May 2006 - ogsa-d-wg - lists.ogf.org

Agenda for tomorrow's telcon
by Dave Berry 30 May '06

30 May '06

The next teleconference of the OGSA Data Architecture working group will be held on Wednesday May 31st, 2006 at the usual time of 8:00am Pacific / 11:00am Eastern / 4:00pm UK / 5:00pm Europe. We will review the latest draft of the architecture document - please read this in advance of the meeting. The URL is below. Here is the teleconference information: UK dialin: 0845 245 0224 US dialin: 1 866 838 0046 Intl dialin: +44 1452 542309 Passcode: 275359 Draft agenda for the May 24th teleconference: 1) Early discussion (5 minutes) Note taker assignment Roll call Minutes Approval (http://tinyurl.com/fv8hf) Agenda bashing 2) Action report (5 minutes) - Stephen to post his version of architecture document with the description of SRM functions to the list - Stephen to chase Luc about the provenance scenario. - Everyone to prepare for review of arch doc - Chris to draft GFS scenario - Stephen & Dave to review scenarios doc from a storage perspective. - Dave to draft metadata catalog scenario & services (cf. SRB) - Ann to check the Access section for suitability for file replication. - Section authors review security aspects of their sections. 3) Architecture document review (45 minutes) https://forge.gridforum.org/projects/ogsa-d-wg/document/Strawman-Archite cture_V.6.0.4/en/1 4) Wrap up (5 minutes) F2F date Topics for future meetings June 7 - Review new scenarios. June 14 - Review scenarios doc. Dave Berry Deputy Director, Research & E-infrastructure Development National e-Science Centre, 15 South College Street Edinburgh, EH8 9AA +44 131 651 4039

1 0

Minutes of today's telcon
by Dave Berry 24 May '06

24 May '06

Minutes are attached and on GridForge at http://tinyurl.com/fv8hf. In next week's meeting we will review the latest version of the architecture document. Please read this before the meeting. Best wishes, Dave Berry Deputy Director, Research & E-infrastructure Development National e-Science Centre, 15 South College Street Edinburgh, EH8 9AA +44 131 651 4039

1 0

Agenda for tomorrow's telcon
by Dave Berry 23 May '06

23 May '06

The next teleconference of the OGSA Data Architecture working group will be held on Wednesday May 24th, 2006 at the usual time of 8:00am Pacific / 11:00am Eastern / 4:00pm UK / 5:00pm Europe. Here is the teleconference information: UK dialin: 0845 245 0224 US dialin: 1 866 838 0046 Intl dialin: +44 1452 542309 Passcode: 275359 Draft agenda for the May 24th teleconference: 1) Early discussion (5 minutes) Note taker assignment Roll call Minutes Approval Agenda bashing 2) Action report (5 minutes) - Dave to mail Joel to cancel GGF session. - Dave to mail Hiro about OGSA WG F2F - Allen to clarify use of "data transfer" and "data access" in the architecture document. - Allen to integrate Neil's changes and put latest version of architecture document online. - Stephen to add a paragraph to the architecture document about reasons for naming, if still needed after Allen's revisions. - Chris to draft GFS scenario - Stephen & Dave to review scenarios doc from a storage perspective. - Stephen & Dave to add interfaces to the scenarios doc. - Dave to draft metadata catalog scenario & services (cf. SRB) - Ann to check the Access section for suitability for file replication. - Section authors review security aspects of their sections. 3) RNS/Naming update (10 minutes) - Report on the status of RNS and other naming activities 3) Progress report and planning (30 minutes) We need to schedule work and discussion of the following: 1. Review of latest data arch doc. 2. Interfaces for arch doc - can we arrange a F2F? 3. Interfaces for scenarios doc - Stephen & Dave. 4. Review scenarios from storage perspective - Stephen & Dave. 5. New GFS scenario - Chris. 6. New Provenance scenario - Stephen 7. Metadata catalog scenario & services (cf. SRB) - Dave? We have previously discussed the following items, and need to check on progress: - Storage in cache & federation services - Operations to add data elements to replication systems - Metadata operations 7) Wrap up (10 minutes) Topics for future meetings Dave Berry Deputy Director, Research & E-infrastructure Development National e-Science Centre, 15 South College Street Edinburgh, EH8 9AA +44 131 651 4039

1 0

No telcon this week
by Dave Berry 16 May '06

16 May '06

Dear all, There will not be an OGSA-D telcon this week. While good progress has been made since the last call, several of us will be travelling this week. The next call will be on May 24th. In the meantime, please review the current draft of the architecture document and the refactored RNS document. Best wishes, Dave Berry Deputy Director, Research & E-infrastructure Development National e-Science Centre, 15 South College Street Edinburgh, EH8 9AA +44 131 651 4039

1 0

Fwd: [gfs-wg] Refactored RNS Specification - Post GG17 Discussion
by Christopher Jordan 13 May '06

13 May '06

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Just in case anyone missed this on the GFS or OGSA-Naming lists. This is the minimalist version of RNS, which is intended to provide a basis for other groups, including GFS and other groups in the Data area, to build profiles upon for specific functions. Dave, can we put discussion of this draft on the agenda for the next call? I'd like to get feedback from this working group on the draft, if there is any. Begin forwarded message: > From: Manuel Pereira <mpereira(a)almaden.ibm.com> > Date: May 11, 2006 11:58:56 AM PDT > To: gfs-wg(a)ggf.org > Cc: ogsa-naming-wg(a)ggf.org > Subject: [gfs-wg] Refactored RNS Specification - Post GG17 Discussion > > > Hello all, > > This note is intended to inform you that the most recent revision > of the "refactored" RNS specification document is now available on > GridForge: > https://forge.gridforum.org/projects/gfs-wg/document/ > Resource_Namespace_Service_Refactored/en/4 > > This revision incorporates the very minor adjustments discussed > during the GFS-WG session in Tokyo. > > Best regards, > Manuel Pereira > ------------------------------------------------------ > IBM Almaden Research Center > 1-408-927-1935 [Tieline: 457] > mpereira(a)us.ibm.com > ------------------------------------------------------ - ---------------------------------------------------- Chris Jordan HPC Systems Engineer High End Computing Systems Group San Diego Supercomputer Center ctjordan(a)sdsc.edu 858.534.8347 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (Darwin) iD8DBQFEZe5aPCVtcXn6kg8RAtQuAJ9SWz9Ww6B/GWx3Mhiw3esieiOn8ACeLwAG nVJsC2/l+3+1tI0JaS56aqY= =UcSu -----END PGP SIGNATURE-----

1 0

Architecture Document V.6.0.4 Uploaded to Grid Forge
by Allen Luniewski 11 May '06

11 May '06

The latest version of the architecture document is now on Grid Forge and available from: /projects/ogsa-d-wg/document/Strawman-Architecture_V.6.0.4/en/1 This version reflects all changes agreed to in this mailing list and on our teleconferences since the previous version was uploaded. It also includes numerous comments, updates and additions from WG members. Finally, I made another editing pass to correct spelling errors, typos, issues with the prose, etc.. Please look over the document and send comments, changes, updates, corrections, etc. to the mailing list or to me, as appropriate. I will keep the lock on the document at this point just so that we do not get confusion from conflicting edits. If you wish to work on a section of the document, please drop me a line to get a virtual lock on the document. Allen

1 0

FW: BOUNCE ogsa-d-wg@ggf.org: Non-member submission from ["Marvin Theimer" <theimer@microsoft.com>]
by Dave Berry 08 May '06

08 May '06

Marvin's mail bounced. -----Original Message----- From: owner-ogsa-d-wg(a)ggf.org [mailto:owner-ogsa-d-wg@ggf.org] Sent: 07 May 2006 21:52 To: owner-ogsa-d-wg(a)ggf.org Subject: BOUNCE ogsa-d-wg(a)ggf.org: Non-member submission from ["Marvin Theimer" <theimer(a)microsoft.com>] >From owner-grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov Sun May 7 15:52:16 2006 Return-Path: <owner-grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov> X-Original-To: grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov Delivered-To: grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov Received: from localhost (localhost [127.0.0.1]) by mailbouncer.mcs.anl.gov (Postfix) with ESMTP id 6556912A04 for <grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov>; Sun, 7 May 2006 15:52:16 -0500 (CDT) Received: from mailbouncer.mcs.anl.gov ([127.0.0.1]) by localhost (mailbouncer.mcs.anl.gov [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 20217-04 for <grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov>; Sun, 7 May 2006 15:52:15 -0500 (CDT) Received: from mail3.microsoft.com (mailb.microsoft.com [131.107.1.8]) by mailbouncer.mcs.anl.gov (Postfix) with ESMTP id 7112412A16 for <ogsa-d-wg(a)gridforum.org>; Sun, 7 May 2006 15:52:14 -0500 (CDT) Received: from mailout5.microsoft.com ([157.54.69.148]) by mail3.microsoft.com with Microsoft SMTPSVC(6.0.3790.1830); Sun, 7 May 2006 13:52:14 -0700 Received: from RED-MSG-42.redmond.corp.microsoft.com ([157.54.61.167]) by mailout5.microsoft.com with Microsoft SMTPSVC(6.0.3790.1830); Sun, 7 May 2006 13:52:14 -0700 X-MimeOLE: Produced By Microsoft Exchange V6.5 Content-class: urn:content-classes:message MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----_=_NextPart_001_01C67218.107EBCFE" Subject: RE: [ogsa-wg] Initial draft of HPC profile working group charter Date: Sun, 7 May 2006 13:51:47 -0700 Message-ID: <19A328037921AA42847A717566D1D6A10811465F(a)RED-MSG-42.redmond.corp.micros oft.com> In-Reply-To: <C0829389.4349%david.wallom(a)ierc.ox.ac.uk> X-MS-Has-Attach: X-MS-TNEF-Correlator: Thread-Topic: [ogsa-wg] Initial draft of HPC profile working group charter thread-index: AcZv3YOIV4NrIcq3T8O0WWdBbEA4rAAb2oTQAAI5bCAANgJAeAA6bKQg From: "Marvin Theimer" <theimer(a)microsoft.com> To: "David Wallom" <david.wallom(a)ierc.ox.ac.uk>, "Dave Berry" <daveb(a)nesc.ac.uk>, <ogsa-wg(a)ggf.org>, <dmis-bof(a)ggf.org>, <ogsa-d-wg(a)gridforum.org> X-OriginalArrivalTime: 07 May 2006 20:52:14.0014 (UTC) FILETIME=[1E5275E0:01C67218] This is a multi-part message in MIME format. ------_=_NextPart_001_01C67218.107EBCFE Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable Hi; =20 As I've said from the beginning, I view data transfer as being something that can and should be able to stand separately. So creating a separate data profile certainly seems reasonable on first reflection. However, I would argue that the HPC profile will need to reference/incorporate that profile in some manner since and end-to-end vertical profile for HPC is meaningless without a data component to it. =20 We should definitely discuss this issue in the BoF. =20 Marvin. =20 ________________________________ From: David Wallom [mailto:david.wallom@ierc.ox.ac.uk]=20 Sent: Saturday, May 06, 2006 9:55 AM To: Marvin Theimer; Dave Berry; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; ogsa-d-wg(a)gridforum.org Subject: Re: [ogsa-wg] Initial draft of HPC profile working group charter =20 Hi Marvin, >From reading most of the correspondence on this topic and from various conversations about this with various people I was wondering if we could actually launch a separate Data profile since tacking this onto the end of the HPC profile could possibly prove limiting. I was wondering if the data discussion would be a specific part of the BOF? Regards David On 5/5/06 16:15, "Marvin Theimer" <theimer(a)microsoft.com> wrote: Hi; =20 You are right that most of the discussion so far has been about job submission and not about the related need to get data from client to execution subsystem(s) and back again. But since the goal of the group is to define a profile covering the end-to-end vertical use cases, I know that we will need to tackle the topic of data staging at some point. As with JSDL and BES's relation to the job submission parts of the work, I'm hoping we will be able to substantially leverage other existing work, such as that of the data DMIS groups, as appropriate. I'll make that more explicit in the next revision of the draft charter. =20 Thanks for pointing this matter out, Marvin. ________________________________ From: Dave Berry [mailto:daveb@nesc.ac.uk] <mailto:daveb@nesc.ac.uk%5d> Sent: Friday, May 05, 2006 7:14 AM To: Marvin Theimer; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; ogsa-d-wg(a)gridforum.org Subject: RE: [ogsa-wg] Initial draft of HPC profile working group charter Hi, All the discussion I've seen about this profile so far has focussed on specifying and submitting jobs, but the proposed charter says that this is only one of two areas of interest; the other being data staging. The immediate question is what link will this profile work have to the Data Movement Interface Specification group? Will the profile refer to the DMIS spec in the same way that it will refer to JSDL and BES? (Of course, JSDL also covers data staging to some extent). Work is also continuing on the data aspects of the OGSA architecture, in the OGSA Data WG. I would encourage the HPC profile group to engage with the OGSA Data group and the DMIS group concerning how to fit data staging into the overall architecture. Unfortunately I won't be in Tokyo next week but it would be useful if members of these groups could get together there to agree a working relationship. Best wishes, Dave. =09 ________________________________ =09 From: owner-ogsa-wg(a)ggf.org [mailto:owner-ogsa-wg@ggf.org] <mailto:owner-ogsa-wg@ggf.org%5d> On Behalf Of Marvin Theimer Sent: 05 May 2006 01:48 To: ogsa-wg(a)ggf.org Subject: [ogsa-wg] Initial draft of HPC profile working group charter Hi; =20 Enclosed is an initial draft of the OGSA HPC profile working group charter. This will be brought up for discussion at the HPC profile BoF at the upcoming GGF17 conferenece in Tokyo. In the mean time, please feel free to comment on the draft via email to this mailing list. =20 Thanks, Marvin. =20 --=20 +++++++++++++++++++++++++++++++++ Dr. David Wallom Technical Manager Oxford e-Research Centre University of Oxford c/o OUCS 13 Banbury Road Oxford OX2 6NN Tel : +44 (0)1865 283378 email: david.wallom(a)ierc.ox.ac.uk +++++++++++++++++++++++++++++++++ ------_=_NextPart_001_01C67218.107EBCFE Content-Type: text/html; charset="us-ascii" Content-Transfer-Encoding: quoted-printable <html xmlns:v=3D"urn:schemas-microsoft-com:vml" = xmlns:o=3D"urn:schemas-microsoft-com:office:office" = xmlns:w=3D"urn:schemas-microsoft-com:office:word" = xmlns:st1=3D"urn:schemas-microsoft-com:office:smarttags" = xmlns=3D"http://www.w3.org/TR/REC-html40"> <head> <META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; = charset=3Dus-ascii"> <meta name=3DGenerator content=3D"Microsoft Word 11 (filtered medium)">  <title>Re: [ogsa-wg] Initial draft of HPC profile working group = charter</title> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"Street"/> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"PlaceName"/> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"PlaceType"/> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"address"/> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"place"/> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"City"/> <o:SmartTagType = namespaceuri=3D"urn:schemas-microsoft-com:office:smarttags" name=3D"PersonName"/>  <style>  </style> </head> <body lang=3DEN-US link=3Dblue vlink=3Dblue> <div class=3DSection1> Hi;<o:p></o:p> <o:p> </o:p> As I’ve said from the beginning, I view data transfer as = being something that can and should be able to stand separately.  So = creating a separate data profile certainly seems reasonable on first = reflection.  However, I would argue that the HPC profile will need to reference/incorporate = that profile in some manner since and end-to-end vertical profile for HPC is meaningless without a data component to it.<o:p></o:p> <o:p> </o:p> We should definitely discuss this issue in the = BoF.<o:p></o:p> <o:p> </o:p> Marvin.<o:p></o:p> <o:p> </o:p> <div> <div class=3DMsoNormal align=3Dcenter style=3D'text-align:center'> <hr size=3D2 width=3D"100%" align=3Dcenter tabindex=3D-1> </div> From: David = Wallom [mailto:david.wallom@ierc.ox.ac.uk] Sent: Saturday, May 06, = 2006 9:55 AM To: <st1:PersonName = w:st=3D"on">Marvin Theimer</st1:PersonName>; Dave Berry; ogsa-wg(a)ggf.org; = dmis-bof(a)ggf.org; ogsa-d-wg(a)gridforum.org Subject: Re: [ogsa-wg] = Initial draft of HPC profile working group charter<o:p></o:p> </div> <o:p> </o:p> Hi Marvin, From reading most of the correspondence on this topic and from various conversations about this with various people I was wondering if we could actually launch a separate Data profile since tacking this onto the end = of the HPC profile could possibly prove limiting. I was wondering if the data discussion would be a specific part of the BOF? Regards David On 5/5/06 16:15, "<st1:PersonName w:st=3D"on">Marvin = Theimer</st1:PersonName>" <theimer(a)microsoft.com> wrote:<o:p></o:p> Hi;   You are right that most of the discussion so far has been about job = submission and not about the related need to get data from client to execution subsystem(s) and back again.  But since the goal of the group is to = define a profile covering the end-to-end vertical use cases, I know that we = will need to tackle the topic of data staging at some point.  As with JSDL = and BES’s relation to the job submission parts of the work, I’m = hoping we will be able to substantially leverage other existing work, such as = that of the data DMIS groups, as appropriate.  I’ll make that more = explicit in the next revision of the draft charter.   Thanks for pointing this matter out, Marvin.<o:p></o:p> <div class=3DMsoNormal align=3Dcenter style=3D'text-align:center'> <hr size=3D2 width=3D"100%" align=3Dcenter> </div> From: Dave Berry [<a href=3D"mailto:daveb@nesc.ac.uk%5d">mailto:daveb@nesc.ac.uk]</a> Sent: Friday, May 05, = 2006 7:14 AM To: <st1:PersonName = w:st=3D"on">Marvin Theimer</st1:PersonName>; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; ogsa-d-wg(a)gridforum.org Subject: RE: [ogsa-wg] = Initial draft of HPC profile working group charter Hi, All the discussion I've seen about this profile so far = has focussed on specifying and submitting jobs, but the proposed charter = says that this is only one of two areas of interest; the other being data staging.  The immediate question is what link will this profile work have to = the Data Movement Interface Specification group?  Will the profile = refer to the DMIS spec in the same way that it will refer to JSDL and BES? =  (Of course, JSDL also covers data staging to some extent). Work is also continuing on the data aspects of the = OGSA architecture, in the OGSA Data WG.  I would encourage the HPC = profile group to engage with the OGSA Data group and the DMIS group concerning = how to fit data staging into the overall architecture. Unfortunately I won't be in <st1:City = w:st=3D"on"><st1:place w:st=3D"on">Tokyo</st1:place></st1:City> next week but it would be = useful if members of these groups could get together there to agree a working relationship. Best wishes, Dave.<o:p></o:p> <blockquote style=3D'margin-top:5.0pt;margin-bottom:5.0pt'> <div class=3DMsoNormal align=3Dcenter style=3D'text-align:center'> <hr size=3D2 width=3D"100%" align=3Dcenter> </div> From: owner-ogsa-wg(a)ggf.org [<a = href=3D"mailto:owner-ogsa-wg@ggf.org%5d">mailto:owner-ogsa-wg@ggf.org]</ a= > On Behalf Of = <st1:PersonName w:st=3D"on">Marvin Theimer</st1:PersonName> Sent: 05 May 2006 = 01:48 To: ogsa-wg(a)ggf.org Subject: [ogsa-wg] = Initial draft of HPC profile working group charter Hi;   Enclosed is an initial draft of the OGSA HPC profile working group = charter.  This will be brought up for discussion at the HPC profile BoF at = the upcoming GGF17 conferenece in <st1:City w:st=3D"on"><st1:place = w:st=3D"on">Tokyo</st1:place></st1:City>.  In the mean time, please feel free to comment on the draft via = email to this mailing list.   Thanks, Marvin.<o:p></o:p> </blockquote> <o:p> </o:p> -- +++++++++++++++++++++++++++++++++ Dr. David Wallom Technical Manager <st1:City w:st=3D"on"><st1:place = w:st=3D"on">Oxford</st1:place></st1:City> e-Research Centre <st1:place w:st=3D"on"><st1:PlaceType = w:st=3D"on">University</st1:PlaceType> of <st1:PlaceName w:st=3D"on">Oxford</st1:PlaceName></st1:place> c/o OUCS <st1:Street w:st=3D"on"><st1:address w:st=3D"on">13 Banbury = Road</st1:address></st1:Street> <st1:City w:st=3D"on"><st1:place = w:st=3D"on">Oxford</st1:place></st1:City> OX2 6NN Tel  : +44 (0)1865 283378 email: david.wallom(a)ierc.ox.ac.uk +++++++++++++++++++++++++++++++++<o:p></o:p> </div> </body> </html> ------_=_NextPart_001_01C67218.107EBCFE--

1 0

FW: BOUNCE ogsa-d-wg@ggf.org: Non-member submission from [David Wallom <david.wallom@ierc.ox.ac.uk>]
by Dave Berry 06 May '06

06 May '06

David's message bounced. -----Original Message----- From: owner-ogsa-d-wg(a)ggf.org [mailto:owner-ogsa-d-wg@ggf.org] Sent: 06 May 2006 17:55 To: owner-ogsa-d-wg(a)ggf.org Subject: BOUNCE ogsa-d-wg(a)ggf.org: Non-member submission from [David Wallom <david.wallom(a)ierc.ox.ac.uk>] >From owner-grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov Sat May 6 11:55:18 2006 Return-Path: <owner-grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov> X-Original-To: grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov Delivered-To: grdfm-ogsa-d-wg(a)mailbouncer.mcs.anl.gov Received: from localhost (localhost [127.0.0.1]) by mailbouncer.mcs.anl.gov (Postfix) with ESMTP id 53AD112AAF; Sat, 6 May 2006 11:55:18 -0500 (CDT) Received: from mailbouncer.mcs.anl.gov ([127.0.0.1]) by localhost (mailbouncer.mcs.anl.gov [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 12565-01; Sat, 6 May 2006 11:55:17 -0500 (CDT) Received: from relay6.mail.ox.ac.uk (relay6.mail.ox.ac.uk [163.1.2.167]) by mailbouncer.mcs.anl.gov (Postfix) with ESMTP id 9887712A9E; Sat, 6 May 2006 11:55:16 -0500 (CDT) Received: from smtp2.herald.ox.ac.uk ([163.1.0.235]) by relay6.mail.ox.ac.uk with esmtp (Exim 4.54) id 1FcQ3m-0003LY-LM; Sat, 06 May 2006 17:55:14 +0100 Received: from bb-87-80-250-26.ukonline.co.uk ([87.80.250.26] helo=[192.168.0.2]) by smtp2.herald.ox.ac.uk with asmtp (TLSv1:DES-CBC3-SHA:168) (Exim 3.36 #1) id 1FcQ3m-0002TS-02; Sat, 06 May 2006 17:55:14 +0100 User-Agent: Microsoft-Entourage/11.2.3.060209 Date: Sat, 06 May 2006 17:55:21 +0100 Subject: Re: [ogsa-wg] Initial draft of HPC profile working group charter From: David Wallom <david.wallom(a)ierc.ox.ac.uk> To: Marvin Theimer <theimer(a)microsoft.com>, Dave Berry <daveb(a)nesc.ac.uk>, <ogsa-wg(a)ggf.org>, <dmis-bof(a)ggf.org>, <ogsa-d-wg(a)gridforum.org> Message-ID: <C0829389.4349%david.wallom(a)ierc.ox.ac.uk> Thread-Topic: [ogsa-wg] Initial draft of HPC profile working group charter Thread-Index: AcZv3YOIV4NrIcq3T8O0WWdBbEA4rAAb2oTQAAI5bCAANgJAeA== In-Reply-To: <19A328037921AA42847A717566D1D6A108113F7C(a)RED-MSG-42.redmond.corp.micros oft.com> Mime-version: 1.0 Content-type: multipart/alternative; boundary="B_3229782922_2900600" > This message is in MIME format. Since your mail reader does not > understand this format, some or all of this message may not be legible. --B_3229782922_2900600 Content-type: text/plain; charset="ISO-8859-1" Content-transfer-encoding: quoted-printable Hi Marvin, >From reading most of the correspondence on this topic and from various conversations about this with various people I was wondering if we could actually launch a separate Data profile since tacking this onto the end of the HPC profile could possibly prove limiting. I was wondering if the data discussion would be a specific part of the BOF? Regards David On 5/5/06 16:15, "Marvin Theimer" <theimer(a)microsoft.com> wrote: > Hi; > =20 > You are right that most of the discussion so far has been about job > submi= ssion > and not about the related need to get data from client to execution > subsystem(s) and back again. But since the goal of the group is to > defin= e a > profile covering the end-to-end vertical use cases, I know that we > will n= eed > to tackle the topic of data staging at some point. As with JSDL and > BES=B9= s > relation to the job submission parts of the work, I=B9m hoping we will > be a= ble > to substantially leverage other existing work, such as that of the > data D= MIS > groups, as appropriate. I=B9ll make that more explicit in the next > revisio= n of > the draft charter. > =20 > Thanks for pointing this matter out, > Marvin. > =20 >=20 >=20 > From: Dave Berry [mailto:daveb@nesc.ac.uk] > Sent: Friday, May 05, 2006 7:14 AM > To: Marvin Theimer; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; >ogsa-d-wg@gridforu= m.org > Subject: RE: [ogsa-wg] Initial draft of HPC profile working group > charter =20 Hi, > =20 > All the discussion I've seen about this profile so far has focussed on > specifying and submitting jobs, but the proposed charter says that this i= s > only one of two areas of interest; the other being data staging. The > immediate question is what link will this profile work have to the > Data Movement Interface Specification group? Will the profile refer > to the DM= IS > spec in the same way that it will refer to JSDL and BES? (Of course, > JSD= L > also covers data staging to some extent). > =20 > Work is also continuing on the data aspects of the OGSA architecture, > in = the > OGSA Data WG. I would encourage the HPC profile group to engage with > the= OGSA > Data group and the DMIS group concerning how to fit data staging into > the overall architecture. =20 > Unfortunately I won't be in Tokyo next week but it would be useful if mem= bers > of these groups could get together there to agree a working > relationship. =20 Best wishes, > =20 > Dave. >> =20 >>=20 >>=20 >> From: owner-ogsa-wg(a)ggf.org [mailto:owner-ogsa-wg@ggf.org] On Behalf >>Of Marvin Theimer >> Sent: 05 May 2006 01:48 >> To: ogsa-wg(a)ggf.org >> Subject: [ogsa-wg] Initial draft of HPC profile working group charter >>Hi; =20 >> Enclosed is an initial draft of the OGSA HPC profile working group chart= er. >> This will be brought up for discussion at the HPC profile BoF at the >> upc= oming >> GGF17 conferenece in Tokyo. In the mean time, please feel free to >> comme= nt on >> the draft via email to this mailing list. >> =20 >> Thanks, >> Marvin. >=20 --=20 +++++++++++++++++++++++++++++++++ Dr. David Wallom Technical Manager Oxford e-Research Centre University of Oxford c/o OUCS 13 Banbury Road Oxford OX2 6NN Tel : +44 (0)1865 283378 email: david.wallom(a)ierc.ox.ac.uk +++++++++++++++++++++++++++++++++ --B_3229782922_2900600 Content-type: text/html; charset="ISO-8859-1" Content-transfer-encoding: quoted-printable <HTML> <HEAD> <TITLE>Re: [ogsa-wg] Initial draft of HPC profile working group charter</TI= TLE> </HEAD> <BODY> Hi Ma= rvin, From reading most of the correspondence on this topic and from various conv= ersations about this with various people I was wondering if we could actuall= y launch a separate Data profile since tacking this onto the end of the HPC = profile could possibly prove limiting. I was wondering if the data discussio= n would be a specific part of the BOF? Regards David On 5/5/06 16:15, "Marvin Theimer" <theimer(a)microsoft.com> w= rote: <BLOCKQUOTE><SPAN= STYLE=3D'font-size:16.0px'>Hi;   You are right that most of the discussion so far has been about job submiss= ion and not about the related need to get data from client to execution subs= ystem(s) and back again.  But since the goal of the group is to define = a profile covering the end-to-end vertical use cases, I know that we will ne= ed to tackle the topic of data staging at some point.  As with JSDL and= BES’s relation to the job submission parts of the work, I’m hop= ing we will be able to substantially leverage other existing work, such as t= hat of the data DMIS groups, as appropriate.  I’ll make that more= explicit in the next revision of the draft charter.   Thanks for pointing this matter out, Marvin. = <HR ALIGN=3DCENTER SIZE=3D"2" WIDTH=3D"100%"> From:<= /B> Dave Berry [<a href=3D"mailto:daveb@nesc.ac.uk]">mailto:daveb@nesc.ac.uk]<= /a> Sent: Friday, May 05, 2006 7:14 AM To: Marvin Theimer; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; ogsa-d-wg@gri= dforum.org Subject: RE: [ogsa-wg] Initial draft of HPC profile working group ch= arter Hi, <SP= AN STYLE=3D'font-size:16.0px'> All the discussion I've seen about this pro= file so far has focussed on specifying and submitting jobs, but the proposed= charter says that this is only one of two areas of interest; the other bein= g data staging.  The immediate question is what link will this profile = work have to the Data Movement Interface Specification group?  Will the= profile refer to the DMIS spec in the same way that it will refer to JSDL a= nd BES?  (Of course, JSDL also covers data staging to some extent). <SP= AN STYLE=3D'font-size:16.0px'> Work is also continuing on the data aspects= of the OGSA architecture, in the OGSA Data WG.  I would encourage the = HPC profile group to engage with the OGSA Data group and the DMIS group conc= erning how to fit data staging into the overall architecture. <SP= AN STYLE=3D'font-size:16.0px'> Unfortunately I won't be in Tokyo next week= but it would be useful if members of these groups could get together there = to agree a working relationship. <SP= AN STYLE=3D'font-size:16.0px'> Best wishes, <SP= AN STYLE=3D'font-size:16.0px'> Dave. <BLOCKQUOTE>=20 = <HR ALIGN=3DCENTER SIZE=3D"2" WIDTH=3D"100%"> From: owner-ogsa-wg(a)ggf.org [<a href=3D"mailto:owner-ogsa-wg@ggf.o= rg]">mailto:owner-ogsa-wg@ggf.org]</a> On Behalf Of Marvin Theimer<BR= > Sent: 05 May 2006 01:48 To: ogsa-wg(a)ggf.org Subject: [ogsa-wg] Initial draft of HPC profile working group charte= r Hi;   Enclosed is an initial draft of the OGSA HPC profile working group charter.=  This will be brought up for discussion at the HPC profile BoF at the = upcoming GGF17 conferenece in Tokyo.  In the mean time, please feel fre= e to comment on the draft via email to this mailing list.   Thanks, Marvin. </BLOCKQUOTE><S= PAN STYLE=3D'font-size:12.0px'> </BLOCKQUOTE> -- +++++++++++++++++++++++++++++++++ Dr. David Wallom Technical Manager Oxford e-Research Centre University of Oxford c/o OUCS 13 Banbury Road Oxford OX2 6NN Tel  : +44 (0)1865 283378 email: david.wallom(a)ierc.ox.ac.uk +++++++++++++++++++++++++++++++++ </BODY> </HTML> --B_3229782922_2900600--

1 0

FW: [ogsa-wg] Initial draft of HPC profile working group charter
by Dave Berry 05 May '06

05 May '06

Marvin's message bounced. _____ From: Marvin Theimer [mailto:theimer@microsoft.com] Sent: 05 May 2006 16:15 To: Dave Berry; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; ogsa-d-wg(a)gridforum.org Subject: RE: [ogsa-wg] Initial draft of HPC profile working group charter Hi; You are right that most of the discussion so far has been about job submission and not about the related need to get data from client to execution subsystem(s) and back again. But since the goal of the group is to define a profile covering the end-to-end vertical use cases, I know that we will need to tackle the topic of data staging at some point. As with JSDL and BES's relation to the job submission parts of the work, I'm hoping we will be able to substantially leverage other existing work, such as that of the data DMIS groups, as appropriate. I'll make that more explicit in the next revision of the draft charter. Thanks for pointing this matter out, Marvin. _____ From: Dave Berry [mailto:daveb@nesc.ac.uk] Sent: Friday, May 05, 2006 7:14 AM To: Marvin Theimer; ogsa-wg(a)ggf.org; dmis-bof(a)ggf.org; ogsa-d-wg(a)gridforum.org Subject: RE: [ogsa-wg] Initial draft of HPC profile working group charter Hi, All the discussion I've seen about this profile so far has focussed on specifying and submitting jobs, but the proposed charter says that this is only one of two areas of interest; the other being data staging. The immediate question is what link will this profile work have to the Data Movement Interface Specification group? Will the profile refer to the DMIS spec in the same way that it will refer to JSDL and BES? (Of course, JSDL also covers data staging to some extent). Work is also continuing on the data aspects of the OGSA architecture, in the OGSA Data WG. I would encourage the HPC profile group to engage with the OGSA Data group and the DMIS group concerning how to fit data staging into the overall architecture. Unfortunately I won't be in Tokyo next week but it would be useful if members of these groups could get together there to agree a working relationship. Best wishes, Dave. _____ From: owner-ogsa-wg(a)ggf.org [mailto:owner-ogsa-wg@ggf.org] On Behalf Of Marvin Theimer Sent: 05 May 2006 01:48 To: ogsa-wg(a)ggf.org Subject: [ogsa-wg] Initial draft of HPC profile working group charter Hi; Enclosed is an initial draft of the OGSA HPC profile working group charter. This will be brought up for discussion at the HPC profile BoF at the upcoming GGF17 conferenece in Tokyo. In the mean time, please feel free to comment on the draft via email to this mailing list. Thanks, Marvin.

1 0

RE: [ogsa-wg] Initial draft of HPC profile working group charter
by Dave Berry 05 May '06

05 May '06

Hi, All the discussion I've seen about this profile so far has focussed on specifying and submitting jobs, but the proposed charter says that this is only one of two areas of interest; the other being data staging. The immediate question is what link will this profile work have to the Data Movement Interface Specification group? Will the profile refer to the DMIS spec in the same way that it will refer to JSDL and BES? (Of course, JSDL also covers data staging to some extent). Work is also continuing on the data aspects of the OGSA architecture, in the OGSA Data WG. I would encourage the HPC profile group to engage with the OGSA Data group and the DMIS group concerning how to fit data staging into the overall architecture. Unfortunately I won't be in Tokyo next week but it would be useful if members of these groups could get together there to agree a working relationship. Best wishes, Dave. _____ From: owner-ogsa-wg(a)ggf.org [mailto:owner-ogsa-wg@ggf.org] On Behalf Of Marvin Theimer Sent: 05 May 2006 01:48 To: ogsa-wg(a)ggf.org Subject: [ogsa-wg] Initial draft of HPC profile working group charter Hi; Enclosed is an initial draft of the OGSA HPC profile working group charter. This will be brought up for discussion at the HPC profile BoF at the upcoming GGF17 conferenece in Tokyo. In the mean time, please feel free to comment on the draft via email to this mailing list. Thanks, Marvin.

1 0