=================================
Present: Dave Britton (Chair), Tony Cass, Pete Clarke, Jeremy Coles, David Colling, Pete Gronbech, Roger Jones, Steve Lloyd, Andrew McNab, Andrew Sansum, Louisa Campbell (Minutes).
Apologies: Alastair Dewhurst, Tony Doyle, Dave Kelsey.
1. IRIS Site Selection
======================
DB summarised IRIS identified a sum of money (c. £500K) for h/w for GridPP to provide services to IRIS clients and it was decided to go to sites with a long-term future in supporting disks. Glasgow and Manchester were eliminated – QMUL, Imperial and Lancaster expressed an interest. DB proposed Imperial and Lancaster split the funds if they can accept the conditions contained in the document and submit a draft proposal before end of this week before the submission deadline on 2 July. Also Imperial should confirm the move to Slough will not be problematic. DC believes this will be supported as this is a research facility that will support reasonable growth. This can be seen as support for LZ and LSST and members of DUNE as well as other internal projects – DC has been in discussion with the leaders of these projects at Imperial. DC justified as part of a national and international infrastructure that supports many different activities as part of IRIS. GridPP is underwriting this and it was agreed that GridPP could progress with the proposal. DC and RJ will produce a draft by the end of this week and DB will merge into one document before the submission deadline.
2. UKRI Infrastructure Survey
=============================
Jeremy Yates mentioned Dirac had received the second Infrastructure Survey and DB contacted Claire Deveraux to receive a copy and which he has circulated to PMB members. Most of the feedback provided by DB on version 1 has been incorporated. The deadline for submission is 15 July.
Action 672.1: DB will complete the UKRI Infrastructure Survey and request comments from the PMB by 02/07/18.
3. GridPP6 Background Documents
===============================
DB circulated an email requesting these documents be initiated over the coming 6-8 weeks then built into the agenda for GridPP41 to instigate discussions on the potential shape of GridPP6. It may be useful to have a PMB member to lead each strand and some PMB members could attend an Ops meeting to provide an overview.
There are 5 potential background documents to prepare in the first instance:
a) Storage – Disk storage is defined at Tier1 by the ECHO/CEPH project and technology is in hand, but technologies at Tier2 sites requires consideration and limitations/alternatives. Storage should consider the landscape and storage for the future to provide background for the GridPP6 proposal – i.e. vision and options for the future. There was some discussion on distribution of storage to GridPP and other communities and the document should address community management. Groups should be prompted on the key elements/scenarios that should be considered for inclusion in the documents, e.g. EOS, vision for large sites to develop in conjunction with IRIS, small CPU dominated sites remain close to GridPP, etc. This could be raised at Ops meeting on Tuesday. PC raised the issue of data-management technology such as RUCIO: DB agreed that this should also be part of the discussion. AD is very familiar with RUCIO stuff and could help here.
Action 672.2: JC and/or PG and/or PC to brief Ops-meeting and request storage group draft background document. AD to contribute,
b) Experiment Support posts – previous suggestions were to describe these as workflow experts and the possibility of whether these should continue as LHC posts or pool posts with links to specific communities. Long-term incumbents (e.g. AD, Andrew Lahiff, Raja) should be asked for input in conjunction with PMB experiment reps to draft future driving needs/strategy for these posts. Janus and Dan should also be included, though their roles are clearer (ie embedded into other experiments for significant timescales). One post is covered by PPD and consideration should be given as to whether this format should continue. Experiments could be asked for input and then sign-off on the GridPP6 bid – letters of support have previously been used and a single letter could be used for all.
Action 672.3: RJ, DK and AM to draft the Experiment Support background document
c) Security, Trust and Identity – currently there are 3 different areas of security and correct terminologies should be applied. This be joining up with broader infrastructure and the trajectory should be considered – the security team should be involved (David Crooks is now the security officer and DK formally leads). UK (IRIS and joined-up UK activity for us to participate in), WLCG we have been playing a leading role but the impact of Brexit is not yet clear – EU funding historically has been critical. Priorities should be understood and flexibility in requirements so this is an opportunity for the security team to present requirements and articulate the risks of not funding specific areas.
Action 672.4: DK to draft the Security, Trust and Identity background document.
d) Tier1 – how will this be organised, what services will it provide and what staff are required will be covered in the Tier1 review in September and should not be duplicated. This background document should instead cover the vision, etc. E.g. migration to Echo, what is required for tape and what else is required re IRIS etc. This is a large part of the GridPP6 budget and must be clearly justifiable. This requires thought on direction of travel, restructuring and a visionary approach taking account of IRIS etc.
Action 672.5: AD to draft the Tier1 background document.
e) Tier2 – the Tier-2 posts need careful consideration – the language re research support at institutes should be well developed and well presented. Posts are embedded into s/w regardless of h/w, impact of this on lightweight sites from GridPP5 should be included – e.g. in sites such as Birmingham that have research contribution the roles are essential. Mention should also be made of Cloud experience.
Action 672.6: JC, SL (larger sites) AM and PG (lightweight and medium sites) to draft the Tier2 background document.
Action 672.7: PG will consider the agenda for GridPP41 incorporating the GridPP6 Background Documents.
4. AOCB
=======
a) PG is making a final push to submit final reports and would appreciate submission of QRs asap.
5. Standing Items
===================
SI-0 Bi-Weekly Report from Technical Group (DC)
———————————————–
Nothing significant to report.
SI-1 ATLAS Weekly Review and Plans (RJ)
—————————————
Nothing significant to report.
SI-2 CMS Weekly Review and Plans (DC)
————————————-
Nothing significant to report.
SI-3 LHCb Weekly Review and Plans (PC)
————————————–
There is an ongoing issue with pilots that are being killed and this is being investigated.
SI-4 Production Manager’s report (JC)
————————————-
LSST is now running jobs smoothly on the Grid. If this works out production will commence.
A period of low production was traced and will be included in a report.
SI-5 Tier-1 Manager’s Report (AD)
———————————
No report received.
SI-6 LCG Management Board Report of Issues (DB)
———————————————–
WLCG MB – DB attended and there was a talk on EuroHPC – European wide HPC project not including the UK which appears to relate to Europe building largescale facilities. Convergence with PRACE is not clear.
There was a talk on the applications area.
Discussion on moving effectively to quarterly pledges, but this is driven from CMS re wanting to profile pledges over the year and Atlas made comments. The discussion rather conflated issues on pledges and benchmarking (and an Atlas issue of not knowing what resources are actually available if pledges are late). Changes to Rebus for handling quarterly pledges will be considered.
DOMA update on work in different areas, but there was not much substance.
Outcome of LHC review – high luminosity computing TDR has been requested and WLCG felt this was slightly premature. Now, instead, there will be a review early next year and the TDR has been pushed back to 2022-2023. Focus of review will be on the WLCG strategy document plus progress made before the review.
DK updated GDPR status – original plan was to wait for GEANT’s version 2 was to be written and approved but this looks difficult and has been delayed. CERN will not sign a EU code of conduct for various reasons so the production of a lightweight code of conduct for WLCG is planned entitled security framework, or similar. All WLCG sites are bound to WLCG policy and this code of conduct will not need individual signatures.
SI-7 External Contexts (PC)
———————————
Nothing significant to report.
PC mentioned we should be aware STFC management have advised they want draft projects driven by science to address potential future funding streams. One group should be Infrastructure (1 large, 1 medium and some smaller projects) and we could bring in s/w engineers. There was a doodle poll for a meeting in July to develop these ideas.
REVIEW OF ACTIONS
=================
644.4: AD will progress capture of funds for Dirac with Mark Wilkinson. (Update: funding from DIRAC. AS has emailed Mark. They are now using it more heavily. Could use the money for tape, but have to be careful not to buy tape we won’t use. May be better charging later rather than during this FY? AD will now progress). Ongoing.
663.3: RJ and DC will advise how the experiments want disk divided for the start of Run 3 (Alice and LHCb are resolved). (Update: DB will write to DK with DC in copy with proposed way forward). Ongoing.
665.2: AD will produce Procurement schedule for the coming FY to build in an additional month to buffer any delays in the future. Ongoing.
667.1 PG Clarify with STFC what exactly is required for the OC feedback. wrt the Capital reporting. Ongoing.
667.2 Need to do h/w planning before next OC to provide OC with details of shortfall in funds. Ongoing.
670.1 Discussion Papers to be written for GridPP41, Storage, Expt support, others? Done.
670.2: DB and PG will consider percentage splits of CPU/Disk. Ongoing.
670.3: DB, PG and PC will undertake a high-level discussion of planning manpower for in GridPP6. Ongoing.
670.4 PG Invite Tim to give a talk on the Atlas Liaison Role at GridPP41. Done.
671.1: DB will discuss with the sites involved for IRIS h/w allocation and make recommendations to the PMB to consider. Ongoing
671.2: PG and AM to check if there is a common requirement across the Grid that can be negotiated with Dell for a framework agreement (e.g. Storage, Compute, Configurations). Ongoing.
ACTIONS AS OF 25/06/18
======================
644.4: AD will progress capture of funds for Dirac with Mark Wilkinson. (Update: funding from DIRAC. AS has emailed Mark. They are now using it more heavily. Could use the money for tape, but have to be careful not to buy tape we won’t use. May be better charging later rather than during this FY? AD will now progress). Ongoing.
663.3: RJ and DC will advise how the experiments want disk divided for the start of Run 3 (Alice and LHCb are resolved). (Update: DB will write to DK with DC in copy with proposed way forward). Ongoing.
665.2: AD will produce Procurement schedule for the coming FY to build in an additional month to buffer any delays in the future. Ongoing.
667.1 PG Clarify with STFC what exactly is required for the OC feedback. wrt the Capital reporting. Ongoing.
667.2 Need to do h/w planning before next OC to provide OC with details of shortfall in funds. Ongoing.
670.2: DB and PG will consider percentage splits of CPU/Disk. Ongoing.
670.3: DB, PG and PC will undertake a high-level discussion of planning manpower for in GridPP6. Ongoing.
671.1: DB will discuss with the sites involved for IRIS h/w allocation and make recommendations to the PMB to consider. Ongoing
671.2: PG and AM to check if there is a common requirement across the Grid that can be negotiated with Dell for a framework agreement (e.g. Storage, Compute, Configurations). Ongoing.
672.1: DB will complete the UKRI Infrastructure Survey and request comments from the PMB by 02/07/18.
672.2: JC and/or PG and/or PC to brief Ops-meeting and request storage group draft background document. AD to contribute.
672.3: RJ, DK and AM to draft the Experiment Support background document.
672.4: DK to draft the Security, Trust and Identity background document.
672.5: AD to draft the Tier1 background document.
672.6: JC, SL AM and PG to draft the Tier2 background document.
672.7: PG will consider the agenda for GridPP41 incorporating the GridPP6 Background Documents.