=================================
Present: Dave Britton(Chair), Pete Clarke, Tony Doyle, Roger Jones, Dave Kelsey, Steve Lloyd, Andrew McNab, Andrew Sansum, Gareth Smith, Louisa Campbell (Minutes).
Apologies: Tony Cass, David Colling, Pete Gronbech, Jeremy Coles.
1. GridPP37 Agenda
=========================
Session 1: CHAIR – DB??
Intro – DB (30 Mins)
GridPP5 and WLCG. Plenty of time built in for discussions.
Session 2: CHAIR – ???
Focus on discussion re the accounting system. This
is a good opportunity to air views and reach consensus on essential elements that require to be pushed. Alessandra is unable to attend but John Gordon may speak or contribute to discussion.
GOCBD: George Ryall
APEL: Adrian Coveney
Benchmarking and Publishing at a Diverse Grid Site: Stephen Jones.
Session 3: CHAIR – JC
Overview of lightweight sites: JC
Storage evolution: Sam Skipsey
Open Discussion
Compute approaches: Vac updates: AM;
Stealth cloud: Daniella Bauer; and
Hybrid & Site Clouds: (DB will follow
up with JC)
Service Evolution: Andrew Lahiff (he will produce slides for Ian to give talk)
Evolution Information System – JC will give an overview but may be better placed in Session 1 or 2 as it is a taskforce and more relevant in these sessions. AM will speak to JC. Some slides went through MB on this and the timeframe and whether there will be site impact are of particular interest (10 mins).
Session title “Site (r)evolution” is good title for whole GridPP37 meeting
Session 4: CHAIR – ???
Tier-1 Status & Plans – GS will cover operational and AS
will cover strategic elements
CEPH Status & Plans – is an important element which rightly
has a defined slot.
It may be appropriate to ask the experiments for statements regarding some recent issues that may be pertinent. ATLAS, ALICE, CMS, LHCB can be asked to outline their intended use of CEPH. Alastair’s plans differ from HEPIX re technicalities surrounding CEPH, the planned rollout, how experiments are successful in engaging, etc. DB asked who best to direct these questions to/offer a contribution. Chris Fawkes is attending and may be able to discuss with colleagues
THURSDAY AFTERNOON: Self-organised hierarchical groups as usual. PG, PC and AM may organise A group; SL & RJ will lead B group; C group may not require leadership. Weather – reported to be “mixed with some showers”.
Collaboration dinner at Best Western Salutation Hotel: Reserved, sponsors have been contacted by the venue re payment, dinner menus agreed, wine ordered and one welcome drink per delegate arranged.
Session 5: CHAIR – PC
External Focus: PC
LSST: George Beckett
SKA: JC to cover and ensure this is kept visible as a mainstream element of this GridPP
DiRAC file transfers: Brian Davis
Ganga: Robert Currie
CMS at Home: Ivan Reid – DC noted interesting ongoing elements so this is a good opportunity to have Ivan contribute, particularly since we are giving some funding to Brunel to attend CEPH.
Session 6: CHAIR – DK
Security update: David Crooks (discussion with Ian Neilson on content)
Security in the wider world: DK
WLCG and support for IPv6-only CPU: Alastair Dewhurst
IPv6 testing at QMUL: Dan Traynor and Terry Froy.
Agenda is in very good shape. There is ample time allocated for discussion to provide opportunities for delegates to discuss any relevant issues.
F2F agenda – details as yet unconfirmed. It was suggested that metrics and milestones for GridPP5 should be revisited. LHCb metrics should be amended – AM has agreed this with PG for the coming quarter. Milestones and Metrics for GridPP5 should be included, DB will firm up with PG for inclusion in the agenda to finalise before the oversight committee. Risk Register, procedure changes and corporate reporting etc will require to be signed off (part of “GridPP5 plans” placeholder on the agenda). Content of F2F will point towards the oversight committee and ensuring all elements are in good shape. Alastair’s talk should focus on less technical elements – more focus should be on elements such as risks, assessment of data, engagement with communities and other management matters. Alison Packer is also attending the PMB relating to this presentation – AS will discuss with her content and context of PMB.
Consideration will need to be given to a location for GridPP38 – possibly at Pitlochry again if there are no volunteer institutes, but the costs are often high for universities. Suggestions should be sought at the meeting.
Any other comments/suggestions should be urgently directed to DB.
ACTION 604.1: AM will discuss moving ‘The Evolving Information System’ to Session with with JC and PG
ACTION 604.2: DB to arrange chairs for sessions which do not already have one assigned.
2. AOCB
=======
a) Insufficient Reports submitted
b) OPN Update
3. Standing Items
===================
SI-0 Bi-Weekly Report from Technical Group (DC)
———————————————–
DC absent – no report submitted.
SI-1 Dissemination Report (SL)
——————————
Nothing of significance to report.
SI-2 ATLAS Weekly Review and Plans (RJ)
—————————————
Nothing of significance to report.
SI-3 CMS Weekly Review and Plans (DC)
————————————-
Liverpool disappeared from SAM tests – this is an issue relating to how LHCb conduct tests which has been resolved.
SI-4 LHCb Weekly Review and Plans (PC)
————————————–
Nothing of significance to report.
SI-5 Production Manager’s report (JC)
————————————-
Nothing of significance to report.
SI-6 Tier-1 Manager’s Report (GS)
———————————
Networking:
– The ‘doubled’ OPN link has worked well so far. I attach a plot showing the last month (see Appendix I).
– We have seen some periods of high packet loss across our internal Tier1 network this last week. We are investigating but the cause is, as yet, not understood.
Castor:
– Testing of Castor 2.1.15 is proceeding OK.
– There was a problem on Castor that affected the Atlas instance on the evening of 9th August. It was resolved by the on-call team and fixed by a restart of one of the SRM nodes. There was also a problem that affected the ‘GEN’ instance on 12th August. This was caused by a disk problem in one of the nodes in the database behind Castor. Again, fixed by the on-call team.
Tape System:
– We are scheduling a ‘preventative maintenance’ on the tape libraries.
– The migration of Atlas data from the ‘C’ to ‘D’ media is complete. The migration of LHCb data is awaiting the purchase of some more
‘D’ tape drives.
Batch System:
– HPE Worker nodes: Almost all have done the benchmarking. There is some re-cabling to be done by HPE before they go into the batch system.
SI-7 LCG Management Board Report of Issues (DB)
———————————————–
MB was cancelled therefore no report.
SI-8 External Contexts (PG)
———————————
Nothing of significance to report.
REVIEW OF ACTIONS
=================
ACTIONS AS OF 08.08.16
======================
600.1: DC to contact Julia Sedgebeer at Imperial to informally discuss and address SuperNemo’s computing needs and request Daniella and Tom to await outcome of these discussions before progressing further. Ongoing.
600.2: DB/PC will consider whether to contact the head of SuperNemo in the UK discussing support requirements. (UPDATE: since PPAP meeting PC noted there was some relevant activity Heads in the audience who received the clear message on engaging with GridPP and ethos they should adopt). Done.
602.2: AM and AS to resolve the LHCb request at the end of July. Ongoing.
602.3: AS will request that Jens make a presentation to the PMB supported by a written report on plans for AAAI project with Dirac as well as proposed reporting. Ongoing. (UPDATE: this could perhaps be presented at GridPP37 Session 6, but looks unlikely).
602.4: AS will contact Charlotte to determine how much effort in total STFC funding in the AAAI project so that we can see if there are other contributions we should expect. Ongoing
602.8: JC will discuss with Anna the possibility of giving a talk at non-LHC VO session and put together a session with suggested speakers, e.g. Sam Skipsey and Brian. Done.
602.9: AS will consider potential content for Tier1 session. Done.
603.1: AS will discuss with Yens and confirm agreement for 150 TB tape storage capacity for the Nuclear Physics request on the provision it can be accessed by existing mechanisms in the GridPP suite of tools. Ongoing.
603.2: DK will circulate costings for OPN links to determine which options would be affordable. Perhaps discuss at F2F. Ongoing.
603.3: PG will include an item on F2F agenda for costs so that decisions can be made on the best way forward for OPN load. Ongoing.
603.4: PG will invite Ian Collier to present and others for Session 1 & 2. Done.
603.5: JC to invite speakers for session 3. Done.
603.6: DK will contact Duncan Rand and Dan Traynor and invite them to speak. Done.
603.7: AS will contact Andrew Lahiff to discuss a talk in session 4. Done.
603.8: DB will discuss external contacts with PC and invite Ivan Reid to give a talk. Done.
ACTIONS AS OF 22.08.16
======================
600.1: DC to contact Julia Sedgebeer at Imperial to informally discuss and address SuperNemo’s computing needs and request Daniella and Tom to await outcome of these discussions before progressing further. Ongoing.
602.2: AM and AS to resolve the LHCb request at the end of July. Ongoing.
602.3: AS will request that Jens make a presentation to the PMB supported by a written report on plans for AAAI project with Dirac as well as proposed reporting. Ongoing. (UPDATE: this could perhaps be presented at GridPP37 Session 6, but looks unlikely).
602.4: AS will contact Charlotte to determine how much effort in total STFC funding in the AAAI project so that we can see if there are other contributions we should expect. Ongoing
603.1: AS will discuss with Yens and confirm agreement for 150 TB tape storage capacity for the Nuclear Physics request on the provision it can be accessed by existing mechanisms in the GridPP suite of tools. Ongoing.
603.2: DK will circulate costings for OPN links to determine which options would be affordable. Perhaps discuss at F2F. Ongoing.
603.3: PG will include an item on F2F agenda for costs so that decisions can be made on the best way forward for OPN load. Ongoing.
604.1: AM will discuss moving ‘The Evolving Information System’ to Session with with JC and PG
604.2: DB to arrange chairs for sessions which do not already have one assigned.