFSv4 X-Mailer: Apple Mail (2.752.2) X-Provags-ID: perfora.net abuse@perfora.net login:58580747db913fe15783af8fca7b86e4 X-Provags-ID2: V01U2FsdGVkX1/5H0LTatqezqzh5RNU44rCxxXD/muVM0cVNmF6xz4I8dy2eJmLu5ecRmd07QhOFtDo1wbBF31HfBVfhtoOf+PIE0NvcR3dthgzvZXrZwWSeI7XETlrMm0j X-Spam-Score: 0.0 (/) X-Scan-Signature: f4c2cf0bccc868e4cc88dace71fb3f44 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Should anyone care; June 11->15 clashes with Apples WWDC07 in SF.. -- Robert. On Feb 14, 2007, at 4:28 PM, Lisa Week wrote: > Hi, > > As some of you may already know, sometime in late spring/early > summer we are planning to host an extra Bakeathon. The Bakeathon > will specifically target implementations of NFSv4.1. It is hoped > we can work through the new features of NFSv4.1, allowing > implementers an opportunity to provide feedback on the NFSv4 minor > version 1 document prior to WG Last Call. > > The following contains some more details about the testing event as > well as a couple of questions for you all. Please respond to the > questions by Friday, February 16, 2007. When responding, please > reply to all so that others who are planning to attend will have an > idea of who is interested in testing what. > > Where: Sun's Austin, TX Campus > 5300 Riata Park Court > Austin, TX 78727 > > When: (Sorry if we are not able to accommodate everyone, but we > will just go for the date that the majority votes for.) > > Possible Dates: > May 14-18, 2007 > June 11-15, 2007 > June 18-22, 2007 > > ------ > > What I need from you all by Friday, February 16, 2007: > 1.) Which dates do you prefer? > 2.) How many people do you intend to send? > 3.) What NFSv4.1 technologies do you intend to test? > 4.) How much equipment (and what type) do you intend to bring? > (Note: This doesn't have to be exact. It just lets us get an idea > of how much power we'll need in the rooms that we'll be holding the > event in.) > > Thanks, > Lisa > > p.s. - The NFSv4.1 Bakeathon in May or June will be a held in > addition to the NFSv4 Bakeathon hosted by CITI in the fall. The > exact dates for the fall testing event are TBD. > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Thu Feb 15 16:32:11 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHoC9-0006d0-It; Thu, 15 Feb 2007 16:31:13 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHoC7-0006cr-VT for nfsv4@ietf.org; Thu, 15 Feb 2007 16:31:11 -0500 Received: from e2.ny.us.ibm.com ([32.97.182.142]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HHoC5-0004lC-IK for nfsv4@ietf.org; Thu, 15 Feb 2007 16:31:11 -0500 Received: from d01relay04.pok.ibm.com (d01relay04.pok.ibm.com [9.56.227.236]) by e2.ny.us.ibm.com (8.13.8/8.13.8) with ESMTP id l1FLV5IP002388 for ; Thu, 15 Feb 2007 16:31:05 -0500 Received: from d01av02.pok.ibm.com (d01av02.pok.ibm.com [9.56.224.216]) by d01relay04.pok.ibm.com (8.13.8/8.13.8/NCO v8.2) with ESMTP id l1FLV5s6293092 for ; Thu, 15 Feb 2007 16:31:05 -0500 Received: from d01av02.pok.ibm.com (loopback [127.0.0.1]) by d01av02.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id l1FLV508007583 for ; Thu, 15 Feb 2007 16:31:05 -0500 Received: from d01ml604.pok.ibm.com (d01ml604.pok.ibm.com [9.56.227.90]) by d01av02.pok.ibm.com (8.12.11.20060308/8.12.11) with ESMTP id l1FLV5Xn007578; Thu, 15 Feb 2007 16:31:05 -0500 In-Reply-To: <45D38CFC.1050305@sun.com> To: Lisa Week Subject: Re: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 MIME-Version: 1.0 X-Mailer: Lotus Notes Release 7.0 HF85 November 04, 2005 Message-ID: From: Marc Eshel Date: Thu, 15 Feb 2007 13:31:07 -0800 X-MIMETrack: Serialize by Router on D01ML604/01/M/IBM(Build V80_M3_10312006|October 31, 2006) at 02/15/2007 16:31:09, Serialize complete at 02/15/2007 16:31:09 Content-Type: text/plain; charset="US-ASCII" X-Spam-Score: 0.0 (/) X-Scan-Signature: b4a0a5f5992e2a4954405484e7717d8c Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Lisa Week wrote on 02/14/2007 02:28:12 PM: > Hi, > > As some of you may already know, sometime in late spring/early summer we > are planning to host an extra Bakeathon. The Bakeathon will specifically > target implementations of NFSv4.1. It is hoped we can work through the > new features of NFSv4.1, allowing implementers an opportunity to provide > feedback on the NFSv4 minor version 1 document prior to WG Last Call. > > The following contains some more details about the testing event as well > as a couple of questions for you all. Please respond to the questions > by Friday, February 16, 2007. When responding, please reply to all so > that others who are planning to attend will have an idea of who is > interested in testing what. > > Where: Sun's Austin, TX Campus > 5300 Riata Park Court > Austin, TX 78727 > > When: (Sorry if we are not able to accommodate everyone, but we will > just go for the date that the majority votes for.) > > Possible Dates: > May 14-18, 2007 > June 11-15, 2007 > June 18-22, 2007 > > ------ > > What I need from you all by Friday, February 16, 2007: > 1.) Which dates do you prefer? June 18-22 > 2.) How many people do you intend to send? 2 people > 3.) What NFSv4.1 technologies do you intend to test? pNFS > 4.) How much equipment (and what type) do you intend to bring? (Note: > This doesn't have to be exact. It just lets us get an idea of how much > power we'll need in the rooms that we'll be holding the event in.) about 4 laptops > Thanks, > Lisa > > p.s. - The NFSv4.1 Bakeathon in May or June will be a held in addition > to the NFSv4 Bakeathon hosted by CITI in the fall. The exact dates for > the fall testing event are TBD. > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Fri Feb 16 00:56:06 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHw3n-0000M7-0C; Fri, 16 Feb 2007 00:55:07 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HHw3l-0000Ll-6S for nfsv4@ietf.org; Fri, 16 Feb 2007 00:55:05 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HHw3i-0005W9-TZ for nfsv4@ietf.org; Fri, 16 Feb 2007 00:55:05 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1G5stTJ030456; Fri, 16 Feb 2007 00:54:55 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 16 Feb 2007 00:54:55 -0500 X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 Date: Fri, 16 Feb 2007 00:54:55 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 Thread-Index: AcdQh7lNZNkoQQ9VSAetLCeRVQlJpQBBbcnP References: <45D38CFC.1050305@sun.com> From: "Halevy, Benny" To: "Lisa Week" , X-Spam-Score: 0.0 (/) X-Scan-Signature: 25620135586de10c627e3628c432b04a Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Lisa Week wrote: > =20 > Hi, >=20 > As some of you may already know, sometime in late spring/early summer = we=20 > are planning to host an extra Bakeathon. The Bakeathon will = specifically=20 > target implementations of NFSv4.1. It is hoped we can work through = the=20 > new features of NFSv4.1, allowing implementers an opportunity to = provide=20 > feedback on the NFSv4 minor version 1 document prior to WG Last Call. >=20 > The following contains some more details about the testing event as = well=20 > as a couple of questions for you all. Please respond to the questions = > by Friday, February 16, 2007. When responding, please reply to all so = > that others who are planning to attend will have an idea of who is=20 > interested in testing what. >=20 > Where: Sun's Austin, TX Campus > 5300 Riata Park Court > Austin, TX 78727 >=20 > When: (Sorry if we are not able to accommodate everyone, but we will=20 > just go for the date that the majority votes for.) >=20 > Possible Dates: > May 14-18, 2007 > June 11-15, 2007 > June 18-22, 2007 >=20 > ------ >=20 > What I need from you all by Friday, February 16, 2007: > 1.) Which dates do you prefer? June 11-15, then May 14-18 > 2.) How many people do you intend to send? 2 > 3.) What NFSv4.1 technologies do you intend to test? pnfs > 4.) How much equipment (and what type) do you intend to bring? (Note:=20 > This doesn't have to be exact. It just lets us get an idea of how = much=20 > power we'll need in the rooms that we'll be holding the event in.) maximum of: half Panasas shelf (4 U, 600W) + 2 x 1 U servers (say 150W = each) so that makes a 900W budget. >=20 > Thanks, > Lisa >=20 > p.s. - The NFSv4.1 Bakeathon in May or June will be a held in addition = > to the NFSv4 Bakeathon hosted by CITI in the fall. The exact dates = for=20 > the fall testing event are TBD. >=20 > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 >=20 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 19 16:24:44 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJFzI-0003VT-Og; Mon, 19 Feb 2007 16:23:56 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJFzE-0003Og-Au for nfsv4@ietf.org; Mon, 19 Feb 2007 16:23:52 -0500 Received: from ug-out-1314.google.com ([66.249.92.175]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HJFz9-0006xH-Nm for nfsv4@ietf.org; Mon, 19 Feb 2007 16:23:52 -0500 Received: by ug-out-1314.google.com with SMTP id 72so712667ugd for ; Mon, 19 Feb 2007 13:23:46 -0800 (PST) DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:sender:to:subject:cc:in-reply-to:mime-version:content-type:references:x-google-sender-auth; b=bl0O+KlTIGQqDog+Mi9tCephS81cAgFbf+OQcIVJ0zgUSV5v8pVMFLLrl/Jn9stI/eHtPoiB+qFZySvq0acWRcijl8AHP04R7fAXTVl1tOIKa+rJ+fNbjb8Q7YptBBGisXQH92PdR6oColzMRbFacOz9Li1QjkgpjZCsPt6roLY= Received: by 10.114.195.19 with SMTP id s19mr3084550waf.1171920225449; Mon, 19 Feb 2007 13:23:45 -0800 (PST) Received: by 10.114.107.16 with HTTP; Mon, 19 Feb 2007 13:23:45 -0800 (PST) Message-ID: <89c397150702191323p4bb5bf0awad27d151b2be6a3e@mail.gmail.com> Date: Mon, 19 Feb 2007 16:23:45 -0500 From: "William A. (Andy) Adamson" To: "Lisa Week" Subject: Re: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 In-Reply-To: <45D38CFC.1050305@sun.com> MIME-Version: 1.0 References: <45D38CFC.1050305@sun.com> X-Google-Sender-Auth: cd300f2a978c9f46 X-Spam-Score: 0.1 (/) X-Scan-Signature: 6d95a152022472c7d6cdf886a0424dc6 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: multipart/mixed; boundary="===============0913432600==" Errors-To: nfsv4-bounces@ietf.org --===============0913432600== Content-Type: multipart/alternative; boundary="----=_Part_55600_23573810.1171920225354" ------=_Part_55600_23573810.1171920225354 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline On 2/14/07, Lisa Week wrote: > > Hi, > > As some of you may already know, sometime in late spring/early summer we > are planning to host an extra Bakeathon. The Bakeathon will specifically > target implementations of NFSv4.1. It is hoped we can work through the > new features of NFSv4.1, allowing implementers an opportunity to provide > feedback on the NFSv4 minor version 1 document prior to WG Last Call. > > The following contains some more details about the testing event as well > as a couple of questions for you all. Please respond to the questions > by Friday, February 16, 2007. When responding, please reply to all so > that others who are planning to attend will have an idea of who is > interested in testing what. > > Where: Sun's Austin, TX Campus > 5300 Riata Park Court > Austin, TX 78727 > > When: (Sorry if we are not able to accommodate everyone, but we will > just go for the date that the majority votes for.) > > Possible Dates: > May 14-18, 2007 Won't work for us - May 14-17 is the 8th LCI International Conference on High-Performance Clustered Computing - we're presenting. June 11-15, 2007 This is a good week June 18-22, 2007 This won't work for us: USENIX 2007 Technical Conference: June 17-22** ------ > > What I need from you all by Friday, February 16, 2007: > 1.) Which dates do you prefer? June 11-15, 2007 2.) How many people do you intend to send? 2 3.) What NFSv4.1 technologies do you intend to test? Sessions and pNFS 4.) How much equipment (and what type) do you intend to bring? (Note: > This doesn't have to be exact. It just lets us get an idea of how much > power we'll need in the rooms that we'll be holding the event in.) 4 - 6 laptops Thanks, > Lisa > > p.s. - The NFSv4.1 Bakeathon in May or June will be a held in addition > to the NFSv4 Bakeathon hosted by CITI in the fall. The exact dates for > the fall testing event are TBD. > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 > > ------=_Part_55600_23573810.1171920225354 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline
On 2/14/07, Lisa Week <Lisa.Week@sun.com> wrote:
Hi,

As some of you may already know, sometime in late spring/early summer we
are planning to host an extra Bakeathon. The Bakeathon will specifically
target implementations of NFSv4.1.  It is hoped we can work through the
new features of NFSv4.1, allowing implementers an opportunity to provide
feedback on the NFSv4 minor version 1 document  prior to WG Last Call.

The following contains some more details about the testing event as well
as a couple of questions for you all.  Please respond to the questions
by Friday, February 16, 2007.  When responding, please reply to all so
that others who are planning to attend will have an idea of who is
interested in testing what.

Where: Sun's Austin, TX Campus
    5300 Riata Park Court
    Austin, TX 78727

When: (Sorry if we are not able to accommodate everyone, but we will
just go for the date that the majority votes for.)

Possible Dates:
May 14-18, 2007

Won't work for us - May 14-17 is the 8th LCI International Conference on High-Performance Clustered Computing - we're presenting.


June 11-15, 2007

This is a good week

June 18-22, 2007
 
This won't work for us: USENIX 2007 Technical Conference: June 17-22


------

What I need from you all by Friday, February 16, 2007:
1.) Which dates do you prefer?

June 11-15, 2007
 

2.) How many people do you intend to send?

2

3.) What NFSv4.1 technologies do you intend to test?

Sessions and pNFS

4.) How much equipment (and what type) do you intend to bring? (Note:
This doesn't  have to be exact.  It just lets us get an idea of how much
power we'll need in the rooms that we'll be holding the event in.)

4  - 6 laptops

Thanks,
Lisa

p.s. - The NFSv4.1 Bakeathon in May or June will be a held in addition
to the NFSv4 Bakeathon hosted by CITI in the fall.  The exact dates for
the fall testing event are TBD.

_______________________________________________
nfsv4 mailing list
nfsv4@ietf.org
https://www1.ietf.org/mailman/listinfo/nfsv4


------=_Part_55600_23573810.1171920225354-- --===============0913432600== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 --===============0913432600==-- From nfsv4-bounces@ietf.org Tue Feb 20 01:03:04 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJO4l-0007yh-Qr; Tue, 20 Feb 2007 01:02:07 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJO4k-0007yc-Ln for nfsv4@ietf.org; Tue, 20 Feb 2007 01:02:06 -0500 Received: from nf-out-0910.google.com ([64.233.182.189]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HJO4i-00074j-AU for nfsv4@ietf.org; Tue, 20 Feb 2007 01:02:06 -0500 Received: by nf-out-0910.google.com with SMTP id l36so2795785nfa for ; Mon, 19 Feb 2007 22:02:03 -0800 (PST) DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:mime-version:content-type; b=QcetZpwMplhTxfUcEKz9OSL6vl3LPUV4qY4PmwIycF+S0x9FhmyHXcy44GjvKJ56KJNP/LuQ9W+b0YTIzgi4GJoQovtF4+cc+b9bbfHYEx021HoCu34qpN3dQpvPzviMqbwIjxNozX7I/SrKjKL0X23QnvwfXBJZnbJwdMqscg8= Received: by 10.82.163.13 with SMTP id l13mr12317176bue.1171951323345; Mon, 19 Feb 2007 22:02:03 -0800 (PST) Received: by 10.82.183.3 with HTTP; Mon, 19 Feb 2007 22:02:03 -0800 (PST) Message-ID: <4ad0ec310702192202m274ac31bmf141a7d08ed8364f@mail.gmail.com> Date: Mon, 19 Feb 2007 22:02:03 -0800 From: "Renu Tewari" To: nfsv4@ietf.org MIME-Version: 1.0 X-Spam-Score: 0.1 (/) X-Scan-Signature: e5ba305d0e64821bf3d8bc5d3bb07228 Subject: [nfsv4] Federated Filesystems using v4 (new mailing list) X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: multipart/mixed; boundary="===============0852794506==" Errors-To: nfsv4-bounces@ietf.org --===============0852794506== Content-Type: multipart/alternative; boundary="----=_Part_54690_23947663.1171951323246" ------=_Part_54690_23947663.1171951323246 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline For all those who attended the federated filesystem BoF at the FAST conference last week and the one at Connectathon before that and others who are interested in issues related to federated filesystems using v4 especially creating common namespaces and cross cluster referrals we have a new mailing list setup at xdl-federated-fs@netapp.com Please send a mail to the list if you want to be included. regards Renu IBM Almaden ------=_Part_54690_23947663.1171951323246 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline
For all those who attended the federated filesystem BoF at the FAST conference last week  and the one at Connectathon before that and others who are interested in  issues related to federated filesystems using v4 especially creating common namespaces and  cross cluster  referrals we have a new mailing list setup at xdl-federated-fs@netapp.com 
Please send a mail to the list if you want to be included.
 
regards
Renu
IBM Almaden
 
------=_Part_54690_23947663.1171951323246-- --===============0852794506== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 --===============0852794506==-- From TALK@talon-eng.co.uk Tue Feb 20 09:33:42 2007 Received: from [10.90.34.44] (helo=chiedprmail1.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJW3q-0007rA-Gr for nfsv4-archive@lists.ietf.org; Tue, 20 Feb 2007 09:33:42 -0500 Received: from p54832956.dip0.t-ipconnect.de ([84.131.41.86]) by chiedprmail1.ietf.org with esmtp (Exim 4.43) id 1HJW3o-00048p-MG for nfsv4-archive@lists.ietf.org; Tue, 20 Feb 2007 09:33:42 -0500 Received: from [179.165.154.198] (port=5393 helo=dkDVIdg) by ifLvrenMl with asmtp id bLqwBf-nJBawR-37 for nfsv4-archive@lists.ietf.org; Tue, 20 Feb 2007 15:36:54 +0100 From: "MIGHT ACTUALLY" To: nfsv4-archive@lists.ietf.org Subject: STONEMark LOS ANGELES Date: Tue, 20 Feb 2007 15:36:27 +0100 Message-ID: <000701c754fc$81286b30$56298354@Marcy> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook, Build 10.0.6626 Importance: Normal X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2962 X-Spam-Score: 1.8 (+) X-Scan-Signature: 4adaf050708fb13be3316a9eee889caa Mooremay pmby moorejan wknrmark mooreapr amby guardian. Archives of jim mooremay pmby moorejan wknrmark mooreapr! Mooreten reasons why, was cool, chart attackmark. Off topic tribute album preview. Night, wish youd get, straight click here to. Was cool, chart attackmark moore. WE HELP THE WORLD MOVE! TRANSFORMING THE LIVES OF DEVELOPING NATIONS This is an amazing story. WE urge you to go read the news on this company and visit the website. The company website will be listed in news releases. Watch this company closely starting NOW! TRANSNATIONAL AUTOMOTIVE GROUP TAMG.OB Founded in 2005, TAMG Provides transportation systems and infrastructure to the developing world. Our bus fleets provide an efficient way for communities in need to travel and prosper. Affordable for riders, and economically sustainable for the company, TAMG has turned capital investments in the developing world into sustainable and profitable transportation solutions NEWS February 15, 2007 - Transnational Automotive Group Launches "LeCar" Inter-Urban Bus Operations between YaoundE and Douala, Cameroon *** December 18 , 2006 - After Le Bus, Here comes Le Car *** December 11 , 2006 - Transnational Automotive Announces $800,000 USD Investment by the Chamber of Commerce of Cameroon *** November 30, 2006 - Transnational Automotive Announces Purchase of 60 City Buses for its Urban Transportation Operation in Cameroon *** November 16, 2006 - Transnational Automotive Announces $800,000 USD Investment by the Chamber of Commerce of Cameroon Mooremar usa todaymark, associated pressmark. One torrence webring inc by mark join now ring. Open session links sites worlds add your. Summer long dont you just know, it. Just know it my, mind off. Ring hub, random next search? Swingin sounds from the estate someday we might. Mooredean, remembers rolling, stonemark los angeles, timesmark mooremar usa. Inc by mark join now ring hub? Sounds from the estate someday, we might actually rehearse. Tribute album preview production. Get straight click here to make this! Now ring hub random. Photos welcome guest please login or. Inc by mark join now. Moore, forum jump home talk city dumb angel? From nfsv4-bounces@ietf.org Tue Feb 20 11:07:09 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJXV8-0007ux-NU; Tue, 20 Feb 2007 11:05:58 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJXV8-0007ur-AZ for nfsv4@ietf.org; Tue, 20 Feb 2007 11:05:58 -0500 Received: from brmea-mail-4.sun.com ([192.18.98.36]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HJXUy-0005qn-Dg for nfsv4@ietf.org; Tue, 20 Feb 2007 11:05:58 -0500 Received: from fe-amer-06.sun.com ([192.18.108.180]) by brmea-mail-4.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1KG5lR4026516 for ; Tue, 20 Feb 2007 16:05:47 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JDR00F01QWRX000@mail-amer.sun.com> (original mail from Spencer.Shepler@Sun.COM) for nfsv4@ietf.org; Tue, 20 Feb 2007 09:05:47 -0700 (MST) Received: from [192.168.0.3] (adsl-71-145-188-131.dsl.austtx.sbcglobal.net [71.145.188.131]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JDR0057KRDKTA10@mail-amer.sun.com>; Tue, 20 Feb 2007 09:05:44 -0700 (MST) Date: Tue, 20 Feb 2007 10:05:52 -0600 From: Spencer Shepler Subject: Re: [nfsv4] Federated Filesystems using v4 (new mailing list) In-reply-to: <4ad0ec310702192202m274ac31bmf141a7d08ed8364f@mail.gmail.com> To: Renu Tewari Message-id: <2D9532D2-E47B-469A-AB39-EF1D1592C3C6@sun.com> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.2) Content-type: text/plain; format=flowed; delsp=yes; charset=US-ASCII Content-transfer-encoding: 7BIT References: <4ad0ec310702192202m274ac31bmf141a7d08ed8364f@mail.gmail.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 2409bba43e9c8d580670fda8b695204a Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org On Feb 20, 2007, at 12:02 AM, Renu Tewari wrote: > For all those who attended the federated filesystem BoF at the FAST > conference last week and the one at Connectathon before that and > others who are interested in issues related to federated > filesystems using v4 especially creating common namespaces and > cross cluster referrals we have a new mailing list setup at xdl- > federated-fs@netapp.com > Please send a mail to the list if you want to be included. Sorry that I was not present at these meetings to have the full context at hand but your note does raise a couple of questions. Is there presentation or summary material available for these discussions to provide background for those not present? From that background material, does it make sense to host the discussions here on the NFSv4 IETF alias? In other words, will the work potentially lead to IETF standards track or information documents or are there interpretation issues that may arise that relate to the NFSv4 protocol? Spencer _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 20 12:28:24 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJYmA-00019B-J6; Tue, 20 Feb 2007 12:27:38 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJYm8-000191-N9 for nfsv4@ietf.org; Tue, 20 Feb 2007 12:27:36 -0500 Received: from brmea-mail-2.sun.com ([192.18.98.43]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HJYm5-0000cU-D5 for nfsv4@ietf.org; Tue, 20 Feb 2007 12:27:36 -0500 Received: from fe-amer-05.sun.com ([192.18.108.179]) by brmea-mail-2.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1KHRUYo023193 for ; Tue, 20 Feb 2007 17:27:30 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JDR00H01V4HUX00@mail-amer.sun.com> (original mail from Thomas.Haynes@Sun.COM) for nfsv4@ietf.org; Tue, 20 Feb 2007 10:27:30 -0700 (MST) Received: from [129.150.48.8] by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JDR006TPV5TCBP3@mail-amer.sun.com>; Tue, 20 Feb 2007 10:27:30 -0700 (MST) Date: Tue, 20 Feb 2007 11:27:29 -0600 From: Tom Haynes Subject: Re: [nfsv4] Federated Filesystems using v4 (new mailing list) In-reply-to: <2D9532D2-E47B-469A-AB39-EF1D1592C3C6@sun.com> To: Spencer Shepler Message-id: <45DB2F81.6070801@sun.com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT References: <4ad0ec310702192202m274ac31bmf141a7d08ed8364f@mail.gmail.com> <2D9532D2-E47B-469A-AB39-EF1D1592C3C6@sun.com> User-Agent: Thunderbird 1.5.0.8 (X11/20061204) X-Spam-Score: 0.0 (/) X-Scan-Signature: 0f1ff0b0158b41ac6b9548d0972cdd31 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Another question would be whether this mailing list will be archived and available on the web? _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 20 21:40:41 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJhOS-0006Gi-Ez; Tue, 20 Feb 2007 21:39:44 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJhOS-0006EP-09 for nfsv4@ietf.org; Tue, 20 Feb 2007 21:39:44 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HJhOQ-000269-NZ for nfsv4@ietf.org; Tue, 20 Feb 2007 21:39:43 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 20 Feb 2007 18:39:38 -0800 X-IronPort-AV: i="4.14,198,1170662400"; d="scan'208"; a="34721928:sNHT15667701" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1L2dbTk010484 for ; Tue, 20 Feb 2007 18:39:37 -0800 (PST) Received: from exsvlrb01.hq.netapp.com ([10.56.8.62]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Tue, 20 Feb 2007 18:39:37 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 20 Feb 2007 18:40:41 -0800 Received: from 10.30.32.49 ([10.30.32.49]) by exnane01.hq.netapp.com ([10.97.0.61]) with Microsoft Exchange Server HTTP-DAV ; Wed, 21 Feb 2007 02:40:40 +0000 User-Agent: Microsoft-Entourage/11.3.3.061214 Date: Tue, 20 Feb 2007 21:39:34 -0500 From: Daniel Ellard To: Message-ID: Thread-Topic: Federated Filesystems using v4 (new mailing list) Thread-Index: AcdVYYVNxBMGAsFUEduOBQARJNaE/g== Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit X-OriginalArrivalTime: 21 Feb 2007 02:40:41.0848 (UTC) FILETIME=[ADBE7F80:01C75561] X-Spam-Score: 0.0 (/) X-Scan-Signature: 9ed51c9d1356100bce94f1ae4ec616a9 Subject: [nfsv4] re: Federated Filesystems using v4 (new mailing list) X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Sorry to reply in a non-threaded manner, but Renu brought to my attention some questions that appeared on this list. - Why not just use the nfsv4 list? There's certainly overlap between the people on this list and the people interested in federated file systems, but it's my opinion that there are some important differences in focus: 1. I think the federation effort will flounder if we try to change nfsv4.X in any way whatsoever. It's my opinion -- and shared by others -- that we should assume that the client-facing protocols are a given. So while the nfsv4 list discusses the future of v4 beyond 4.1, the federation list will conservatively assume only v4 (at least until such time as it's proven unworkable...). 2. We're not just thinking about v4. We're thinking about CIFS, and, if possible, we'd like to figure out how we can make v3 work in some reasonably portable manner. We've got a lot of customers who are still happy with v3 and don't want to migrate -- and I suspect we're not the only people in that boat. Of course, the most important thing is to reach the community of people who are interested in this -- so if y'all want to discuss this on this list, I'll join you here. - Will the work lead to a standards initiative? If successful, yes, that's the plan. Whether it will be via IETF is something we need to work out. - Will the materials from the Bof and WiP be posted? We're working on that. It will happen, but I don't have a URL yet... - Will the mailing list be archived? Yes. In fact, it should be already. I need a guinea pig to test whether the majordomo archive actually works properly from outside of netapp. -Dan _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 20 21:55:17 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJhdK-000643-HG; Tue, 20 Feb 2007 21:55:06 -0500 Received: from [10.90.34.44] (helo=chiedprmail1.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJhdJ-00063v-4b for nfsv4@ietf.org; Tue, 20 Feb 2007 21:55:05 -0500 Received: from brmea-mail-1.sun.com ([192.18.98.31]) by chiedprmail1.ietf.org with esmtp (Exim 4.43) id 1HJhdF-0003sC-DV for nfsv4@ietf.org; Tue, 20 Feb 2007 21:55:04 -0500 Received: from fe-amer-03.sun.com ([192.18.108.177]) by brmea-mail-1.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1L2t0M2022616 for ; Wed, 21 Feb 2007 02:55:00 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JDS00H01KGLSG00@mail-amer.sun.com> (original mail from Thomas.Haynes@Sun.COM) for nfsv4@ietf.org; Tue, 20 Feb 2007 19:55:00 -0700 (MST) Received: from [192.168.2.115] ([72.198.16.43]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JDS006WILFOBY30@mail-amer.sun.com>; Tue, 20 Feb 2007 19:55:00 -0700 (MST) Date: Tue, 20 Feb 2007 20:54:56 -0600 From: Tom Haynes Subject: Re: [nfsv4] re: Federated Filesystems using v4 (new mailing list) In-reply-to: To: Daniel Ellard Message-id: <45DBB480.8000005@sun.com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT References: User-Agent: Thunderbird 1.5.0.8 (X11/20061204) X-Spam-Score: 0.0 (/) X-Scan-Signature: 538aad3a3c4f01d8b6a6477ca4248793 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Daniel Ellard wrote: > Sorry to reply in a non-threaded manner, but Renu brought to my attention > some questions that appeared on this list. > > - Why not just use the nfsv4 list? > > There's certainly overlap between the people on this list and the people > interested in federated file systems, but it's my opinion that there are > some important differences in focus: > > 1. I think the federation effort will flounder if we try to change > nfsv4.X in any way whatsoever. It's my opinion -- and shared by > others -- that we should assume that the client-facing protocols > are a given. So while the nfsv4 list discusses the future of v4 > beyond 4.1, the federation list will conservatively assume only v4 > (at least until such time as it's proven unworkable...). > > 2. We're not just thinking about v4. We're thinking about CIFS, and, > if possible, we'd like to figure out how we can make v3 work in some > reasonably portable manner. We've got a lot of customers who are > still happy with v3 and don't want to migrate -- and I suspect we're > not the only people in that boat. > > Of course, the most important thing is to reach the community of people > who are interested in this -- so if y'all want to discuss this on this > list, I'll join you here. > > - Will the work lead to a standards initiative? > > If successful, yes, that's the plan. Whether it will be via IETF is > something we need to work out. > > - Will the materials from the Bof and WiP be posted? > > We're working on that. It will happen, but I don't have a URL yet... > > - Will the mailing list be archived? > > Yes. In fact, it should be already. I need a guinea pig to test > whether the majordomo archive actually works properly from outside > of netapp. > > Just tell us the link... > -Dan > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From avedsvrag@comsig.com Wed Feb 21 02:52:03 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HJmGh-00038k-Rb for nfsv4-archive@lists.ietf.org; Wed, 21 Feb 2007 02:52:03 -0500 Received: from [85.234.165.125] (helo=[85.234.165.125]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HJmGg-0008TN-EJ for nfsv4-archive@lists.ietf.org; Wed, 21 Feb 2007 02:52:03 -0500 From: "dealing" To: nfsv4-archive@lists.ietf.org Subject: Surprises Date: Wed, 21 Feb 2007 09:52:17 -0200 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0002_01C7559D.F8F7E310" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdVnfj3IkbECmQ0T76RYDTa4iFyAQ== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: <9BDF138CEAAA2A8.E79115B730@comsig.com> X-Spam-Score: 1.3 (+) X-Scan-Signature: 93238566e09e6e262849b4f805833007 ------=_NextPart_000_0002_01C7559D.F8F7E310 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
ATTENTION DAY TRADERS AND INVESTORS. GET ON PHYA!

INVESTOR ALERT! DON'T MISS THIS RUN ON PHYA!!! THE ALERT IS ON!!

Watch PHYA Like a Hawk on FEB 21, 2007

Company: PHYSICIANS ADULT DAY
Sym: PHYA.PK
Currently: $0.29 (+0.04) (+16.00% in a day!!!)
Wednesday Target: $0.76

Physicians Adult Daycare Incorporating Cutting-Edge Technology Announced Today

The Company is in the final negotiation stages with TOTALtrak Global, Inc., a global provider of leading-edge Radio Frequency Identification (RFID)-based and patent-pending Multi-Range (MRID) technology solutions, to implement this versatile and powerful technology intothe Company's innovative adult daycare program. RFID systems are becoming one of the most widely adopted tracking and information storage protocols in the world, due to its capability to provide instantaneous identification as well as tracking in a mobile environment. Currently, RFID is employed in product tracking, animal identification, passport control, electronic toll remittance, and the U.S. Food and Drug Administration recently approved the first RFID chips to be implanted in humans.

Keep a look out for additional GREAT weekly news and be sure to watch them trade like crazy on Wednesday Feb 21, 2007
------=_NextPart_000_0002_01C7559D.F8F7E310-- From qeckzaeptdf@shawcable.net Thu Feb 22 03:12:58 2007 Received: from [10.90.34.44] (helo=chiedprmail1.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HK94U-0003Er-0s for nfsv4-archive@lists.ietf.org; Thu, 22 Feb 2007 03:12:58 -0500 Received: from [24.71.158.40] (helo=S0106000ea6ae6a17.ok.shawcable.net) by chiedprmail1.ietf.org with esmtp (Exim 4.43) id 1HK94S-0008Kx-K0 for nfsv4-archive@lists.ietf.org; Thu, 22 Feb 2007 03:12:57 -0500 From: "" To: nfsv4-archive@lists.ietf.org Subject: Earnings: Expected Reports Date: Thu, 22 Feb 2007 00:12:57 +0800 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0003_01C75616.344D0300" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdWFjRNI06HkC/ZRmWWPJuZ4fDBMw== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: <23898DBF9E1CA08.438CC1A9A9@shawcable.net> X-Spam-Score: 3.4 (+++) X-Scan-Signature: 798b2e660f1819ae38035ac1d8d5e3ab ------=_NextPart_000_0003_01C75616.344D0300 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
+Physicians Adult Daycare, Inc. Incorporates New Techgnology+

Physicians Adult Daycare, Inc. (phya.pk)

DATE : FEB 22, 2007
Company: PHYSICIANS ADULT DAY
Currently: $0.31 (+0.02) (+6.90% in a day!!!)
Expected Day Target: $0.76

News:
Physicians Adult Daycare, Inc. (PHYA) announced that the Company is in the final negotiation stages with TOTALtrak Global, Inc., a global provider of leading-edge Radio Frequency Identification (RFID)-based and patent-pending Multi-Range (MRID) technology solutions, to implement this versatile and powerful technology into the Company's innovative adult daycare program......
------=_NextPart_000_0003_01C75616.344D0300-- From redppgxwqt@centraldata.com Thu Feb 22 11:10:51 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKGWx-0002qb-Aw for nfsv4-archive@lists.ietf.org; Thu, 22 Feb 2007 11:10:51 -0500 Received: from [84.4.223.132] (helo=[84.4.223.132]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HKGWv-0001Dl-SG for nfsv4-archive@lists.ietf.org; Thu, 22 Feb 2007 11:10:51 -0500 From: "Old" To: nfsv4-archive@lists.ietf.org Subject: Economic Events & Analysis Date: Thu, 22 Feb 2007 17:10:36 -0100 MIME-Version: 1.0 Content-Type: multipart/related; boundary="----=_NextPart_000_0003_01C756A4.5EDD3890" X-Mailer: Microsoft Office Outlook, Build 11.0.5510 Thread-Index: AcdWpF7dhJzjQQtoT3OfZDvy/w+uAw== X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 Message-Id: X-Spam-Score: 4.9 (++++) X-Scan-Signature: 798b2e660f1819ae38035ac1d8d5e3ab ------=_NextPart_000_0003_01C756A4.5EDD3890 Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable
+Physicians Adult Daycare, Inc. Incorporates New Techgnology+

Physicians Adult Daycare, Inc. (phya.pk)

DATE : FEB 22, 2007
Company: PHYSICIANS ADULT DAY
Currently: $0.31 (+0.02) (+6.90% in a day!!!)
Expected Day Target: $0.76

News:
Physicians Adult Daycare, Inc. (PHYA) announced that the Company is in the final negotiation stages with TOTALtrak Global, Inc., a global provider of leading-edge Radio Frequency Identification (RFID)-based and patent-pending Multi-Range (MRID) technology solutions, to implement this versatile and powerful technology into the Company's innovative adult daycare program......
------=_NextPart_000_0003_01C756A4.5EDD3890-- From nfsv4-bounces@ietf.org Thu Feb 22 13:51:26 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKJ1I-0005GD-Tp; Thu, 22 Feb 2007 13:50:20 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKJ1H-0005Eh-W8 for nfsv4@ietf.org; Thu, 22 Feb 2007 13:50:19 -0500 Received: from brmea-mail-3.sun.com ([192.18.98.34]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HKJ1E-0001M3-Li for nfsv4@ietf.org; Thu, 22 Feb 2007 13:50:19 -0500 Received: from fe-amer-05.sun.com ([192.18.108.179]) by brmea-mail-3.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1MIoGIU026527 for ; Thu, 22 Feb 2007 18:50:16 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JDV00F01NYITY00@mail-amer.sun.com> (original mail from Lisa.Week@Sun.COM) for nfsv4@ietf.org; Thu, 22 Feb 2007 11:50:16 -0700 (MST) Received: from shortset.Central.Sun.COM ([172.20.25.77]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JDV000QEOBQSFQ4@mail-amer.sun.com>; Thu, 22 Feb 2007 11:50:14 -0700 (MST) Date: Thu, 22 Feb 2007 11:49:55 -0700 From: Lisa Week Subject: Re: [nfsv4] NFSv4.1 Bakeathon - May/June 2007 In-reply-to: <7619F3097FAB384287CF636FF92D0CA10874144D@exsvl01.hq.netapp.com> To: "Iyer, Rahul" Message-id: <45DDE5D3.9010608@sun.com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT References: <45D38CFC.1050305@sun.com> <7619F3097FAB384287CF636FF92D0CA10874144D@exsvl01.hq.netapp.com> User-Agent: Thunderbird 2.0b2 (X11/20070129) X-Spam-Score: 0.0 (/) X-Scan-Signature: a7d6aff76b15f3f56fcb94490e1052e4 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Hi Rahul, It looks like a majority of people have said that June 11-15 works for them. (And in one case it is the only one of the choices that works for them.) So, would June 11-15 work for you guys as well? Thanks, Lisa Iyer, Rahul wrote: > Hi Lisa, > Here are our (Garth and Myself) preferences: > >> What I need from you all by Friday, February 16, 2007: >> 1.) Which dates do you prefer? >> > Jun 18 - 22 > > >> 2.) How many people do you intend to send? >> > 2 > > >> 3.) What NFSv4.1 technologies do you intend to test? >> > Sessions + pNFS > > >> 4.) How much equipment (and what type) do you intend to bring? (Note: >> This doesn't have to be exact. It just lets us get an idea >> of how much power we'll need in the rooms that we'll be >> holding the event in.) >> > 4-6 laptops > > Thanks > Regards > Rahul > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Fri Feb 23 09:44:47 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKbeA-0000aU-Cj; Fri, 23 Feb 2007 09:43:42 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKbe8-0000Ye-UM for nfsv4@ietf.org; Fri, 23 Feb 2007 09:43:40 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HKbdD-0005AW-Im for nfsv4@ietf.org; Fri, 23 Feb 2007 09:42:45 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1NEgRm8020101; Fri, 23 Feb 2007 09:42:27 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 23 Feb 2007 09:42:27 -0500 X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Date: Fri, 23 Feb 2007 09:42:27 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: SET_PRIORITY: new op proposal Thread-Index: AcdXWNZ+TRRY857VQRS5J1GjoQzbMQ== From: "Halevy, Benny" To: X-Spam-Score: 0.0 (/) X-Scan-Signature: 944ecb6e61f753561f559a497458fb4f Cc: chuck.lever@oracle.com, "Welch, Brent" Subject: [nfsv4] SET_PRIORITY: new op proposal X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Based on discussions during FAST 07 we'd like to propose a SET_PRIORITY operation that allows the client to set a relative priority for the session and/or operations. The benefits from this operation are pretty obvious. It can be used by clients for example to execute metadata operations in higher priority than data operations, or to execute operations on specific files in a different priority, or to give different priority to different client hosts. I'd appreciate your prompt comments since we would like to introduce this operation as soon as possible (draft-09) Thanks, Benny Operation: SET_PRIORITY - set relative priority SYNOPSIS priority_how, priority_level -> actual_priority_level ARGUMENT enum priority_how4 { PRIORITY_SESSION =3D 0, PRIORITY_OPERATION =3D 1 }; enum priority_range4 { PRIORITY_MIN =3D -50, PRIORITY_DEFAULT =3D 0, PRIORITY_MAX =3D 49 }; struct SET_PRIORITY4args { enum priority_how4 priority_how; int32_t priority_level; }; RESULT struct SET_PRIORITY4res { int32_t actual_priority_level; }; DESCRIPTION This operation may be used to set a relative priority for the current = session or for the following operations in the compound RPC. The default = priority level is implicitly zero for all sessions and operations. = SET_PRIORITY for PRIORITY_SESSION sets the priority_level of the current session such = that all operations following SET_PRIORITY in the same compound RPC and all = operations related to the sessions will be executed in the given priority_level. SET_PRIORITY for PRIORITY_OPERATION sets the priority_level only for = the operations following it in the compound RPC and does not affect the = current priority_level of the related session. There are 100 priority levels, such that the priority_level MUST be greater than or equal to PRIORITY_MIN and less than or equal to = PRIORITY_MAX. If the priority_level is outside the valid range the server should = return an NFS4ERR_INVAL error. The server replies SET_PRIORITY with the actual_priority_level that = was assigned to the session and/or following operations. Servers that do not = support priorities MUST either return an NFS4ERR_NOTSUPP error or return zero for the actual_priority_level. Servers that support priorities SHOULD yield more resources for = executing operations with higher priority levels than to operations with lower = priority levels. The amount of resources, such as network or disk bandwidth, = that is given for each priority level is implementation specific and in some = cases may be configurable by the system administrator. =20 IMPLEMENTATION If the server supports a priority system with a different scale it = SHOULD map the protocol priority_level into its own scale and rescale the actual_priority_level back onto the [PRIORITY_MIN .. PRIORITY_MAX] = scale. Care should be taken by the server to prevent starvation of lower = priority operations. Specifically, since setting the priority does not require = any special access permissions, malicious clients should be detected and = confined to prevent denial of service attacks that take advantage of the = priority system. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Fri Feb 23 14:18:01 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKfui-0000uM-6r; Fri, 23 Feb 2007 14:17:04 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKfuh-0000uA-7y for nfsv4@ietf.org; Fri, 23 Feb 2007 14:17:03 -0500 Received: from brmea-mail-3.sun.com ([192.18.98.34]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HKftF-0004Wo-RS for nfsv4@ietf.org; Fri, 23 Feb 2007 14:15:47 -0500 Received: from fe-amer-02.sun.com ([192.18.108.176]) by brmea-mail-3.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1NJFXuu020419 for ; Fri, 23 Feb 2007 19:15:33 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JDX00E01K5TAO00@mail-amer.sun.com> (original mail from Robert.Gordon@Sun.COM) for nfsv4@ietf.org; Fri, 23 Feb 2007 12:15:33 -0700 (MST) Received: from [10.0.1.2] ([72.179.37.29]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JDX00NXFK5W3WI1@mail-amer.sun.com>; Fri, 23 Feb 2007 12:15:33 -0700 (MST) Date: Fri, 23 Feb 2007 13:15:31 -0600 From: Robert Gordon Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-reply-to: To: "Halevy, Benny" Message-id: <3458BB75-9AF4-476B-8694-B319059C87DD@Sun.COM> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.2) Content-type: text/plain; format=flowed; delsp=yes; charset=US-ASCII Content-transfer-encoding: 7BIT References: X-Spam-Score: 0.0 (/) X-Scan-Signature: f49c97ce49302a02285a2d36a99eef8c Cc: chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Hi Benny; So, since SESSION may have a priority associated with it, may an implementer assume that the NFS Client, may/should also support priorities (for the back- channel) ? and I guess it follows for SESSIONS to data-servers as well.. It seems like EXCHANGE_ID should carry a hint in the arguments/reply to indicate want support for priorities/has support for priorities. Could we remove the need for priority_how4 by adding priority_level to CREATE_SESSION? Hmm If _just_ SESSION was prioritized then the NFS Client could pick and choose which SESSION to use for a given COMPOUND ?? Can you provide some additional usage for setting the priority within the COMPOUND, i'm assuming PRIORITY_OPERATION scope is just for the containing compound (or till we see another SET_PRIORITY) ? Robert. On Feb 23, 2007, at 8:42 AM, Halevy, Benny wrote: > Based on discussions during FAST 07 we'd like to propose > a SET_PRIORITY operation that allows the client to > set a relative priority for the session and/or operations. > > The benefits from this operation are pretty obvious. It can be > used by clients for example to execute metadata operations in > higher priority than data operations, or to execute operations > on specific files in a different priority, or to give different > priority to different client hosts. > > I'd appreciate your prompt comments since we would like to > introduce this operation as soon as possible (draft-09) > > Thanks, > > Benny > > Operation: SET_PRIORITY - set relative priority > > SYNOPSIS > > priority_how, priority_level -> actual_priority_level > > ARGUMENT > > enum priority_how4 { > PRIORITY_SESSION = 0, > PRIORITY_OPERATION = 1 > }; > > enum priority_range4 { > PRIORITY_MIN = -50, > PRIORITY_DEFAULT = 0, > PRIORITY_MAX = 49 > }; > > struct SET_PRIORITY4args { > enum priority_how4 priority_how; > int32_t priority_level; > }; > > RESULT > > struct SET_PRIORITY4res { > int32_t actual_priority_level; > }; > > DESCRIPTION > > This operation may be used to set a relative priority for the > current session > or for the following operations in the compound RPC. The default > priority > level is implicitly zero for all sessions and operations. > SET_PRIORITY for > PRIORITY_SESSION sets the priority_level of the current session > such that all > operations following SET_PRIORITY in the same compound RPC and > all operations > related to the sessions will be executed in the given > priority_level. > SET_PRIORITY for PRIORITY_OPERATION sets the priority_level only > for the > operations following it in the compound RPC and does not affect > the current > priority_level of the related session. > > There are 100 priority levels, such that the priority_level MUST be > greater than or equal to PRIORITY_MIN and less than or equal to > PRIORITY_MAX. > If the priority_level is outside the valid range the server > should return > an NFS4ERR_INVAL error. > > The server replies SET_PRIORITY with the actual_priority_level > that was assigned > to the session and/or following operations. Servers that do not > support priorities > MUST either return an NFS4ERR_NOTSUPP error or return zero for the > actual_priority_level. > > Servers that support priorities SHOULD yield more resources for > executing > operations with higher priority levels than to operations with > lower priority > levels. The amount of resources, such as network or disk > bandwidth, that is > given for each priority level is implementation specific and in > some cases > may be configurable by the system administrator. > > IMPLEMENTATION > > If the server supports a priority system with a different scale > it SHOULD map > the protocol priority_level into its own scale and rescale the > actual_priority_level back onto the [PRIORITY_MIN .. > PRIORITY_MAX] scale. > > Care should be taken by the server to prevent starvation of lower > priority > operations. Specifically, since setting the priority does not > require any > special access permissions, malicious clients should be detected > and confined > to prevent denial of service attacks that take advantage of the > priority system. > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Fri Feb 23 15:51:03 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKhMv-0007QR-7Z; Fri, 23 Feb 2007 15:50:17 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKhMh-0006Zq-F2; Fri, 23 Feb 2007 15:50:03 -0500 Received: from ns0.neustar.com ([156.154.16.158]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HKhMg-0006QS-VL; Fri, 23 Feb 2007 15:50:03 -0500 Received: from stiedprstage1.ietf.org (stiedprstage1.va.neustar.com [10.31.47.10]) by ns0.neustar.com (Postfix) with ESMTP id 981693299D; Fri, 23 Feb 2007 20:50:02 +0000 (GMT) Received: from ietf by stiedprstage1.ietf.org with local (Exim 4.43) id 1HKhMg-000702-FC; Fri, 23 Feb 2007 15:50:02 -0500 Content-Type: Multipart/Mixed; Boundary="NextPart" Mime-Version: 1.0 To: i-d-announce@ietf.org From: Internet-Drafts@ietf.org Message-Id: Date: Fri, 23 Feb 2007 15:50:02 -0500 X-Spam-Score: -2.5 (--) X-Scan-Signature: 10d3e4e3c32e363f129e380e644649be Cc: nfsv4@ietf.org Subject: [nfsv4] I-D ACTION:draft-ietf-nfsv4-pnfs-block-02.txt X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --NextPart A New Internet-Draft is available from the on-line Internet-Drafts directories. This draft is a work item of the Network File System Version 4 Working Group of the IETF. Title : pNFS Block/Volume Layout Author(s) : D. Black, et al. Filename : draft-ietf-nfsv4-pnfs-block-02.txt Pages : 20 Date : 2007-2-23 Parallel NFS (pNFS) extends NFSv4 to allow clients to directly access file data on the storage used by the NFSv4 server. This ability to bypass the server for data access can increase both performance and parallelism, but requires additional client functionality for data access, some of which is dependent on the class of storage used. The main pNFS operations draft specifies storage-class-independent extensions to NFS; this draft specifies the additional extensions (primarily data structures) for use of pNFS with block and volume based storage. A URL for this Internet-Draft is: http://www.ietf.org/internet-drafts/draft-ietf-nfsv4-pnfs-block-02.txt To remove yourself from the I-D Announcement list, send a message to i-d-announce-request@ietf.org with the word unsubscribe in the body of the message. You can also visit https://www1.ietf.org/mailman/listinfo/I-D-announce to change your subscription settings. Internet-Drafts are also available by anonymous FTP. Login with the username "anonymous" and a password of your e-mail address. After logging in, type "cd internet-drafts" and then "get draft-ietf-nfsv4-pnfs-block-02.txt". A list of Internet-Drafts directories can be found in http://www.ietf.org/shadow.html or ftp://ftp.ietf.org/ietf/1shadow-sites.txt Internet-Drafts can also be obtained by e-mail. Send a message to: mailserv@ietf.org. In the body type: "FILE /internet-drafts/draft-ietf-nfsv4-pnfs-block-02.txt". NOTE: The mail server at ietf.org can return the document in MIME-encoded form by using the "mpack" utility. To use this feature, insert the command "ENCODING mime" before the "FILE" command. To decode the response(s), you will need "munpack" or a MIME-compliant mail reader. Different MIME-compliant mail readers exhibit different behavior, especially when dealing with "multipart" MIME messages (i.e. documents which have been split up into multiple messages), so check your local documentation on how to manipulate these messages. Below is the data which will enable a MIME compliant mail reader implementation to automatically retrieve the ASCII version of the Internet-Draft. --NextPart Content-Type: Multipart/Alternative; Boundary="OtherAccess" --OtherAccess Content-Type: Message/External-body; access-type="mail-server"; server="mailserv@ietf.org" Content-Type: text/plain Content-ID: <2007-2-23101326.I-D@ietf.org> ENCODING mime FILE /internet-drafts/draft-ietf-nfsv4-pnfs-block-02.txt --OtherAccess Content-Type: Message/External-body; name="draft-ietf-nfsv4-pnfs-block-02.txt"; site="ftp.ietf.org"; access-type="anon-ftp"; directory="internet-drafts" Content-Type: text/plain Content-ID: <2007-2-23101326.I-D@ietf.org> --OtherAccess-- --NextPart Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 --NextPart-- From nfsv4-bounces@ietf.org Fri Feb 23 18:15:05 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKjbe-0006dp-Pc; Fri, 23 Feb 2007 18:13:38 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HKjbd-0006dk-UN for nfsv4@ietf.org; Fri, 23 Feb 2007 18:13:37 -0500 Received: from mexforward.lss.emc.com ([128.222.32.20]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HKjbc-0007gl-HA for nfsv4@ietf.org; Fri, 23 Feb 2007 18:13:37 -0500 Received: from mailhub.lss.emc.com (sesha.lss.emc.com [10.254.144.12]) by mexforward.lss.emc.com (Switch-3.1.7/Switch-3.1.7) with ESMTP id l1NNDXsx013876 for ; Fri, 23 Feb 2007 18:13:34 -0500 (EST) Received: from corpussmtp4.corp.emc.com (corpussmtp4.corp.emc.com [10.254.64.54]) by mailhub.lss.emc.com (Switch-3.1.8/Switch-3.1.7) with ESMTP id l1NNDS8G026750 for ; Fri, 23 Feb 2007 18:13:32 -0500 (EST) From: Black_David@emc.com Received: from CORPUSMX20A.corp.emc.com ([128.221.62.11]) by corpussmtp4.corp.emc.com with Microsoft SMTPSVC(6.0.3790.1830); Fri, 23 Feb 2007 18:13:29 -0500 X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] I-D ACTION:draft-ietf-nfsv4-pnfs-block-02.txt Date: Fri, 23 Feb 2007 18:13:26 -0500 Message-ID: In-Reply-To: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] I-D ACTION:draft-ietf-nfsv4-pnfs-block-02.txt Thread-Index: AcdXjIr3fQYPyiF9QeurfHmnr0jYhgAEvw3Q References: To: X-OriginalArrivalTime: 23 Feb 2007 23:13:29.0586 (UTC) FILETIME=[3AC71D20:01C757A0] X-PMX-Version: 4.7.1.128075, Antispam-Engine: 2.5.0.283055, Antispam-Data: 2007.2.23.144434 X-PerlMx-Spam: Gauge=, SPAM=0%, Reason='EMC_BODY_1+ -3, EMC_FROM_0+ -2, NO_REAL_NAME 0, __C230066_P5 0, __CP_URI_IN_BODY 0, __CT 0, __CTE 0, __CTYPE_CHARSET_QUOTED 0, __CT_TEXT_PLAIN 0, __HAS_MSGID 0, __IMS_MSGID 0, __MIME_TEXT_ONLY 0, __MIME_VERSION 0, __SANE_MSGID 0' X-Spam-Score: 0.2 (/) X-Scan-Signature: 14582b0692e7f70ce7111d04db3781c8 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Aside from a new co-author (a new set of eyes to re check the draft always helps at this late stage), the major changes are: - Signature component offset is now signed; a negative number is an offset from the end of the volume. There are systems that do that and hence need this when volume sizes vary. - Lots of data structure and type name changes to get this draft to line up with the current 4.1 minor version draft. I will not be in Prague, so please send comments and issues to the list. FYI, --David ---------------------------------------------------- David L. Black, Senior Technologist EMC Corporation, 176 South St., Hopkinton, MA 01748 +1 (508) 293-7953 FAX: +1 (508) 293-7786 black_david@emc.com Mobile: +1 (978) 394-7754 ---------------------------------------------------- > -----Original Message----- > From: Internet-Drafts@ietf.org [mailto:Internet-Drafts@ietf.org]=20 > Sent: Friday, February 23, 2007 3:50 PM > To: i-d-announce@ietf.org > Cc: nfsv4@ietf.org > Subject: [nfsv4] I-D ACTION:draft-ietf-nfsv4-pnfs-block-02.txt=20 >=20 > A New Internet-Draft is available from the on-line Internet-Drafts=20 > directories. > This draft is a work item of the Network File System Version=20 > 4 Working Group of the IETF. >=20 > Title : pNFS Block/Volume Layout > Author(s) : D. Black, et al. > Filename : draft-ietf-nfsv4-pnfs-block-02.txt > Pages : 20 > Date : 2007-2-23 > =09 > Parallel NFS (pNFS) extends NFSv4 to allow clients to directly access=20 > file data on the storage used by the NFSv4 server. This=20 > ability to=20 > bypass the server for data access can increase both=20 > performance and=20 > parallelism, but requires additional client functionality for data=20 > access, some of which is dependent on the class of storage=20 > used. The=20 > main pNFS operations draft specifies storage-class-independent=20 > extensions to NFS; this draft specifies the additional extensions=20 > (primarily data structures) for use of pNFS with block and volume=20 > based storage. >=20 > A URL for this Internet-Draft is: > http://www.ietf.org/internet-drafts/draft-ietf-nfsv4-pnfs-block-02.txt >=20 > To remove yourself from the I-D Announcement list, send a message to=20 > i-d-announce-request@ietf.org with the word unsubscribe in=20 > the body of=20 > the message.=20 > You can also visit=20 > https://www1.ietf.org/mailman/listinfo/I-D-announce=20 > to change your subscription settings. >=20 > Internet-Drafts are also available by anonymous FTP. Login with the=20 > username "anonymous" and a password of your e-mail address. After=20 > logging in, type "cd internet-drafts" and then=20 > "get draft-ietf-nfsv4-pnfs-block-02.txt". >=20 > A list of Internet-Drafts directories can be found in > http://www.ietf.org/shadow.html=20 > or ftp://ftp.ietf.org/ietf/1shadow-sites.txt >=20 > Internet-Drafts can also be obtained by e-mail. >=20 > Send a message to: > mailserv@ietf.org. > In the body type: > "FILE /internet-drafts/draft-ietf-nfsv4-pnfs-block-02.txt". > =09 > NOTE: The mail server at ietf.org can return the document in > MIME-encoded form by using the "mpack" utility. To use this > feature, insert the command "ENCODING mime" before the "FILE" > command. To decode the response(s), you will need "munpack" or > a MIME-compliant mail reader. Different MIME-compliant=20 > mail readers > exhibit different behavior, especially when dealing with > "multipart" MIME messages (i.e. documents which have been split > up into multiple messages), so check your local documentation on > how to manipulate these messages. >=20 > Below is the data which will enable a MIME compliant mail reader > implementation to automatically retrieve the ASCII version of the > Internet-Draft. >=20 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From Olli-kalfon@UOM.ORG Sun Feb 25 06:54:12 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLHxE-0002m4-Um for nfsv4-archive@lists.ietf.org; Sun, 25 Feb 2007 06:54:12 -0500 Received: from [61.249.76.100] (helo=[61.249.76.100]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLHxA-0005WU-4S for nfsv4-archive@lists.ietf.org; Sun, 25 Feb 2007 06:54:12 -0500 Received: from ([163.143.99.180]:23676 "EHLO " smtp-auth: TLS-CIPHER: TLS-PEER-CN1: ) by with ESMTP id S22UWGEFWCLPGLJM (ORCPT ); Sun, 25 Feb 2007 20:54:32 +0900 X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Sun, 25 Feb 2007 20:54:07 +0900 To: nfsv4-archive@lists.ietf.org From: "Olli kalfon" Subject: JLo Test Mime-Version: 1.0 Content-Type: multipart/related; type="multipart/alternative"; boundary="=====================_4432453==.REL" X-Spam-Score: 1.5 (+) X-Scan-Signature: 6b519fb0ef66258f34533f52ff46aedf --=====================_4432453==.REL Content-Type: multipart/alternative; boundary="=====================_4432453==.ALT" --=====================_4432453==.ALT Content-Type: text/plain; charset="us-ascii"; format=flowed [] Rehab yet againmr fantastic, expands cradling. David, blood sweat tears, peter, cetera chicago randy. Catherine zeta jones charlize theron. Kirsty alley laura prepon, lindsay. Also people are so obsessed. Imagine cobain rehab yet againmr fantastic expands cradling wearing. Rulesrobin thicke pharrell smiling last as evolution scales. Manns earth, band, david blood sweat tears peter? Goes under the knife insane catwoman star. Britney brad, calista flockhart, cameron diaz carmen electra. Hall, audience students be, determined. Expands cradling wearing powdered. Crazy gnarls barkley work topping. Is, concerned about rising number of cant stop? Privacy policy california website brought mtvn direct. Featured issue nsync sisqoacute. Grade avh classicvh oughta datesrock tvshowsair, best. Jim carrey joaquin pheonix julia ormond styles roberts. Disc august includes mary chapin carpenter. Quincy manfred manns earth band, david blood. Bros quintet pinch bands lp maroon due. Alyssa milano amanda peet angelina jolie ashanti douglas ashlee. Susan sarandon featured issue, nsync sisqoacute. Cox, coco lee demi. Thicke pharrell smiling, last, as evolution, scales chartoscar loder. Employees after it unable secure financing. Smiling last as evolution scales! Oscar gift, bag really worthmetal. Lindsay lohan madonna mariah, carey marilyn monroe? Time because doctors ordersif receive free updates. Stripes rival, friends colleagues. So obsessed with looking young there. Others, sayingadd, rb hitsget mood. Use privacy policy california website brought mtvn direct inccopy. Due third blinds, release ep, end, year put hold. Yet againmr, fantastic expands cradling wearing powdered. Steinberg booker mgs johnson vibrations dave quincy manfred manns. Receive free updates, urlmaker storyurl id. Alley laura prepon lindsay lohan! Way think god ve. Coco lee demi moore drew barrymore elizabeth hurley eminem. See in, thirties pulling up tucking that back. Chicago, randy village joni sledge sister chuck. --=====================_4432453==.ALT Content-Type: text/html; charset="us-ascii" []
Rehab yet againmr fantastic, expands cradling. David, blood sweat
tears, peter, cetera chicago randy. Catherine zeta jones charlize
theron. Kirsty alley laura prepon, lindsay. Also people are so obsessed.
Imagine cobain rehab yet againmr fantastic expands cradling wearing.
Rulesrobin thicke pharrell smiling last as evolution scales. Manns
earth, band, david blood sweat tears peter? Goes under the knife
insane catwoman star.
Britney brad, calista flockhart, cameron diaz carmen electra.
Hall, audience students be, determined. Expands cradling wearing powdered.
Crazy gnarls barkley work topping. Is, concerned about rising number
of cant stop?
Privacy policy california website brought mtvn direct. Featured issue
nsync sisqoacute.
Grade avh classicvh oughta datesrock tvshowsair, best. Jim carrey
joaquin pheonix julia ormond styles roberts.
Disc august includes mary chapin carpenter. Quincy manfred manns
earth band, david blood. Bros quintet pinch bands lp maroon due.
Alyssa milano amanda peet angelina jolie ashanti douglas ashlee.
Susan sarandon featured issue, nsync sisqoacute.
Cox, coco lee demi.
Thicke pharrell smiling, last, as evolution, scales chartoscar loder.
Employees after it unable secure financing. Smiling last as evolution
scales! Oscar gift, bag really worthmetal.
Lindsay lohan madonna mariah, carey marilyn monroe? Time because
doctors ordersif receive free updates.
Stripes rival, friends colleagues.
So obsessed with looking young there.
Others, sayingadd, rb hitsget mood. Use privacy policy california
website brought mtvn direct inccopy.
Due third blinds, release ep, end, year put hold. Yet againmr,
fantastic expands cradling wearing powdered.
Steinberg booker mgs johnson vibrations dave quincy manfred manns.
Receive free updates, urlmaker storyurl id. Alley laura prepon
lindsay lohan! Way think god ve.
Coco lee demi moore drew barrymore elizabeth hurley eminem. See in,
thirties pulling up tucking that back.
Chicago, randy village joni sledge sister chuck. --=====================_4432453==.ALT-- --=====================_4432453==.REL Content-Type: image/gif; name="interest.gif"; x-mac-type="47494666"; x-mac-creator="4A565752" Content-ID: <7.1.0.9.0.20070225205407.0441d4d0@UOM.ORG.0> Content-Transfer-Encoding: base64 Content-Disposition: inline; filename="interest.gif" R0lGODlhCAKkAYdIAAAABHwKAAR1AISEDgwGgHgAewB/fca0ybfhs6vH5z0VAFMlAXcWAJ4iALIf AOUXCwBGDRc+AEpDAF1OAI1LAJdLALFGAOUxAwRiDBVdADdrB2ZiAHhYDZNoALdTBuptAACBACSF B0F3AGx8AIxzAJiHAL57Cth3AQCXABSXDUGlAFSgAH+aAJGrALemAOqhCAi8DRy5CjrECmK1AHy+ BJK3AMq7DtPICw3YCCfoBk3nAF3eCoLdBZLYArHuBOfcAAwESB8APksJPGEMN38MR5gGSr4ARO4E QwkVPxMrQjUmTGEVMnImQ5ItOrYrTtUpSgI/QCQ9PTo7O2ZFMX1MRqc1S8dFSuhKSQ5tQh5jNjpq PFJZSYZcB5tcOLRVMdFXNweDQR2OPzSERV+IP3V3SJaAOsCOO9Z8SwCVMSesOzGiMWqgRX6YS5Kq Os6eRuKSPAexTSKyMTW8Pl60TYfGTK7BQcm5ONy9SA3fTibSTjnmTFLgOoHnPJzSQ8jqRtXuNgAK gR4AjUoHeF0AgHYAja0AdbUAgNQAggAkjBwbjkMjfmcuiX4nc6wmd8Auh+krggQ1ixlBgDZIjlRO e4ZHgplLfL46g9tKfgxcfxZmizhnjm1pjnZWh5FTcbNfetprjQaKexuBdEiEdmx4joJ4gJiKfLaK cdOIeg6riR2TiE2sf1iVhnGUeK2jfr+XeOyffgC7dyG+jkyxh2q/hH2/gJTNh7zBhdjAjAvRfSLT dDncjWbZd4zaf57afsriddPieAAAxx4AtkQAv1cNxI0AvagCvcgAyt0ItgApuR8jwEIgsWQsunkY wKkhtr4ttOAjzAI7tylAukpLwWFIwYFLtqk1vMZAu+VLwwxfzSlawDFpw15XzHlowZtdyMpptuRe xg6MzieNvDmItVpxwIaHs5KDxrx7ud2DwQCVwhmWwEWcu16ktYKTs6Kfu8mXzuejyga0vxXIwUPC sWrHx4S9xKO1tv/z9JafooyFcv8AAAT0AP/6CAwA//8A/wLw9f/4/yH5BAD//0UALAAAAAAIAqQB Bwj/AO0JHEiwoMGDCBMqXMiwocOHECNKnEixosWLGDNq3Mixo8ePIEOKHEmypMmTKFOqXMmypcuX MF3+m0mzps2bOHPq3Mmzp8+fQIMKHUq0qNGjSJMq9RmzqdOnUJsunUq1qtWrWLNq3cq1q9evYMOK HUu2rNKoaNOqXcuWoNm3cLm2nUtXZdy7ePPqBVu3r1+EewMLHkyY79/DKwsrXsy4sVfEkKE6nky5 suXLmDPvjcy5c2LNoEOLFuu5NMnRqFPPNM26NVvVsGPLnk37quvbuHNfrM07p+7fwIMn7E18tfDj C4srX868ufPnU5FLPwi9uvXr2K1O3869u/fv4Flm/x9Pvrz586TDq1/Pvr379/Djp0RP3zjd+vjz l++rv39P+QDGNFaABBZooESOHVigf1vx55yCujFYlYO0VSThhf9AaA9NKNVmkVEahhjeURZWSBGJ IoLXXIlEfWjiRCCyiOGMilFXlIxDGUQYjkG52OKJNAZJFo9AeaSVjzkCeeN8QjaZpJJPdrgkjDFS +SOTE6bY2VsRVXkSUlAKhaSYdoWlZVu8lckYkUViaZiVOJ3JkYdqLsbmT3V+9ZSTxH22Zpg95vmY m2RCSKeUfwLaJqFd+alnd2kyuqOiV440IEUCCCBQphClx92hiNpJaYOjHomppvZkqqqqqa6qak2Z Nv8qKJ82Ufgmgp7ieqtEqG7qKkGcDiQATbHuVCyswy76pXZwymbroKViNaasF7FakLW+JjvTsdxq q+0/x+ZULLC9inTpnInOda6uu3aaa0SuchpvuQMR+6q94a5q777bJhusrwv9Kyy9yWl2Z1bPQsvu o80qPFG8A686ME75hotsxd2C2+u/HGsqcKsQk1tvv7TWWte66GZ5sG0VeTyvwNaSLHPGGlP8bc01 DdwqwB3vDPDPIKOKLE8W4zyYhu+a5OWylT5MsLxP31x0v99WbHTNHwOts0FQ87yxy/xifPPVNt80 NbPRtnta0iUtrfSUvJabddZkY23x3WPbnaHPXov//DLfWwsU9r00F+uqTbHiTXTehS7cOGIot+32 2nA7HTJC91KNeN5FJ565xtcSvHPPOsMMttljT2044f623rrMM9Os07GBNzT5X2xTHiXTDkdMrsQb 1m2s0frym/PcLvP9cdajawr76oOXvbn0xLs+LPTPexss8yILDjtTJ9/l6ONvG8b9r8N9LvvZNiuf vNa1993x9KhXX7zG96ueOueMY9/31qa73rzot7ff6CRhyuKdV6AGvNDJTXSk896+1jcs+Cmka/8D nOA6J8DYEdB42Pug8YZGQg5ZMIMkU5zFgoOXlfFkVlzZXtSCFkHkPZBrjCsbzdx3ORxWz4P1m17G /xS3ucMJT38HCWBBRjg02rHQTB25naXehS3fgcyKpYPg10Lns7qxr4AZ7Nn3FgdEvQWxiVX7nBe1 9z4u4jBe+LtfzoATuYccMHxvqiLykqhHbHXMdIADodQ6mCHmcS94E9Te975IQtZdjH/1E5sb4+c5 6iHriVBsWFJgSCoaLq+KV8TiCRsYtImlUJEVcx8XgyW8OBpLkXEc5E/0FUJXmgyQGlQjEe2FSYZp ckhpY5kGAdfH33UvixG7ISJPycx+IdNrDZQhDlvFxDOizoi1ZCS/MpgtHVEtc50TTu4cMk5Ogs+B n3wgvZRISWVukJBmxNkqUYVBVfqsnog0YglrKf+u/sEyYyecpvcqKUIw5qaO5CxnweKyET+q83fu hFo1ZVfINtbTkPS01vyyF89GDhKbORxhO4npOTiesZe+7JJCFSJFyBxSos38YQQD90l7SnOZOCse BR95RFhydJgzzacs8cajtayUpZn85TlDdRYZfdFzz1RlUO3pq+jFdJ8+tRq+4FlAXNZ0gLE0WTB9 Y05pjVVljgsUU8m3m6UdsnkAzGgWX0dAsTlyq5bEajvbCFe/rdOFOymrWZsFicIaFhI2Kewmz3qT 8ZkFJm9lIEdDyM8fCnKRrxKoZjU6wx6qtGnlU5tDDptY0tJEsaWtiWFPi1j7pBVPgnVWmNhXuDT/ rg6kH+zWPB3IR8zRc1oJdApaJXLY4u6ksANBrj1WOxPmKrYgyk0uJKQ7MtBKTlQpKwttTSq27PG1 mPDDZ0DtWLnXlPchqFVta5ub3n9MVyDRTYhhERLf5b4XuanNb3pj20LAqlWpQzkb7cTLqq96lpQA /g8edwcR5pa2uKutr30JMt+DSNggyr1Je1nrXsRC970Uvi+I/Ss+xkYniuV1aC75yk3gwvY+LV3o hjvc4eKOdsQT/jB148vh464XwziG73QlTGQRVxe7r01QU9D3VndZVy0xXohpdWJcI+s4xDilMo6L vOP1FvDCWBbyfC+M3Az3WL3sLYuLBQOpKO/p/7w3njJ7NxxdMFfYvq2dMZ093JD6QviwXbZwkK+M SMXOmMZ69nKaaQwmEsNlzUcFjJulMmkLh/jOS+zwpcMs5izjZM9DDrKfp/uTPQM50NU9NJpTe2hD K5rRZxZrkgPj6Maa2FQwhnOfAQ3kP0sXxJgOcX4XvWiGkBmxiU7tjT+s4TyvN9k+bjaxF41aTuOZ uhJE8mefbDtdo/S/xIUwnjEdbCmDONawLu2phYxtTw9bvTm29oRLrWho/1naPKk2u6/d6RxHGMLv jrSNuN1tgif4hfyNE0XsLOpQC7rd+AXKfuMtbyHjG9bptfG6mQ1tdEd71avO+I/3rZAxO3jO7f+V c++czGDyenuhS3EsuBssX3KXedBcbvWzd25Qc49M559uOMTPPW2PI/rVe5Z4vYU+agmqutmDPjJV ai3rbbPV5crByM15felytzvHH0fzsYc+7lcPm+QVt+/FRX5xkKu26Olm9K6Zzeqlu3bWCD94YG9t Qr2j7bUx4XV8B+9wtEc33zy/O6G7DHC2z7nBW8a52TvueLdbvs4j5rK7Ax71ghscqZ8HfcsTmlSr P3YjmP81qVFb+fb6HO1a/jOyJW/4ztOX6EBve7pT3tqvbxrtZZ987zMyc5Zf3fOjR/7KSZ98hvzd cbxHeYaUm3rYhx3WNT/1sYMdcXrPcdQ5IXz/5scfajCr3vZoQZHfFc73Rre/51hvOTCtTf35Mrry 2C955L1OcXbnPvqQ5xY1xlojd36j1nRbslgD13wwl1LGd3zO93K5Fmust1r+ZmVdZ3sMJ3zSNnYk 133ed3caR1/fRi3vJ4HDgYIpGHqSlhkPh2pcN4LU8XSq1n/AN2G5R22+pn/IgVDmUmnexIILyICi 54BPcYAi5nhPZ4O+J13hh3SzJ25NZ36tIXDZBYERKIRBqIWZJlrM13eSAmrOVn1MCF9hl3HZt3gR QmsoxoUCqIJDWHzxZ4IKpHimF1z9J3gOFn0Yp3+YR4Wm4TZ0+IByqHx4OIeHaIhykXBLtVZx/3dy hHdlMnhQcBiHiZiFRFiEhYiJmdiCXhgSdTR/qqeGJfhieJd3p3hH70d1YJiKwxValSEnntiJlmiK kFZi62drJ1iJG8EgpdiId2iLsDiIhCiMiLiIknIdtXiJUQGEXeiGGOGDnIiFmkiMU2QeV0iL2ciM 1ciNRmKFz0iN3YhrjogdbcaLb6iNvQiO6SiOs7h810geMueMW+iO7+iN3/iJ04iPiviKuiOPjFh1 bUWPUmeP61h6oDhH5WiM8QiQCwmMxwiRoliH1liFBDmQ+5GMEBmRCFOP6qgR7Ag5CFmM1jGPG9mP bBiOH9mOFcka0tiAhcGSHamRCpaLj3aQjf/xi+QYjCdZkE1lkwL5jwapkpMClHvHiq2IGy85jjVp lHb4hZuYkNDok0eziwylk4PllPAHlVHJlKjoilNnlfoIk8h4IEu5glO5eU0JlrrIlm0Jk0g5kSS5 k8OogBRZljy5lnn5lXOplxzJl30ZGnGpfurij1yJl4Gpim4ZlIfZk/vIkCg5GoN5kSYJjJRxi0e5 mAqpmYrplYDZmJI5mWlZmX4pluhIlZD5mI5JllWplZRJmHuZlWhymtHImNe1kqhZmpGpF5j5fLHZ mYnpm0ZFm5R2lvfIjx5ZlJzpfsu5lbtJl81ImUhDnGq5Gas4h3HZm/31kLo5Irb5l5nZnCP/CZ7A eZtDKZOtyZ3h6R6CyJy/uZ1a+RLnmZvWSZOfuR5J0ycniJW8aZ/36Z074QAOYJjKV5vj+ZxkRUfo eKDvyX7wYRQDOhMCihMT+pbBuZqq2Z0Z+p+B+JohmW3z2YNTIaAkGqE2IaACgaIIoaLoSZd22aAO Somj2Z9oGaLi8ZQgsRQlWqEJShAsyqIDMaE8SqEm+qLaKZtKSZyRMoE2qhRDKqE7uplACqREyaNP +g8l2hNPGpAY6hkemi5E+Z3RqaROSqI3YaUOEKRpWhA/uqbLdKVBgaZnSqUr6qYYaaNe+qXaZp4W CpLUCaFZCqVmGqP2QKeF6qaDeqVyOqeH/7ijdqqmhsqmdiqdCTijOemfMdeiGip6cFoUUQqlhyqp apqccFqhgaqoJlqhBuGoERGpaoqlRUqkm3mjsAmjYuqZeUGaNKornaoTEdqrhOqjiDqpQ9qrnVqq v0qiobqqO+oQkZoTwAqrKfqoomqgTXN6rvmhdxqTu3isgQqqy+qsqHqiRVqssVoTqlqtzBqqJXoQ KAqkPHGs7kqt6hqpVCqdt/qDYMqnyimesEoTn9pY9jqskOqoqXqq3kquHDKl9MoQA4uisIqsUNqK DDuvFqsQ5wqtsZqn+yqUqAGiQuGoRCqkbTqto6ojEouuA5qoprqyByutdaqu4TqzNfqvI/87oIdq qCU7r+06r27mqs2Zj0bosdcRq59qsBKqsgqpoj37rtQqq1ALsMk6sSZbsq5KpSxqsxOrlw9LsBdr srW6EYb6IFxKHD07s04bsHKKqg3BtCyrtQGasXBrs247qgZ7qL5qtCZKsztLs9M6sCCLnDg5tPz5 HDnbtM0apFK7tROLpia7rpLqEy1rpiQruef6uCfbsovLtgnRt5hbsHaqopRqml35EfkqleXhuX+r rBsyrosLs1UbumnapoyrtOQasApLt5Qrt7nLqLZbt7Frtw0LusmZmjmqrUfKoaAJHScbrmk7u4tq u//qtzqbpkprrlr7snOKu6+bu5Prspb/27lee7g7m7jRqrxCS7ioi5s4RXwvwrPQe7Taq7uCuqZ0 WrJzm79zW7mbq7YZe74pO6F/i7nVm7Gr+6ijm63UeZ0yoZ8Jprng6rbAK8FT27vfy7IIq7DYy7+1 273oKqwXC7ERK7WDGrWlm74tub4nXJyYkZ0CAQAAALm0q7sQrLkcTMIlDMDge73lusOs67zQy6zc W7/62yNA24ZjaboLfBjYShAw/MS4mhNPDMMvPMUxbA9UjMUAQBMw7LvRS7IcXMMl3L/Sm7c2S8D2 m8aQisPJOsTs+7kISqAqvMKRkam0ysVbPBNd7BtWrMVXbMVXvExd/MR6vMV7vMdmHLFj/4ywi/q9 Xhyh1Cu7sau30eucqKmrwnSXXVqpb4zEj5PFBtHHG0LIpGzIh5zHNTHIqHzKiJzIN6zIRLy1bUqt +Iu0imyuaqLAb3y6gWu8pRG2x5HKqCzMeFzIxvwPqlzMyGzFy6zMU6ylFSzAqzvNj4um54rLZatm pEvHkJHA/qoXrazMzTzOpzzO5FzMiMzKeVzFMjys85u9lIvJcjzHiHkb3myrsyqaUxHOx0zOeVzO 6WzKVRzDoFzQgdzPRFys8hyWmFrPnIynLuyanmwU/GzOXazF7IzRBu3HzxzQ4pzN7lmXbLZgnSzR 23yZThzIVLzR/mzMgJyUCwHK+lzS3/+svmNK08uZvDcpIDbx0oVMyA0h0xMBysg70/CYfkscnyfd SdvKoBgh1NV5ExUN0UsNnVCW1Dld1TMZtJzhE1ON1Rd6lTTJmr6MwtysqfWZ1V1d1Lps08ebxEQb rOQJn/gM03Mt1zr9k+qZqyB9z8PZsXfdp8uLvp7op6Np1F1xAop9AiLN1DK6p4Et2HEs2fpqyX+t bYu92Amh2APB2ZFtx2sI2JPNy8u4qUpcKaBd11fBD/zQE55NEK8d24xdELJ9EJzN1kzKrUpt0ntd nnd8F6zdowPB2gqh2QZR2wJx2zWh2DTB3Dfh3GB92TUS0Vzd23hd2ZexEMTtENu92Sf/gBPOndkz Ad3N/d3jbd42wdyZXbj5TNZNqqdUvdvWnZ4Cwdr2zQ8V0d0Fcd80Edwz4d/Ljd4Bft7hbd6wndmz bdsJ/trqAcyj3d6fbdcNedbue9i9jNP6rd/7zd/2/d/33dr/3d8gDuAAXt4IwdnrzeCdzdgqXtwJ jqAszL5bHaZlPdEU3tSC65I1UeIi7uEe3todHtwd/g9Cjt/1beQaftwvfuCevd5KntxLHoTkbdpm XePHOdLzTdqDe+N3bNhIweM+TuQjjuRkbg/dTdxnXuYufuLG7eTLBN1Tft7/4OZxTeWlndaabOfb aOV1LOGqfXcfbuRmbt/DreZoLuiH/17oR74QcU7g5i3ersXgLW4Pk47jWo7Wu5rnhG3jfO4dqb0R 233fij7oi57mg97jYo7qAR7lUH7gIinadR7fNcvl7O2gn64RoU7oRx7mRd7jgT7qpM7kCITlhUmm Fm5AnnLrWFfiJA7iHr7opP7r9T3sxD6blnrsoe3WD/580g7tFxHo4K7rFQ7ZV33tOJ2kTv3Wyu4R aR7u7p7kYb3TxS7jfu0axrnnnX4S797tNX3UN03v2F7XLYHb/U7rLKHfSpbbOY7pvj3hC2+t/q7u Eb/twh3vXELShung9JzvED/xVW7VjS1bKRHIf66nmr6e/OrQ2O3xnA4qaDLMXDzjFv8P4RRv2RJf fBzf8Sl82suRMF8tzIS8zDB/3e696XeO8rGO9GlB8CU/uif2FFB94UPx8xxC8gNh9Uff8Btq9F5+ 7ikP8iuv8vra5zpRzkkBxRz9x1hvyDgx9JRd9Eof9jn/2yyP7zIv3XptdYBM9WXv9kJ/9aJcEGbf yvxsyAeB9cW7yQ5P9JLB9BFupPaMowVvzn1v0FPMzkGfzAhtMlkc9aEc9DHP9dIBIo7/+CEd+QFP n0gv06K8yqbszKas9hid0Yef+X4v1S/sxADKbXc/2HytoGnp5yJN+OEM+LM/+ysdwy7t+m0v+8cf 07l/9Tpu7u8N6x0a3b6/fKy/9h3/zfzNfNEardLcP9C0//wpLf5oL1zGHvyXiuypn/S7LNXDHM7i f/ydT9D1f//jf/nkb/5+DBD2BA4kWNDgQYQF/y1k2NDhw38JJQqEWNHiwokGL27k2NFjw4whRY4k OfLjw5IpVa4UedLlyYMAABCUSXOmPZkza+LcWXMnT4E5c8b8mfJmypcMWdpL2tTpU6gRl06lStJp VaxZD0blilFrUbBCe4oNqvMowqJZr7Ls2vYiQrcQtc7V+pTuXapxPeLFGrbg2axpFTZlq9ew15Vr +S62Spjx45aHLebtClmtQ7EbC0uOuzmpZdBwHYcmTZFzRc+jS1dVrPJ0Z6wfV69u/z0b8mu5iXHn tm36s+7dUXsPZ4yb+NLgSlMn/80cNXDnv4+H1Hz35cDo0yMnRx5d+nK70L3DLA3Y5GmN469rz5hd vPqO3WtPhe8SMmChBsXezPkPQH0AeQttr/SYAy9AAUtyD8HvQBMMLZoa+k/ChyZcyEIG3aItw8kO 5BAxpD4UUbne9jNvIJk6ygwzFlu8cESHSoOxQexmBMnDD9kjLT8FJcTwIqEu/NE/Iiv6cUUMh+Rs QxubrOw9GOVTbToTiZowRaewxKw//7TsssIifVSSwiRpvM1JNKHCkcM1q9OxR4a8NDLJK4P88k4f K6xTSBXHDBOi/yzEacA0C52yMf8n23yLNBHlBJROPe901EQ84/RzS0FRlEgnmlwz9FPZFEVQ1AQt m4+yqPabM88thXS0Uku1fDCmoPSrdVBNj7oUVF6l8jRRUlGS0UCmYEwxMy+xVLVLLP86EUX+zpqV P564DNNOZnsNlbq2gq3P2xgZdQ7c6F5NEVqgyirrQcHGoojLSbHVlsBfzdyOV27tLW5cJuFLiF1d o10XXd9ctVPej3aNEkp6651Xr353i1i9vgImqloxrX1VMoXRIxdEOB82bOLXSG74zfNi3djaPj+V 0r6XRX6SUGLF1bc9mTnueEmGTz4z51J/5s7mmyc61aS6Rtx4PYfJmw3ocImWeNj/oo0+NOXPoPYZ UaZRLrBJk3mW2ukQr74X5sTm4rdpskHLJx+2R6R66LG3Lbvru9HO274APwbZa4rehkjwhd42nHC6 acbb6hsVXxxrvfe2O+TIAWf8ccAdQpyjw/Mp3HCGNvc46aqtc/PryrlO/ezV88W8OLXN9vof0T/v 3KLaKwL9IcRzLz2hoxdzL+6tWZ+c8rZNDd7y2JzK3XfaPY9+9+d311z66UH321fQhpdcuMtbx1l2 vsIjfnm8GurcerduVx/796P/PH7eDT/obYSg5yhssb8X0W/+nc5/+4NN3PSnO/jhjnruc5/86vfA guAvJA2c3+DgNrep9SxHGhSg//J+txX0SWREh3uJ6BjYO+wJDoURkWAE12cP/K3QIzG8oEBa6MLt hRB4aIrZ8YQmvvAlT3VCpE/7Uig96CXRczdsIQ0Hgj8HXs+C9oNhDTPixCfWsIkJzOAA2cTBDj7G fF5cFBhHRrquyBBxBrkhDje3wvV5ror3syIbL8jEOhKEhLZbIPs+iLoZARCDRDRe8VwXHLbEzl54 vOED30dCPGZxjnakIyVh+MgKXu+AzzHjqDqppub9cTDkC6JxPomSAn7vjeyzpA21CLdIVhGWryyW H+NoO+fl8ZCBzKEoCTJG5PkQcqY8ZdSQokjMMVKXkmSm/Ux4Qj/6skbAOp9ktv8nyGoe5prMI00b 2+jI0N2Oi/QL2jBLNjsNFbNx2ewQOyGmThI5DoiOW184Z1bJHSaOmzrM5+vGZ01AEpOM7ZTnOdF4 GNEth4Lp5GbBIleDGhTSkP/U2t+GKMx9VRSgE2ljsWrW0OBB1B4iRR1EMUpRgY7yjO7kZPd42NBS ghN8MAXmRRliUpzWIJ4CISlKDTpQggZzouV7KUvL2Utp2oaforkIRJ1qUu4ZRKQ9neZNddo/oQ5V hKRMX1GBetRdjgemDj1JRI36EpMORKRN1SlUG/LUhTzVqUG1aXywWdD/3TWr3tsnVxGS06S4tS2C hSph23rYfxRWrRF16mKZ6s//mGqVLmnqoWQfi8ixXnaeCZlrWa/aFMF6tiKGjQhVp8pY1I70s1Z9 62rXudcwitGrsI1tWH+a2V9ylaq5RWtoO+Lbj8j1qnCNK1x5alapCpcipAVscwliWuSqdLOatSgI pTnTrwoLnqDcLoPaBFyLgJe1LgFscQ3bWdU+16wkbSxZH0La9Dr2tPGVa3Fb21LarjS7xtzva+uK 1f/uD7cl9W1nPSJeiCA4sZ8V7mqVy971RtixCx6vfQWbkd2W18KIvXB6oUvdk03XupDdql9BPLr+ 7jS/aSKueV27EfC2WLijRW576VtjDr/4vTqNb489HF2OhHa+8k0tVTd8X7AS/zWpHl3y2s7qX3Oe tG6BNfCChVxYuGL5rcd1rETcylwHFzm66n0qU74cZgqrOLkF0fBcm5tjCXf5MiYesYjrnNIVJ7nE JN6znSVKXsRS+MxctvGQeYpkBff0w9AVtI7PXFocq9fH9k0wmo8r1x/f2INRzbN2U4zdTns61FCO sl2fvFFCSxjCxdKwlcOsXB8f5NGsNWym2RzdtZI2zR3e7WIxjVvujporehV2dW1r2TtL2XFY1nJr Da3aMcdYx62Vs62Pu+vhBtrKUikztCPdm+Pxtarv7O42T23sYwv4OLWB8Kqv3Whnh/mvY05uhbFt 3h5329s2nnJez83pUpv60/8AD3htfarsAUNu1vdOtaQVPetEu5vLl+b3pm1UWYEXG92RVffACZ5u gyuZzxrnXq8bbuZWN9vV0DU5vX/Iy39//OAZ17i5Bx5A/RIHyTvG9rMfDu7ZdlXNBS+jx4kd4KK7 VJ9AV43Jb+xy2VKzr3QOKLKTbXXp+pk1Tq55wkMJtrHWlOh0HTvZ/xxyoS+97Avr9wZpSvWq03zt /lzqQfGMdE9Oh7Jhh3sRZc7xL+IVxSTn+nCCbjmxez3rZsP61j9K+MfjXaOZrbvimax1pqv97BlC Kr74vmTKV97wkZd837qb+JmjHmWiT7jqdSTuuX+r84QUebfa3nHLAz7pzIP//ea9e3rWo0r2/859 7EmNTtL7Pu8eDz7GNXr84vMW9NC5edz523Xlyz37tr/98/8e/cvTvvZdtDjm3dt46ZO//FAD/9Gj jtnum3371zf+sAepNeDjd/3oF776X47wE9M+kNOm+HuY2QO10tOzySq8/+O/8APAACTAAtQW58u5 rzM/v9M84Wm+5rM5pXu+A4TAxUPABgSwEsQ97BM8FDxBmQlBB+y7jII/FUS7fho5uxM/00m+87O/ mIPBccPBCDy898PADnS/GJTBFGQ+0OPA6QvC3RtCIvTBDMTACrTABKS/+bsnknNBBoRCEbQ+GlzA JuzBJmNCHUy9MHTCiqpC//lDwzScszGEvDJcwjN0wzbUvd9bNzO0wRt0QDYktwvUvyvkQaPLPw1M O4aqvgkUNcTjuNDzK0HMQujDw+VDvDycwSdsv9aTwj9UwBqEuamjQvZwPU18uziUQ3rZO1O8LiuU xI0rxVUURTL0vkfkQzCMxP4DQli0RE40RBD8PFtMP8yTwF3cxFMcRO/DQuSbw2AURgEsxtwrQl9c Q2Ckwj1sRmjMHGlUQlospkD8whF8Rkr0RDVUxmz8RnDMxWSMQjpkRmx8QD/cxnO8OnFExHXUxXJk xPPQmKV5xU9Mxx8ESHh8wXd8E3lERWqMObZYFleJFakYioHpM3y8xUwcwP87HEdC1MNenMVfVEgo kRd+jJaAGUmmYBmWIUeKxEWLVEmM5D6d20iOnLxyYwmGZBY6ORGyiEieEBOHzBZmsYlnCUiClMLe s0ct3L97dDujGBNKYZWQ/ImTNBgLgZdMqZaBIQuIXJc3DMd6/MfBQ8qKVKqkBDuVCMmePEuebEg+ 6ckV8UlMocpAaZexMAugyEqrlEiBHEhU+0BZhMOxZLu76Q8TORJZKUzClJOTVJYhEUwkARi6tEq7 jMih8AmzwJStdMbbAsvLFMq/7MiyVJLExBbGnEpruUuIDE2TXJrIhEzK1EmgZE2zWEzDPBYegZag 3EETPEJ2bMbOBJDCqMn/jGlLtLRJkoxMiLRJ4nRLIUkX13QW85hMyozNR9mT0dQPqMwP4VROl+TL iUxJlFTH3pRC4IRLxawT0GwW46zNaoFL7fxJ1qzLtIhO2/yXeIlL6nTMdYFO2STN0exHljTKoTxG SRw/udmMqCROs0zLbLlLdbHOm9BO4YTOq5RL84RPBsWYBE3OqKzO9TSX2bTPm8yYWHFQAO3KfDRH At3LPsxN1qlJkPTP/pjP1xyY9pxOV7FO5sRQ2rRPPeHPHUVMhkTN9hxNlTlPHzVPkSTR5rzQEx26 lfxOdGRRvPSXlaCUwTxQn3xKktyUmhjOBF1NK9FKnvxSHt3QD03OtGTP/zHNyiz90DC1TWnJSefU lPvzQy7czDv9Pq9EUPPkiAOdUclszF2J0ebMyuPMzreMzdccCrVUFTM9UjRtSJ20y9Os1C3NzzfF 1Kc5yPojQS/E0yf1CLME0zktkEdF0CWd0yIN0mbJz2c5TrdsylgNEjP1itpUT0qN00vtUF0FVEy8 yBw8xBJtRcd7nPTEmI340yXVTx0d1HMp1Ot8UMvs0TQ1zBt1VSZNz13N0QutkszrS24EV4R0mffA Uvfk0hMZzmypTlKdTy+1Vhul1oecSxnNVfnUVEC1V7EUUFckxWANz6VrV/0UUu1aTWbl1WRNFiDl z+WU0VKd1S0RU4Ph0//brCs7BNYUJVbhOQSO/QeOPYSG+FiGEFkhnNKMHCJzVc9M5a1T1dKEnRBo 3VI1ldcMbch2DVUUPT/wW0HddAiS9diOXQiRJdmPBdmRDdo6NFmMJb5S7VCrfFkgqU+fdFp0NQ2C nVWECc5O1Md55EWgNVqL+NmK+FmiDdqhFduv7UBO3VQFtVn/rFFftVSrNVe1rNtGDRIPRMauBc+j PVuyRdqxRduHKFujJdyiHVyOzdsBawshJVT6TNdqZViVgVo9bVInxdlJ3NuEKFqwFdrDPdqOMFyw FdyQ/dyw7VjO/VqB4NxDOAjStVN1ytgV1FdGjdqOcdFWnUmP1FwFSd3/0kVb1EVav/VcjxDdwgVc xP3YiVDexG1eszVdn03cOjVR3pPXdf3RhYVSzqRe7+Ra3jUa1kVeiPDb4wXZv+1bzzXf5y3e5y3a 1ZVehHDezk1eoK1f+GVd14XfQrQ8vWhKlUXGy23JzP1egxBb8mXdtE3f+b2I4U1f1X3f8k1bpM0I 5bUH5g3eBUbfCt5c9+XcgQjfAhbf7tREf7Vcf9xTniVgzRLc1PVdCRbhBEZf/Lrg1oVgC75f6aXh G/7gDJZhkd3hDQ7h1g3i/KVh4cXg+SXi6h1hFgxLAR5gFYbgHlZg9yUI0hVdDRbhG65hK9ZfDh5i HAbj0W3fr0ViLy6I/wpOYw+O3/Bl4MNd4y2W4gKe3nU0wigO4TIGXjhe3jD+XfE1XhtWYhtG4zO+ vDc+YvXl4g32YEYu5EH+29eFZImo4jjmYUVeZEfGXE8FNpicx/Bt49+tZEqu4NBFXi6W4lN+ZOcN 5DNOZPoVEDW+ZDG2ZDbe4hh+ZUwW5Ep+Xz6W5S4+5SqG4a+UXbG645D4ZC/W5V1eZluGZBmm4Ezm 4R0m5Boe3gMO5laO5l3OZVt24PFNZGb+5UGW4/yl5km+36Ik5qQ1ZvylZvxVZlomKwM2ZfmN53Bm 41QumAb24RyeZV1WYl32ZoH2W3vuYlbO53gOYkoW5+1V0U/lXmPOCv+EbmcQ/uIi3gjfFWKGpmVu VuUrFmFfJuJYRuVZvujonQyRDuMtLukQJukvrucu7Nl4ND2vg2eA7udUfl2BDuVz/mf9TWlXvuU9 xmdLDuOFFmWjZmlz3mgh/maWbueW5uF0Vuel7V7vNWHYTYmclt+j1uiX/t3SjV6ELmiybmnpfeWd fuGhhmemRmpfTuikDueB1uk8xmYinup/3U1rpGmJ3mOgdmsuRuvk/WlttulCRuYxDmqxBmuw1uG2 tmiG7miP9uNbVopPvthE5M68vEYp1ZGRhuDFdua/UWa/Lmxhrut9durK3mk9LmmF1mamLtuT5mdg NmL8XWcxfMcSpsf/OoaSeS5fc5Zsry7n34Zhuv7oKUZtTnvtrXZtyS7lMd5pwB7rTq3cq+tXxe3X i6Nq/btppY7j515s1WZh6E1r8RZryA5n5ibkuSZjBXbjoQbgE+Zth8buPL1E8PPubs7iCD7dHk7t 807fni7i9CbvJD5iGX5vqAYp3Mbq+8Zv+QZE5DHwyr7m5F5tBb5nZjbsiRZmej7wBa5oBm9wq85Z FG7BBw/gKXwKCm9ttb4+Qe5owm5u+HbqNtbjWkRC+d5az4tJgF1tghbnzyZqrybeBKZw/9ZeVAlX vWbihhaZFC/mYcU9/f7rWA7sAAddxkZgxKXjwGNaHwfMcS3QUlzv/5Wm7b797xsHXC/nvNN7aLIM c39j8k0OK8L1Y9MtbuteUaVMQs10czmfcz9/4vHg8pDFOQjfQESvxAgvWU2eb6vewE5udBIvRUEf 80uv7j3nyq3s7CkH9Ig+cY3F7F6xY1I3cWhUxVCnb2LE9Ey3791dxh/f9DsWMSXXSxTX3f0Nxc5c 9Z1Nxux+dFr/1vr2Syf39VHk7LuDdTAf8d5E9mhU9mGu7mBfPfyD9nNU20rndCdWWlBd9LHE9lg8 drwW9W439/9M9lmPc3Hf7RI/WWo39ddbd89MdWn3dG+HGHd/SXo3FGTXdmHN90Q3xn4v+BSWdN2O 6VOn0mw3+FLXdP+IxswA1XGI3/YaGXeHV3VXt/gnl/CNb/Udb/OMf3XtzkuZxnesLnd0v3UeH3m+ /niXj/LtjHCRr2qXTyWYpxiET3ipG3Q4//abD7acf3mv0/iQX0RUZ/WgP/eVf/hAB3Z5z2uB3O2r znU6F3NKf/Y3R/qkf3dIN/ZlH0GZZ/inP8rcbnKT13VF/FWc/3MDnMawz/Fjb3kVb/qr/vRR1w5/ h/vMlHqib+Kq5nam5/Nit/aez3qK//mAP3u0z+qrj3hix3rE97+Th/x5b8eCHPu613tHJ3TvAPe7 93xG1/Sab/uyQ6btLvu893vLx/U07Htm12zYF3a6l/LHR3nCB9X/tU35aa98kD/62y/8hd98ryd+ sJ/6SS+9XVT44f96iQewviPK5I93tXd7UBz6W9/35/996md7lo/6lC/9zBb4vW/24B98pU931BdX 0q9+wPd4xh/97sf+0Lf7ro9S0zd/n/f91d9X4QcIewIHEvxn8CDChAr/EWzo0OHCiBInSnxoESLF ihc3cuyY8SNIhB0vhix5kKTJkyNXrkzpUiHLmDJn0qy58aVBmzhx2rTHs2fNnS97Ci1qEihNoymR Mm3q9OlTpSWJDoXqUWpInVi3wrR6lStFr2LH3gRrlqvWqmQxno2Ytq3UtRbhLpRrl+zPkXR3vj16 t+DehH0D5/1L/1jk38ROC8vMqjgm47uHcw6e7Ddp3a+HH3Ou7Biz5dCZE4f2LDojVZczjXZu3Vgt aMKuZ/u0bPr0xNuog9qmLTcyy9K+OwuPjRuk7tzJ0Q5fC7xl7+aAjzPnTf1j6qWK+UrnGBYl7NeT u3vH/js85OvIl7vd/py8wOjG98IHr7p+cPXm5091Hxd+cavJh99A7+m1H1767cbfev5t5qBs1j1I 4HTaMYiVXQOKZyFp4z0W4IYRUhifgeV56FuJJnIomYYZnnihiACmaF9g2SlXH3cdvsjijukpeKOO K4ZIH3szImUkVCC62GN+P2oEYX8wnlVkiyMeOGGQMQ7pJGJZXv8mIJPQcTmailNKqCWPaPo4pmBQ fiYlWDaySZmVNNboJl1UUscZkg9VeeWcKsnI5od/ahYoQ4XeB2ecZwZaJ4nX8WlomY/i2SCYWG5J KKSILsjoVnJyeumnmX4ppqijWjnmkpquiWiqT9Z2Z46GeUrnqrfq+h2o6um5a5tezgnprMA2it+u vxqbKKlOErusmn5Ca1as05Jp663PWguXc9u256i317YKa6fhmkmepb1aO6mu5Zp7LLHxVvhuV82a yy69/8lrar7OKqpmnvb2e+q+gA7sr7ABq1svtgcXVfCm3B76Lr7RGhxlwg4LCXFZrr76bbeLZnzu wl2OrDGmHE//rDC/GNtJ7b93lmxymiijp/JclHYsslUyt8xyxAjWbPPGOLPlsZhF0+awsrg2THDO 9SpNstEvSwxuylWfx3PQvJ4M5Ih9Qqxkk1xrfXatQ7tModgFp92Q112DfXZTQo/19tZKo0131Hrf fTPf1cYd+M5QE354gYBfDPK8ayM+s9OPH2245HzjnbTFla/8ptoMJ6i45lq33TjQoZdN+efTmv74 6IkjvXrhjufts9XVwY4s6JUSefvinI9LO+/Bxy5771cLX7vdswN/PPOu+627aM0Xi/rfYQ4qqeSt T5/uwkxxqL3g8IbtrbZmY8693HOfvnzIr1+feaSlK0/85qxi/531+sPe31b58APlP/IG9zH9QY5Z BSTb+eSHO+uljnENpB/07Lc/ASZQVT/jn7vcJxYMEihZE6Rg8bjUNKH0D4BJQtj8LDhA/OVPhS00 3vg0uMF2RTBcIwyffnDIQRzpzCse5Bj4tPfDAzKwejLsGQ2l98LkVVCCFxRhzHb3NQWVUFxGpF4N UZi+HH5wND1EYrYyiMVceUqHvuoiFwWWxhiaz3tEG2PfyIXGM05RVlu04gLbeEU8+vCL0gojEYvY OT6GEITvg+AM9ahGBy5Riyt04uEux0NFJvJ5ATziJak4R+yxLnfdkeQeEZlJRhIniYHEpMrAF0Xf /Y6VjVRf3eiYtsk9VU6V46uYKOMIx6iQb5bHqaUtlQg3T46SlA90Jemo9kgoCg+WTYzc6kCZRWce k4VufGMuhVlIQ4qOmMX03CBLFU1BavOV1OwmJb8JzhRa85DBamU7y7lMEhpNmuqkWTi5+cleyvN/ 5GzOEJ+WTRT9qJ+rVOAky3hQJiZUjrrcYST9uJihBBSe8dwnIJ9oQGEisJr5wiUy3elCcxoTmKjk JcpAelHpVJSkJTUja3wZ00Wua6Hi7KAp77jO2aSUpjUlqD5ZmlGNnrOKkLQovQzqz6Hq9J0RtaPl bKZUmNLygCb1W0AAADs= --=====================_4432453==.REL-- From nfsv4-bounces@ietf.org Mon Feb 26 07:38:09 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLf5n-0003kJ-8n; Mon, 26 Feb 2007 07:36:35 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLf5m-0003kD-2n for nfsv4@ietf.org; Mon, 26 Feb 2007 07:36:34 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLf5j-00032I-Mm for nfsv4@ietf.org; Mon, 26 Feb 2007 07:36:34 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1QCaGmi019519; Mon, 26 Feb 2007 07:36:16 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 26 Feb 2007 07:36:16 -0500 Received: from [192.168.0.140] ([172.17.19.37]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 07:36:16 -0500 Message-ID: <45E2D43E.7040305@panasas.com> Date: Mon, 26 Feb 2007 14:36:14 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: "Muntz, Daniel" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: <01AE8AF878612047A442668306EAEB054DB015@SACEXMV01.hq.netapp.com> In-Reply-To: <01AE8AF878612047A442668306EAEB054DB015@SACEXMV01.hq.netapp.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 26 Feb 2007 12:36:16.0467 (UTC) FILETIME=[B54D6230:01C759A2] X-Spam-Score: 0.0 (/) X-Scan-Signature: 3fbd9b434023f8abfcb1532abaec7a21 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Dan, thanks for the feedback, answers below. Benny Muntz, Daniel wrote: > Seems like a pretty significant change to include in draft-09, which is > due out any day now. In particular the implementation mentions some > potentially non-trivial issues in correctly implementing priority > queuing. > > E.g., rather than leave it to the server and client to figure out some > mapping of different priority schemes, why not define the the priority > scheme used at the NFS layer by both clients and servers. If the the > server has some priority scheme implemented in lower layers (e.g., at > physio), leave it to the server to do such mappings so as not to clutter > the NFS protocol with extra negotiations/mappings. The proposal allows the server to do that. Mandating the NFS priority scale seems to be more demanding on the server, isn't it? > > Also, mixing non-idempotent operations with priority queuing (e.g., the > suggestion that metadata operation priority is > data operation > priority), suggests to me that there might be some potentially > significant implementation details in maintaining a correct lattice for > execution ordering. I agree that implementing a good priority queuing system is not trivial :) Can you please elaborate on issues you see with non-idempotent operations and priority queuing? Such corner cases are good candidates to be documented in the spec. > > The last paragraph in "Implementation" seems a bit sparse, but other > people would be better judges of what level of detail should go into an > RFC on this topic. > > > > -----Original Message----- > From: Halevy, Benny [mailto:bhalevy@panasas.com] > Sent: Friday, February 23, 2007 6:42 AM > To: nfsv4@ietf.org > Cc: chuck.lever@oracle.com; Welch, Brent > Subject: [nfsv4] SET_PRIORITY: new op proposal > > Based on discussions during FAST 07 we'd like to propose a SET_PRIORITY > operation that allows the client to set a relative priority for the > session and/or operations. > > The benefits from this operation are pretty obvious. It can be used by > clients for example to execute metadata operations in higher priority > than data operations, or to execute operations on specific files in a > different priority, or to give different priority to different client > hosts. > > I'd appreciate your prompt comments since we would like to introduce > this operation as soon as possible (draft-09) > > Thanks, > > Benny > > Operation: SET_PRIORITY - set relative priority > > SYNOPSIS > > priority_how, priority_level -> actual_priority_level > > ARGUMENT > > enum priority_how4 { > PRIORITY_SESSION = 0, > PRIORITY_OPERATION = 1 > }; > > enum priority_range4 { > PRIORITY_MIN = -50, > PRIORITY_DEFAULT = 0, > PRIORITY_MAX = 49 > }; > > struct SET_PRIORITY4args { > enum priority_how4 priority_how; > int32_t priority_level; > }; > > RESULT > > struct SET_PRIORITY4res { > int32_t actual_priority_level; > }; > > DESCRIPTION > > This operation may be used to set a relative priority for the current > session > or for the following operations in the compound RPC. The default > priority > level is implicitly zero for all sessions and operations. > SET_PRIORITY for > PRIORITY_SESSION sets the priority_level of the current session such > that all > operations following SET_PRIORITY in the same compound RPC and all > operations > related to the sessions will be executed in the given priority_level. > SET_PRIORITY for PRIORITY_OPERATION sets the priority_level only for > the > operations following it in the compound RPC and does not affect the > current > priority_level of the related session. > > There are 100 priority levels, such that the priority_level MUST be > greater than or equal to PRIORITY_MIN and less than or equal to > PRIORITY_MAX. > If the priority_level is outside the valid range the server should > return > an NFS4ERR_INVAL error. > > The server replies SET_PRIORITY with the actual_priority_level that > was assigned > to the session and/or following operations. Servers that do not > support priorities > MUST either return an NFS4ERR_NOTSUPP error or return zero for the > actual_priority_level. > > Servers that support priorities SHOULD yield more resources for > executing > operations with higher priority levels than to operations with lower > priority > levels. The amount of resources, such as network or disk bandwidth, > that is > given for each priority level is implementation specific and in some > cases > may be configurable by the system administrator. > > IMPLEMENTATION > > If the server supports a priority system with a different scale it > SHOULD map > the protocol priority_level into its own scale and rescale the > actual_priority_level back onto the [PRIORITY_MIN .. PRIORITY_MAX] > scale. > > Care should be taken by the server to prevent starvation of lower > priority > operations. Specifically, since setting the priority does not require > any > special access permissions, malicious clients should be detected and > confined > to prevent denial of service attacks that take advantage of the > priority system. > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 07:46:26 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLfFK-0000pt-81; Mon, 26 Feb 2007 07:46:26 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLfFJ-0000pn-DM for nfsv4@ietf.org; Mon, 26 Feb 2007 07:46:25 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLfFI-00047T-0n for nfsv4@ietf.org; Mon, 26 Feb 2007 07:46:25 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1QCkNXO019744; Mon, 26 Feb 2007 07:46:23 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 26 Feb 2007 07:46:23 -0500 Received: from [192.168.0.140] ([172.17.19.37]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 07:46:22 -0500 Message-ID: <45E2D69D.9030103@panasas.com> Date: Mon, 26 Feb 2007 14:46:21 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: Robert Gordon Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: <3458BB75-9AF4-476B-8694-B319059C87DD@Sun.COM> In-Reply-To: <3458BB75-9AF4-476B-8694-B319059C87DD@Sun.COM> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 26 Feb 2007 12:46:23.0119 (UTC) FILETIME=[1EE521F0:01C759A4] X-Spam-Score: 0.0 (/) X-Scan-Signature: 156eddb66af16eef49a76ae923b15b92 Cc: chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Robert Gordon wrote: > Hi Benny; > > So, since SESSION may have a priority associated with it, may an > implementer assume > that the NFS Client, may/should also support priorities (for the back- > channel) ? Good point. The intent was to set a priority for the server only and not for the client callback channel. > and I guess it follows for SESSIONS to data-servers as well.. Yes. > > It seems like EXCHANGE_ID should carry a hint in the arguments/reply > to indicate > want support for priorities/has support for priorities. It could, although the reply to SET_PRIORITY should be sufficient to tell that too. > > Could we remove the need for priority_how4 by adding priority_level to > CREATE_SESSION? Hmm If _just_ SESSION was prioritized then the NFS > Client > could pick and choose which SESSION to use for a given COMPOUND ?? > > Can you provide some additional usage for setting the priority within > the COMPOUND, i'm assuming PRIORITY_OPERATION scope is just for the > containing compound (or till we see another SET_PRIORITY) ? Right. You're interpretation is exactly what I meant :) I don't have a particular use case besides saving on sessions and allowing a different priority for specific operations. This is not exactly the same is having different priorities for different sessions as the latter can have an affect at a higher layer, such as the polling layer, e.g. executing operations off of higher priority sessions before lower priority sessions. Meaning a high priority operation coming from a low priority session may have to wait behind in the low priority session queue before its SET_PRIORITY operation is even parsed. That said, I'm ok with taking this mechanism out if people think the benefit of having it is too low for the cost of implementing it. Benny > > Robert. > > On Feb 23, 2007, at 8:42 AM, Halevy, Benny wrote: > >> Based on discussions during FAST 07 we'd like to propose >> a SET_PRIORITY operation that allows the client to >> set a relative priority for the session and/or operations. >> >> The benefits from this operation are pretty obvious. It can be >> used by clients for example to execute metadata operations in >> higher priority than data operations, or to execute operations >> on specific files in a different priority, or to give different >> priority to different client hosts. >> >> I'd appreciate your prompt comments since we would like to >> introduce this operation as soon as possible (draft-09) >> >> Thanks, >> >> Benny >> >> Operation: SET_PRIORITY - set relative priority >> >> SYNOPSIS >> >> priority_how, priority_level -> actual_priority_level >> >> ARGUMENT >> >> enum priority_how4 { >> PRIORITY_SESSION = 0, >> PRIORITY_OPERATION = 1 >> }; >> >> enum priority_range4 { >> PRIORITY_MIN = -50, >> PRIORITY_DEFAULT = 0, >> PRIORITY_MAX = 49 >> }; >> >> struct SET_PRIORITY4args { >> enum priority_how4 priority_how; >> int32_t priority_level; >> }; >> >> RESULT >> >> struct SET_PRIORITY4res { >> int32_t actual_priority_level; >> }; >> >> DESCRIPTION >> >> This operation may be used to set a relative priority for the >> current session >> or for the following operations in the compound RPC. The default >> priority >> level is implicitly zero for all sessions and operations. >> SET_PRIORITY for >> PRIORITY_SESSION sets the priority_level of the current session >> such that all >> operations following SET_PRIORITY in the same compound RPC and >> all operations >> related to the sessions will be executed in the given >> priority_level. >> SET_PRIORITY for PRIORITY_OPERATION sets the priority_level only >> for the >> operations following it in the compound RPC and does not affect >> the current >> priority_level of the related session. >> >> There are 100 priority levels, such that the priority_level MUST be >> greater than or equal to PRIORITY_MIN and less than or equal to >> PRIORITY_MAX. >> If the priority_level is outside the valid range the server >> should return >> an NFS4ERR_INVAL error. >> >> The server replies SET_PRIORITY with the actual_priority_level >> that was assigned >> to the session and/or following operations. Servers that do not >> support priorities >> MUST either return an NFS4ERR_NOTSUPP error or return zero for the >> actual_priority_level. >> >> Servers that support priorities SHOULD yield more resources for >> executing >> operations with higher priority levels than to operations with >> lower priority >> levels. The amount of resources, such as network or disk >> bandwidth, that is >> given for each priority level is implementation specific and in >> some cases >> may be configurable by the system administrator. >> >> IMPLEMENTATION >> >> If the server supports a priority system with a different scale >> it SHOULD map >> the protocol priority_level into its own scale and rescale the >> actual_priority_level back onto the [PRIORITY_MIN .. >> PRIORITY_MAX] scale. >> >> Care should be taken by the server to prevent starvation of lower >> priority >> operations. Specifically, since setting the priority does not >> require any >> special access permissions, malicious clients should be detected >> and confined >> to prevent denial of service attacks that take advantage of the >> priority system. >> >> >> _______________________________________________ >> nfsv4 mailing list >> nfsv4@ietf.org >> https://www1.ietf.org/mailman/listinfo/nfsv4 > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 08:15:51 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLfhi-0003Zh-0v; Mon, 26 Feb 2007 08:15:46 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLfhg-0003ZW-Uu for nfsv4@ietf.org; Mon, 26 Feb 2007 08:15:44 -0500 Received: from web31808.mail.mud.yahoo.com ([68.142.207.71]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HLfhf-0007Pv-DY for nfsv4@ietf.org; Mon, 26 Feb 2007 08:15:44 -0500 Received: (qmail 11843 invoked by uid 60001); 26 Feb 2007 13:15:42 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=M9rplb85XK5RONyoEcWACsUq4szBgS1KvdnD4UbGg1mBwf2r3b6UFTJ9qQRIFsVStoOWXfXsGud5Q9x9mf61Ab3FVmF7XYvBi632+YcPU4fyeFK9RyAS6KLQ+hi2v82lYjviZ0wOMIRIkBXh3DFddo6fr/+lidTcgLTaPVM4G/0=; X-YMail-OSG: HhwMi8UVM1l87oG2ae_m5E_Zl6VkMpAmDjeoYBKr_Znhi1ksAx82qt7PBnYVu.6L9tlqEhRX3fxC7AuWWIM3YmsRpmQ5beOK_FVdC5eheIuHu0asxn.e72c34ToQNdKPGLUiXvIGmpE- Received: from [198.95.226.224] by web31808.mail.mud.yahoo.com via HTTP; Mon, 26 Feb 2007 05:15:42 PST Date: Mon, 26 Feb 2007 05:15:42 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: Benny Halevy , "Muntz, Daniel" In-Reply-To: <45E2D43E.7040305@panasas.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <749349.10451.qm@web31808.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 7d33c50f3756db14428398e2bdedd581 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- Benny Halevy wrote: > Dan, thanks for the feedback, > answers below. > > Benny > > Muntz, Daniel wrote: > > Seems like a pretty significant change to include in draft-09, > which is > > due out any day now. In particular the implementation mentions I agree that the priority system as proposed, is too big for draft-09, and hence, NFSv4.1, since draft-09 is supposed to be the last draft for .x file changes. I will send two more messages on this in the next few minutes. One that responds to Benny's reponse to Robert Gordon, and another that proposes an alternative that might be considered small enough to put into draft-09. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 08:24:28 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLfpn-0000ck-6M; Mon, 26 Feb 2007 08:24:07 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLfpm-0000cZ-0R for nfsv4@ietf.org; Mon, 26 Feb 2007 08:24:06 -0500 Received: from web31807.mail.mud.yahoo.com ([68.142.207.70]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HLfpk-0000Ba-Mk for nfsv4@ietf.org; Mon, 26 Feb 2007 08:24:05 -0500 Received: (qmail 69018 invoked by uid 60001); 26 Feb 2007 13:24:04 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=KsHpiEDSt3gdAI8o73F82+1VdOdGhB91lX5PQuzIRX4Ceihwd9297N2ko6xJSR47wosvf23AKdBaLLZEbmtjwMx+JmgxtdP3QZ687sYqCO0nrHqMX3J3nOQS+h5B2QqUQ3bP5ImMxGQ23iURMruTwNGIBHAcBWXwWPh0OC/8Knk=; X-YMail-OSG: pUBXai8VM1kRXotY9KKOfQyBM7l13cshVzkZWdxaYZwbVs9WnvDza8QMS0M1s6RJFvZZmP2IsWFF5ke7zbQs41lVYT8biLbo60QIBsiPizA96uzp9w1U7KioJa.oQgZzawqX_qx895Y- Received: from [198.95.226.224] by web31807.mail.mud.yahoo.com via HTTP; Mon, 26 Feb 2007 05:24:04 PST Date: Mon, 26 Feb 2007 05:24:04 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: Benny Halevy , Robert Gordon In-Reply-To: <45E2D69D.9030103@panasas.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <90147.66474.qm@web31807.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 0bc60ec82efc80c84b8d02f4b0e4de22 Cc: chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- Benny Halevy wrote: > > Could we remove the need for priority_how4 by adding priority_level > to > > CREATE_SESSION? Hmm If _just_ SESSION was prioritized then the NFS > > > Client > > could pick and choose which SESSION to use for a given COMPOUND ?? > > > > Can you provide some additional usage for setting the priority > within > > the COMPOUND, i'm assuming PRIORITY_OPERATION scope is just for the > > containing compound (or till we see another SET_PRIORITY) ? > > Right. You're interpretation is exactly what I meant :) > I don't have a particular use case besides saving on sessions > and allowing a different priority for specific operations. Having a separate operation does complicate recovery from partially completed COMPOUND procedures, e.g. 10 ops send, 6 executed. The client has to re-send the SET_PRIORITY with the remaining re-sent operations. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 08:36:01 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLg17-0001Ae-3s; Mon, 26 Feb 2007 08:35:49 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLg16-0001AZ-7A for nfsv4@ietf.org; Mon, 26 Feb 2007 08:35:48 -0500 Received: from web31803.mail.mud.yahoo.com ([68.142.207.66]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HLg14-0001e1-UX for nfsv4@ietf.org; Mon, 26 Feb 2007 08:35:48 -0500 Received: (qmail 27660 invoked by uid 60001); 26 Feb 2007 13:35:46 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=04B02inl8OsFsm5rBOAAXvI2OIJrc4rAT3bOd/Vls3e4PDnNyPZ409ZIj5ndd1NGrVrbi/xxoDmnsDu+yl5HNFKwnro7O2TNyh/x8NCmvDus9lIkyrGhRy37Cup8sxPzVzn2Wml+o46cAHyNNAMZx8eFi5lakDG+TM/6GZrR2Xc=; X-YMail-OSG: P0OVdDkVM1mOn4wfw915lEZwjH6o3smt6mky1kn3BDTL0ZWGCl8utxuDzplNHR9rEw-- Received: from [198.95.226.224] by web31803.mail.mud.yahoo.com via HTTP; Mon, 26 Feb 2007 05:35:46 PST Date: Mon, 26 Feb 2007 05:35:46 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: "Halevy, Benny" , nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <236320.27492.qm@web31803.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 0bc60ec82efc80c84b8d02f4b0e4de22 Cc: chuck.lever@oracle.com, "Welch, Brent" X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org If we were talking about NFSv4.2, SET_PRIORITY would be a natural way to add this operation. Since we are still working on NFSv4.1, we have an opportunity to add this to "existing" NFSv4.1 core infrastructure. My counter proposal is: - add a priority field to CREATE_SESSION arguments (which the server can confirm as it does various other session values). The priority is relative to other sessions, and represents the priority the server and client will take when servicing the fore and back channels of the session. For completeness, there can be separate fore and back channel priorities. - add a priority field to SEQUENCE and CB_SEQUENCE arguments and results. The priority represents priority of the COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs executed on the session. - There is no way to update the session's priority once the session is created. Just as there is no way to update the maximum request size. Maybe, someday, we'll need such capabilities, but a general purpose operation to updated session and channel attributes should be added. Thus far, I haven't seen a clamor for that. In the mean time, just create another session, and gracefully destroy the old session once replies for all outstanding COMPOUNDs have been received. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 08:39:18 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLg4A-0002hh-IA; Mon, 26 Feb 2007 08:38:58 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLg49-0002hc-LD for nfsv4@ietf.org; Mon, 26 Feb 2007 08:38:57 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLg47-00021j-3f for nfsv4@ietf.org; Mon, 26 Feb 2007 08:38:56 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1QDcsFr021069; Mon, 26 Feb 2007 08:38:54 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 26 Feb 2007 08:38:54 -0500 Received: from [192.168.0.140] ([172.17.19.37]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 08:38:54 -0500 Message-ID: <45E2E2EC.5050303@panasas.com> Date: Mon, 26 Feb 2007 15:38:52 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: email2mre-ietf@yahoo.com Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: <236320.27492.qm@web31803.mail.mud.yahoo.com> In-Reply-To: <236320.27492.qm@web31803.mail.mud.yahoo.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 26 Feb 2007 13:38:54.0789 (UTC) FILETIME=[756FCF50:01C759AB] X-Spam-Score: 0.0 (/) X-Scan-Signature: b19722fc8d3865b147c75ae2495625f2 Cc: chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Mike Eisler wrote: > If we were talking about NFSv4.2, SET_PRIORITY would be a natural > way to add this operation. > > Since we are still working on NFSv4.1, we have an opportunity > to add this to "existing" NFSv4.1 core infrastructure. > > My counter proposal is: > > - add a priority field to CREATE_SESSION arguments (which the server > can > confirm as it does various other session values). The priority is > relative to other sessions, and represents the priority the server > and client will take when servicing the fore and back channels of > the session. For completeness, there can be separate fore and back > channel priorities. > > - add a priority field to SEQUENCE and CB_SEQUENCE arguments > and results. The priority represents priority of the > COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs > executed on the session. > > - There is no way to update the session's priority once the session is > created. Just as there is no way to update the maximum request size. > Maybe, someday, we'll need such capabilities, but a general purpose > operation to updated session and channel attributes should be added. > Thus far, I haven't seen a clamor for that. In the mean time, just > create another session, and gracefully destroy the old session once > replies for all outstanding COMPOUNDs have been received. works for me. Benny _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 12:22:55 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLjXm-000149-PC; Mon, 26 Feb 2007 12:21:46 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLjXl-000144-Qa for nfsv4@ietf.org; Mon, 26 Feb 2007 12:21:45 -0500 Received: from brmea-mail-2.sun.com ([192.18.98.43]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLjXk-0007Ap-C3 for nfsv4@ietf.org; Mon, 26 Feb 2007 12:21:45 -0500 Received: from fe-amer-03.sun.com ([192.18.108.177]) by brmea-mail-2.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1QHLhK6009506 for ; Mon, 26 Feb 2007 17:21:43 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JE200G01YW2EJ00@mail-amer.sun.com> (original mail from Robert.Gordon@Sun.COM) for nfsv4@ietf.org; Mon, 26 Feb 2007 10:21:43 -0700 (MST) Received: from [10.0.1.2] ([72.179.37.29]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JE2006F8YW7BXN1@mail-amer.sun.com>; Mon, 26 Feb 2007 10:21:43 -0700 (MST) Date: Mon, 26 Feb 2007 11:21:41 -0600 From: Robert Gordon Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-reply-to: <236320.27492.qm@web31803.mail.mud.yahoo.com> To: email2mre-ietf@yahoo.com Message-id: <3708A4B8-565B-464B-A5DF-7BE796B5AFD4@Sun.COM> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.2) Content-type: text/plain; format=flowed; charset=US-ASCII Content-transfer-encoding: 7BIT References: <236320.27492.qm@web31803.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 7baded97d9887f7a0c7e8a33c2e3ea1b Cc: "Halevy, Benny" , chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org exactly what i was thinking.. Robert. On Feb 26, 2007, at 7:35 AM, Mike Eisler wrote: > If we were talking about NFSv4.2, SET_PRIORITY would be a natural > way to add this operation. > > Since we are still working on NFSv4.1, we have an opportunity > to add this to "existing" NFSv4.1 core infrastructure. > > My counter proposal is: > > - add a priority field to CREATE_SESSION arguments (which the server > can > confirm as it does various other session values). The priority is > relative to other sessions, and represents the priority the server > and client will take when servicing the fore and back channels of > the session. For completeness, there can be separate fore and back > channel priorities. > > - add a priority field to SEQUENCE and CB_SEQUENCE arguments > and results. The priority represents priority of the > COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs > executed on the session. > > - There is no way to update the session's priority once the session is > created. Just as there is no way to update the maximum request size. > Maybe, someday, we'll need such capabilities, but a general purpose > operation to updated session and channel attributes should be added. > Thus far, I haven't seen a clamor for that. In the mean time, just > create another session, and gracefully destroy the old session once > replies for all outstanding COMPOUNDs have been received. > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 12:39:16 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLjoW-0003tP-6A; Mon, 26 Feb 2007 12:39:04 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLjoU-0003tK-Jy for nfsv4@ietf.org; Mon, 26 Feb 2007 12:39:02 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLjoT-0000FL-93 for nfsv4@ietf.org; Mon, 26 Feb 2007 12:39:02 -0500 Received: from smtp2.corp.netapp.com ([10.57.159.114]) by mx2.netapp.com with ESMTP; 26 Feb 2007 09:38:58 -0800 X-IronPort-AV: i="4.14,221,1170662400"; d="scan'208"; a="36500749:sNHT15992655" Received: from svlexc02.hq.netapp.com (svlexc02.corp.netapp.com [10.57.157.136]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1QHcwTN011902; Mon, 26 Feb 2007 09:38:58 -0800 (PST) Received: from exsvlrb01.hq.netapp.com ([10.56.8.62]) by svlexc02.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Mon, 26 Feb 2007 09:40:04 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 09:40:04 -0800 Received: from tmt.netapp.com ([10.30.32.36]) by exnane01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Mon, 26 Feb 2007 12:40:03 -0500 X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Mon, 26 Feb 2007 12:38:36 -0500 To: email2mre-ietf@yahoo.com, "Halevy, Benny" , Robert Gordon From: "Talpey, Thomas" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-Reply-To: <3708A4B8-565B-464B-A5DF-7BE796B5AFD4@Sun.COM> References: <236320.27492.qm@web31803.mail.mud.yahoo.com> <3708A4B8-565B-464B-A5DF-7BE796B5AFD4@Sun.COM> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Message-ID: X-OriginalArrivalTime: 26 Feb 2007 17:40:03.0373 (UTC) FILETIME=[256285D0:01C759CD] X-Spam-Score: 0.0 (/) X-Scan-Signature: f607d15ccc2bc4eaf3ade8ffa8af02a0 Cc: chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org But, what does the server actually do with the priority? Normally, any operation is eligible once received at the server, does this mean the server is required to implement strict queuing within the session, and if so does it mean that it will need to delay the processing of requests which are otherwise ready? If not, then what does it actually do? Benny's text documents the field, but doesn't describe the server's requirements. Call me confused, perhaps... Tom. At 12:21 PM 2/26/2007, Robert Gordon wrote: > >exactly what i was thinking.. > >Robert. >On Feb 26, 2007, at 7:35 AM, Mike Eisler wrote: > >> If we were talking about NFSv4.2, SET_PRIORITY would be a natural >> way to add this operation. >> >> Since we are still working on NFSv4.1, we have an opportunity >> to add this to "existing" NFSv4.1 core infrastructure. >> >> My counter proposal is: >> >> - add a priority field to CREATE_SESSION arguments (which the server >> can >> confirm as it does various other session values). The priority is >> relative to other sessions, and represents the priority the server >> and client will take when servicing the fore and back channels of >> the session. For completeness, there can be separate fore and back >> channel priorities. >> >> - add a priority field to SEQUENCE and CB_SEQUENCE arguments >> and results. The priority represents priority of the >> COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs >> executed on the session. >> >> - There is no way to update the session's priority once the session is >> created. Just as there is no way to update the maximum request size. >> Maybe, someday, we'll need such capabilities, but a general purpose >> operation to updated session and channel attributes should be added. >> Thus far, I haven't seen a clamor for that. In the mean time, just >> create another session, and gracefully destroy the old session once >> replies for all outstanding COMPOUNDs have been received. >> >> _______________________________________________ >> nfsv4 mailing list >> nfsv4@ietf.org >> https://www1.ietf.org/mailman/listinfo/nfsv4 > > >_______________________________________________ >nfsv4 mailing list >nfsv4@ietf.org >https://www1.ietf.org/mailman/listinfo/nfsv4 > > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 13:45:17 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLkpX-0002Vi-Qf; Mon, 26 Feb 2007 13:44:11 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLkpW-0002VV-O9 for nfsv4@ietf.org; Mon, 26 Feb 2007 13:44:10 -0500 Received: from web31801.mail.mud.yahoo.com ([68.142.207.64]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HLkpS-0000c4-Ew for nfsv4@ietf.org; Mon, 26 Feb 2007 13:44:10 -0500 Received: (qmail 88827 invoked by uid 60001); 26 Feb 2007 18:44:05 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=O8f2o9FQdVkI7Zc11c5moNpBVz1t+lQUkTNTWkZfs2E7VvXPnsq/ZTZ0OWHFIrIM1yvn7zVNjPRN3VzpM13p97uBCvBjPzY5w0UPf8empJudZkCufHnGltSs/fCEX63kyM8xWPuHRQSyI4FjUVDNQG17E+mqEUveghZ1okjVlUk=; X-YMail-OSG: RBmnjbEVM1lTxypve7PCn87FO6Sg.fKc0iN51YTkMTKsRa6xyfCgnsI_SMK4tBg4gA-- Received: from [198.95.226.224] by web31801.mail.mud.yahoo.com via HTTP; Mon, 26 Feb 2007 10:44:05 PST Date: Mon, 26 Feb 2007 10:44:05 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <915379.88693.qm@web31801.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 7baded97d9887f7a0c7e8a33c2e3ea1b X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- "Talpey, Thomas" wrote: > But, what does the server actually do with the priority? Normally, > any > operation is eligible once received at the server, does this mean the > server is required to implement strict queuing within the session, > and > if so does it mean that it will need to delay the processing of > requests > which are otherwise ready? If not, then what does it actually do? > Benny's > text documents the field, but doesn't describe the server's > requirements. I believe Chuck Lever called this a UNIX-like "nice" priority system. The man page, http://www.opengroup.org/onlinepubs/007908799/xcu/renice.html for re-nice is very interesting in that it doesn't say anything about how the operating system is supposed to implement it. Nothing for example about whether processes with a higher priority are always ahead of the processes with a lower priority. http://www.opengroup.org/onlinepubs/007908799/xbd/glossary.html under system scheduling priority has more weasel words, ending with: Because of the use of "implementation-dependent" in nice and renice, a wide range of implementation strategies is possible. If I thught the OpenGroup copyrights allowed me to, I'd lift its language almost verbatim. :-) Instead, I'd note the inspiration for model,and make an informative reference. But the point is that there is an existance proof of an underspecified priority system having achieved success. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 14:00:23 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLl59-0008QP-Tl; Mon, 26 Feb 2007 14:00:19 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLl59-0008QH-1K for nfsv4@ietf.org; Mon, 26 Feb 2007 14:00:19 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLl56-0004xJ-Iv for nfsv4@ietf.org; Mon, 26 Feb 2007 14:00:19 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 26 Feb 2007 11:00:14 -0800 X-IronPort-AV: i="4.14,221,1170662400"; d="scan'208"; a="36524683:sNHT24344656" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1QJ0DiU022843; Mon, 26 Feb 2007 11:00:13 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Mon, 26 Feb 2007 11:00:13 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 11:01:19 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] SET_PRIORITY: new op proposal Date: Mon, 26 Feb 2007 14:01:18 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] SET_PRIORITY: new op proposal Thread-Index: AcdZ1qe7xWh1wl5YSsOjhv0RGv3MRwAAXkgQ From: "Noveck, Dave" To: , X-OriginalArrivalTime: 26 Feb 2007 19:01:19.0979 (UTC) FILETIME=[80118BB0:01C759D8] X-Spam-Score: 0.0 (/) X-Scan-Signature: 0a7aa2e6e558383d84476dc338324fab Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org > If I thught the OpenGroup copyrights allowed me to, I'd lift its > language almost verbatim. :-) Instead, I'd note the inspiration for > model,and make an informative reference. It's short enough it might pass muster under Fair Use, but I'm not a lawyer and I don't play one on television. -----Original Message----- From: Mike Eisler [mailto:email2mre-ietf@yahoo.com]=20 Sent: Monday, February 26, 2007 1:44 PM To: nfsv4@ietf.org Subject: Re: [nfsv4] SET_PRIORITY: new op proposal --- "Talpey, Thomas" wrote: > But, what does the server actually do with the priority? Normally, > any > operation is eligible once received at the server, does this mean the > server is required to implement strict queuing within the session, > and > if so does it mean that it will need to delay the processing of > requests > which are otherwise ready? If not, then what does it actually do? > Benny's > text documents the field, but doesn't describe the server's > requirements. I believe Chuck Lever called this a UNIX-like "nice" priority system. The man page, http://www.opengroup.org/onlinepubs/007908799/xcu/renice.html for re-nice is very interesting in that it doesn't say anything about how the operating system is supposed to implement it. Nothing for example about whether processes with a higher priority are always ahead of the processes with a lower priority. http://www.opengroup.org/onlinepubs/007908799/xbd/glossary.html under system scheduling priority has more weasel words, ending with: Because of the use of "implementation-dependent" in=20 nice and renice, a wide range of implementation=20 strategies is possible.=20 If I thught the OpenGroup copyrights allowed me to, I'd lift its language almost verbatim. :-) Instead, I'd note the inspiration for model,and make an informative reference. But the point is that there is an existance proof of an underspecified priority system having achieved success. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 14:11:02 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLlF7-0002NX-Sa; Mon, 26 Feb 2007 14:10:37 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLlF6-0002NM-Fg for nfsv4@ietf.org; Mon, 26 Feb 2007 14:10:36 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLlF5-0006oy-5t for nfsv4@ietf.org; Mon, 26 Feb 2007 14:10:36 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 26 Feb 2007 11:10:34 -0800 X-IronPort-AV: i="4.14,221,1170662400"; d="scan'208"; a="36528075:sNHT19125337" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1QJ9kiS024850; Mon, 26 Feb 2007 11:10:30 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Mon, 26 Feb 2007 11:10:22 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 11:11:29 -0800 Received: from tmt.netapp.com ([10.30.32.36]) by exnane01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Mon, 26 Feb 2007 14:11:27 -0500 X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Mon, 26 Feb 2007 14:10:04 -0500 To: email2mre-ietf@yahoo.com From: "Talpey, Thomas" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-Reply-To: <915379.88693.qm@web31801.mail.mud.yahoo.com> References: <915379.88693.qm@web31801.mail.mud.yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Message-ID: X-OriginalArrivalTime: 26 Feb 2007 19:11:27.0935 (UTC) FILETIME=[EA7044F0:01C759D9] X-Spam-Score: 0.0 (/) X-Scan-Signature: ffa9dfbbe7cc58b3fa6b8ae3e57b0aa3 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org At 01:44 PM 2/26/2007, Mike Eisler wrote: >I believe Chuck Lever called this a UNIX-like "nice" priority system. I must have missed some messages in this thread. The mail archive doesn't show any of this discussion? >The man page, > http://www.opengroup.org/onlinepubs/007908799/xcu/renice.html >for re-nice is very interesting in that it doesn't say anything >about how the operating system is supposed to implement it. I would make the observation that process schduling is very different from NFS request scheduling. NFS requests are in effect run-to-completion. As such, I don't see the server as having very many options when a new request arrives, no matter what its priority. The request is by its very nature eligible to run at its arrival. For the server to handle the request otherwise, it would have to begin processing the COMPOUND up to the point of decoding the OP_SEQUENCE, then make a decision to either defer or continue the processing. This, to me, seems very unnatural and certainly inefficient. I would like to see the MUSTs SHOULDs and MAYs for the server's end before committing to this proposal. Tom. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 14:20:04 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLlNy-0000yk-87; Mon, 26 Feb 2007 14:19:46 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLlNw-0000xy-Gr for nfsv4@ietf.org; Mon, 26 Feb 2007 14:19:44 -0500 Received: from web31814.mail.mud.yahoo.com ([68.142.206.167]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HLlNv-0008MT-7Q for nfsv4@ietf.org; Mon, 26 Feb 2007 14:19:44 -0500 Received: (qmail 14798 invoked by uid 60001); 26 Feb 2007 19:19:42 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=OepfvgmT1EBfmgcDw29lWsnMvXb+J3z/OHFdjRj+NdRY7jwW2VpeHUpgAsDZ8GHGV/HKkbF7ZzcBw6v3YjW+B+MYyeqCvV7oz8oPQmo5DdofARKPnNU5AJLWCBGsHglSgWRxTR8HJHf87N4OOD9JubM38LbT2rqrytz2CV/fZ6c=; X-YMail-OSG: 4IQEhxQVM1m0yA70xQF1gQm71AENdQrTvltBdlEA6tHPyMyVyg8426.FqUfffLaFtk4ob_Zh_HhMIHrpMItNkvY_yh2YIPmVNx_.sIZf33kTof2TJzAwGktTDwxTr5IzfRc0xZGcSNM- Received: from [198.95.226.224] by web31814.mail.mud.yahoo.com via HTTP; Mon, 26 Feb 2007 11:19:42 PST Date: Mon, 26 Feb 2007 11:19:42 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: "Talpey, Thomas" , email2mre-ietf@yahoo.com In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <754187.14787.qm@web31814.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 7baded97d9887f7a0c7e8a33c2e3ea1b Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- "Talpey, Thomas" wrote: > >The man page, > > http://www.opengroup.org/onlinepubs/007908799/xcu/renice.html > >for re-nice is very interesting in that it doesn't say anything > >about how the operating system is supposed to implement it. > > I would make the observation that process schduling is very different > from NFS request scheduling. NFS requests are in effect > run-to-completion. Implementors with thread-based repliers running on pre-emptive kernels would disagree. One obvious implementation of priorities on such kernels would be assign the priority based on the sessionid priority and/or the per-SEQUENCE priority. Event-driven implementations apparently have less obvious implementations, but since I think event-driven can be mapped 1-1 to threads, the obvious implementation can happen there too. > As such, I don't see the server as having very many options when a > new > request arrives, no matter what its priority. The request is by its > very > nature eligible to run at its arrival. > > For the server to handle the request otherwise, it would have to > begin processing the COMPOUND up to the point of decoding the > OP_SEQUENCE, then make a decision to either defer or continue > the processing. This, to me, seems very unnatural and certainly > inefficient. I would like to see the MUSTs SHOULDs and MAYs for > the server's end before committing to this proposal. I think it is all OPTIONAL. > > Tom. > > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 14:49:03 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLlpZ-0003fq-F1; Mon, 26 Feb 2007 14:48:17 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLlpY-0003fk-8w for nfsv4@ietf.org; Mon, 26 Feb 2007 14:48:16 -0500 Received: from brmea-mail-4.sun.com ([192.18.98.36]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLlpW-0003KU-Q2 for nfsv4@ietf.org; Mon, 26 Feb 2007 14:48:16 -0500 Received: from fe-amer-02.sun.com ([192.18.108.176]) by brmea-mail-4.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1QJmEv0028900 for ; Mon, 26 Feb 2007 19:48:14 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JE3002015ABWY00@mail-amer.sun.com> (original mail from Robert.Gordon@Sun.COM) for nfsv4@ietf.org; Mon, 26 Feb 2007 12:48:14 -0700 (MST) Received: from [10.1.194.250] ([192.18.98.64]) by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JE300NXX5OD3WV2@mail-amer.sun.com> for nfsv4@ietf.org; Mon, 26 Feb 2007 12:48:14 -0700 (MST) Date: Mon, 26 Feb 2007 13:48:10 -0600 From: Robert Gordon Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-reply-to: <754187.14787.qm@web31814.mail.mud.yahoo.com> To: NFSv4 Message-id: <1CD8D53A-6929-4C43-BA8A-5389F67BB82B@Sun.COM> MIME-version: 1.0 X-Mailer: Apple Mail (2.752.3) Content-type: text/plain; format=flowed; charset=US-ASCII Content-transfer-encoding: 7BIT References: <754187.14787.qm@web31814.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: cab78e1e39c4b328567edb48482b6a69 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org I think it should be, and had assumed it would be OPTIONAL. Robert. On Feb 26, 2007, at 1:19 PM, Mike Eisler wrote: > > --- "Talpey, Thomas" wrote: > >>> The man page, >>> http://www.opengroup.org/onlinepubs/007908799/xcu/renice.html >>> for re-nice is very interesting in that it doesn't say anything >>> about how the operating system is supposed to implement it. >> >> I would make the observation that process schduling is very different >> from NFS request scheduling. NFS requests are in effect >> run-to-completion. > > Implementors with thread-based repliers running on pre-emptive > kernels would disagree. One obvious implementation of priorities on > such kernels would be assign the priority based on the sessionid > priority and/or the per-SEQUENCE priority. > > Event-driven implementations apparently have less obvious > implementations, but since I think event-driven can be mapped > 1-1 to threads, the obvious implementation can happen there too. > >> As such, I don't see the server as having very many options when a >> new >> request arrives, no matter what its priority. The request is by its >> very >> nature eligible to run at its arrival. >> >> For the server to handle the request otherwise, it would have to >> begin processing the COMPOUND up to the point of decoding the >> OP_SEQUENCE, then make a decision to either defer or continue >> the processing. This, to me, seems very unnatural and certainly >> inefficient. I would like to see the MUSTs SHOULDs and MAYs for >> the server's end before committing to this proposal. > > I think it is all OPTIONAL. >> >> Tom. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Mon Feb 26 17:01:47 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLntp-0001wf-Vk; Mon, 26 Feb 2007 17:00:49 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLnto-0001wB-L0 for nfsv4@ietf.org; Mon, 26 Feb 2007 17:00:48 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLk6W-0001vi-0m for nfsv4@ietf.org; Mon, 26 Feb 2007 12:57:41 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 26 Feb 2007 09:57:39 -0800 X-IronPort-AV: i="4.14,221,1170662400"; d="scan'208"; a="36505679:sNHT43652651" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1QHvYdS010437; Mon, 26 Feb 2007 09:57:35 -0800 (PST) Received: from exsvlrb01.hq.netapp.com ([10.56.8.62]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Mon, 26 Feb 2007 09:57:34 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Mon, 26 Feb 2007 09:58:41 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] SET_PRIORITY: new op proposal Date: Mon, 26 Feb 2007 12:58:40 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] SET_PRIORITY: new op proposal Thread-Index: AcdZzWQslMGVuzngTKme1JEv3SI+yAAAaRMA From: "Noveck, Dave" To: "Talpey, Thomas" , , "Halevy, Benny" , "Robert Gordon" X-OriginalArrivalTime: 26 Feb 2007 17:58:41.0513 (UTC) FILETIME=[BFD92590:01C759CF] X-Spam-Score: 0.0 (/) X-Scan-Signature: 73734d43604d52d23b3eba644a169745 Cc: chuck.lever@oracle.com, "Welch, Brent" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org As I understand the proposal, there are no requirements per se. This is a case of the client proposes and the server disposes. While there may be valid objections to leaving things so loose, anything that imposes strict requirements seems like it will add to implementation complexity and complicate the specification process. I think there would have to be a strong case made to justify inclusion of such a feature at this stage in the=20 development of v4.1. =20 -----Original Message----- From: Talpey, Thomas=20 Sent: Monday, February 26, 2007 12:39 PM To: email2mre-ietf@yahoo.com; Halevy, Benny; Robert Gordon Cc: chuck.lever@oracle.com; Welch, Brent; nfsv4@ietf.org Subject: Re: [nfsv4] SET_PRIORITY: new op proposal But, what does the server actually do with the priority? Normally, any operation is eligible once received at the server, does this mean the server is required to implement strict queuing within the session, and if so does it mean that it will need to delay the processing of requests which are otherwise ready? If not, then what does it actually do? Benny's text documents the field, but doesn't describe the server's requirements. Call me confused, perhaps... Tom. At 12:21 PM 2/26/2007, Robert Gordon wrote: > >exactly what i was thinking.. > >Robert. >On Feb 26, 2007, at 7:35 AM, Mike Eisler wrote: > >> If we were talking about NFSv4.2, SET_PRIORITY would be a natural >> way to add this operation. >> >> Since we are still working on NFSv4.1, we have an opportunity >> to add this to "existing" NFSv4.1 core infrastructure. >> >> My counter proposal is: >> >> - add a priority field to CREATE_SESSION arguments (which the server >> can >> confirm as it does various other session values). The priority is >> relative to other sessions, and represents the priority the server >> and client will take when servicing the fore and back channels of >> the session. For completeness, there can be separate fore and back >> channel priorities. >> >> - add a priority field to SEQUENCE and CB_SEQUENCE arguments >> and results. The priority represents priority of the >> COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs >> executed on the session. >> >> - There is no way to update the session's priority once the session is >> created. Just as there is no way to update the maximum request size. >> Maybe, someday, we'll need such capabilities, but a general purpose >> operation to updated session and channel attributes should be added. >> Thus far, I haven't seen a clamor for that. In the mean time, just >> create another session, and gracefully destroy the old session once >> replies for all outstanding COMPOUNDs have been received. >> >> _______________________________________________ >> nfsv4 mailing list >> nfsv4@ietf.org >> https://www1.ietf.org/mailman/listinfo/nfsv4 > > >_______________________________________________ >nfsv4 mailing list >nfsv4@ietf.org >https://www1.ietf.org/mailman/listinfo/nfsv4 > > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 03:23:37 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLxbe-00065w-PP; Tue, 27 Feb 2007 03:22:42 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLxbd-00065i-7Y for nfsv4@ietf.org; Tue, 27 Feb 2007 03:22:41 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLxbY-0008Rk-U2 for nfsv4@ietf.org; Tue, 27 Feb 2007 03:22:41 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1R8MaBH023339; Tue, 27 Feb 2007 03:22:36 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 27 Feb 2007 03:22:36 -0500 Received: from [192.168.0.140] ([172.17.19.38]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 27 Feb 2007 03:22:35 -0500 Message-ID: <45E3EA4A.4020707@panasas.com> Date: Tue, 27 Feb 2007 10:22:34 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: email2mre-ietf@yahoo.com, "Talpey, Thomas" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: <754187.14787.qm@web31814.mail.mud.yahoo.com> In-Reply-To: <754187.14787.qm@web31814.mail.mud.yahoo.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 27 Feb 2007 08:22:36.0152 (UTC) FILETIME=[6FB35F80:01C75A48] X-Spam-Score: 0.0 (/) X-Scan-Signature: f4c2cf0bccc868e4cc88dace71fb3f44 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Mike Eisler wrote: > --- "Talpey, Thomas" wrote: > >>> The man page, >>> http://www.opengroup.org/onlinepubs/007908799/xcu/renice.html >>> for re-nice is very interesting in that it doesn't say anything >>> about how the operating system is supposed to implement it. >> I would make the observation that process schduling is very different >> from NFS request scheduling. NFS requests are in effect >> run-to-completion. > > Implementors with thread-based repliers running on pre-emptive > kernels would disagree. One obvious implementation of priorities on > such kernels would be assign the priority based on the sessionid > priority and/or the per-SEQUENCE priority. > > Event-driven implementations apparently have less obvious > implementations, but since I think event-driven can be mapped > 1-1 to threads, the obvious implementation can happen there too. In either case, the priority can also be applied for I/O scheduling at the disk driver queue level. > >> As such, I don't see the server as having very many options when a >> new >> request arrives, no matter what its priority. The request is by its >> very >> nature eligible to run at its arrival. >> >> For the server to handle the request otherwise, it would have to >> begin processing the COMPOUND up to the point of decoding the >> OP_SEQUENCE, then make a decision to either defer or continue >> the processing. This, to me, seems very unnatural and certainly >> inefficient. I would like to see the MUSTs SHOULDs and MAYs for >> the server's end before committing to this proposal. > > I think it is all OPTIONAL. Right. My intent was to leave this open to the server since this is highly dependent on the server's architecture and implementation. The clients can only express the relative importance of their requests. If you want a stricter definition of the server MUST, SHOULD, or MAY do, I think you're going in the direction of strictly defining many more QoS parameters, not just priority. The only thing I left in the proposal is defining the "direction" so that higher priority_level values mean "more important" stuff to do. >> Tom. >> >> > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 03:51:05 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLy2y-0002sM-1X; Tue, 27 Feb 2007 03:50:56 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HLy2w-0002s6-F6 for nfsv4@ietf.org; Tue, 27 Feb 2007 03:50:54 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HLy2v-0002jY-3Y for nfsv4@ietf.org; Tue, 27 Feb 2007 03:50:54 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1R8op6C024140; Tue, 27 Feb 2007 03:50:51 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 27 Feb 2007 03:50:51 -0500 Received: from [192.168.0.140] ([172.17.19.38]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 27 Feb 2007 03:50:51 -0500 Message-ID: <45E3F0E9.3060708@panasas.com> Date: Tue, 27 Feb 2007 10:50:49 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: "Noveck, Dave" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 27 Feb 2007 08:50:51.0544 (UTC) FILETIME=[623BA980:01C75A4C] X-Spam-Score: 0.0 (/) X-Scan-Signature: 37af5f8fbf6f013c5b771388e24b09e7 Cc: email2mre-ietf@yahoo.com, "Talpey, Thomas" , Robert Gordon , "Welch, Brent" , nfsv4@ietf.org, chuck.lever@oracle.com X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Noveck, Dave wrote: > As I understand the proposal, there are no requirements per se. > This is a case of the client proposes and the server disposes. > While there may be valid objections to leaving things so loose, > anything that imposes strict requirements seems like it will > add to implementation complexity and complicate the specification > process. agreed. > I think there would have to be a strong case made to > justify inclusion of such a feature at this stage in the > development of v4.1. I can't speak for application vendors but I can provide several possible use cases: * namespace related: - per volume: /production vs. /home - per subtree: /home/sales/* vs. /home/dev/* - per file type: *.tbl (standing for a database table) vs. *.mp3 * operation type: - better response time for GETATTRs and READDIRs vs. READ/WRITE (and from a workstation vs. from an application server). - lower priority for client readahead READs. - higher priority for WRITEs and COMMITs when client is under low memory pressure. * deployment: - clients with different priorities: app servers in the data center vs. user workstations. - hosting farm SLAs (over shared storage ;-). - job scheduling in a cluster of clients (compute farm) - just translating the process nice priority into NFS I/O priority. Benny > > -----Original Message----- > From: Talpey, Thomas > Sent: Monday, February 26, 2007 12:39 PM > To: email2mre-ietf@yahoo.com; Halevy, Benny; Robert Gordon > Cc: chuck.lever@oracle.com; Welch, Brent; nfsv4@ietf.org > Subject: Re: [nfsv4] SET_PRIORITY: new op proposal > > > But, what does the server actually do with the priority? Normally, any > operation is eligible once received at the server, does this mean the > server is required to implement strict queuing within the session, and > if so does it mean that it will need to delay the processing of requests > which are otherwise ready? If not, then what does it actually do? > Benny's > text documents the field, but doesn't describe the server's > requirements. > > Call me confused, perhaps... > > Tom. > > At 12:21 PM 2/26/2007, Robert Gordon wrote: >> exactly what i was thinking.. >> >> Robert. >> On Feb 26, 2007, at 7:35 AM, Mike Eisler wrote: >> >>> If we were talking about NFSv4.2, SET_PRIORITY would be a natural >>> way to add this operation. >>> >>> Since we are still working on NFSv4.1, we have an opportunity >>> to add this to "existing" NFSv4.1 core infrastructure. >>> >>> My counter proposal is: >>> >>> - add a priority field to CREATE_SESSION arguments (which the server >>> can >>> confirm as it does various other session values). The priority is >>> relative to other sessions, and represents the priority the server >>> and client will take when servicing the fore and back channels of >>> the session. For completeness, there can be separate fore and back >>> channel priorities. >>> >>> - add a priority field to SEQUENCE and CB_SEQUENCE arguments >>> and results. The priority represents priority of the >>> COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs >>> executed on the session. >>> >>> - There is no way to update the session's priority once the session > is >>> created. Just as there is no way to update the maximum request > size. >>> Maybe, someday, we'll need such capabilities, but a general purpose >>> operation to updated session and channel attributes should be > added. >>> Thus far, I haven't seen a clamor for that. In the mean time, just >>> create another session, and gracefully destroy the old session once >>> replies for all outstanding COMPOUNDs have been received. >>> >>> _______________________________________________ >>> nfsv4 mailing list >>> nfsv4@ietf.org >>> https://www1.ietf.org/mailman/listinfo/nfsv4 >> >> _______________________________________________ >> nfsv4 mailing list >> nfsv4@ietf.org >> https://www1.ietf.org/mailman/listinfo/nfsv4 >> >> > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 09:31:27 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM3LV-0004ak-Fo; Tue, 27 Feb 2007 09:30:25 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM3LU-0004Yb-GD for nfsv4@ietf.org; Tue, 27 Feb 2007 09:30:24 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HM3LR-0005CF-Vn for nfsv4@ietf.org; Tue, 27 Feb 2007 09:30:24 -0500 Received: from smtp2.corp.netapp.com ([10.57.159.114]) by mx2.netapp.com with ESMTP; 27 Feb 2007 06:30:21 -0800 X-IronPort-AV: i="4.14,226,1170662400"; d="scan'208"; a="36766079:sNHT87484908" Received: from svlexc02.hq.netapp.com (svlexc02.corp.netapp.com [10.57.157.136]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1REU4GW028286; Tue, 27 Feb 2007 06:30:16 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc02.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Tue, 27 Feb 2007 06:31:11 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Tue, 27 Feb 2007 06:31:10 -0800 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] SET_PRIORITY: new op proposal Date: Tue, 27 Feb 2007 09:31:08 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] SET_PRIORITY: new op proposal Thread-Index: AcdaTJPlPDA++x9+SMSm6+cWDkTKQgALneOw From: "Noveck, Dave" To: "Benny Halevy" X-OriginalArrivalTime: 27 Feb 2007 14:31:10.0368 (UTC) FILETIME=[ECCCF200:01C75A7B] X-Spam-Score: 0.0 (/) X-Scan-Signature: 8f374d0786b25a451ef87d82c076f593 Cc: email2mre-ietf@yahoo.com, "Talpey, Thomas" , Robert Gordon , "Welch, Brent" , nfsv4@ietf.org, chuck.lever@oracle.com X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Just to clarify here, when I said, > I think there would have to be a strong case made to justify inclusion > of such a feature at this stage in the development of v4.1.=20 I was referring back to "anything that imposes strict requirements". For something that is loose on implementation requirements, as I=20 think we agree this is, the justification threshold would be much lower. I believe that including this functionality in v4.1, in the form that Mike proposed is quite reasonable. -----Original Message----- From: Benny Halevy [mailto:bhalevy@panasas.com]=20 Sent: Tuesday, February 27, 2007 3:51 AM To: Noveck, Dave Cc: Talpey, Thomas; email2mre-ietf@yahoo.com; Robert Gordon; chuck.lever@oracle.com; Welch, Brent; nfsv4@ietf.org Subject: Re: [nfsv4] SET_PRIORITY: new op proposal Noveck, Dave wrote: > As I understand the proposal, there are no requirements per se. > This is a case of the client proposes and the server disposes. > While there may be valid objections to leaving things so loose,=20 > anything that imposes strict requirements seems like it will add to=20 > implementation complexity and complicate the specification process. agreed. > I think there would have to be a strong case made to justify inclusion > of such a feature at this stage in the development of v4.1. I can't speak for application vendors but I can provide several possible use cases: * namespace related: - per volume: /production vs. /home - per subtree: /home/sales/* vs. /home/dev/* - per file type: *.tbl (standing for a database table) vs. *.mp3 * operation type: - better response time for GETATTRs and READDIRs vs. READ/WRITE (and from a workstation vs. from an application server). - lower priority for client readahead READs. - higher priority for WRITEs and COMMITs when client is under low memory pressure. * deployment: - clients with different priorities: app servers in the data center vs. user workstations. - hosting farm SLAs (over shared storage ;-). - job scheduling in a cluster of clients (compute farm) - just translating the process nice priority into NFS I/O priority. Benny >=20 > -----Original Message----- > From: Talpey, Thomas > Sent: Monday, February 26, 2007 12:39 PM > To: email2mre-ietf@yahoo.com; Halevy, Benny; Robert Gordon > Cc: chuck.lever@oracle.com; Welch, Brent; nfsv4@ietf.org > Subject: Re: [nfsv4] SET_PRIORITY: new op proposal >=20 >=20 > But, what does the server actually do with the priority? Normally, any > operation is eligible once received at the server, does this mean the=20 > server is required to implement strict queuing within the session, and > if so does it mean that it will need to delay the processing of=20 > requests which are otherwise ready? If not, then what does it actually do? > Benny's > text documents the field, but doesn't describe the server's=20 > requirements. >=20 > Call me confused, perhaps... >=20 > Tom. >=20 > At 12:21 PM 2/26/2007, Robert Gordon wrote: >> exactly what i was thinking.. >> >> Robert. >> On Feb 26, 2007, at 7:35 AM, Mike Eisler wrote: >> >>> If we were talking about NFSv4.2, SET_PRIORITY would be a natural=20 >>> way to add this operation. >>> >>> Since we are still working on NFSv4.1, we have an opportunity to add >>> this to "existing" NFSv4.1 core infrastructure. >>> >>> My counter proposal is: >>> >>> - add a priority field to CREATE_SESSION arguments (which the server >>> can >>> confirm as it does various other session values). The priority is >>> relative to other sessions, and represents the priority the server >>> and client will take when servicing the fore and back channels of >>> the session. For completeness, there can be separate fore and back >>> channel priorities. >>> >>> - add a priority field to SEQUENCE and CB_SEQUENCE arguments >>> and results. The priority represents priority of the >>> COMPOUND/CB_COMPOUND relative to other COMPOUNDs/CB_COMPOUNDs >>> executed on the session. >>> >>> - There is no way to update the session's priority once the session > is >>> created. Just as there is no way to update the maximum request > size. >>> Maybe, someday, we'll need such capabilities, but a general purpose >>> operation to updated session and channel attributes should be > added. >>> Thus far, I haven't seen a clamor for that. In the mean time, just >>> create another session, and gracefully destroy the old session once >>> replies for all outstanding COMPOUNDs have been received. >>> >>> _______________________________________________ >>> nfsv4 mailing list >>> nfsv4@ietf.org >>> https://www1.ietf.org/mailman/listinfo/nfsv4 >> >> _______________________________________________ >> nfsv4 mailing list >> nfsv4@ietf.org >> https://www1.ietf.org/mailman/listinfo/nfsv4 >> >> >=20 >=20 > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 13:16:24 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM6rQ-0001E9-Ea; Tue, 27 Feb 2007 13:15:36 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM6rP-0001DT-TH for nfsv4@ietf.org; Tue, 27 Feb 2007 13:15:35 -0500 Received: from mailms.chase.com ([170.148.48.205] helo=sb7.jpmchase.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HM6rO-0007yi-KE for nfsv4@ietf.org; Tue, 27 Feb 2007 13:15:35 -0500 Received: from se6.svr.bankone.net (se6.svr.bankone.net [155.180.234.127]) by sb7.jpmchase.com (Switch-3.1.8/Switch-3.1.7) with ESMTP id l1RIQJ5o000823 (version=TLSv1/SSLv3 cipher=EDH-RSA-DES-CBC3-SHA bits=168 verify=FAIL) for ; Tue, 27 Feb 2007 13:26:19 -0500 Received: from svr.bankone.net (imj3.svr.bankone.net [155.180.50.146]) by se6.svr.bankone.net (Switch-3.1.8/Switch-3.1.7) with ESMTP id l1RIFWD5014919 for ; Tue, 27 Feb 2007 13:15:32 -0500 Received: from ([10.31.58.37]) by imj3.svr.bankone.net with ESMTP id KP-BRBHL.18696493; Tue, 27 Feb 2007 12:15:17 -0600 To: Lisa.Week@Sun.COM, eshel@almaden.ibm.com MIME-Version: 1.0 X-Mailer: Lotus Notes Release 6.5.4 CCH5 September 12, 2005 Message-ID: From: david.f.gutierrez@jpmchase.com Date: Tue, 27 Feb 2007 12:15:14 -0600 X-MIMETrack: Serialize by Router on SMAIL122/JPMCHASE(Release 6.5.4FP1|June 19, 2005) at 02/27/2007 12:15:17 PM, Serialize complete at 02/27/2007 12:15:17 PM X-Spam-Score: 0.7 (/) X-Scan-Signature: 4b800b1eab964a31702fa68f1ff0e955 Cc: nfsv4@ietf.org Subject: [nfsv4] Bakeathon. X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: multipart/mixed; boundary="===============0438140265==" Errors-To: nfsv4-bounces@ietf.org This is a multipart message in MIME format. --===============0438140265== Content-Type: multipart/alternative; boundary="=_alternative 006445A38625728F_=" This is a multipart message in MIME format. --=_alternative 006445A38625728F_= Content-Type: text/plain; charset="US-ASCII" Everyone, Any update on the latest bakeathon? Have we agreed on a specific date and time. Kind Regards, David F. Gutierrez JP Morgan Unix Engineering ----------------------------------------- This transmission may contain information that is privileged, confidential, legally privileged, and/or exempt from disclosure under applicable law. If you are not the intended recipient, you are hereby notified that any disclosure, copying, distribution, or use of the information contained herein (including any reliance thereon) is STRICTLY PROHIBITED. Although this transmission and any attachments are believed to be free of any virus or other defect that might affect any computer system into which it is received and opened, it is the responsibility of the recipient to ensure that it is virus free and no responsibility is accepted by JPMorgan Chase & Co., its subsidiaries and affiliates, as applicable, for any loss or damage arising in any way from its use. If you received this transmission in error, please immediately contact the sender and destroy the material in its entirety, whether in electronic or hard copy format. Thank you. --=_alternative 006445A38625728F_= Content-Type: text/html; charset="US-ASCII"
Everyone,
Any update on the latest bakeathon? Have we agreed on a specific date and time.

Kind Regards,

David F. Gutierrez
JP Morgan Unix Engineering



This transmission may contain information that is privileged,
confidential, legally privileged, and/or exempt from disclosure
under applicable law. If you are not the intended recipient, you
are hereby notified that any disclosure, copying, distribution, or
use of the information contained herein (including any reliance
thereon) is STRICTLY PROHIBITED. Although this transmission and
any attachments are believed to be free of any virus or other
defect that might affect any computer system into which it is
received and opened, it is the responsibility of the recipient to
ensure that it is virus free and no responsibility is accepted by
JPMorgan Chase & Co., its subsidiaries and affiliates, as
applicable, for any loss or damage arising in any way from its use.
If you received this transmission in error, please immediately
contact the sender and destroy the material in its entirety,
whether in electronic or hard copy format. Thank you.

--=_alternative 006445A38625728F_=-- --===============0438140265== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 --===============0438140265==-- From nfsv4-bounces@ietf.org Tue Feb 27 13:34:53 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM79x-0005ZC-KF; Tue, 27 Feb 2007 13:34:45 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM79v-0005Yf-BC for nfsv4@ietf.org; Tue, 27 Feb 2007 13:34:43 -0500 Received: from brmea-mail-4.sun.com ([192.18.98.36]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HM79s-0001rg-H7 for nfsv4@ietf.org; Tue, 27 Feb 2007 13:34:43 -0500 Received: from fe-amer-01.sun.com ([192.18.108.175]) by brmea-mail-4.sun.com (8.13.6+Sun/8.12.9) with ESMTP id l1RIYeRb026474 for ; Tue, 27 Feb 2007 18:34:40 GMT Received: from conversion-daemon.mail-amer.sun.com by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) id <0JE400601WTROT00@mail-amer.sun.com> (original mail from Lisa.Week@Sun.COM) for nfsv4@ietf.org; Tue, 27 Feb 2007 11:34:39 -0700 (MST) Received: from [172.20.25.77] by mail-amer.sun.com (Sun Java System Messaging Server 6.2-6.01 (built Apr 3 2006)) with ESMTPSA id <0JE400G6AWXRUDU3@mail-amer.sun.com>; Tue, 27 Feb 2007 11:34:39 -0700 (MST) Date: Tue, 27 Feb 2007 11:34:13 -0700 From: Lisa Week In-reply-to: To: david.f.gutierrez@jpmchase.com Message-id: <45E479A5.6010905@sun.com> MIME-version: 1.0 Content-type: text/plain; format=flowed; charset=ISO-8859-1 Content-transfer-encoding: 7BIT References: User-Agent: Thunderbird 1.5.0.8 (X11/20061204) X-Spam-Score: 0.0 (/) X-Scan-Signature: e1e48a527f609d1be2bc8d8a70eb76cb Cc: eshel@almaden.ibm.com, nfsv4@ietf.org Subject: [nfsv4] Re: Bakeathon. X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Hi David, In tallying up the responses, it looks like the following date is the winner: June 11-15, 2007 We will move forward with that date for the NFSv4.1 Bakeathon. I will send out more information on this shortly. Thanks, Lisa david.f.gutierrez@jpmchase.com wrote: > > Everyone, > Any update on the latest bakeathon? Have we agreed on a specific date > and time. > > Kind Regards, > > David F. Gutierrez > JP Morgan Unix Engineering > ------------------------------------------------------------------------ > > > This transmission may contain information that is privileged, > confidential, legally privileged, and/or exempt from disclosure > under applicable law. If you are not the intended recipient, you > are hereby notified that any disclosure, copying, distribution, or > use of the information contained herein (including any reliance > thereon) is STRICTLY PROHIBITED. Although this transmission and > any attachments are believed to be free of any virus or other > defect that might affect any computer system into which it is > received and opened, it is the responsibility of the recipient to > ensure that it is virus free and no responsibility is accepted by > JPMorgan Chase & Co., its subsidiaries and affiliates, as > applicable, for any loss or damage arising in any way from its use. > If you received this transmission in error, please immediately > contact the sender and destroy the material in its entirety, > whether in electronic or hard copy format. Thank you. > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 14:48:10 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8Ie-0007MC-7D; Tue, 27 Feb 2007 14:47:48 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8Id-0007M4-93 for nfsv4@ietf.org; Tue, 27 Feb 2007 14:47:47 -0500 Received: from citi.umich.edu ([141.211.133.111]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HM8Ic-0007sV-2d for nfsv4@ietf.org; Tue, 27 Feb 2007 14:47:47 -0500 Received: by citi.umich.edu (Postfix, from userid 103558) id A7F8939690; Tue, 27 Feb 2007 14:47:45 -0500 (EST) Received: from localhost (localhost [127.0.0.1]) by citi.umich.edu (Postfix) with ESMTP id A5C9B3968F for ; Tue, 27 Feb 2007 14:47:45 -0500 (EST) Date: Tue, 27 Feb 2007 14:47:45 -0500 (EST) From: Fredric Isaman To: nfsv4@ietf.org Subject: [nfsv4] nfsv41.x naming inconsistency Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Spam-Score: 0.2 (/) X-Scan-Signature: 9466e0365fc95844abaf7c3f15a05c7d X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org nfsv41.x has very consistent naming conventions, which are quite useful for auto-code generation. However, I came across an apparent oversight within the definitions of nfs_argop4 and nfs_resop4. I suppose it is best explained with this suggested patch. Fred --- --- nfsv41.x 2007-02-27 13:46:35.000000000 -0500 +++ new_nfsv41.x 2007-02-27 13:48:17.000000000 -0500 @@ -2248,7 +2248,7 @@ /* Operations new to NFSv4.1 */ case OP_BACKCHANNEL_CTL: BACKCHANNEL_CTL4args opbackchannel_ctl; case OP_BIND_CONN_TO_SESSION: BIND_CONN_TO_SESSION4args opbind_conn_to_session; - case OP_EXCHANGE_ID: EXCHANGE_ID4args opcreate_clientid; + case OP_EXCHANGE_ID: EXCHANGE_ID4args opexchange_id; case OP_CREATE_SESSION: CREATE_SESSION4args opcreate_session; case OP_DESTROY_SESSION: DESTROY_SESSION4args opdestroy_session; case OP_FREE_STATEID: FREE_STATEID4args opfree_stateid; @@ -2309,7 +2309,7 @@ /* Operations new to NFSv4.1 */ case OP_BACKCHANNEL_CTL: BACKCHANNEL_CTL4res opbackchannel_ctl; case OP_BIND_CONN_TO_SESSION: BIND_CONN_TO_SESSION4res opbind_conn_to_session; - case OP_EXCHANGE_ID: EXCHANGE_ID4res opcreate_clientid; + case OP_EXCHANGE_ID: EXCHANGE_ID4res opexchange_id; case OP_CREATE_SESSION: CREATE_SESSION4res opcreate_session; case OP_DESTROY_SESSION: DESTROY_SESSION4res opdestroy_session; case OP_FREE_STATEID: FREE_STATEID4res opfree_stateid; _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 15:01:21 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8Vh-0000XW-00; Tue, 27 Feb 2007 15:01:17 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8Vf-0000XQ-LR for nfsv4@ietf.org; Tue, 27 Feb 2007 15:01:15 -0500 Received: from citi.umich.edu ([141.211.133.111]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HM8Ve-0001BU-FV for nfsv4@ietf.org; Tue, 27 Feb 2007 15:01:15 -0500 Received: by citi.umich.edu (Postfix, from userid 103558) id 3C424393BC; Tue, 27 Feb 2007 15:01:14 -0500 (EST) Received: from localhost (localhost [127.0.0.1]) by citi.umich.edu (Postfix) with ESMTP id 39CA33920C for ; Tue, 27 Feb 2007 15:01:14 -0500 (EST) Date: Tue, 27 Feb 2007 15:01:14 -0500 (EST) From: Fredric Isaman To: nfsv4@ietf.org Subject: [nfsv4] Question about maxrequestsize Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Spam-Score: 0.0 (/) X-Scan-Signature: 30ac594df0e66ffa5a93eb4c48bcb014 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org In section 16.36.5 of nfsv4.1-draft08.txt discussing CREATE_SESSION, it talks about maxrequestsize and maxresponsesize. In particular, it states that RPC header size must be included, presumably so that we are discussing actual over-the-wire sizes. But in that case, are we meant to calculate header_size + xdr_encoded_response, or the actual over-the-wire sizes, which are affected by GSS wrapping? Fred _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 15:19:12 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8mr-0003IS-1K; Tue, 27 Feb 2007 15:19:01 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8mp-0003I6-H9 for nfsv4@ietf.org; Tue, 27 Feb 2007 15:18:59 -0500 Received: from web31804.mail.mud.yahoo.com ([68.142.207.67]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HM8mo-0002ze-4y for nfsv4@ietf.org; Tue, 27 Feb 2007 15:18:59 -0500 Received: (qmail 10452 invoked by uid 60001); 27 Feb 2007 20:18:57 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=a2CnHKUDMrmn4tzqX26ve4gng13L1GXCVOkcpwnAokOL+rHCNjwtZyTPYmOyrmkWAXpnjuu/ZY1rcuUse2fUtcV07y7SmeX23aj80jaFpQUnV08akhpm/zJk+JyGWHCSMPwiXjzX7dRKvt1M+gmt00Rln5TFouiE56bIviVCWyw=; X-YMail-OSG: 1CsoXVkVM1luAZoe80Zh1D1TVImBuefJ0TLOdbwwkmw_QB59TXThg9x7zsSu3JgHD6tZVrKyaKdOLWTlGkosLT6dB7nJ.l5YT1Ytzc3W.tNOrjhge7gAF0n3rxGKE3BFw1kZTHM- Received: from [198.95.226.224] by web31804.mail.mud.yahoo.com via HTTP; Tue, 27 Feb 2007 12:18:57 PST Date: Tue, 27 Feb 2007 12:18:57 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] nfsv41.x naming inconsistency To: Fredric Isaman , nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <563295.9634.qm@web31804.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 7a6398bf8aaeabc7a7bb696b6b0a2aad Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- Fredric Isaman wrote: > nfsv41.x has very consistent naming conventions, which are quite > useful > for auto-code generation. However, I came across an apparent > oversight > within the definitions of nfs_argop4 and nfs_resop4. I suppose it is > best > explained with this suggested patch. Thanks. This will be fixed in draft-09. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 15:21:56 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8pc-0005pb-EJ; Tue, 27 Feb 2007 15:21:52 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HM8pb-0005o7-3Q for nfsv4@ietf.org; Tue, 27 Feb 2007 15:21:51 -0500 Received: from web31809.mail.mud.yahoo.com ([68.142.207.72]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HM8pY-0003Di-Of for nfsv4@ietf.org; Tue, 27 Feb 2007 15:21:51 -0500 Received: (qmail 15240 invoked by uid 60001); 27 Feb 2007 20:21:48 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=fDDAA03rkYFxZotppQKc5CxIaOmsMzY8nSbi5HmqLILqAWsVo02VMgsjCvWJGxCij0Kl14AeV4r52nZGJdhS8OmX63pHAYOjKarA6fqDnmSCCSK3RXltU0L7mc0K1NEjLUHuGVRm6voYMFoBKBWbSUIFqG1VfM8h7hqqNiCPkNs=; X-YMail-OSG: Ux164VEVM1lSr0CT9aRg3jN_uJPWsjtFb23y1bNYQo_zVnzF6YXfSLyumUJlxhp.4e56.Nf.3w05XaRQ0DsYNFHsuL79Vsdwd5Y6C2Tnl6.rErxKVaIcMfTWg2WJ7n.1DNrUIfHyBLhClaw- Received: from [198.95.226.224] by web31809.mail.mud.yahoo.com via HTTP; Tue, 27 Feb 2007 12:21:48 PST Date: Tue, 27 Feb 2007 12:21:48 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] Question about maxrequestsize To: Fredric Isaman , nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <143916.15147.qm@web31809.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: e5ba305d0e64821bf3d8bc5d3bb07228 Cc: X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- Fredric Isaman wrote: > In section 16.36.5 of nfsv4.1-draft08.txt discussing CREATE_SESSION, > it > talks about maxrequestsize and maxresponsesize. In particular, it > states > that RPC header size must be included, presumably so that we are > discussing actual over-the-wire sizes. But in that case, are we meant > to > calculate header_size + xdr_encoded_response, or the actual > over-the-wire > sizes, which are affected by GSS wrapping? You are meant to calculate the actual over-the-wire sizes. Imagine a request or response with a single Record Marking header. The length encoded there must be less than or equal to the maxrequestsize or maxresponsesize. I will clarify in the draft-09. > > Fred > > > _______________________________________________ > nfsv4 mailing list > nfsv4@ietf.org > https://www1.ietf.org/mailman/listinfo/nfsv4 > _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From fabioDivinec@cole-n-co.co.nz Tue Feb 27 20:46:49 2007 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMDu5-0003sL-4X for nfsv4-archive@lists.ietf.org; Tue, 27 Feb 2007 20:46:49 -0500 Received: from [211.193.74.36] (helo=[211.193.74.36]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMDu0-0005Q4-5g for nfsv4-archive@lists.ietf.org; Tue, 27 Feb 2007 20:46:49 -0500 Received: from [111.139.195.91] (port=19326 helo=[111.139.195.91]) by with esmtp id 1vxRaC-000ZUI-38 for nfsv4-archive@lists.ietf.org; Wed, 28 Feb 2007 10:46:48 +0900 Message-ID: <001101c75ada$45638970$00000000@dd> From: "fabio Divinec" To: nfsv4-archive@lists.ietf.org Subject: positional parameter rather template Date: Wed, 28 Feb 2007 10:46:31 +0900 MIME-Version: 1.0 Content-Type: multipart/related; type="multipart/alternative"; boundary="----=_NextPart_000_000D_01C75B25.B54B3170" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2180 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2180 X-Antivirus: avast! (VPS 000718-0, 27/02/2007), Outbound message X-Antivirus-Status: Clean X-Spam-Score: 3.4 (+++) X-Scan-Signature: 65215b440f7ab00ca9514de4a7a89926 ------=_NextPart_000_000D_01C75B25.B54B3170 Content-Type: multipart/alternative; boundary="----=_NextPart_001_000E_01C75B25.B54B3170" ------=_NextPart_001_000E_01C75B25.B54B3170 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Thomas, willemeit quiz loft berlinthe newly launched df clooney. Followup program zeros, trouble. Winona ryder drew sidewalks, york. Wife = cream pie babbles squirms. Listedall, surnames tropical cyclones surname useorthe? Picker, = certified fresh submission, linking igncom gamespy comrade arena. Popular liggett, am glesne hasazi sb schattman ra, teaming. Lewis = atlasti popular liggett am glesne hasazi sb. Owen wilson paris hilton = pete, doherty rachel bilson. Surrey preparing tallerico tesch falmer = weaver, avebury. Childs struggles, faced facets parenting flavors spices. Massive, scale = nowhere bit excessive pantyless getups catapulted! Chubby rentals fem dom plump game! ------=_NextPart_001_000E_01C75B25.B54B3170 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
Thomas, willemeit quiz loft berlinthe = newly=20 launched df clooney.
Followup program zeros, trouble. Winona = ryder drew=20 sidewalks, york. Wife cream pie babbles squirms.
Listedall, surnames tropical cyclones = surname=20 useorthe? Picker, certified fresh submission, linking igncom gamespy = comrade arena.
Popular liggett, am glesne hasazi sb = schattman ra,=20 teaming. Lewis atlasti popular liggett am glesne hasazi sb. Owen wilson = paris=20 hilton pete, doherty rachel bilson. Surrey preparing tallerico tesch = falmer=20 weaver, avebury.
Childs struggles, faced facets = parenting flavors=20 spices. Massive, scale nowhere bit excessive pantyless getups = catapulted!
Chubby rentals fem dom plump = game!
3D""
------=_NextPart_001_000E_01C75B25.B54B3170-- ------=_NextPart_000_000D_01C75B25.B54B3170 Content-Type: image/gif; name="Gonzalez.gif" Content-Transfer-Encoding: base64 Content-ID: <000c01c75ada$45638970$00000000@dd> R0lGODlhdAJwAYcAAAAAAH4CAACABHyOAQEAh4MAfAB8fMe4t8DQtaLY8DEbAF8dCowcAKotBscg COMtAAVLCRhKAEc5A1wxBHc9AKozALRLDOg5AwRRAB9oBUJtAGtkAHVrAKRtAMNZAO5sDQB0ACaO DUN/AFx7AHmKAJ56Bbd/BeJ7BgCeDR2rAzqYDWWfAHioAJOpAMOfANqaAAK7BynGBT/JCVu4CobH CabFAM3GAOS7DgblACLrADXmC2XWAHXUAJTmBLXuCuriBQAAPikAQDEBS1EBSn8MS6cCN7kOQdgA SAIhQiwgPU4tO2sfQIAmOpMjNcMdRuEkSQA8RiM5MjhHOWJJO3RNOaVCSrpCP9hJRwdgShNYPEBT SlhsNHpuAKxTPr5kOextOwB8My6EQUSEQGV4OXWFR65xRrV4PO15MgWWPCirTD+uRV+nSXyiQqak QbeRQuikPA29QSvLPjbKOFHMPIu9P6nBTLG6ROrKSgDZOxPsTELjSGjRM47fTajeQcLmQtLkQgIA gCkAezoHjloFh4YAcZgHjrsAgOINewAheiYbekQddWkmin4hgJQqe8ERieQffQxMcxRNhjdLgFM7 jYxKfKhChMkzgeE9fQBZgR9WjUJfe1tmh4FeeqNsgLhic9llgQCCjBl6ikN0hVyFf3KEcZtzh76B eet7gwCeix6rdUKSd1isfHmge5+udbmriNWidQC7exjGfzTMhWa/cYK2dKvKcsO/htW8hgDZjRfu izLielTaiXnei57ZgMPdhO3edQAAvygByjENyWkExX8AvaICy7UAzdkAzAMWtR0ntkcZwFcRw30W tpUds8UTueAkwQg1uiQ/tj8yzl04vYZBu5RHt7xAxNk8tQBhxS1iu0paxVhZvXxmyp1StcBdw+Zi ygt+wxN7ykaIuFOCuolztZGOt7eOx9N3vw6hxxWmvk2VzVSks3iuyaOZyMOuwtiptwDLtS6+zEjB vVS2y4G9zJHKt/T6+ZusnXGNfvkHAAD/BP/wAAAA+P8A/wD///zz/yH5BAD//y0ALAAAAAB0AnAB Bwj/AP8JHEiwoMGDCBMqXMiwocOHECNKnEixosWLGDNq3Mixo8ePIEOKHEmypMmTKFOqXLnQnsuX MGPKnEmzps2bOHPq3Mmzp8+fQIMKHUq0qNGjSJMqXcq0qVOmLKNKnUq1qtWrWLNqTfm0q9evYMOK HUu2rNmzaNOqXcu2rdu3cJdunUu3rt27ePPq3cu3r9+/gPnGHUy4sOHDiA0HXsy4sePHkCNLnkwZ YeLLmDNr3sy5s+fPoEOLHk26tOnTqFP3rMy6tWuQqmPL1vm6NsvZuHPrTmy7t2/Gu4ML//m7uPHj yJM3Hs68ufPn0OEqn069uvXr2LNr3869u8no4MPL//VOfrL48+jTq19vr7x19vDjB0fZ3r19ivLz 65/JVej9/wAGyF1YGA1l0X4IyiTggr65FJWBDEYo4YQjYfagfxUlqOGGHJI1EFIBhChiAC6NCNOF QR3Y4YosztZXTCOKWKKJM5IIU4whvhQjikBRCFiLQLrlkYgE7SiQjDrimKM9StqYZJM18khchkFW aeV8BhE5kJH/aNmll18eGaKYS9aopJk0PknjiFL6pKJqPsZpW1NIommjl2AWhOeeASTUZJlnMhlo jTNxqRKGciYqJ4EfglimoCQuiWSdhZb5ZZ9k+jkmmZtmuuWYMT5ZKZSjrtkmTxddqWppfslEqYyw Sv/6qKuP1kkpjDkW2emlumLKq6d6bhpqqZO+KquTUd6W4kQvUbnqs6BxBKaWoB5r059OYksortnW uuSv4PYa0bRpFguouYOeeepXirYLG1gFQfipr7/iCOxBf96YL6S0dousreciK6qDDZHL57wI27km lNjGaum60EYc25vbVmxknsH2iTHGCP+jr78fD1txyLPWZOzBwKKcJbmQapummWraGybEEtdsk1Ty hsuntSYfm7Gm9Ka866AjxyzyqCTfGfDA4YrL0MZsCtSy0QsPXW3DOJfl7tYcfey1mvVxLDS3PTvZ sc6dquw0mdd6G6nS/+Z4Mk23Nrv2vGlH3XSvSzf/nCtCSuqZtc3oLRY42mPCnOTIVge99sD8Qg7p vWc7ZDC/c5985st0l4xjy3k7jrevUDveOdFNji52R4S3HtNFhxtM75/3llsy5LU33mvRRT+te5gG Ix4o0V97LbfIdcdcOeWA76w6usgf/rzozGrGdV3jwS5z09TSfimpjAeMKccY4zT397ui/7NChxcv aqgAkxor78mvHLTKbDqPLd8X+819qq5rTkLMAjv09S91nOqe/G5Xt4UEz2NHAx23HqI35uXvgv4a 3vHodzuy9StZmQqe3kYYuvFhLU8KnJ2wDFW9AGbvLwTUSOykZ0AiaatsX1Mf/zLGkzpZcIUmJF36 /5x2PIFFrm1GjNzLHJY0gglNhY4r3fq4lEK/Ya1ALozL4MaSEdrtD18y89LUSDZBCnaKg3AD4eq6 t7fVSW5gmXNb8szlvh/eD4hqq6IV8bg9GlLsMtSBCs2eMqQwNi6KQ0yeoLhltjYO8VJvLB4L92Y/ MAaxiBbD5AePyLkjvlFGOkScJUc5PT5WcJDDOYl0UNkU7SXylan74ofqNsfQAW10m+QP8+qFQC/u Co7g+1glxQW6NEpuebmjXgUfKZgsrnIlZ7HIDCdpR0tGUnKnpGSjamnMQ6qtY36cpedmBUobBvFu 1zxZ86iHHMKoEjysbKU0YUnKGiqQb7nUJfdsif+0fILzasqkJxExOTe7UfJy/azJf5z5zEPF0JXT 5NswLaO4MXrSfRhVIs9eJ8XdTQ54v9smA+Vor2zGa1n2mY0AVspSAcSkpTBZ6W7iKUiKdNR3NBRj RivKyaXls2h0LCZGdynCYRHPifhB6fUM0pSWOtWlL3FqVGXqEpa+1KoxhWpuaPrCebJQbGvclydp OU6BBVWC6Rxp3EjEvu01qkd/XI27ggLTqmLVHlK1q1bvOlWt6tWvM6krc7iqFBkyM4EP5BQPGQm2 nhbUg5C9KBIFFle5OmtK7bwJRQSr175SFa+f5WtfPYsTztrkqXv9rG4Ii5QC3u17r0Usn0K2U27/ 7hSHR6ksqnRLm5B4hqUHAe4/niqQu4r2r6BVbU1MSxPUUvW4qM1qXlerLA/Nk6nFXKtEa0gQyY61 g6djC297e1k3KeS3yu1sckGr14EI1yDAFe5Nnjpfvj43vdH9a17te9zBVpeL0qRtdsv4vATSirHR Kq95FXyiq/ykv1i1qoRDm179anUhxD3paJtb4fWSdqrqTS5gA8tfv/Y3wXR5qE3J+bnsmhOBGt4q g3dL0a6EBLgyifB9PczjHDOXw8wlyHuDu9K3hrjHV4Xqj32s2hJLN8mp7fBgHKPiiVStkw1OKnW1 XOWNDNm9RR5umDOMZCjrRMcj3jCQDVrcMItZ/wADnLCUzfxk5IqYzke+c5nb8psuRyRnEsESTSXy 5Te3Gc6HdnOhhexmI9f5xHtWc5IlrSDUOoS+G94vfvlqaKkZd86e6bPWxosTAOoHIj2BKZgR3ek3 K7rR8IV1Qpx7kDxPmsRRPu10S+tURiO612+GcpPlzOpDN2SmorbujMnL5bV8ZyeEhqlgSxxlhSw6 1rQmcrGxreFPp9mz38Y1Z3XM3uQWJMOrdvWTSRLNZeekOH5GtVJb2NqsPNjS6V41qyG9Z27n298I ufZ7r51oUGd62C6VqcI3bVr6nlvWWon3QxDVG4k7hOL0LoxFREttcLfU1zU+cn+NHXCIt5rgrv9G ub57TF9MHxywu7a1Qls1aneXOtkAtrlmWYvxiDi3zgrSt6+37Wn+2prkSOf2x62d7YLDmczqhW6F +V1vqS3YocputmUrXnOt14fdiKGY1NPsdOE6d+EmNrq5W13yfQ+81+guO9HfC3TU8NwopsYs17Pu aA69Kb8iPvvb8e1tXV94yEtP+dDjzvZ/H7soGRfL3SFP6p03qOoVYs/Gdw34wRM90b6WbpT9GmxK czrpmZ/3ny2e+px7Hdo4ZyjmA/3hW3tW6KBfuekNDnto9lzefO9P8FcPV+DIHi0H8vboRT90kKsF i66n/fDfOf2Jq37yx39+RRhed0q7U+dOqbz/PP8refDfbCPsinz2Z796qotG/DV9vVe2WH75M9tj 88f6+hX0e+DzBv/XZ33Vd3Fdp3/1l3HPdnXCFzF5p4DSF30PqHcRyCjm11ULeIB2R37P0oBbp37p V4E0AX8WSHwQSH1Xgn37wYE0Zn+EJIL6xILh54JJwSMlgWy+JzEq2HswyGbdFYACKIETCC8yyH47 SDgoeGpDmGU3CIQk6IBNSIFFOIK+VTNHmB85eH/00X8/6IT+d4AeuH+ApIGrcoXvJoYr+IVlCIIz mIQ9AoZSWINEEYWjQYY3t4RM2IUdGIQfeBduWFhmqIN6CCdsiFQXyIVbmIdPaIhd83UG2Idx//iH WIiHIRhyYSiHL1iIiCiJgBhoJniHcOiIeAeJadiIYaeGQWeHivh4xceHWgh2oEh5qJiJn6iEDMF6 LdGKreeJDkaIWeiDrviKgNaLq7gXtnheuCgSwYiMxziFvpiLwDiMwqiLKVaMA7SMP8KLiXiG0ZiK yviM1vgRlygZ7WaJp8iK0JiNm9iJsjiL3iiNPjKOaCgkg8iI8ViHpJiO6tiO2tgu8IiOmJeMmhiJ ASmQ7LiOv6iPBvmOAxhx30iJCXmL55iP+HiQCPmQE/J9VAGQh7iPA2mP90iQBFiRULhU26GRIemO EImSzKiS1WiDgZiBJGmMr3N5zViLNZmS3P/YkWtoip9Bh6axNSZJGUGJkzkpk+fnEdTYg6k0j5sB lA1JZU8ZYyxpb8/ok6wyV1FpfDfZkhFpjq9olaRRj48IlVsJGUNplFOJFd4Ilj3pjDz4GmcZGXHp kBbJkMDIlmlBkbC4d11ZGXNZa1lZFWvJlPIImAsplIEZGH+JXWVJlXdJmEJIjrkVe3VplokJgH2J PVWpk2NpmGnJmCXoGkf5HtZDcyI5fpL5lv7YgjH5Ihr3GKdJj6BZlFxJm3S5hzwXk9ioipmJmIXj lrT4kh4pnJaXmnuJiRzZmrz5mcuRGlOxmFJpm54pnbM5kttYmRmpmq0BnVrpX+/SmNWJneH/OZEn 6YV/xpQomJ48GZyimX/dOHOxmJzLSZ3RKZ/zWYqcCZLASZ77qZ9EKZ7diXz/aZ/vyZx9B6BKaaAH qh7qGZ/8OaAPWpKjSJzFiZwRWpv0maAZuqDp0aAf6Z9ouaHNyZpiOZoWCqIYiqAcOqEUCk+iOJwS eaG3KaPreaH9uJowmoC9GaIqipkKanXy4aEnyqL5CZ88SoRIWYAtaqRDmqPlKaLcqaGa96IVep0E eqQzuZJVGqM2hp5UaqI4uqUbeaVY+psOiqLgCJ5pihQAEBNtWoU7WqZEqqM/GqVAGqcpOqaCeKZz WpCe0aYwAaiAKhOCOhNvCgB8GoM1upt+/0qj0wmll0l//5eoYiqXOTGoLoGpNqGpmdqpEYmoBQGq 6KekYQqmXOqkT9qjdvqcpUmpTNoYohqrmQoAg9qmtEqrgXqrnDoUnLqrcPqjPiqieFmOJfqqRTqJ rpkZg9Sf4YgQsToQiPqs/wCqokoQ1GoPt/oSumqo2Uqo3sqmDlGtGmGLfsiqeDqjWbqIamoVTdme l4qtgTqtBkGtB0Gtz1qt4qphuiqo22qru9oT//qtxGqlimGawCqketGurqqd9Sqv0Dqrteqpbpqp 1uqwApGvFYuvFiuvtAqt04qrEKutIBuoOhGwrYixNgmTzXSuahmpv4qkNKWp4kqvG+ux0/9Ksvva q7q6sdGasRXrsfdqs9C6rRAbsdjarU1hsox6nxNDc3x5sF8qrFExszfrqYX6rRqLshdrrfCqrV3b qZh6q1tLtc7qszbbs0DrtRIrsiCrtEr7tXXqkkl4H6sqqbhZEmK7tRebr2LrtWE7sbPKs4KrsR/L r7U6sl4LtD+LtnortFrLsdF6uEjLttpnnJ3hpe5Rt2sqXlNhrx07rx0brSL7tbj6t7LZuKjrsGC7 r2BLstjKsTU7r4P7s457sUVrq0fbq2fhr5a7k6lKpujap9qhuY8aalMbunvbszNbuqTbvK47tg1L uLiLu4TarwTDuDVbrRSbtdIqtPDqr7r/O7lA8baV+rvu2buYWx7Eu6TOxhKx+rmFC7qFarrUK7Gw y7dm6zH1C7ch27p+67pq2x6RK7R7q7jdarT8K74UmLd62qWLeroNLLzZgaybKxtTO7Tw67n4GsAA zLwOgr1aS69/a7ocvL8yi7Nfx7jda7O5O78nvLZBQb7Neqy+W6wUzL4zTJkBRBUoK7aM+72j28Fg m7/Zy7UkvLYm3Lr7q7bc27BjS7QjfLQC6xWASrsRrKiWO6wDq5BW6L7JG7sMLLqzCrcvfLSCa8Vo a7VAvKtX67+G2rVZm7EYy7pti7Q7G6zja4ivuahanK7/ccfjCcDPIRXIS7jWGrpJLMjU/6u3yhu7 DhvFNEG9kOzGhFrAqAvC8ou8Z2u7MGymWZy+v2HIEPG4JYu4wqERj5sQ+yq7Z+vBzou1KezI0Ku6 QIzCkYzEtuypBIzJ95u3gHzIn4uEfAzKeDyZHIG/ouzEDTHHKZoeK/wQqXynNYHAgNu8Jmu0s5zN skvGdMy6ikzGbgy7BHzJkDvHYfyxRiHDbTnMClagTojMPgu/rZzByZy6DBHN0jwbprwT+NzM/NzG bxzE9evK3nrGVtyDkwzH4HzECx3LaGzJA5y8IqzB6gwdffyWlxG+ONvDskuzv7yzv8zKzCoebMnG lLvErnvEifzBRCzCHwK+4pvQZazQnf+qzRF9xspLzwy8oudx0Wqh0f97yxNbq/b8yIvryx8NuRzx AR/QhEzNoMscvDghs3aswIdLuvMrsrJMzojKwS3ctgGcxCotwB+ruOO8yoV7r/aazzyhzhWNkWyd W0kB1JQMuN5sxwFNwps8uO+70wLB1IDd1P8Q2IKdEUx9EIT91x+AHv/q0ycdslebrSuNy1VcxCLd 1d9Lx99cy5R8wg9d1qCd03090bJasj85jdVM01IcsJMtyEx810xM2SRLwIet2AZR2IdN2Lgd2Ihd 2ANR24Pd1Lot2In928C92JepsM1W0YbLxgfs2vSrtuL82VvL2dY90+D8yrxrzzft0WH/nMHFayF8 8dGFPM1Y7bwmzb+ZDdYNHcRw+9QuAd8wUdu5Td/CvdvBXdwJUd+3jd/B/d+Avd++Hd6OWp9SiHH9 zNPv6qZ4LbFi3cGCOrtnjZnR7eDZncsKHceMnKQC+i5a4bmP3LGdrNrXrcZBvbqIK9/wrdvxvdgq 7uLIbQ9PfdwD3t/5XRA0btv8rRHAbb5oSuA/Xq8KjKpMy89FC8OS3dnn/bzkbLH3mtLWG9sJPeJ2 C7X+DLwhIc9O/t1SrNoEHbAvLuMxvuIw/hIzzuJhXhPybebE7d/13eO9nd8BHuenyuY5XORBbuCD kdWvjdIjW+HWHMsavuE527/q3Zkf/2rMSekRKhy5jXzIa0vmZS7myH3mdr7mLW7nMwHYNGHpmd7i nA7nBPHmto3jul3q9i3qHqHqq9rqYsHckdzcYe23EXvV0f24qbzochqKD+yyFaHlcp7qAS7mxJ7p YZ7mMYHpyT7pxT7fod7pzL7mxo3qbf7ff40Q9k3tDaHqV0i+xFykRGvkbJq7jw3oJw7Qflyq2VOw vb6uD8HtOu7mvK3YlC4Tyn7sYx7jxs7szi7m096DL87iza7q2Q7g973bc17w8G4R+Ozq7h7XLawU b82tf/7nb+jjBU7D8WfDNRzsw63fEzHvo37qHj/w+k7snr7sJj+TNE7yNE7pkk7Ymf8e79O+4zuu yr4M2iKtpT1azBmv4EItt7RHp5Pau/Ye2Dfx8UpP8hSB8HDe8nic8spu8gL/4tg+3Ipt6fge5tZ+ z6GNwcB+xwlewTeBtI4NwRhP0u78JhN/o+quFEsf9wsvpdh486Le7MWO7FMP80if92/O23Nu3Cdf 9l873ZZt00odqj78EcwcyBKcsiyr53vK4aE49kD/r23P60YfFHIf9xiS8NUu+Iet5pWe70d/9FNf 44q/+A/L0FEMtI2/y0od0WKvzAft9RD6+Lmv+1fOIv065P66tEVdtUSR+Q8P8V3R+UqvkQWf9aFu +p5O5uZ94q+bzBpe115d2d29wo7//rnkjcjAfvsUgbKR6vCHqa4xjMsMfuTs//ula2rGT/jluvlA ofwfLy/FrfAyr962juEzDRAA7Am09+8fgIMGFSpEuLDhv4ER7U0kSHGiRYEMDT50uLHjQQAhN4YU qREhx4UpVa5kuZLjRZgxL1a82NLmQpk5dU68eXPnT6BBhRbsWRQnQZo0LS6VCBMpU4oklUYNiZGg RqM4mzqFOtTr15hZWYIl+/PDWbRp1a79UBamR5UkE3I8OVNp0q0Cp3ZNmvDjSKl+l+59OjMuXLog Hco9DBKlWMhYU7rlGVmrW8uXKX/N/DFxyocNtw7my9W01Zx6q1KtKJXoY7+wDcZs/y1TKsnRmzl3 hqibMlvgbLt6dex3ccnienXetZv39MyaDWFLv90bukS8fSV3DA26OODuio3K5r2Zt/Wy5yObl/5X cvjqsb33Zg5978DaeGnjX81adWuUwnNJodyCws03zDpDkDLyetLtpJYCS86517gjsLD9crutPePm cug5jHQSz0OsIESMMceQU2/F2Shj8cUWZToPQw2vIxExuLYL0MLJnNPPNMKiuu461+5rqsOiQqtt p5UWTE9BJ8kqjz33UsxRvsYS049G5eyS0DMVIcoOyK06NPFKGNPMKkonx2LvJBT/Cq2p1WiUCE0t WdIyvuoK5NI2pozMrj/XMqxQTf8H2QxqRaFs0m1KBhnaEby4OFTSTKDqM8wkzwATk6sfZUR0VEYV rSzNBz29NLCHRhtTxjznwzFLMLtcMjWn8gPxPqSK5O8tUn3KKVhijXoUSgbPFEmuMxvjEclXSQO1 us+aNK9YVE0lCts1qQSNMdh8BLW5gQY081zjyKNr3CG9jDYiQgG179f9uLX3XsuOzezBME98LFYc u5sqVFH3vRZfhBMuNVkUv2R2I1zFjQpNPd2D80uX5tXYqj/jzRU/1PgDsCr1GlT45ERrsnez+Kz0 90plG9Q334Mh03ZblHPWrKx+46SuLjp30s4jk+dr9ugP39UU3lvhPfU2L6MO60X/AW8q+rtgG9U5 MiOHcnhZUmde78mtyzZ7ZylHQtJidktziuhn1wYY2ha7hMpuip5VdrJeCTtQL1mzKvrqe2u+l/CW xC7ccGO1PftxfPX9eTqonRaS4HOrhRlduD/ceLi3q84cTtacrvPAtZ09GfGUyYZcWBcVvllRhFl/ XfZrf74RSTrx1nT3uecCF7k4GSrw7iM5FF7HT5sWWbVTsbU97Nhvd5Rx6yFNkOKKU8/+e9jlBSq5 FP/Fzfe2LYowcI/ozdVXIj/fMt0slTxQ5Ewhm95qhBUHP8btdYt2iLrf8eSlPIVAQIEKhBEE/ne4 zDToX98iHrg2ZreBsW+Cs8GQ/+8q95QgOYdT23FJndxXOZXxZn8o89//ZsemkhXPYe1TCgRiYkMR RcaBLNnhA2dUPLFIkGr2k9R0gvYc3+UIaXEJ0QE/1kTQTQ1OI8QTkf72HO/lbDrqaeHrXqgtBJrL Uinp4UIcuEACgQWHldlhGX2IMiGWDYguQ0j8oEih9mxxdFXZ0E9MqLSCIU1zTBtZB/NGKj2erIuI clzrvFaormFnMGRcCQMNcsYFtvEfaLxkJrWCwzUOpTNufCPktBbB5uANf4FaDvJwRrifSWw4tkrf XUR3IwgVkGPuip65jBZEEkYOe/07ZZI857crSvKGmZxIKG1owwRusodnNCMZPf/JSWlaEm1eIWU1 s4nNUm5tkSnjFV9ASCZDAY9C7AIkEp1YGDwJrCO0ueL9kALMcKrki/sUH8k2OCvpAOWZMHnmGgd6 kYM2MyxtnOYmvRlNbHrSoZfMpk4UqNAcYmuHwMonsjCzwkK2y118bFt/MtTOdvXtj1Rx2x2vsjni IcY/pcPfSzvKQkWdb5bkKozJqAnRb9rDmUIlqExAWdShErShZdTkUlXy026mMYA9IeU4b2qTSI5v fVjFI0n7WdKloc9yABKf5VpqVmUusVNEg+QJTdrL2zWyKL55q07TekO8DhWHD3UoUydzVIQKNZOh JGpgk5rQvXqToeBMoDYl+s3/ThL2J5Kl6vWq98YVAtBQP+lMUuzp1ZT2bkhdQynytuRSJ4bIJPAh oVVZxE8mac83g20mM2urUL0iVLKaBGpL9EpbjAY3sMIdLkJ7S1E3NrSvjpUoJxkXVTdd9qpicYtN aYYd0HpWl6WV5V231FbUvqtgBpOu9Vxr2Z1IVrfCBeVFd8vewhIXmsit5EQnqlTbFnWySMUrTzB5 3L5G05rKHWxfhynAoRB2uvg8b3RDu0p3nhatYtWV/FgKQ9ly9qZWhS56yrJA/ea3uEQ9bHzXWN+n PvWigmUmYXNrWP5y1L5NrSYDHbvcaT72wPqML4IWPLbyUneVKOzp5XhqYYJl/xW2OEvYbposUA17 lDLtXbFB15sTwMqXKD/lq3032eNnKlabI8ZtjCm6XAAnt8bZrKR607vkKDNSq08OsuBsld07Kyda SoZzn/usyB3PNUoGBbFRywxj/TbTy1z2cqPZTN/jFjahJE70mZGrXBVfOseM9fCC3MzNOZN3qouL 3f7+5D4/B1rKqS6mMOuMYLKsmMWErnKhXyxYE8N1oozmNaR97WUwB3tYaP51ciN6bBtvczNZNtV5 GgwjE6Zt1aymdrXlSsxXN27KIXZvbd+LUcQmdNeLJjdfez1gSqeZksVutF//G2Bkq5fZ1i60s1WN 1czeG73Xxqm1lwzobDtyyv+ypjKlhzvpcL/F3V3OMbn9um5LB9jc0qyxUwXcWDTGu9OxTnCU7B3w rIE8fP6OM5BJzk+Aj1rIHe8vwr3dYxO7vNK9frg1I5txiEtc3TUX8I15TuzHOvfT/X1hoWM7bSdj 23WuRjnST85vUquchzwG9TIHClyrG/zQuC7qryPucEou/OI9X/PYKR5xaoJbmzdnu1SdZGWo20zk 1Cv5a5++KKffHcN0tqjRp2YUN2IZ1Ift9jK1fviYtxvsZh83RAs8cQBf0tAHN2rPOblwed/s09/G 78eX/mMH673uKxf9zVIuqsfapMM92ra3aV3wMJfd12s/s9injvHL3zjnvGX/vct/28tr4rixg578 vOeeOJA3W+mlz+h1ma/8ra3+RbpxsbBBnNjay77diRa8UFNM9hTzXuc6nzyJ4W5c4bedoUQn89CH 7vEMfzGczx89rOnfJtDbn+VZPzinec7lNio/ScOyxmM36LK4rzM/ROM+7/u6cbsmAWS+kau2jrq/ 5jM5C1yQ/KusjRMlsws62ts9B5wNZvM9GZuxcsM52zO7AWw5cKstxtu3DJQ6QTu+x5nBv3M+HHy2 hEk9lDE23fu+xaO4MiI6EzSuFay9ZHM03uKtF0w6DIS/bKHBGqTC7NnBFNJBLLTCDVQPpkK28RNC mhu+W1vABiSlJoys7CM9/2kTtS0kjrxrNR+awel7Q337MekTCwTctWRLQp2rsuJ7QkU7O27ZMTsc IDdswzditdNTRLlLtTfKQ2J5uOZSQ/FbQ/HjQRg5xPvzvM97IEbEHRukOj/rQo36Pt57PElkPS78 MU78RDZ0RFPUp3zSRGVrulkMllWsQxqMu0J8RbDwRFnMxemyRbeDM2I0RToURWD0wDjEO50JxmQM vWHUtj+bRvBpNmprxGasP/2DwqirxmQ0Rs36N2ysRSZ7xFJkxm4MNS2URr4TR2K8Q2qErXNkx1ZE PkjER04sFsaBx0QEx3OkR2tZR1dsR137xn3qtx3kRlwMSDi8x2MEyHd8yP9x3ML4s0imw0GHXMiM dEaJ7ECQrEiP5EXog8hOfEbT60j6Y8kXEkaBxEaCJEVkZEUNnEiKjMIM/Ej5c8nSY0h3LMecVEd5 zMWZtEly9MejvMXng0mNDMedRMdRpMmhlMmpRMq9y5mkFMmm5MmX9EnRq8ClxMmIDEnD+cr5G0uh TEmV9EVseUOxvEqyLEuJPEE5y0dTUku49MrZAcuwlEq8LMjADEmTLMq40kuM5MuVtMYs1EkLjMvB xMqYLMYcXL6qzEbExEKnZEuSbEnAhEXGNMwq/Et+pMs5zMyGVEzS7MyuTEu5XMuIRESmRMt4vMzv Scq9bEu9U83d/EzRjC7/NRm2zCCAUCzNkTzN1+TK1kRJz2TO5VzEa5HN2fwJAqjOhahOAjAI7NTH azROOQRF1ORInhQ4c3ROCURH8KlOmMDOiWDPHNrOf4DPCbRHv7zAldnM44zFqKzN8mTN88y/o4sM +JTPuXJP9wxKouzPjfzNejTNBLVN8nxMyQxQx3xKhWxO3XRQ2AyKAbVO7fRQ7CTQ6/TQCM1P/bTQ t1RL5UTQE03H4KzMEsXQCu3JDH26FcW/4SROezhQ9jRQ9YxP6wxREZ1C0AxN+uTPyTRSDZ3G3PTP xTRP8WxQoQDR7FSI7RxSINXRA2XRX4zMCaVRy4TQGIVGs0xMKHVLJS1O/xgRUh1tT/Vk0/Wk0iod TTENOS+dzqysT/t80CW9SM2sUSkUJ28sCiEd0Spl00NVzx1V1O9s0Ubt0iKl0yS9QhVVUchcRkDF UUj9ihBNCRHt1Cz90DmV1EkdUy5N0Tudy0e9zfBkUAD900xFU94I0ZjYUjfVUjldmUpNTvxcVVI1 UcxMzq281P100kCFjE8N0lzN0lut01HZyrN0VikF1jT1VfNqVWndQFi1uycVVVGVzw4d1V+lVmKB 1n08UwqdUTKFTmG1VNesSag80kJVSl7lzT11VNpU13XV13RFzlS90UE1yn9F0pIM01Klu3/dxlht TMI01n69UGttWNBT0/8FzVYijdT5PFKHvVeJrdaI5U6M9dNTpVSDNNg+LVds1Vh+DdiOlUGL/dKP LcxiZdfuNFlytdOEpdiWDdacnUqEjNkbPFebBdqLdVWYzVdH2tmh3Vd8/dmapVl4XdqRxdmQBVlM VdpNfVkXtVenndrDLNmKPdhnTVnOxFp67Vq0ZVoXEtqwPVmqHca0NdtZTNvefNeobdubRVi6vUm5 FcynXdm9RVFWBdt4Fdty7NXAfVnfnFnA9Qp+eFzITdy8zUu2LdyC3VjJZdm5lVApg1zPjVzf+NzM Zdi1rVxdJVw+HV3DRVytBQrQnYjXLVnPXYjZpUrX/Vzc5QfVXV2zUVj/ggVTzN1dGM0nyFWI2rWH yI3d103eBYld2H1c4bSM3NVdNsld4V1cTQ1a1G1a4U1IdLXLlCjef6jd2RXf8TXf4lVe6H1e6s0J z5WJ93US83XS6W3foHBe1SVWxRXU7YXYfjxWjwVd0UXfxzUI8i1gA+YH4yVgBW4S/GVfCN6MBz7Z 2j3fAhaKCe5eoy2bYfVOpE1dp1WT9P1cC74IAX7f5UXgA25glphf2lVhBIaIFNbd+DXh9VWUB4Ze 1vU3220wd/1dou1d0+XeDg6WES7fGD7iI15g6h3gG3bfGA5fGGZhC2ZiEn5h+4UJ0dXiGobfJ87T xvXaTeTVH5ZazfWi/yH2X+8N3jW2YBiu4gRWYNyF4yqeYxeW4iy24SZ+YgamYjxWifq14i2O4NVk Y9LN2v1VVbXl2aql3L9tEv6F4hN24Ssu4Cg+Xze25Ev+45UQ3/md4Z+IXE6mYyRm4J6wXi5u30Hm 2zEG4NMd2DLG2yDm4L5sZXGs5NlN5fVdZeQ9YEy2iTuOY2FmYmJuieJN5ZiY5Jow5ZuYXiwW5Bxe 5QyeZTwF46V9W94V4nr14AxUX+rF4im+5C3mZUkGZE+OYmZuYXFe5wY23wj25tcd5T52Y3C+4hKO X9yVVVM9474FWI4d3IH11yjxZklGZi8OZz/+5C/uZVXm4yTe5GeO6P9ipuQprmcWTuYbBmX2ZeF5 zmQlrmAey2ddzmMy3mbCjGXLndyFjd4wDmWHJmmCxugsVuiHDmc9dulvHuaJZmedjmg5nmOddmdl NmhRLuYENmZn9ug+xucuZmVDbuN+VmQxdmSMdWVE/gr7xV/nrd+ZTmo67uQYJuR3fmJS3uSPtud0 hmOubucLvmkMVuigrum1hmidBeFFjmqpnmrtLVulDmSuleQJnl631ol4jmuORmeNRuYKTmeajuOk puhgxmPC/uJJZutzhmjZsuu7HtfNxusivkun1uzbnWuv/l6cPm2ZFmmGzl08puIjNmiGHmyG7mlz 9mOlRmrbpu3Lhu3/2B4vgd7gav5nvPZn4YaSos3mox1t0gbqlU7trhbskc7nFT5s6sZisT5ouGLu Ud5utUZs16ZrlL5qt81YlZbbcbJqIi5u8h6K5S5tY53m6H7uQU7s2dZty4bNwMZsyO7pxj5u5I7G XQ3ok+ZnRk7kDX3r9rbnZt5k3ZjvjNbhONZjVC5s7zbqhb7uSZborwZKAQfizl7vDy9TH7uqAHeL BNfup+7l1k7nje7iGX5hw2Zi3i5qWpZObS1x4D5MXpRYHJ9smD5xkE5xaObuCYfu+uZvzNbf/yZx si3vFAXtHGcJLMVSM1Zvl8VqII9sNd4JBc9kyZbtDG7Yz/5tAx/z/wPvcXCcchLdsJI28SzXco8N tf722/EWWJOG2ij3H6jecmouR1tt1kPuCSov8CU/c5x+8x228uFO8a0V2Uamc+lcEDhd1ElnMjUf VbcYdEenyCV7czjnbL3mRiWv8xuvs+y1N0btUR9tU0TNiVb/6+G1yh0kbQKHdFJ/0TuX5RAv9ctd kSsl0V9X1D+ndOLcUiGlzh9tbkTRdA4P3ERn6ZTuc60M7yfTW3hE1FD1VnBdcysFdlZ/U0aViVWn VVoldvaEdfDN9mW3dUVn97hF9z0f21yP9lC3dhu3mVWn9ItQ9Tm99G7Pzm0X13+HCHLnd2LXd3P/ dmPndj4d9lj3Vv91Z/Yrv/Ueplt4j3coj/Jmp3jLklndCPiIV1aFd/VUF/mBX4lwhfhg7/ZbbVN9 z3cePfZ9L3eUZ/iKR/iYF3jxdkYNLnQzT+92P5uauffNyHmEf3lv1/mAT3iHX3WVN3ltX3OQ306k x1WrP3qmJ3ktNYql3/VX7vleB3po/3qNb0SPPw9hN3hAL3mXn/mRl/inv/qqd3t1D3mAB1WIN9R/ X/twd3u+v3pEhXuqG3WwP8mWfvizfXSUFb3At3uWL/daTXu551DJj3u7x/rAt/qkB/mo73ebB1JR /ftb/XeZ14nSp3ZULXzgFe1at2XFn1ZgnFdPZVNDnXnTl3zRN3r/AmX2cm/1zKf0k1cJbAd9y//W vJ/9u0/Utz/9EVcT3sf7OFf90BZ736Z3rbp34rZR2pdyOc193Mf8vtd65E/+mh95rQd3zuf8ug/+ le98nW8Rmdf98L9MTRd8/5Z+a+bzoHd9kt1B5QeIf/8IEBxI8CABgQYJ2GvY8KBDgvYgTpTo8KFE ihcrJhR4UCHIhQURMsRYUiNEjwVDLlT48aPKhDBZulw5cmVLkgx1RkTYc+NFjUA50ixadKbRpEpp Dm3q9CnUqFKnUq1q9eLSpFc3Zu3q9SvYsF63kr0qNGhHkDprkuRo8i3GuHCH+iTJNubduWhLup35 EidNpHjxIkWo//ZmR50WFQP1SXawWKWFIyssa/ky5sxlKf+7DFIz59CijWpuehZ0zMJ2Y3Lk29ii 254nYVNsydIvYtmxTQOG/Detbd+IE9vsHbJta9fJ+Z6O2lU1cMGjmZaubv36ZsrXp3PvHhlqc+xV FRvF7ZoiStqw9+o2Hzzw+rkQa793b17v67S/a95VnH6nY1EJBZ13BXYmHoIJKlggVAY6+CBYCiII mHmr7bbRfIupB6ByGBr334UD+ufWYNIdNhtz8b0VnH0wyRafiOep6BSEEEp4I44N1RiSZzv6+OOB OZZm3IkUosgheB2CGCN7+el2YX7C6bfWbkvCRpiR0a0X3nZAdv8nJJg42miZl2U6GKZmdpl43Gyx 1bUlnB3Kp6GcT/pHHJ5S9odTlRvudeJXaOpo5miC9sidc4QG+ZiijYZm6GUVGgadhyn2mWd5BUE5 J4p3YaklTu6x1eRUjwrqKGeQ2vPjoWa2iiqsXala1oer3bdpkyaKCuJbMa4FWX1EakWmdobGKhZm 0yVabHaEvnostNTNapWk8HXUp5vohbqtTFk6xeSq7+34bKDGRnuuQMQyy6izzaL7brrTWpUat6sZ ZGeGygmbFX5SNUruWObCK+uy37mLrLquHjxwtPJS+5uatf6kl0apJlwmwASfGhZWhS5oMbsGLwzk xQxD6/B49gb/mxauBXNcMskwB4wyzcmCvJWpISuss8mx1lzqmkplzK/MPg69FM7e/Vxazkmve5Wj Rfes6NIuvzzyzDzHjPWwVXsN9c1gPz3vv1xP3e7XQzUttshas0o22mnLuzbcbbO9s9Nnwyq32mHX jbDZY+ZIN98CA+521ncv6q/fVel9bOFcNU4V4Y7bHfhnUhMduaqTU+65hJWX+nhlmgvN+aBjW676 6KKtfnjesKMeJuiMs36j6LaTfvTpqOdude/hesl714hrPLvNWxu/Oe23t7676cVH/rvk8RKPaPSk Za898ssL/rmyG1/+t97XF4V8uYZjvL203gffPfmkjy+m87o//85++1Vnbn7pmD/IP0sAGED4xU5+ shNS7YA3NfwNMHRfUlz63HcmBu5PgufLzPxwZ8DJJQ6CHYzfAv0nvadUkG/UaxDVKNg/C+bPgx+k 3wbjVsAIzjCELESV+q52wweK8II9bCEIX6jBGOKthsczoslcyLAcRkiFHlOiEGkUvh8CEYZEHJ4T FwfFvc2qbGg6IQmvWL4sanFwYsQiFXlERqR1DIzW8WLz6qfAM6JLgGr8Ih3flsYSbvFk4isiAhOI wjwukYxMJCSD9shHBwLSjDIMpBwHich3ve6JeJzk/6gIqaj9cX2XzKD9MCnKJnZylNiTIg/BBMc4 NtKKBwSfKf+NFkrlsTKWryTgLPX4SU/WUofCs+UjgziuQ+YRl7tE4zFpCUlgEtGOU0zmJI25TF72 UpmVZCY2V4jEGm3SQF2KpDRRE8xv+nGH2SzmGsGJnSg+b5zhJCc1+6jLj52zns60ZHXqyb13JmiV 8vRmKfVpy3u6ril3JGgM+cnIVsIyno4EaBgF6tBr4nNa+lQoPRmaxIDSUJgSzaQiSUlMU2K0nx/1 5TRRStGTfg9B2izcRUsqHpaKVJWCRCVN1dlOnaIspjKF59s2OFLm/TOWb+Si7+xJQJWu9IhFbRhH 2SnJK7rUgOhTKufcaFCeAkWoUXVqUwGptJDicHY+nd5Nccr/1IaOEZpSjShEydrAbQ7squc0a1q3 Cspc9myobNRZRhnK140mtZBdzavDtNq3vc6RsNXsaD4P+tSxmtNneHXnTt9nV8ZOtaaThdwfD+s3 xVYPs401bFZT+NOjcrW0a82sDZ+VvJd69K90bWlt4bXZiXbOtjZtrUNI69q2ilZ1iC3uLQc7zMoi NbWmNSlwMXjcNnIWrqpl2lxvu0/tbje3E5SrP0143d9Wd53TDe550Svczy4yrL5lL23Zak331vWy gg3sa/HrWfpq1rvPhK/1mFtG/o6QwHHl7rl2i0zyJle/kJXvgykpV4IiNJ3l1Sv0Cntf6F6YtR2W HHJfG14I/7/Vuvs1cBVJjFsEQ1XDvF1ogzl8QJCymLI1liyAKTzcFbuSuGh9blWjm6wQg1bABTWy jsE73pSejcjdZfI8oVxiFSdUyUJer3pj3Nkmf1WU3QTyTEeb0/jCNsooTrFy0QxgTrp1lF/ecJDJ LN27WvnD1AWri30sZTd3mZt1xnOZSfrn/K72xs19rKDbzGMLP5nKXh70gwsdPbUumMHA9GukxQln E18a0lEk6uAUPN8eDxSXoD5zKg1NVU/LkqyiNvNDmWlkMGP4xWnGJKNtfdr+ym3EpMYmQper6iPP Wn53TrSAX91qRSfYySwNtpB/OeZoZlHZwrb0tec87QE7mv/Gw942atdsbT8zW81xBre5twzrbqM7 w98e96LDTOvFtju7a05v6up9RkPaV9cOPrB/cwptkem7nOKecL8LrmVKF3zgCq8ywpGccEJj19is 5vPFHx7bd0f8azaGMZczjutca9zdHJd4nnn9a8d+26qNK7nCK9zxXZ+Y01M2r8nvveSAw7zn6bb5 zZ0NxErzHMd7rq/IvV10nzM9wCenOdKT3WfdktzpDM801JuudasvvaK3/q7Uyy3hmXddzlnfetNh ++NNXx3QIA952FHecrTTtNY1X5qvv97oIea87NwO9KnZTfeeSzrL/m672//N8hyzz8ODh3jhe7pz wfsQ0YvT9zu8H5/3yHt88oB/b6z1jPmJa/6/nJc0m5+O7Y0zPuVbt/uyT+9csDue4vLuO6rbmzaN Vz3xstcfvmUu9mwrHvS9prbQjf95pf/++NHm9/ATOfW9dx7ufv+73qXffJgGH/qWJ3f07S1egL95 4YgH/+ntrGnzb4f0sT+68qsf9LkFf/MYxfJs2b/9Y4/67VjnqOzhn7QRXTiR38r53v7R2+HhnPop UAIeXNJRn9fY37nZ3gMaHgHy3S1V3gUWX/xl38ftkcNZIFDdXQfu2Lr5n1EEBAA7 ------=_NextPart_000_000D_01C75B25.B54B3170-- From nfsv4-bounces@ietf.org Tue Feb 27 22:22:17 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMFNQ-0002z6-PD; Tue, 27 Feb 2007 22:21:12 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMFNP-0002yz-At for nfsv4@ietf.org; Tue, 27 Feb 2007 22:21:11 -0500 Received: from pat.uio.no ([129.240.10.15]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMFNL-0000o5-Ol for nfsv4@ietf.org; Tue, 27 Feb 2007 22:21:11 -0500 Received: from mail-mx1.uio.no ([129.240.10.29]) by pat.uio.no with esmtp (Exim 4.66) (envelope-from ) id 1HMFNG-0004qx-AA; Wed, 28 Feb 2007 04:21:02 +0100 Received: from smtp.uio.no ([129.240.10.9] helo=mail-mx1.uio.no) by mail-mx1.uio.no with esmtp (Exim 4.66) (envelope-from ) id 1HMFNF-000735-Tb; Wed, 28 Feb 2007 04:21:02 +0100 Received: from [12.104.234.231] by mail-mx1.uio.no with esmtpsa (SSLv3:RC4-MD5:128) (Exim 4.66) (envelope-from ) id 1HMFNF-00072u-1R; Wed, 28 Feb 2007 04:21:01 +0100 Subject: Re: [nfsv4] SET_PRIORITY: new op proposal From: Trond Myklebust To: Peter Staubach In-Reply-To: <45E44087.8010903@redhat.com> References: <45E3F0E9.3060708@panasas.com> <45E44087.8010903@redhat.com> Content-Type: text/plain Date: Tue, 27 Feb 2007 22:20:57 -0500 Message-Id: <1172632857.10626.11.camel@heimdal.trondhjem.org> Mime-Version: 1.0 X-Mailer: Evolution 2.9.92 Content-Transfer-Encoding: 7bit X-UiO-Resend: resent X-UiO-Spam-info: not spam, SpamAssassin (score=0.0, required=12.0, autolearn=disabled, none) X-UiO-Scanned: F827AA5E202B2769B2CC8684805203C7034ED80E X-UiO-SPAM-Test: remote_host: 129.240.10.9 spam_score: 0 maxlevel 200 minaction 2 bait 0 mail/h: 63 total 131295 max/h 2679 blacklist 0 greylist 0 ratelimit 0 X-Spam-Score: 0.1 (/) X-Scan-Signature: e5ba305d0e64821bf3d8bc5d3bb07228 Cc: email2mre-ietf@yahoo.com, "Talpey, Thomas" , Robert Gordon , "Welch, Brent" , nfsv4@ietf.org, chuck.lever@oracle.com, "Noveck, Dave" , Benny Halevy X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org On Tue, 2007-02-27 at 09:30 -0500, Peter Staubach wrote: > It seems to me that most of these things can be better handled by the > client making appropriate priority calls for itself and scheduling > requests to the server to match its own priorities. > > There are other solutions to issues such as wanting decreased latencies > for operations such as GETATTR versus READ/WRITE, etc. The use of a > separate TCP connection can be used to help to avoid the blocking that a > single TCP connection may introduce. The metadata intensive style > operations can be run over one connection while the data intensive > operations could be run over another. Even more connections could be > used to differentiate between different client priorities if desired. > > I am also somewhat dubious about the value of using these priorities > for scheduling i/o on the server. I/o is generally scheduled by the > server given its own set of information, none of which is available to > the client. Having a client think that it can affect the i/o scheduling > on the server for some benefit seems questionable to me. > > The ability for the client to convey priorities to differentiate between > different sessions or network connections may be interesting but still > seems to assume a lot about the server implementation to me. ACK. Nobody in this thread has so far presented a real-life use case where this operation would show the "obvious benefits" that Benny talked of in his introduction. If the client wants clever scheduling of metadata operations, it can do so all by itself without having to introduce new state for the server to carry around. Trond _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Tue Feb 27 23:07:09 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMG5T-00083O-Gx; Tue, 27 Feb 2007 23:06:43 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMG5P-00080A-6Z for nfsv4@ietf.org; Tue, 27 Feb 2007 23:06:41 -0500 Received: from web31804.mail.mud.yahoo.com ([68.142.207.67]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HMG5N-0006Xy-SZ for nfsv4@ietf.org; Tue, 27 Feb 2007 23:06:39 -0500 Received: (qmail 36979 invoked by uid 60001); 28 Feb 2007 04:06:37 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=edDekeyOx8nk+sg14uKjdClf7tuuXfsBD9HBdPoBJifl6XsxsnrRf4VLYBkveIFc3NjSdNsO7f5JMoZqEicONiCBbYHc5bXkN/ydFrxC3EwubwJZB6I34RkF1QmllTrBdHkxLJ4d5EbJKDFbrgNjFUA9g2wtOENpIgc7WuziAj0=; X-YMail-OSG: YR4H5roVM1kNpmonYXoAhhDRG9GFlfA155_ivUi16Cm8HgrGwBBPYCa7X5BEMJQkvh19jMo.2AF7tN_BVD9WV0AC9Jht_IHKxOIRIBd.1VF6j47.d7YtMsbrdCs0vWgA291nkVnfui6k9Ok- Received: from [198.95.226.224] by web31804.mail.mud.yahoo.com via HTTP; Tue, 27 Feb 2007 20:06:37 PST Date: Tue, 27 Feb 2007 20:06:37 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: nfsv4@ietf.org In-Reply-To: <1172632857.10626.11.camel@heimdal.trondhjem.org> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <312815.36591.qm@web31804.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: d6b246023072368de71562c0ab503126 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- Trond Myklebust wrote: > On Tue, 2007-02-27 at 09:30 -0500, Peter Staubach wrote: > > It seems to me that most of these things can be better handled by > the > > client making appropriate priority calls for itself and scheduling > > requests to the server to match its own priorities. > > > > There are other solutions to issues such as wanting decreased > latencies > > for operations such as GETATTR versus READ/WRITE, etc. The use of > a > > separate TCP connection can be used to help to avoid the blocking How does a client indicate which TCP connection carries the higher traffic? Until, NFSv4.1 there's been no way to indicate that. With sessions a session can be tagged, and all the connections bound it serviced in higher priority. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 07:51:12 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMOG0-0003vp-Mz; Wed, 28 Feb 2007 07:50:08 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMOFz-0003uq-Kc for nfsv4@ietf.org; Wed, 28 Feb 2007 07:50:07 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMOFy-0006PN-Cf for nfsv4@ietf.org; Wed, 28 Feb 2007 07:50:07 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1SCnphN006509; Wed, 28 Feb 2007 07:49:51 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 28 Feb 2007 07:49:51 -0500 Received: from [192.168.0.140] ([172.17.19.38]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Wed, 28 Feb 2007 07:49:50 -0500 Message-ID: <45E57A6C.2080608@panasas.com> Date: Wed, 28 Feb 2007 14:49:48 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: Trond Myklebust Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: <45E3F0E9.3060708@panasas.com> <45E44087.8010903@redhat.com> <1172632857.10626.11.camel@heimdal.trondhjem.org> In-Reply-To: <1172632857.10626.11.camel@heimdal.trondhjem.org> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 28 Feb 2007 12:49:51.0218 (UTC) FILETIME=[EFC20520:01C75B36] X-Spam-Score: 0.0 (/) X-Scan-Signature: d6b246023072368de71562c0ab503126 Cc: email2mre-ietf@yahoo.com, "Talpey, Thomas" , Robert Gordon , "Welch, Brent" , nfsv4@ietf.org, chuck.lever@oracle.com, "Noveck, Dave" X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Trond Myklebust wrote: > If the client wants clever scheduling of > metadata operations, it can do so all by itself without having to > introduce new state for the server to carry around. > > Trond > There a couple of shortcomings with this approach: First, the client can't schedule its operations with respect to other clients' work and second, if the prioritization is done only on the client side it will be very hard for the client to achieve low latency for metadata ops while keeping the server busy with a pipeline full of data I/O operations. Sending metadata ops over a high priority session can allow the op to pass I/O operations waiting in the server queues. Benny _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 07:51:35 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMOHP-0004MC-8Y; Wed, 28 Feb 2007 07:51:35 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMOHN-0004M7-QN for nfsv4@ietf.org; Wed, 28 Feb 2007 07:51:33 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMOHM-0006VV-Im for nfsv4@ietf.org; Wed, 28 Feb 2007 07:51:33 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 28 Feb 2007 04:51:32 -0800 X-IronPort-AV: i="4.14,230,1170662400"; d="scan'208"; a="37059132:sNHT14658560" Received: from svlexc02.hq.netapp.com (svlexc02.corp.netapp.com [10.57.157.136]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1SCpVgg007260 for ; Wed, 28 Feb 2007 04:51:31 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc02.hq.netapp.com with Microsoft SMTPSVC(5.0.2195.6713); Wed, 28 Feb 2007 04:52:38 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Wed, 28 Feb 2007 04:52:38 -0800 Received: from tmt.netapp.com ([10.30.32.33]) by exnane01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Wed, 28 Feb 2007 07:52:40 -0500 X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Wed, 28 Feb 2007 07:49:15 -0500 To: nfsv4@ietf.org From: "Talpey, Thomas" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-Reply-To: <312815.36591.qm@web31804.mail.mud.yahoo.com> References: <1172632857.10626.11.camel@heimdal.trondhjem.org> <312815.36591.qm@web31804.mail.mud.yahoo.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Message-ID: X-OriginalArrivalTime: 28 Feb 2007 12:52:40.0353 (UTC) FILETIME=[5491F910:01C75B37] X-Spam-Score: 0.0 (/) X-Scan-Signature: 7a6398bf8aaeabc7a7bb696b6b0a2aad X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org At 11:06 PM 2/27/2007, Mike Eisler wrote: >that. With sessions a session can be tagged, and all the connections >bound it serviced in higher priority. Yipes - does this proposal allow each request (or session) to *globally* specify its priority? Holy denial of service, Batman. I still want to see the server's MUSTs and SHOULDs w.r.t the client-specified priority. If everything is a MAY, then I think we should ask ourselves a) what good is it and b) why are we adding it now. Tom. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 08:27:12 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMOpp-0007tf-Ns; Wed, 28 Feb 2007 08:27:09 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMOpo-0007gF-70 for nfsv4@ietf.org; Wed, 28 Feb 2007 08:27:08 -0500 Received: from mexforward.lss.emc.com ([128.222.32.20]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMOpm-0003pX-Uf for nfsv4@ietf.org; Wed, 28 Feb 2007 08:27:08 -0500 Received: from mailhub.lss.emc.com (sesha.lss.emc.com [10.254.144.12]) by mexforward.lss.emc.com (Switch-3.1.8/Switch-3.1.7) with ESMTP id l1SDQth1008743; Wed, 28 Feb 2007 08:26:55 -0500 (EST) Received: from corpussmtp3.corp.emc.com (corpussmtp3.corp.emc.com [10.254.64.53]) by mailhub.lss.emc.com (Switch-3.1.8/Switch-3.1.7) with ESMTP id l1SDQW1m015875; Wed, 28 Feb 2007 08:26:54 -0500 (EST) From: vanderputten_thomas@emc.com Received: from CORPUSMX40B.corp.emc.com ([10.254.64.48]) by corpussmtp3.corp.emc.com with Microsoft SMTPSVC(6.0.3790.1830); Wed, 28 Feb 2007 08:26:37 -0500 X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Subject: RE: [nfsv4] SET_PRIORITY: new op proposal Date: Wed, 28 Feb 2007 08:26:36 -0500 Message-ID: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] SET_PRIORITY: new op proposal Thread-Index: AcdbN37tQtbYdtpvRYCvaRgiM20C6wAA3nmL References: <45E3F0E9.3060708@panasas.com> <45E44087.8010903@redhat.com><1172632857.10626.11.camel@heimdal.trondhjem.org> <45E57A6C.2080608@panasas.com> To: , X-OriginalArrivalTime: 28 Feb 2007 13:26:37.0633 (UTC) FILETIME=[12E23B10:01C75B3C] X-PMX-Version: 4.7.1.128075, Antispam-Engine: 2.5.0.283055, Antispam-Data: 2007.2.28.51934 X-PerlMx-Spam: Gauge=, SPAM=2%, Reason='EMC_FROM_0+ -2, NO_REAL_NAME 0, __CT 0, __CTE 0, __CTYPE_CHARSET_QUOTED 0, __CT_TEXT_PLAIN 0, __HAS_MSGID 0, __IMS_MSGID 0, __MIME_TEXT_ONLY 0, __MIME_VERSION 0, __SANE_MSGID 0' X-Spam-Score: 0.2 (/) X-Scan-Signature: 5a9a1bd6c2d06a21d748b7d0070ddcb8 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Apart from the previously mentioned DOS problem, wouldn't adding a = client controlled global priority also introduce issues of fairness and = starvation between clients? While the server could arbitrate that away somewhat, it seems like a = good bit of added complexity. Also wouldn't this assume that the clients are somehow aware of each = other, and aware of their own status in the world? If it was an administrative action, I can just see a sysadmin jacking = the value up to maximum for all the clients. I'm not necessarily opposed to the idea, I am only having trouble = understanding the ultimate utility. -- Tom Vanderputten -----Original Message----- From: Benny Halevy [mailto:bhalevy@panasas.com] Sent: Wed 2/28/2007 7:49 AM To: Trond Myklebust Cc: email2mre-ietf@yahoo.com; Talpey, Thomas; Robert Gordon; = Welch,Brent; nfsv4@ietf.org; chuck.lever@oracle.com; Noveck, Dave Subject: Re: [nfsv4] SET_PRIORITY: new op proposal =20 Trond Myklebust wrote: > If the client wants clever scheduling of > metadata operations, it can do so all by itself without having to > introduce new state for the server to carry around. >=20 > Trond >=20 There a couple of shortcomings with this approach: First, the client can't schedule its operations with respect to other clients' work and second, if the prioritization is done only on the client side it will be very hard for the client to achieve low latency for metadata ops while keeping the server busy with a pipeline full of data I/O operations. Sending metadata ops over a high priority session can allow the op to pass I/O operations waiting in the server queues. Benny _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 08:38:17 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMP0Y-0005Hn-Qy; Wed, 28 Feb 2007 08:38:14 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMP0X-0005Hc-RM for nfsv4@ietf.org; Wed, 28 Feb 2007 08:38:13 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMP0V-0005ai-DA for nfsv4@ietf.org; Wed, 28 Feb 2007 08:38:12 -0500 Received: from smtp1.corp.netapp.com ([10.57.156.124]) by mx2.netapp.com with ESMTP; 28 Feb 2007 05:38:11 -0800 X-IronPort-AV: i="4.14,230,1170662400"; d="scan'208"; a="37071496:sNHT15783950" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp1.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1SDcAPA013962; Wed, 28 Feb 2007 05:38:10 -0800 (PST) Received: from exsvlrb02.hq.netapp.com ([10.56.8.63]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Wed, 28 Feb 2007 05:38:10 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb02.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Wed, 28 Feb 2007 05:39:18 -0800 Received: from tmt.netapp.com ([10.30.32.33]) by exnane01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Wed, 28 Feb 2007 08:39:21 -0500 X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Wed, 28 Feb 2007 08:37:50 -0500 To: Benny Halevy From: "Talpey, Thomas" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal In-Reply-To: <45E57A6C.2080608@panasas.com> References: <45E3F0E9.3060708@panasas.com> <45E44087.8010903@redhat.com> <1172632857.10626.11.camel@heimdal.trondhjem.org> <45E57A6C.2080608@panasas.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Message-ID: X-OriginalArrivalTime: 28 Feb 2007 13:39:21.0406 (UTC) FILETIME=[DA20BDE0:01C75B3D] X-Spam-Score: 0.0 (/) X-Scan-Signature: 68c8cc8a64a9d0402e43b8eee9fc4199 Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org At 07:49 AM 2/28/2007, Benny Halevy wrote: >busy with a pipeline full of data I/O operations. Sending >metadata ops over a high priority session can allow the op >to pass I/O operations waiting in the server queues. Okay, now I'm against this proposal. Your stated design goal is in fact a denial of service - to prioritize one client's stream above another's. It even sounds as if you envision dedicated server threads (slots) to handle them. Tom. _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 08:54:51 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMPGN-0006xk-3I; Wed, 28 Feb 2007 08:54:35 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMPGM-0006tZ-Cy for nfsv4@ietf.org; Wed, 28 Feb 2007 08:54:34 -0500 Received: from mx2.netapp.com ([216.240.18.37]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMPGL-00006T-56 for nfsv4@ietf.org; Wed, 28 Feb 2007 08:54:34 -0500 Received: from smtp2.corp.netapp.com ([10.57.159.114]) by mx2.netapp.com with ESMTP; 28 Feb 2007 05:54:31 -0800 X-IronPort-AV: i="4.14,230,1170662400"; d="scan'208"; a="37075872:sNHT58783340" Received: from svlexc03.hq.netapp.com (svlexc03.corp.netapp.com [10.57.156.149]) by smtp2.corp.netapp.com (8.13.1/8.13.1/NTAP-1.6) with ESMTP id l1SDsLqk009583; Wed, 28 Feb 2007 05:54:31 -0800 (PST) Received: from exsvlrb01.hq.netapp.com ([10.56.8.62]) by svlexc03.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.0); Wed, 28 Feb 2007 05:54:24 -0800 Received: from exnane01.hq.netapp.com ([10.97.0.61]) by exsvlrb01.hq.netapp.com with Microsoft SMTPSVC(6.0.3790.1830); Wed, 28 Feb 2007 05:55:31 -0800 Content-class: urn:content-classes:message Subject: RE: [nfsv4] SET_PRIORITY: new op proposal MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Date: Wed, 28 Feb 2007 08:54:21 -0500 X-MimeOLE: Produced By Microsoft Exchange V6.5.7226.0 Message-ID: In-Reply-To: X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [nfsv4] SET_PRIORITY: new op proposal Thread-Index: AcdbPhHRwxL7FpOaRMSDkzBQsiX19gAAR20g References: <45E3F0E9.3060708@panasas.com> <45E44087.8010903@redhat.com><1172632857.10626.11.camel@heimdal.trondhjem.org><45E57A6C.2080608@panasas.com> From: "Ellard, Daniel" To: "Talpey, Thomas" , "Benny Halevy" X-OriginalArrivalTime: 28 Feb 2007 13:55:31.0681 (UTC) FILETIME=[1C74F510:01C75B40] X-Spam-Score: 0.0 (/) X-Scan-Signature: 2409bba43e9c8d580670fda8b695204a Cc: nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org =20 > -----Original Message----- > From: Talpey, Thomas=20 > Sent: Wednesday, February 28, 2007 8:38 AM > To: Benny Halevy > Cc: nfsv4@ietf.org > Subject: Re: [nfsv4] SET_PRIORITY: new op proposal >=20 > At 07:49 AM 2/28/2007, Benny Halevy wrote: > >busy with a pipeline full of data I/O operations. Sending=20 > metadata ops=20 > >over a high priority session can allow the op to pass I/O operations=20 > >waiting in the server queues. >=20 > Okay, now I'm against this proposal. Your stated design goal=20 > is in fact a denial of service - to prioritize one client's=20 > stream above another's. It even sounds as if you envision=20 > dedicated server threads (slots) to handle them. This does sound problematic. As I believe someone pointed out a while ago on this thread, it's the tragedy of the commons. I'm not opposed to priorities as *hints* that the server can choose to ignore, or normalize in whatever way it sees fit. -Dan _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 09:24:37 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMPj8-0000IQ-W0; Wed, 28 Feb 2007 09:24:18 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMPj7-0000IF-A9 for nfsv4@ietf.org; Wed, 28 Feb 2007 09:24:17 -0500 Received: from gw-e.panasas.com ([65.194.124.178] helo=cassoulet.panasas.com) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1HMPj4-0003Cq-W1 for nfsv4@ietf.org; Wed, 28 Feb 2007 09:24:17 -0500 Received: from riverside.int.panasas.com (localhost.localdomain [127.0.0.1]) by cassoulet.panasas.com (8.13.1/8.13.1) with ESMTP id l1SEOELw008649; Wed, 28 Feb 2007 09:24:14 -0500 Received: from 172.17.1.41 ([172.17.1.41] helo=riverside.int.panasas.com) by ASSP-nospam; 28 Feb 2007 09:24:14 -0500 Received: from [192.168.0.140] ([172.17.19.38]) by riverside.int.panasas.com with Microsoft SMTPSVC(6.0.3790.1830); Wed, 28 Feb 2007 09:24:13 -0500 Message-ID: <45E5908B.4080004@panasas.com> Date: Wed, 28 Feb 2007 16:24:11 +0200 From: Benny Halevy User-Agent: Thunderbird 1.5.0.7 (X11/20060909) MIME-Version: 1.0 To: "Ellard, Daniel" Subject: Re: [nfsv4] SET_PRIORITY: new op proposal References: <45E3F0E9.3060708@panasas.com> <45E44087.8010903@redhat.com><1172632857.10626.11.camel@heimdal.trondhjem.org><45E57A6C.2080608@panasas.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 28 Feb 2007 14:24:13.0874 (UTC) FILETIME=[1EF6C120:01C75B44] X-Spam-Score: 0.0 (/) X-Scan-Signature: e5ba305d0e64821bf3d8bc5d3bb07228 Cc: "Talpey, Thomas" , nfsv4@ietf.org X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org Ellard, Daniel wrote: > > >> -----Original Message----- >> From: Talpey, Thomas >> Sent: Wednesday, February 28, 2007 8:38 AM >> To: Benny Halevy >> Cc: nfsv4@ietf.org >> Subject: Re: [nfsv4] SET_PRIORITY: new op proposal >> >> At 07:49 AM 2/28/2007, Benny Halevy wrote: >>> busy with a pipeline full of data I/O operations. Sending >> metadata ops >>> over a high priority session can allow the op to pass I/O operations >>> waiting in the server queues. >> Okay, now I'm against this proposal. Your stated design goal >> is in fact a denial of service - to prioritize one client's >> stream above another's. It even sounds as if you envision >> dedicated server threads (slots) to handle them. > > This does sound problematic. As I believe someone pointed out a while > ago on this thread, it's the tragedy of the commons. > > I'm not opposed to priorities as *hints* that the server can choose to > ignore, or normalize in whatever way it sees fit. > Right. That's exactly what is proposed. > -Dan _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 10:50:14 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMR36-00084a-Tg; Wed, 28 Feb 2007 10:49:00 -0500 Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMR35-00082Y-3A for nfsv4@ietf.org; Wed, 28 Feb 2007 10:48:59 -0500 Received: from web31810.mail.mud.yahoo.com ([68.142.207.73]) by ietf-mx.ietf.org with smtp (Exim 4.43) id 1HMR32-0006HY-Mu for nfsv4@ietf.org; Wed, 28 Feb 2007 10:48:59 -0500 Received: (qmail 28347 invoked by uid 60001); 28 Feb 2007 15:48:56 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=JGHUWlyW7odP79h+jJ7DZU1UoG5W7Nr8en28zsYtM5ojZWdbzZ/vDicjBwxpplds2azr/7J+Sh7c+MK0Q9Os3Ndu9e8Reix2vVQ4tPOLIfd/cnuuy0Daxw/1n/Uew6eA3eVajkVBe+6ga4HGxJZ8fBdTf9kGHNkRoX5WV7XXKYI=; X-YMail-OSG: pxqCm1cVM1k2hxLlSvZfqE4z31zeGtgvTp7euTcwweKoF9z1JLRvZQ0gqLTLljw8Kcj0okEcOkS2BtNsWy5jblFUxRI_EadzzHuxhW.KVsoqw0zFTzFAH1UiTaARyoudaK01KnXwU6ydTeQ- Received: from [198.95.226.224] by web31810.mail.mud.yahoo.com via HTTP; Wed, 28 Feb 2007 07:48:56 PST Date: Wed, 28 Feb 2007 07:48:56 -0800 (PST) From: Mike Eisler Subject: Re: [nfsv4] SET_PRIORITY: new op proposal To: nfsv4@ietf.org In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <165121.26562.qm@web31810.mail.mud.yahoo.com> X-Spam-Score: 0.0 (/) X-Scan-Signature: 5ebbf074524e58e662bc8209a6235027 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: email2mre-ietf@yahoo.com List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org --- "Talpey, Thomas" wrote: > At 11:06 PM 2/27/2007, Mike Eisler wrote: > >that. With sessions a session can be tagged, and all the connections > >bound it serviced in higher priority. > > Yipes - does this proposal allow each request (or session) to > *globally* > specify its priority? Holy denial of service, Batman. Servers don't have to allow clients to set higher, service denying priorities, if they don't want to. Besides which, AUTH_SYS is the ultimate in denial of service, and who cares? :-) > > I still want to see the server's MUSTs and SHOULDs w.r.t the > client-specified > priority. If everything is a MAY, then I think we should ask > ourselves a) what > good is it and b) why are we adding it now. How about this: Priority is a 32 bit signed integer. Zero means the peer doesn't care. 1 is the base priority. Priorities other than "don't care" are in the set { ..., -3, -1, 1, 3, ... } The higher the number, the higher the priority. Clients and servers MAY implement per-session priority. If they do not, they express priority with the zero value. At CREATE_SESSION time, the client offers two priorities, one for the back channel, one for the fore channel, and the server responds with confirmed values. The server MAY override the fore channel priority with any value. The server MUST NOT override the back channel priority, except if it is not implementing priority, in which case it MAY set the back channel priority to zero. Clients and Servers MAY support per-message priorities. At CREATE_SESSION time the client offers to support per-message priorities on the fore and/or back channels, and the server confirms the choices. If the client wants per message priority on the fore channel the server MAY deny it. If the client wants no per message priority on the back channel, the server MUST agree. If the per-session priority of the channel is zero, then no per-message priority on the channel is allowed, and the CREATE_SESSION results will indicate that. Each SEQUENCE and CB_SEQUENCE operation takes a 32 bit priority formatted the same as the session priority field. If the client offers non-zero values for fore and/or back channel priorities, and the server confirms (in CREATE_SESSION results) non-zero values for fore and/or back channel priorities, then the receiver MUST implement priority If there are two sessions bound to the same client_owner/server_owner paid, each with two different non-zero priorities, then the receiver MUST give priority to requests send over the higher priority session. The means for how this is done is not specified. If the same server_owner has sessions with two different client_owners with different non-zero fore channel priorities, then the server MUST give higher priority to the requests with the high session priority. Similarly if the same client_owner has sessions with two different server_owners with different non-zero back channel priorities, then the client MUST give higher priority to the callback requests sent over the the higher priority session. For per message priorities, the receiver SHOULD give higher priority processing to a message with a higher priority than that of the session, and lower priority processing to a message with lower priority than of the session. The receiver SHOULD give messages with a higher priority in one session higher priority processing over messages with a lower priority (either per-message or per-session) in another session that shares the same client_owner/server_owner paid. The receiver MAY give messages with a higher priority in one session higher priority processing over messages with a lower priority (either per-message or per-session) in another session that has a different client_owner/server_owner pair. This document does not specify strategies for avoiding starvation of serverive to lower priority sessions or messages. A server_owner might allow one client_owner to set a higher priority than another, based on an implementation specific configured priority control policy that considers client name, client network address, client principal, etc. A server might also provide a way for server administrators to force certain client_owners to have specific priorities on the fore channel. For e.g. a particular client is consuming most of the server's processing capability, and the sysadmin forcibly terminates the client's session and indicates that any subsequent sessions the client creates will have a lower priority than over (well behaved) clients. [BTW, I have customers mention the above use case all the time. There are other ways to implement it, but sessions seem the most natural approach.] _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4 From nfsv4-bounces@ietf.org Wed Feb 28 14:48:35 2007 Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMUmL-0005SW-50; Wed, 28 Feb 2007 14:47:57 -0500 Received: from [10.90.34.44] (helo=chiedprmail1.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1HMUmJ-0005SH-EL for nfsv4@ietf.org; Wed, 28 Feb 2007 14:47:55 -0500 Received: from citi.umich.edu ([141.211.133.111]) by chiedprmail1.ietf.org with esmtp (Exim 4.43) id 1HMUmI-00076Q-5K for nfsv4@ietf.org; Wed, 28 Feb 2007 14:47:55 -0500 Received: by citi.umich.edu (Postfix, from userid 103558) id 961B739751; Wed, 28 Feb 2007 14:47:51 -0500 (EST) Received: from localhost (localhost [127.0.0.1]) by citi.umich.edu (Postfix) with ESMTP id 93C3539746 for ; Wed, 28 Feb 2007 14:47:51 -0500 (EST) Date: Wed, 28 Feb 2007 14:47:51 -0500 (EST) From: Fredric Isaman To: nfsv4@ietf.org Subject: [nfsv4] SET_SSV4res improperly specified Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Spam-Score: 0.0 (/) X-Scan-Signature: 69a74e02bbee44ab4f8eafdbcedd94a1 X-BeenThere: nfsv4@ietf.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: NFSv4 Working Group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: nfsv4-bounces@ietf.org SET_SSV4res has no way to return error codes. Below is a patch that encodes the result in a manner consistent with other operations. In a similar vein, the list of legitimate error codes for SET_SSV seems a little short. In particular, at least NFS4ERR_OP_NOT_IN_SESSION should be added. Fred --- nfsv41.x 2007-02-27 13:46:35.000000000 -0500 +++ new_nfsv41.x 2007-02-28 14:33:25.000000000 -0500 @@ -2084,10 +2084,18 @@ opaque ssa_digest<>; }; -struct SET_SSV4res { +struct SET_SSV4resok { opaque ssr_digest<>; }; +union SET_SSV4res switch (nfsstat4 status) { +case NFS4_OK: + SET_SSV4resok ssr_resok4; +default: + void; +}; + + struct TEST_STATEID4args { stateid4 ts_stateids<>; }; _______________________________________________ nfsv4 mailing list nfsv4@ietf.org https://www1.ietf.org/mailman/listinfo/nfsv4