Difference between revisions of "Operations Bulletin Latest"

From GridPP Wiki
Jump to: navigation, search
()
()
 
(45 intermediate revisions by 7 users not shown)
Line 27: Line 27:
 
====== ======
 
====== ======
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->
<!-- ***********************Start General text*********************** ----->'''
+
'''Tuesday 18th June'''
'''Tuesday 14th May 2019'''
+
* DPM Workshop last week - come to this week's storage meeting for an in-depth look.
* Registration is still open for the HEPSYSMAN + SECURITY DAY meeting next week, the Security Day training is especially important: https://indico.cern.ch/event/721692/
+
** https://indico.cern.ch/event/776832/
* The DIRAC users workshop is at Imperial this week: https://indico.cern.ch/event/756635
+
* DIRAC downtime this week due to the move to Slough - good luck!
* WLCG Operations Coordination meeting this Thursday 16th: https://indico.cern.ch/event/820489
+
* EGI Ops meeting this week.
 +
** https://wiki.egi.eu/wiki/Agenda-2019-06-17
 +
** HTCondorCE commissioning ongoing, SRM decommissioning survey
 +
** State of SRM usage at DPM sites?
  
'''Tuesday 30th April 2019'''
 
* GridPP 42 was last week, any thoughts or comments? https://indico.cern.ch/event/780766/
 
* Related, Dave B has sent out a "consulation" for GridPP43
 
* There was a technical meeting on the future of DPM in the UK shortly before Easter https://indico.cern.ch/event/813140/
 
* The summer HEPSYSMAN + SECURITY DAY is scheduled for the 23rd-24th of May: https://indico.cern.ch/event/721692/
 
* Vis-a-vis the thread on TB-SUPPORT started by Simon - how many more of the "old ways of doing stuff" can we drop?
 
  
''' Tuesday 9th April 2019 '''
+
'''Tuesday 11th June'''
* Any comments from [http://event.twgrid.org/isgc2019/program ISGC]?
+
* ISGC also hosted the April [https://indico.cern.ch/event/739877/ GDB]
+
* Last week also had the [https://indico.ph.qmul.ac.uk/indico/conferenceDisplay.py?confId=446 IRIS FTF].
+
* Any other meetings or announcements I missed?
+
* Most importantly - remember to tell Alastair what you want for your tea at the GridPP42 collaboration dinner.
+
  
 +
* Technical Meeting last week about the New JSON based Information System:  https://indico.cern.ch/event/821105/
 +
* This week we will get round to looking at the outcome of the Security Day (and HEPSYSMAN).
 +
* The DPM Workshop is this week: https://indico.cern.ch/event/776832/ There's a Vidyo Room planned for people to listen in.
 +
* CentOS7 Migration https://twiki.cern.ch/twiki/bin/view/AtlasComputing/CentOS7Deployment
 +
<!-- ***********************Start General text*********************** ----->'''
 +
'''Tuesday 4th June 2019'''
 +
* The Security Day  + HEPSYSMAN was on t'other week: https://indico.cern.ch/event/721692/
 +
* Please can sites review their GOCDB information: https://ggus.eu/?mode=ticket_info&ticket_id=141296
 +
* iris.ac.uk VO - Andrew explained this.
 +
* New(-ish) HEPOSLib release - 7.2.9 https://twiki.cern.ch/twiki/bin/view/LCG/WLCGBaselineTable
 +
* Gareth's query about the WS interface to ARC on TB-SUPPORT
 +
* Anything else?
  
''' Tuesday 02 April 2019 '''
 
* Fermilab VOMS Changes
 
* https://indico.cern.ch/event/762505/overview 9-11 April
 
* CERN AFS phasing out
 
* XCache ready in Birmingham
 
* Site Storage & Satisfaction Survey
 
* Anything Else
 
 
 
'''Tuesday 27th March 2019'''
 
* HOW HSF/OSG/WLCG workshop last week: https://indico.cern.ch/event/759388/
 
* Reminder that GridPP42 registration closes next week: https://indico.cern.ch/event/780766/
 
* Do people have anything they'd like to added to the agenda? Although you might need a shoehorn to fit anything in.
 
* Provisional technical meeting this Friday@11am on HTCondor, and one is planned on EOS experiences soon(tm). 
 
 
* Anyone have anything else?
 
 
 
''' Tuesday 12th March 2019'''
 
* https://indico.cern.ch/event/739876/
 
* https://indico.egi.eu/indico/event/4321/
 
* EGI A/R Report http://argo.egi.eu/lavoisier/site_reports?ngi=NGI_UK&report=Critical&accept=html
 
* Any other updates
 
 
 
 
'''Tuesday 5th March 2019'''
 
* Atlas Site Jamboree is currently ongoing: https://indico.cern.ch/event/770307/
 
* Anyone have any other general updates?
 
* GDB Next week: https://indico.cern.ch/event/739876/
 
* WLCG Ops meeting this Thursday: https://indico.cern.ch/event/803145/
 
 
 
'''Monday 18th February 2019'''
 
* GTF is about to release a regular update to the trust anchor repository (1.96) on Monday, FEB 25th 2019. See the [https://rt.egi.eu/rt/Ticket/Display.html?id=15335 ticket] for more information.
 
* [https://indico.cern.ch/e/cvm19 CernVM Users Workshop 2019] will take place from 3 June to 5 June 2019 at CERN.
 
* [https://twiki.cern.ch/twiki/bin/view/LCG/WLCGOpsMeetingWeek190218 Notes from the Monday WLCG operations meeting] are available.
 
* Talks from the GDB last week are now on the [https://indico.cern.ch/event/739875/ agenda page].
 
 
 
'''Tuesday 12th February'''
 
* DPM release - 1.11
 
* Approved VOs: changes to BIOMED and ENMR
 
* Simon:  VAC with VM condor VM to support local batch jobs?
 
* There is a GDB this week - [https://indico.cern.ch/event/739875/ agenda].
 
* NGI Argus/Central Banning config (see DC message).
 
* There was a WLCG ops meeting yesterday. [https://twiki.cern.ch/twiki/bin/view/LCG/WLCGOpsMeetingWeek190211 Minutes] are available.
 
* [https://indico.cern.ch/e/how2019 HOW19 registration] (early bird rate has ended). HSF-OSG-WLCG joint workshop.
 
* A/R explanations for January: QMUL power outage; Bham now on EOS so SE tests fail; ECDF 80% LHCb??
 
 
 
'''Tuesday 5th February'''
 
* The EGI RP/RC A/R Report for January 2019 is [http://argo.egi.eu/lavoisier/site_reports?ngi=NGI_UK&report=Critical&accept=html available]. UKI overall fine. Bham and RAL-LCG2 may wish to examine their results.
 
* A reminder.... Please could everyone think about their WLCG (and beyond) engagements and commitments and put anything of note in the [https://www.gridpp.ac.uk/wiki/Engagements_and_commitments wiki table here].
 
* Notes from yesterday's WLCG ops meeting are [https://twiki.cern.ch/twiki/bin/view/LCG/WLCGOpsMeetingWeek190204 available]. Issues at RAL noted by LHCb.
 
* It is CMS week this week.
 
* In case missed here is Elena's ATLAS update:
 
** https://ggus.eu/index.php?mode=ticket_info&ticket_id=138033: singularity jobs failing at RAL. A job that Alessandra submitted  still has a problem with the home directory. Ral is trying to fix it.
 
** There was  a power  lost to a rack and the two storage nodes in it in Lancaster over weekend which cause a problem to ATLAS jobs. This was fixed on Monday.
 
** Raul asked for srmless atlas transfers for Brunel. Elena is changing transfer configuration in AGIS but the jobs are still failing. Peter will look into this.
 
** There was a discussion on lightweight ATLAS Grid sites @ADC weekly last week.  Sheffield, Cambridge, Brunel, Durham, Bham and Sussex should become diskless sites.
 
* There is an ongoing discussion about LSST jobs on GridPP resources that may be of wider interest. Their VOMS was down so the question was raised about using GridPP VOMS or setting up another VOMS in the UK to read its data from the SLAC instance.
 
* The 9th DIRAC Users Workshop will be held in London 14. - 17. May 2019. Here is the [https://indico.cern.ch/event/756635/overview registration link].
 
* December's WLCG A/R final report is available at via [http://wlcg-docs.web.cern.ch/wlcg-docs/?dir=reporting/reliability-availability/2018/12-18 this link].
 
* The figures for January 2019 are now available and updates from 3 sites requested:
 
** [http://wlcg-sam.cern.ch/reports/2019/201901/wlcg/WLCG_All_Sites_ALICE_Jan2019.pdf ALICE]
 
** [http://wlcg-sam.cern.ch/reports/2019/201901/wlcg/WLCG_All_Sites_ATLAS_Jan2019.pdf ATLAS]
 
** [http://wlcg-sam.cern.ch/reports/2019/201901/wlcg/WLCG_All_Sites_CMS_Jan2019.pdf CMS]
 
** [http://wlcg-sam.cern.ch/reports/2019/201901/wlcg/WLCG_All_Sites_LHCB_Jan2019.pdf LHCb]
 
* Simon G asks: VAC with VM condor VM to support local batch jobs? Has anyone done it??
 
* EGI has started an HTCondor integration process and captures progress here: https://ggus.eu/index.php?mode=ticket_info&ticket_id=139377.
 
* End of Support for CREAM-CE: The CREAM working group has announced that official support for the CREAM-CE component will cease at the end of the EOSC-hub project, i.e. in Dec 2020.  The CREAM working group will be providing full support until the end of 2019, including one minor release already scheduled. During 2020 only security updates will be released. 
 
  
  
Line 136: Line 68:
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->
 
<!-- ***********************Start ops coord text*********************** ----->
 
<!-- ***********************Start ops coord text*********************** ----->
 +
'''Tuesday 11th June'''
 +
 +
* I got stuck (figuratively) in my machine room last Thursday afternoon so missed it. [https://indico.cern.ch/event/823800/ Agenda.] [https://twiki.cern.ch/twiki/bin/view/LCG/WLCGOpsMinutes190606 Minutes.] Ste was there - any observations?
  
 
'''Tuesday 14th May'''
 
'''Tuesday 14th May'''
Line 176: Line 111:
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->
 
<!-- ***********************Start T1 text*********************** ----->
 
<!-- ***********************Start T1 text*********************** ----->
'''29th April 2019''' Report for the Experiments Liaison Report (29/04/2019) is [https://www.gridpp.ac.uk/wiki/Tier1_Operations_Report_2019-04-29 here].
+
 
 +
'''17 June 2019''' Report for the Experiments Liaison Report (17/06/2019) is [https://www.gridpp.ac.uk/wiki/Tier1_Operations_Report_2019-06-17 here].
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->
 
<!-- **********************End T1 text************************** ----->
 
<!-- **********************End T1 text************************** ----->
* We are seeing high outbound packet loss over IPv6. Investigation has restarted now that the appropriate resources are back in office.
+
* Ongoing, we are seeing high outbound packet loss over IPv6. Central networking performed a firmware update to the border routers but this didn’t resolve the issue.  Plan to move connections to the new border routers in Mid June.  Will do this before trying to debug any further.
* High CMS job failure rates. Due to the workloads submitted by CMS, there is currently no issue. We are however still looking at making changes to the XrootD caches on the WN to improve performance.
+
 
* On Wednesday 24th April gdss738 (LHCb) crashed and was removed from production. It was returned to production on Friday 26th April at lunchtime.
+
'''11 June 2019''' Report for the Experiments Liaison Report (10/06/2019) is [https://www.gridpp.ac.uk/wiki/Tier1_Operations_Report_2019-06-10 here].
 +
<!-- *********************************************************** ----->
 +
<!-- **********************End T1 text************************** ----->
 +
* Ongoing, we are seeing high outbound packet loss over IPv6. Central networking performed a firmware update to the border routers but this didn’t resolve the issue. Plan to move connections to the new border routers in Mid June.  Will do this before trying to debug any further.
 +
* Three certificates were revoked mistakenly on ARGUS on Thursday.  All SAM tests failed until this was fixed the next morning.  Batch farm also did not start any new jobs during this time.  We used this accidental draining to reboot nodes that needed to pick up security patching.
 +
* LHCb Castor instance has been completely disabled for LHCb and will be decommissioned.
 +
* Brian Davies has transferred from his role as GridPP Tier-2 Storage Support Officer and has joined the Tier-1 Production Team. Although this has happened with immediate effect he will still be available for ad-hoc/informal storage support.  
 +
 
 
|}
 
|}
 +
 
<!-- ****************Start Storage & DM****************** ----->
 
<!-- ****************Start Storage & DM****************** ----->
 
{| style="background-color: #ffffff; border: 1px solid silver; border-collapse: collapse; width: 100%; margin: 0 0.5em 1em 0;"
 
{| style="background-color: #ffffff; border: 1px solid silver; border-collapse: collapse; width: 100%; margin: 0 0.5em 1em 0;"
Line 193: Line 137:
 
<!-- ******************Edit start********************* ----->
 
<!-- ******************Edit start********************* ----->
  
'''[http://storage.esc.rl.ac.uk/weekly/20190410-minutes.txt Wed 10 Apr]'''
+
'''[http://storage.esc.rl.ac.uk/weekly/20191030-minutes.txt Wed 30 Oct]'''
* Summary of mostly storage and data management related stuff at IRIS F2F meeting
+
* DOME upgrade problems at Edinburgh
 +
* Data management support/development for IRIS users
 +
 
 +
'''[http://storage.esc.rl.ac.uk/weekly/20191023-minutes.txt Wed 23 Oct]'''
 +
* Rucio reporting
 +
 
 +
'''Wed 16 Oct'''
 +
* CEPH workshop at CERN report
 +
 
 +
'''[http://storage.esc.rl.ac.uk/weekly/20191002-minutes.txt Wed 02 Oct]'''
 +
* Safe to upgrade to DPM 1.13 but make sure the BDII is working if you support DIRAC
 +
* Roadmap for xroot and http TPC for RAL FTS(es)
 +
 
 +
'''[http://storage.esc.rl.ac.uk/weekly/20190925-minutes.txt Wed 25 Sept]'''
 +
* Storage support for IRIS VOs?
 +
 
 +
'''[http://storage.esc.rl.ac.uk/weekly/20190918-minutes.txt Wed 18 Sept]'''
 +
* Report from yesterday's Rucio Face Meeting at Coseners
 +
* Suggestions for following up from yesterday's CEPH day hosted by CERN
  
'''Tuesday 09/04/19'''
+
'''[http://storage.esc.rl.ac.uk/weekly/20190911-minutes.txt Wed 11 Sept]'''
* Progress with xCache at Birmingham , ATLAS to use and test before other sites to try
+
* Storage related stuff at the FNAL (pre-)GDBs
** ATLAS have two modes but "transparent cache" not use case for when a site has no storage, so investigating "Volatile RSE"
+
* DOME upgrade tickets for non-DOME DPM sites
* Site Storage Status & Satisfaction Survey
+
** Please can remaining sites send responses to Brian Davies
+
* New gfal-* rpms available
+
* Request to discuss DPM at GRIDPP42
+
  
'''[http://storage.esc.rl.ac.uk/weekly/20190227-minutes.txt Wed 27 Feb]'''
+
'''[http://storage.esc.rl.ac.uk/weekly/20190904-minutes.txt Wed 04 Sept]'''
* Report from [https://indico.cern.ch/event/765497 HEPiX]
+
* Banning in SSC not entirely successful in non-DOME DPM, and end of support is nigh; tickets to upgrade will go out shortly.
* Update on IPv6
+
* Storage-and-data-management-wise, GridPP43 was interesting although no-one volunteered to install the next CEPH.
  
'''[http://storage.esc.rl.ac.uk/weekly/20190220-minutes.txt Wed 20 Feb]'''
 
* There's a Rucio workshop next week, in Oslo
 
* Data lakes and analytics facilities.
 
  
 
<!-- ******************Edit stop********************* ----->
 
<!-- ******************Edit stop********************* ----->
Line 280: Line 235:
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->
 
<!-- ******************Edit start********************* ----->
 
<!-- ******************Edit start********************* ----->
 +
 +
''' Tue 9th July 2019'''
 +
 +
LHCb has added this to their requirements:
 +
 +
Sites not having an SRM installation must provide:
 +
 +
* disk only storage
 +
* a GRIDFPT endpoint (a single dns entry)
 +
* an XROOT endpoint (a single dns entry)
 +
* a way to do the accounting (preferably following the WLCG TF standard: https://twiki.cern.ch/twiki/bin/view/LCG/StorageSpaceAccounting)
 +
 
''' Tue 16th April 2019'''
 
''' Tue 16th April 2019'''
  
Line 480: Line 447:
  
 
===== =====
 
===== =====
'''Tuesday 30th April
+
'''Tuesday 11th June
  
* Operational update
+
* NTR
* EGI Conference Security talks/sessions
+
* HEPSYSMAN Security plans
+
  
 
|}
 
|}
Line 536: Line 501:
 
===== =====
 
===== =====
 
<!-- ******************Edit start********************* ----->
 
<!-- ******************Edit start********************* ----->
'''Monday 13th May 2019, 14.00 BST'''<br />
 
37 Open UK Tickets this month.
 
 
'''IPv6 Tickets'''<br />
 
'''Oxford:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131615 131615] On Hold (13/3)<br />
 
This ticket could likely do with a progress update once you jump under the DOME.
 
 
'''Birmingham:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131612 131612] In Progress (5/2)<br />
 
How goes things with the v6 DNS? The ticket could do with an update, or if you're not having much joy perhaps being set back to "On Hold".
 
 
'''Glasgow:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131611 131611] In Progress (5/2)<br />
 
I suspect this ticket should be put On Hold until the big move?
 
 
'''Durham:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131609 131609] On Hold (4/12/18)<br />
 
This ticket could do with an update (even a null one).
 
 
'''Manchester:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131607 131607] In Progress (9/4)<br />
 
There's light at the end of the v6 tunnel for Manchester, did you roll deploying this into last week's work?
 
 
'''Liverpool:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131606 131606] On Hold (6/2)<br />
 
Another ticket that could do with an update, even if it's just to fill the silence.
 
 
'''RHUL:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131603 131603] In Progress (8/4)<br />
 
Simon and Tony have been poking their network manager but no joy in getting the paperwork to use the JANET services signed off. Anything we can do?
 
 
'''Sheffield:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131608 131608] On Hold (7/5)<br />
 
Elena has layed out the Sheffield plan - with the SE on the way out this year it's not going to be dual-stacked, and a plan to reinstall their perfsonars next month (dual-stacked?).
 
 
The rest of the tickets...
 
 
'''BIRMINGHAM'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140679 140679] (10/4)<br />
 
Ticket tracking the decommissioning of the Birmingham CREAM CE. I believe things have progressed further then are reflected in the ticket? But in general there doesn't seem to be any big uproar over switching it off (yet). In progress (29/4)
 
 
'''OXFORD'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141099 141099] (9/5)<br />
 
A DUNE ticket about jobs not working, it looks like a classic problem of wrong voms settings and DUNE jobs are running now, so maybe this ticket can be closed. Waiting for reply (13/5)
 
 
'''GLASGOW'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141124 141124] (10/5)<br />
 
Atlas analysis jobs not running properly at Glasgow. Gareth as on held the ticket until AC problems at the site are fixed, to see if that solves the issue as well. On Hold (13/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140222 140222] (15/3)<br />
 
MICE DFC migration ticket. I think the conversation has stalled, last update was from Daniela asking if a user was still a user, and if their data can be purged or not. In progress (10/4)
 
 
'''ECDF'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140802 140802] (22/4)<br />
 
LHCB Pilots aborting at ECDF. This seems to come and go in cycles - any joy in figuring out what the underlying issues are? I assume you're waiting to see if all is okay after your recent downtime. In progress (26/4)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141098 141098] (9/5)<br />
 
Another DUNE ticket (they've found their voice!). Teng has confirmed that ECDF is in a "let's wait and see if it's all working now" period. On Hold (10/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140846 140846] (24/4)<br />
 
ROD ticket for the ECDF CE, a symptom of all the badness that the site's been experiencing. A quick check shows that ce8 is looking fairly green in nagios. In Progress (29/4)
 
 
'''DURHAM'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141104 141104] (10/5)<br />
 
Multiple ROD alarms at the site. Adam was investigating, but things look okayish now. In Progress (10/5)
 
 
'''SHEFFIELD'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141134 141134] (12/5)<br />
 
Atlas transfer failures due to what looks like an expired cert. In progress (12/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140866 140866] (25/4)<br />
 
Biomed jobs failing with what look like authentication errors. Any joy/time in looking at this? In progress (25/4)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140987 140987] (2/5)<br />
 
Another DUNE ticket. A number of small showstoppers have been fixed, so hopefully DUNE jobs are running at Sheffield now? Waiting for reply (10/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=138649 138649] (3/12/18)<br />
 
(The last) T2K migration ticket. Elena has it in her schedule, but her plate is full. Hopefully tomorrow. On Hold (13/5)
 
 
'''LIVERPOOL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=139411 139411] (30/1)<br />
 
A Biomed ticket from Biomed asking if using the BIOMEDDISK spacetoken could be made automagic. John explained the situation, what's the plan with this ticket. Keep it open until you're DOME'd? You could close it as the initial question has been answered. On Hold (1/2)
 
 
'''UCL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=139101 139101] (8/1)<br />
 
Any joy getting ViaB working at UCL? In Progress (8/4)
 
 
'''QMUL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141133 141133] (12/5)<br />
 
LHCB FTS transfer problems. Terry reports power problems at the site, with no news when juice will be restored. Hopefully soon! On Hold (13/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141132 141132] (12/5)<br />
 
Atlas issues for the same reason. The atlas response was quite harsh though. In Progress (13/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140190 140190] (14/3)<br />
 
The old LHCB FTS ticket, left on hold whilst things are investigated in the event problems crop up again. On Hold (23/4)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=138364 138364] (19/11/18)<br />
 
T2K DFC migration ticket - it's all in the VO's hands now and Daniela proposes closing the ticket. In progress (13/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=134573 134573] (17/4/18)<br />
 
CMS request to install singularity. I'll ask you how it's going at a later date. On Hold (5/11/18)
 
 
'''BRUNEL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140669 140669] (10/4)<br />
 
LHCB job failures, by the looks of it on a pair of v6-only WNs. I'm not sure how things are going, but the ticket is being actively investigated on both sides. In Progress (9/5)
 
 
'''IMPERIAL MASTER TICKETS'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=138359 138359] -T2K DFC migration<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140198 140198] -MICE DFC migration
 
 
'''TIER 1'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141108 141108](10/5)<br />
 
DUNE having problems submitting to the Tier 1. Any joy? In Progress (10/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140870 140870] (25/4)<br />
 
T2K spotted a number of files that should be on type according to the DFC aren't. After a bit of digging it seems that the files simply weren't moved to their correct (according to the DFC) places yet. How goes the move? In Progress (29/4)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140773 140773] (18/4)<br />
 
LHCB ticket over slow ECHO deletions. Investigating thoroughly, spotting a possible issue with gridftp session reuse. Trying to replicate the issue elsewhere. In progress (8/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=141105 141105] (10/5)<br />
 
ROD SRM failures. George notes a problem with the castor certs that are being fixed. In progress (10/5)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140220 140220] (15/3)<br />
 
MICE DFC migration ticket. The last update had some questions from Daniela to both the CASTOR admins and MICE - neither of which have had a reply in the ticket. In progress (8/4)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=140447 140447] (27/3)<br />
 
Duncan spotted outbound v6 packet loss from the Tier 1. Brian confirms that only v6 is affected, and there is a plan to upgrade the firmware in the border router (I think that's what the plans are?). Hopefully that will get it. On Hold (10/5)
 
  
[https://ggus.eu/?mode=ticket_info&ticket_id=139672 139672] (13/2)<br />
+
32 Open Tickets this week, which is an in depth a look as I've been able to take.
LIGO pilots not running at RAL. Did Catalin get his LIGO membership reinstated for debugging purposes? In progress (30/4)
+
  
 
<!-- ******************Edit stop********************* ----->
 
<!-- ******************Edit stop********************* ----->

Latest revision as of 14:09, 30 October 2019

Bulletin archive


Week commencing Monday 25th February 2019
Task Areas
General updates

Tuesday 18th June


Tuesday 11th June

Tuesday 4th June 2019


WLCG Operations Coordination - AgendasWiki Page

Tuesday 11th June

  • I got stuck (figuratively) in my machine room last Thursday afternoon so missed it. Agenda. Minutes. Ste was there - any observations?

Tuesday 14th May

  • Next meeting this Thursday.

Tuesday 9th April


Tuesday 26th March

Monday 11th February 2019

  • There was a WLCG ops coordination meeting last Thursday. You can view the meeting notes here.
    • End of CREAM support Dec 2020.
    • Migration from CREAM to be discussed at the EGI conference 6-8 of May in Amsterdam.
    • Operational intelligence discussion (see slides).
    • Experiment updates (see ATLAS discussion on DOMA)
    • WG updates (few).




Tier-1 - Status Page

17 June 2019 Report for the Experiments Liaison Report (17/06/2019) is here.

  • Ongoing, we are seeing high outbound packet loss over IPv6. Central networking performed a firmware update to the border routers but this didn’t resolve the issue. Plan to move connections to the new border routers in Mid June. Will do this before trying to debug any further.

11 June 2019 Report for the Experiments Liaison Report (10/06/2019) is here.

  • Ongoing, we are seeing high outbound packet loss over IPv6. Central networking performed a firmware update to the border routers but this didn’t resolve the issue. Plan to move connections to the new border routers in Mid June. Will do this before trying to debug any further.
  • Three certificates were revoked mistakenly on ARGUS on Thursday. All SAM tests failed until this was fixed the next morning. Batch farm also did not start any new jobs during this time. We used this accidental draining to reboot nodes that needed to pick up security patching.
  • LHCb Castor instance has been completely disabled for LHCb and will be decommissioned.
  • Brian Davies has transferred from his role as GridPP Tier-2 Storage Support Officer and has joined the Tier-1 Production Team. Although this has happened with immediate effect he will still be available for ad-hoc/informal storage support.
Storage & Data Management - Agendas/Minutes

Wed 30 Oct

  • DOME upgrade problems at Edinburgh
  • Data management support/development for IRIS users

Wed 23 Oct

  • Rucio reporting

Wed 16 Oct

  • CEPH workshop at CERN report

Wed 02 Oct

  • Safe to upgrade to DPM 1.13 but make sure the BDII is working if you support DIRAC
  • Roadmap for xroot and http TPC for RAL FTS(es)

Wed 25 Sept

  • Storage support for IRIS VOs?

Wed 18 Sept

  • Report from yesterday's Rucio Face Meeting at Coseners
  • Suggestions for following up from yesterday's CEPH day hosted by CERN

Wed 11 Sept

  • Storage related stuff at the FNAL (pre-)GDBs
  • DOME upgrade tickets for non-DOME DPM sites

Wed 04 Sept

  • Banning in SSC not entirely successful in non-DOME DPM, and end of support is nigh; tickets to upgrade will go out shortly.
  • Storage-and-data-management-wise, GridPP43 was interesting although no-one volunteered to install the next CEPH.


Tier-2 Evolution - GridPP JIRA

Tuesday 30 Apr 2019

  • ATLAS CernVM4 VMs (equivalent to CentOS 7.6) being tested


Accounting - UK Grid Metrics HEPSPEC06 Atlas Dashboard HS06

Tuesday 6th February


Tuesday 30th January

Tuesday 24th Oct


Monday 16th January

  • The discussion topic for next week will be accounting comparisons. Please note Alessandra's comments last week.

Monday 14th November

  • Alessandra has written an FAQ to extract numbers from ATLAS and APEL avoiding the SSB.

Monday 26th September

  • A problem with the APEL Pub and Sync tests developed last Tuesday and was resolved on Wednesday. This had a temporary impact on the accounting portal.
Documentation - KeyDocs

Tue 9th July 2019

LHCb has added this to their requirements:

Sites not having an SRM installation must provide:

Tue 16th April 2019

Minor change to LHCB requirements in Approved VOs:

  • Sites having migrated to the Centos7 (including "Cern Centos7") operating system or later versions are requested to provide support for singularity containers.

https://www.gridpp.ac.uk/wiki/GridPP_approved_VOs#VO_Resource_Requirements

Tue 2nd April 2019

Changes to Approved for DUNE (and LZ)

There is a new "Approved VOs" document showing new settings for DUNE. And, since both LZ's voms servers now show up in the EGI Portal, I've removed the (now spurious) entry for voms.hep.wisc.edu that was formerly being inserted by hand.

https://www.gridpp.ac.uk/wiki/GridPP_approved_VOs

I've also created a new set of RPMs (each has all LSC, VOMS, and XML for one VO) for all approved VOs. See Approved VOs doc for details, version is 1.9.

Sites with DUNE services need to update using whatever method they employ.

Special note: Since voms1.fnal.gov changed yesterday, I've updated documentation for that right away. But voms2.fnal.gov remains as it is until 23rd April (3 weeks). I'll update documentation for that when it is closer. Staggering the updates like this gives a time margin, so any particular site can have at least one service properly configured at any time. But it does mean that two site updates are needed; one now, and one in three weeks. However, since it's sufficient for only one (of the two) voms servers to be configured properly, sites could save effort and wait until (say) 19th April, then update both at once. But I can't dictate what site admins should do. It's your call.

Ste


Tuesday 5th Mar 2019 New VOMs details for Biomed: https://www.gridpp.ac.uk/wiki/GridPP_approved_VOs

New VOMs rpms to match.

http://hep.ph.liv.ac.uk/~sjones/RPMS.voms/

Tuesday 12th Feb 2019 Documentation done for HTCondor-CE apel accounting. https://twiki.cern.ch/twiki/bin/view/LCG/HtCondorCeAccounting


Tuesday 12th Feb 2019 New CA DN for Biomed

< VOMS_CA_DN="'/C=FR/O=CNRS/CN=GRID2-FR' "
---
> VOMS_CA_DN="'/C=FR/O=MENESR/OU=GRID-FR/CN=AC GRID-FR Services' "

Tuesday 5th Feb 2019 For enmr, certificate of voms-02.pd.infn.it

New DN: /DC=org/DC=terena/DC=tcs/C=IT/L=Frascati/O=Istituto Nazionale di Fisica Nucleare/CN=voms-02.pd.infn.it, New CA_DN: /C=NL/ST=Noord-Holland/L=Amsterdam/O=TERENA/CN=TERENA eScience SSL CA 3

Please check approved VOs: https://www.gridpp.ac.uk/wiki/GridPP_approved_VOs


General note

See the worst KeyDocs list for documents needing review now and the names of the responsible people.

Interoperation - EGI ops agendas Indico schedule

14 May 2019

  • Meeting for May cancelled. Next meeting is on 10th June.

Monday 11th March


Tuesday 12th February

  • There was an EGI ops meeting yesterday - Agenda. We were asked to review the IPv6 readiness information (see here). We should perhaps link in the GridPP IPv6 table for updates status.


Friday 1st February

Thursday 17th January EGI OMB meeting

  • CREAMCE to be out of support by Dec 2020
  • More effort to fix accounting issue of HTCondor CE

Monday 14th January 2019

  • No UK specific issue mentioned.
  • IPv6 readiness plan is going to be summarized at OMB.

'


Monitoring - Links MyWLCG

Tuesday 4th July

  • There were a number of useful links provided in the monitoring talks at the WLCG workshop in Manchester - especially those in the Wednesday sessions.

Monday 13th February

  • This category is pretty much inactive. Are there any topics under "monitoring" that anyone wants reported at this ops meeting? If not we will remove this section from the regular updates area of the bulletin and just leave the main links.

Tuesday 1st December


Tuesday 16th June

  • F Melaccio & D Crooks decided to add a FAQs section devoted to common monitoring issues under the monitoring page.
  • Feedback welcome.


On-duty - Dashboard ROD rota

Tuesday 5th February

  • Birmingham decommissioning of SRM and BDII still going on so tickets are on hold.
  • Few availability tickets on hold
  • Lancaster has WebDav ticket on hold which seems to be effect of DOME rollout

Tuesday 14th August

  • A couple of new availability tickets (QMUL and Lancaster), both for well-publicised reasons. Otherwise quiet. AM on shift this week.


Rollout Status WLCG Baseline

Monday 20th November



Historical References


Security - Incident Procedure Policies Rota

Tuesday 11th June

  • NTR


Services - PerfSonar production dashboard |PerfSonar ETF | OSG Networking and perfSONAR pages | GridPP VOMS

- This includes notifying of (inter)national services that will have an outage in the coming weeks or will be impacted by work elsewhere. (Cross-check the Tier-1 update).

Monday 5th March

Monday 10th September

Monday 2nd July

Monday 30th April

Monday 19th February

Please could sites upgrade their perfsonar hosts to CentOS7. Instructions are here. Current OS versions here.

  • Duncan has recreated the UK perfSONAR mesh. Link here!


Tickets

32 Open Tickets this week, which is an in depth a look as I've been able to take.

Tools - MyEGI Nagios

Monday 20th November

Tuesday 18th July

  • Following our ops discussion last week, Steve will focus his tests on supporting the GridPP DIRAC area and decommission the other tests.


VOs - GridPP VOMS VO IDs Approved VO table

Monday 20th November

  • Tom Whyntie has requested (and been granted) access to the GridPP VO to get some pipelines working for large-scale processing and analysis of MRI scans associated with the UK Biobank project.
  • All VOs in the incubation page being prompted for updates by the end of November (required input for OC documents).
  • QMUL (Steve L) is following up on the biomed MoU. GridPP want to be cited in research papers for the support our resources/sites provide.


Site Updates

Date



Meeting Summaries
Project Management Board - MembersMinutes Quarterly Reports

Empty

GridPP ops meeting - Agendas Actions Core Tasks

Empty


RAL Tier-1 Experiment Liaison Meeting (Wednesday 13:30) Agenda Meeting takes place on Vidyo.

Highlights from this meeting are now included in the Tier1 report farther up this page.

WLCG Grid Deployment Board - Agendas MB agendas

Empty



NGI UK - Homepage CA

Empty

Events
UK ATLAS - Shifter view News & Links

Atlas S&C week 2-6 Feb 2015

Production

• Prodsys-2 in production since Dec 1st

• Deployment has not been transparent , many issued has been solved, the grid is filled again

• MC15 is expected to start soon, waiting for physics validations, evgen testing is underway and close to finalised.. Simulation expected to be broadly similar to MC14, no blockers expected.

Rucio

• Rucio in production since Dec 1st and is ready for LHC RUN-2. Some fields need improvements, including transfer and deletion agents, documentation and monitoring.

Rucio dumps available.

Dark data cleaning

files declaration . Only Only DDM ops can issue lost files declaration for now, cloud support needs to fill a ticket.

• Webdav panda functional tests with Hammercloud are ongoing

Monitoring

Main page

DDM Accounting

space

Deletion

ASAP

• ASAP (ATLAS Site Availability Performance) in place. Every 3 months the T2s sites performing BELOW 80% are reported to the International Computing Board.


UK CMS

Empty

UK LHCb

Empty

UK OTHER
  • N/A
To note

  • N/A