=================================
Present: Dave Britton (Chair), Tony Doyle, Pete Gronbech, Dave Kelsey, Roger Jones, Steve Lloyd, Andrew McNab, Andrew Sansum, Gareth Smith, Louisa Campbell (Minutes).
Apologies: Tony Cass, Pete Clarke, Jeremy Coles.
1. Reporting
============
PG discussed the Quarterly Reports. The Tier1 report is being worked on and one section remains outstanding, Finance section is done and manpower section needs to be worked on – GOK and Apple contributions have been included. It will be sent to PG asap.
Other VOs report, Ops Report and Security report will soon be available.
PG noted Q3 reports will soon also be due and work should begin on them now.
2. HAG
======
PG noted there will be another HAG meeting on Wednesday at RAL (10am) and hopes to complete this. AS hopes to attend.
3. GridPP40
==================
Two possible dates were circulated for hosting GridPP40 at the Atholl Palace, Pitlochry (9-11th and 16-18th April) and 16-18th April originally appeared preferred because the first week overlaps GDB. However, it is now clear that second proposed set of dates clash with Atlas Upgrade week and (provisional) CMS week so decisions need to be made on preferred dates to reserve the hotel. It was agreed that 9-11th is preferred. LC will contact Athol Palace at Pitlochry to confirm the reservation.
4. AOCB
=======
A date for the next OSC needs to be set – a Doodle poll covered January and early February. DB suggested the January dates were too close to Christmas to be helpful but the first week in February appears to be the most popular – Wednesday 7th February the date most contributors are available. This will require documents to be prepared immediately after Christmas and quarterly reports must be submitted timeously (for both Q3 and Q4).
5. Standing Items
===================
SI-0 Bi-Weekly Report from Technical Group (DC)
———————————————–
DC reported on the meeting and will circulate a link to the minutes. Discussion on GPUs and its use by various experiments. Tagging GPU jobs in Dirac and how to describe them – this is quite complex and discussions will continue developing. Pre-production on Dirac will allow for testing, production will not be moved over until full testing is complete. There was some discussion on Glomus and forecasts. Change to the authorisation working group was proposed. Standing Items need to evolve – VAC: AM is bringing in containers which are being tested in Manchester. Storage: some testing and redirecting. CMS resources by Dirac (including CERN) are being worked on. David Crooks updated on security on several groups which the minutes summarise very well.
SI-1 Dissemination Report (SL)
——————————
Still awaiting confirmation of what is happening with the Janet post as it is not clear whether Imperial have sent any invoices. DC confirmed agreement has been reached for invoicing to commence soon – Janus will be fully in the role asap.
SI-2 ATLAS Weekly Review and Plans (RJ)
—————————————
Nothing significant to report.
SI-3 CMS Weekly Review and Plans (DC)
————————————-
Nothing significant to report.
SI-4 LHCb Weekly Review and Plans (PC)
————————————–
AM updated longstanding storage configuration at QMUL has been resolved.
SI-5 Production Manager’s report (JC)
————————————-
1. We reviewed our “incubator VOs”: https://www.gridpp.ac.uk/wiki/GridPP_VO_Incubator . We need to rename the area as some VOs are now very active others are hard to get updates
DEAP3600: No activity
HPC DiRAC: Data from all sites now. Active.
EUCLID: No response
GalDyn: Checking again.
LIGO: Secure CVMFS discussion.
LOFAR: No response
LSST: Slow down over summer but USLSST now enabled 3 sites. Active including Southampton.
LZ: Active. Summer mock data challenge a success
DUNE: One user was active. Currently recruiting.
PRaVDA: No communication.
SKA: Added additional sites. Change of personnel. Active.
SNO+: T2K contact left but seeing bursts of activity.
SuperNEMO: No recent jobs. Unclear status.
UKQCD: No activity.
2. There was an EGI Operations Management Board last week that may be of interest (https://indico.egi.eu/indico/event/3241/). The main focus was CMD/UMD updates, storage accounting, containers in HTC. An item of possible interest is Jupyter and Galaxy as a service and the results of a cloud (FedCloud) security challenge.
3. Still following up on LFC comments made in previous weeks. DPM community are not actively maintaining it as it was not being used by any LHC experiements, but it now appears LHCb might be!
4. Notes from the September GDB are now available https://twiki.cern.ch/twiki/bin/view/LCG/GDBMeetingNotes20170913.
There is a further discussion scheduled between CERN (Ian) and SKA (various). It includes discussion of the Community White Paper mentioned last week.
SI-6 Tier-1 Manager’s Report (GS)
———————————
Echo:
——-
The re-distribution of data in Echo onto the 2015 capacity hardware is ongoing. This is being done cautiously owing to the ongoing problem where disk errors in the newly added systems trigger a bug in CEPH that requires some manual intervention to work round.
Castor:
———
– We had a problem with the LHCb SRM SAM tests – although LHCb did not see operational problems as a result of this. Two disk servers that are involved in the failing transfers were set read-only last week and the tests cleared consistently. These disk servers were two out of five that were added. Work is going on to understand what is incorrect with these two servers.
– We are working with Chris Brew working on removal of some CMS dark data. This had been a cause of our CMS disk-only storage in Castor filling.
GS advised the person selected to take over his role has accepted the position. The Tier1 manager role is awaiting approval for internal advertising.
SI-7 LCG Management Board Report of Issues (DB)
———————————————–
There was a meeting on 26th September and not much to report. There was mention of ATLAS and WLCG data loss (Ian Collier gave a statement on this). Marcus provided a talk on the working group on the cost model – following up the WLCG workshop in June in Manchester relating to efficiencies and measuring. The intention is to establish a working group to determine how this is best costed (money and the best model to evaluate best value for money) – there is a call for volunteers out and DB has emailed Marcus and suggested Gareth Roy, Glasgow, who has considered this in detail recently. AS may volunteer as he is working on SKA models currently and will begin with cost models shortly. DB mentioned the cost model for NorduGrid regarding metrics and mapping the model on to small and medium sized sites in order to test applicability – DB will send AS the links for background reading.
SI-8 External Contexts (PC)
—————————
AS noted responses from the referees to the UKT0 bid – these have been gathered and responded to. The response reads well and strikes a good balance. The PPRP will take place very soon.
REVIEW OF ACTIONS
=================
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.
644.1: DB will discuss Grant funding and resources with Tony Medland. Ongoing.
644.2: PG and AS will document plans and costings for the remainder of GridPP5 taking account of the Oracle tape issues experienced. Ongoing.
644.3: AS put together a starting plan for staff ramp-down. Ongoing.
644.4: AS will progress capture of funds for Dirac with Mark Wilkinson. Ongoing.
644.6: (during GridPP39 meeting) DB will ascertain what Biomed do and how they use the Grid. (Update: Holloway then Manchester and Imperial are biggest representatives – DC and AM will investigate this and ascertain whether our input is being explicitly credited).
ACTIONS AS OF 02.10.17
======================
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.
644.1: DB will discuss Grant funding and resources with Tony Medland. Ongoing.
644.2: PG and AS will document plans and costings for the remainder of GridPP5 taking account of the Oracle tape issues experienced. Ongoing.
644.3: AS put together a starting plan for staff ramp-down. Ongoing.
644.4: AS will progress capture of funds for Dirac with Mark Wilkinson. Ongoing.
644.6: (during GridPP39 meeting) DB will ascertain what Biomed do and how they use the Grid. (Update: Holloway then Manchester and Imperial are biggest representatives – DC and AM will investigate this and ascertain whether our input is being explicitly credited).