=================================
Present: Dave Britton(Chair), Tony Cass, Pete Clarke, Jeremy Coles, David Colling, Tony Doyle, Pete Gronbech, Roger Jones, Steve Lloyd, Andrew McNab, Andrew Sansum.
Apologies: Dave Kelsey, Gareth Smith
1. NEI Survey
====================
PC, AS, Dave Corney and Pete Oliver met to discuss last week, SCD is well placed to respond. There are two parts of the spreadsheet, for details of the entity being surveyed (i.e. the site): CPU Core count, no of TB etc…, the other is a survey monkey survey with a range of questions about the site, (which come from an HPC background so don’t match well with our sites). We will devise our best response for SCD and Pete Oliver is looking at our previous answers, though this is challenging for GridPP. This may result in double counting, though that may be preferable to not being counted. PC confirms it is important for GridPP to be represented, though sites should be informed this will be done. The entry should be consistent with the tier-1 in respect of the services we list. PG will collate numbers before the deadline of 31st July and confirm by email.
ACTION 640.1: PG to collage numbers for NEI Survey before the deadline of 31 July and confirm by email.
2. National e-Infrastructure Bid
================================
Several related issues were discussed. PC advised a call was released today by Anthony Davenport which he will read later. The PMB were previously aware of this and had already discussed a response. Following the spirit of UK-T0 we are happy to put in a joint bid for it all – there has been agreement to submit a joint bid across PPAN – SKA and LSST are very keen. This will have to be submitted by 22nd August (not the most convenient of timing). It is not particularly for PP, but erring towards Astronomy and facilities, and National custodial support. There are other aspects to discuss regarding PP, more information will become available in the next few weeks. DB scanned through this and there is nothing which immediately jumps out as challenging other than the need to imbed industry. AS noted it makes several references to moving towards an NEI. Procurement deadlines may present AS with a challenge… The outcome will be known by November and must be spent by end of March, this is very tight and challenging. GridPP is not primarily trying to increase our capacity, but more related to capturing resources for non-PP to relieve pressure on our resources.
UKT0, UK Custodial storage system is one of the things that could be addressed but the chances of getting something substantial developed in the timescale is low and solving the Tape issue on this timescale will be challenging so this has to be around building a community. Funding is capital to be spent by March, though there is a small amount of resource may be made available to support this. The PMB should give AS and PC the mandate to progress this on GridPP’s behalf. How it is presented is important and there must by universal support across the communities. Paul Alexander has suggested an editing meeting in London in the next two weeks. AS could book an STFC meeting room at the MRC.
Separate to all this, Susan Morrell’s committee has been asked to resubmit a “grand plan” to BEIS. AS and Dave Corney are on the committee and PC may now also be involved. PC is triple booked that day for PPAP town meeting in pm and on Friday morning; DB could try to attend the afternoon session. DB should be included in the email loop. The meeting is on 20th July.
3. AOCB
=======
a) FOREX
TM has listened to our positioning at the OC meeting and noted he may be able to find some capital to partially meet the increased pledge – we had mentioned needing £630k for Tier-1 but this is way beyond what could be found. DB proposed to spend any additional capital at the Tier-1 as it would be too difficult to divide relatively small sums between many Tier-2 institutes.
DB noted at the OC that GridPP will not be able to deliver the resources requested for the first time in our history and this is STFC’s response to that need – so it is gratifying that STFC had received the message and had indicated a willingness to do what they could.
Separately, TM has sent the cap/res profile for the rest of GridPP5 to AS who will forward to PG.
b) LSST Stats
AF and AM have done all the work at Manchester – there has been a huge peak in the last couple of months and AF noted at a recent Ops meeting that only Lancaster/Manchester/RAL were used, though all sites that support LSST are welcome to join in.
LZ also started a major data challenge at GridPP sites and DB notes a particular thanks to Daniela, Simon and Elena for work on this.
5. Standing Items
===================
SI-0 Bi-Weekly Report from Technical Group (DC)
———————————————–
Nothing of significance to report.
SI-1 Dissemination Report (SL)
——————————
Post, QM and IC think this can go ahead and Janusz’ time could be billed. This will need to be factored into the reporting and ensure progress on the DIRAC side. (The extra 50% is for that.)
SI-2 ATLAS Weekly Review and Plans (RJ)
—————————————
Nothing of significance to report.
SI-3 CMS Weekly Review and Plans (DC)
————————————-
Nothing of significance to report. The CDF efficiency taskforce have identified 4 sources of inefficiency and will work on this. Perhaps DC could present at next GridPP.
SI-4 LHCb Weekly Review and Plans (PC)
————————————–
Nothing of significance to report.
SI-5 Production Manager’s report (JC)
————————————-
1. Imperial unable to run (real as opposed to test) CMS jobs on SL7. This is affecting usage of the site.
2. LZ data challenge. “Heroic effort” at Imperial, generated 370 TB of data, 700K files, all transferred to NRSC in California. Test successful. LZ happy.
3. Dune: Good progress. Running jobs at several GridPP sites from pilot factory in Fermi-lab/OSG.
4. Cambridge VAC instance is now in production.
5. Investigating several perfSONAR issues at sites – several cases of data not available.
6. 100IT are the only UK EGI FedCloud site and they are struggling with keeping up with EMI updates to work with their OpenStack environment. I will review how we might be able to assist in this area.
7. GDB reports on WLCG workshop (https://indico.cern.ch/event/578988/) included thanks to the local team for their organisaiton – special thanks to Alessandra. Of the GDB updates the PMB may be most interested in the item on the HNSciCloud: https://indico.cern.ch/event/578988/contributions/2646077/attachments/1491769/2319237/BobJones-GDB-12July2017.pdf
8. SKA and CERN signed an MoU last week to collaborate on computing (https://skatelescope.org/news/ska-signs-big-data-cooperation-agreement-cern/).
SI-6 Tier-1 Manager’s Report (GS)
———————————
GS not present, no report submitted.
SI-7 LCG Management Board Report of Issues (DB)
———————————————–
Nothing to report.
SI-8 External Contexts (PC)
———————————
Nothing to report.
REVIEW OF ACTIONS
=================
630.2: DB and PG will continue to work on metrics and funding strategies at the macro level. Done.
630.3: DB will tweak his metrics and funding model based on CPU. Done.
638.1: PC will update the text on the Network Forward Look document for the forthcoming 2 years. Ongoing.
638.2: AS will check when equipment is due to become obsolete and investigate legal and manpower of donation to the African Data Centre for Bioinformatics and Medical Research. (Update: AS is looking into how this may impact Global Challenge Research Fund – GCRF – which would involve a cross-Council bid) Ongoing.
638.3: SL and DC will prepare a statement relating to Locked Space technologies. Done.
639.1: DC and SL will investigate the possibility of filling the Dissemination Officer post at Imperial or QMUL with 50% FTE. Done.
639.2: AS will email Susan Morrell for clarification on terminologies relating to the NEI Survey. Done.
639.3: DB will write to Catalin advising that GridPP will support the planned HT-Condor workshop to c. £2000. Done.
ACTIONS AS OF 17.07.17
======================
638.1: PC will update the text on the Network Forward Look document for the forthcoming 2 years. Ongoing.
638.2: AS will check when equipment is due to become obsolete and investigate legal and manpower of donation to the African Data Centre for Bioinformatics and Medical Research. (Update: AS is looking into how this may impact Global Challenge Research Fund – GCRF – which would involve a cross-Council bid) Ongoing.
640.1: PG to collage numbers for NEI Survey before the deadline of 31 July and confirm by email.