Difference between revisions of "Operations Bulletin Latest"

From GridPP Wiki
Jump to: navigation, search
()
(... added about four weeks?!)
Line 143: Line 143:
 
====== ======
 
====== ======
 
<!-- ******************Edit start********************* ----->
 
<!-- ******************Edit start********************* ----->
 +
 +
'''[http://storage.esc.rl.ac.uk/weekly/20181031-minutes.pdf Wed 31 Oct]'''
 +
* The role of [http://eos.web.cern.ch/ EOS] in the present and future GridPP
 +
 +
'''[http://storage.esc.rl.ac.uk/weekly/20181024-minutes.txt Wed 24 Oct]'''
 +
* GridPP storage and data management - well placed to contribute to IRIS
 +
* Rucio+cache, proposed EOS evaluations, DOME testing update(s)
 +
 +
'''[http://storage.esc.rl.ac.uk/weekly/20181017-minutes.txt Wed 17 Oct]'''
 +
* DUNE view of GridPP
 +
* Options for RHUL - from basic operations to existential angst?
  
 
'''[http://storage.esc.rl.ac.uk/weekly/20181010-minutes.txt Wed 10 Oct]'''
 
'''[http://storage.esc.rl.ac.uk/weekly/20181010-minutes.txt Wed 10 Oct]'''
Line 151: Line 162:
 
* GridPP41 Hackathon report
 
* GridPP41 Hackathon report
 
* GridPP41 everything else report, and archiving data
 
* GridPP41 everything else report, and archiving data
 
'''[http://storage.esc.rl.ac.uk/weekly/20180815-minutes.txt Wed 15 August]'''
 
* Updates on the forward view for GridPP6
 
* Unfortunately Vidyo has been "upgraded" to VidyoConnect which has several work-hindering features.
 
 
'''[http://storage.esc.rl.ac.uk/weekly/20180808-minutes.txt Wed 08 August]'''
 
* Updates on the forward view for GridPP6 - storage technologies, future directions
 
* Vidyo annoyances
 
 
'''[http://storage.esc.rl.ac.uk/weekly/20180801-minutes.txt Wed 01 August]'''
 
* IRIS
 
* GridPP planning - hack day on DOME?
 
  
 
<!-- ******************Edit stop********************* ----->
 
<!-- ******************Edit stop********************* ----->

Revision as of 16:47, 5 November 2018

Bulletin archive


Week commencing Monday 5th November 2018
Task Areas
General updates

Monday 5th November

  • Restarting Technical Meetings on Friday. Topics to be announced at the ops meeting.
  • ISGC 2019 Submission Deadline Extended to 19 November.
  • Winnie: LCG frontier-squid server, w/DNS alias - ok?
  • WLCG weekly ops notes from Monday 5th.


Tuesday 30th October

  • EGI Trust Anchor release 1.94-1. Update by 5th November.
  • Minutes from this week's WLCG ops meeting are available.
  • The GridPP Technical Group is to provide the forum for the various strands of Rucio-related work in the UK.
  • AF: LSST VOMS changes. Impact on those using YAIM.
  • Important notice concerning the support of TLS v1.2 on EGI: minimum supported version to be set to

TLS v1.0 again in /etc/grid-security/gsi.conf


Tuesday 23rd October

  • Monday's WLCG ops meeting minutes.

Tuesday 16th October

  • There is a GDB this week. Agenda.
  • September WLCG T2 A/R figures circulated:
    • ALICE
      • Birmingham 52%
    • ATLAS
      • QMUL 82%
      • Lancs 87%
    • CMS
      • Bristol 88%
    • LHCb
      • QMUL 86%
  • VOMS admin requests
  • CERN accounts
  • Chris B: Modifying Firewall rules on PerfSONAR hosts?

Tuesday 8th October

  • HEPiX this week
  • The latest from WLCG operations. Monday's minutes
  • Next LHCOPN and LHCONE meeting: Fermilab, Batavia US, 30-31October 2018. Agenda.


Monday 24th September


WLCG Operations Coordination - AgendasWiki Page

Tuesday 30th October

  • The ops meeting is shifting to the 8th November.

Tuesday 16th October

  • There was an ops coordination meeting on 11th October: Agenda/slides | Minutes.
  • Next meeting is on 1st November.


Monday 8th October

  • There will be an Ops Coordination meeting this Thursday 12th: Agenda.

Monday 17th September

  • There was a WLCG ops coordination meeting last Thursday. The minutes are now available and the presentations uploaded to this agenda page.
  • Highlights:
    • A report on EOS incidents, improvements and plans
    • DPM Storage Resource Reporting deployment TF introduction
    • CMS CRIC is deployed in production
    • Sites should upgrade perfSONAR to v4.1 on CentOS 7
    • The next meeting is planned for 11th October.



Tier-1 - Status Page

Tue 30th October Report for the Experiments Liaison Report (29/10/2018) is here.

  • Availability of the CMS-AAA service is improving. Machines have had their memory doubled, which has stopped the machines going in to swap. The other problem is a bug which is fixed in a later version of XRootD than we are running. We will need to recompile XRootD, create an RPM and deploy as appropriate.
  • Patching of machines against CVE-2018-14634 is in progress. The WN which were the most at risk of being exploited by this vulnerability were done on the 22nd - 23rd October. We still need to reboot ~500 other machines (total 1500).
  • A Ceph storage node developed a hardware fault and was removed from production on Saturday 27th morning. No degradation of service/unavailability of data was reported (as expected).
  • OPs tests are finally passing for Echo solving a ticket that was open for nearly 2 years!
Storage & Data Management - Agendas/Minutes

Wed 31 Oct

  • The role of EOS in the present and future GridPP

Wed 24 Oct

  • GridPP storage and data management - well placed to contribute to IRIS
  • Rucio+cache, proposed EOS evaluations, DOME testing update(s)

Wed 17 Oct

  • DUNE view of GridPP
  • Options for RHUL - from basic operations to existential angst?

Wed 10 Oct

  • Finally finalising GridPP fwd view?
  • How GridPP-storage-and-data-management would interface with and contribute to IRIS-TWGs

Wed 05 Sept

  • GridPP41 Hackathon report
  • GridPP41 everything else report, and archiving data
Tier-2 Evolution - GridPP JIRA

Tuesday 22rd October

  • VacMon monitoring pages running again, on CentOS7/ES5. Still slower than previous SL6/ES5 machine so may try again in a larger memory VM.

Tuesday 16th October

  • Vacmon was working for a while but is now timing out. AM looking at ways of downgrading back to the previous version for now.


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

Tuesday 18th September 2018

  • We need to flag documents that are obsolete and update our monitoring!

Tuesday 18th September 2018

  • Changes to Approved VOs: LZ record at Imperial now showing up in the portal (had been inserted as a special case until now.)


Tuesday 11th June 2018

Steve Jones is updating the User Guide with various mods that have cropped up since Tom Whyntie left (pending permission to edit GridPP website docs...)

Tuesday 11th June 2018

Approved VOs now contains two new SKA VOMS servers (at Oxford and Imperial, as well as Manchester).

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


Tuesday 8th May 2018

  • Updating GridPP website certificate to avoid Chrome warnings

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

Monday 08 October 2018

  • Argo notification is working so sites can subscribe to notification by enabling notification from GOCDB

Monday 17th September

  • There was an EGI ops meeting on 10th September. The agenda page is here.

Tuesday 24 July

  • EGI OPS meeting on 16 July 2018, meeting agenda [1]
  • UMD 4.7.0 release

Recommend not to update CREAM issue with canl-java, in progress https://ggus.eu/index.php?mode=ticket_info&ticket_id=136074

  • Does site requires MPI for Centos7? Is any site willing to support MPI for grid?
  • No meeting in August, next meeting on 10 Sep


Monday 2nd July

Monday 11th June

  • Meeting agenda : [2]
  • Upcoming releases relevant to UK sites
    • gfal2 major release(2.5.4)
    • Arc 5.4.2
  • Yearly review of information in GOCDB. UK ticket status is in progress. Should each site update the ticket?
  • Sites can enable ARGO notification through GOCDB. It can be done at site level or at the service level
  • Final call for WMS decommission. No UK WMS is in the list.
  • WebDav probes will be added to ARGO_MON_CRITICAL profile which means that unavailability of webdav will be added to A/R figures. All UK endpoints are passing the test at the moment
  • Next meeting 9th July

Monday 14th May

  • Next meeting June 11th

Tuesday 24th April

  • The next EGI OMB is on 3rd May

Tuesday 6/3


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 14th August

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

Tuesday 12th June

  • Four availability tickets still open. One ticket on hold at RAL as they are figuring out that how to deal with castor publishing issue.
  • Dashboard struggled during the week and it was slow but now it seems to be OK.
  • One Bristol ticket got stuck in weird state where it can not be deleted from dashboard although it has been solved.

Monday 21st May


Monday 5th March

  • AM->GS. A quiet week last week.


Rollout Status WLCG Baseline

Monday 20th November



Historical References


Security - Incident Procedure Policies Rota

Tuesday 30th October


Services - PerfSonar production dashboard |PerfSonar development dashboard | 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 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

Monday 5th November 2018, 14.00 GMT
41 Open UK Tickets this month

SUSSEX
https://ggus.eu/?mode=ticket_info&ticket_id=138071 (2/11)
A fresh ticket from atlas about SRM problems. The lack of links in the ticket made it hard for Leo to debug, and he has asked for clarification. Waiting for reply (2/11)

BIRMINGHAM
https://ggus.eu/?mode=ticket_info&ticket_id=138026 (31/10)
A ticket concerning the alice VOBOX at Birmingham. It looks like the problem went away on its on and this ticket can be closed, but there appear that there will be other conversations to have about alice needs at Birmingham at a later date. In Progress (can be closed) (3/11)

https://ggus.eu/?mode=ticket_info&ticket_id=137801 (17/10)
A Birmingham related ticket rather then a ticket for the site, the tracking of the decommissioning of their DPM SE. I can't quite remember how things are properly done, but shouldn't this be put On Hold until the 28th November? In progress (22/10)

BRISTOL
https://ggus.eu/?mode=ticket_info&ticket_id=138041 (1/11)
A CMS ticket concerning failing transfers. Lukasz has traced the problem due to the files being on disk but not in the namespace, and emailed the dpm support list for help fixing this (if a fix is possible). In progress (5/11)

OXFORD
https://ggus.eu/?mode=ticket_info&ticket_id=137941 (25/10)
Sno+ had problems accessing data on the Oxford SE due to BDII issues. Kashif fixed the IPv6 routing problems that were the cause of these, and things are working once again. Another ticket that can be closed. In progress (30/10)

GLASGOW
https://ggus.eu/?mode=ticket_info&ticket_id=134689 (23/4)
Request to upgrade Perfsonar boxes to CentOS7. Gareth gave his plan and (good) reasons why they won't be able to do this just yet at Glasgow - getting v6 working comes first. On hold (30/10)

ECDF
https://ggus.eu/?mode=ticket_info&ticket_id=137985 (29/10)
Atlas deletion errors at Edinburgh. Andy is reckoning this is a consistency problem as the system tries to delete files that aren't there anymore, and has asked if it's lots of different file deletion attempts failing or the same few deletion attempts failing repeatedly. I used to have a dodgy bash script that could help with that (by working on the downloaded xml from the DDM pages), but I don't think it made it off of our old SE I'm afraid. Waiting for reply (1/11)

DURHAM
https://ggus.eu/?mode=ticket_info&ticket_id=134687 (23/4)
Request to upgrade Perfsonar to CentOS7. It was mentioned verbally that this has been postponed to be part of "CentOS 7 Big Push" early next year, could that be put into the ticket. Be aware that Perfsonar support on SL6 will end soon though (we're already in the "grace period"). In progress (26/9)

SHEFFIELD
https://ggus.eu/?mode=ticket_info&ticket_id=137732 (15/10)
One of the ROD availability tickets, waiting for the time to pass. There's been a good stretch of green 100%s in the argo monitoring, so things are looking good. On hold (15/10)

https://ggus.eu/?mode=ticket_info&ticket_id=138095 (5/11)
Another ROD ticket, this is for the "APEL-Pub" tests. Set In Progress (5/11)

MANCHESTER
https://ggus.eu/?mode=ticket_info&ticket_id=137112 (11/9)
An atlas ticket about Manchester's Space Token numbers being broken after trouble with a draining script moving data outside of the tokens. The process to move them back was expected to take weeks. How are things looking now? Tim provided some figures from rucio a few weeks back, but that picture might be out of date now. On Hold (16/10)

LANCASTER
https://ggus.eu/?mode=ticket_info&ticket_id=136635 (9/8)
A very long running low availability ticket caused by issues with Lancaster's SE. The recent problems were caused by the CertLifetime check not working for a while during the move to DOME was underway, returning an "Unknown" status. As every other aspect of our DPM worked in that time I've requested a recomputation, which may or may not be a bit cheeky. On Hold (5/11)

https://ggus.eu/?mode=ticket_info&ticket_id=137996 (30/10)
Another ROD ticket (sorry ROD shifters), this time failing a non-critical http test. The issue has been tracked to a problem in the DOME code and a fix will hopefully be out this month. Until then... On Hold (5/11)

QMUL
https://ggus.eu/?mode=ticket_info&ticket_id=134573 (17/4)
CMS request to install singularity, on hold until the QM move to CentOS7. CMS has re-poked the ticket, asking again for the site's plans. On Hold (31/10)

BRUNEL
https://ggus.eu/?mode=ticket_info&ticket_id=133956 (9/3)
CMS ticket regarding Brunel's xroot configs. Raul has done some work involving DOME in the background, perhaps some of that progress could be used to update the ticket? In progress (16/10)

TIER 1
https://ggus.eu/?mode=ticket_info&ticket_id=138033 (1/11)
Atlas singularity jobs failing at RAL, with some reference to similar issues for SKA. It's being looked at, and Tim has provided some extra observations. In progress (1/11)

https://ggus.eu/?mode=ticket_info&ticket_id=137650 (9/10)
CMS seeing low HC xroot success rates at RAL. Lots of back and forth on the ticket, I don't think a conclusion has been reached yet though. In progress (2/11)

https://ggus.eu/?mode=ticket_info&ticket_id=138077 (2/11)
CMS SAM tests failing at RAL. Things seem to have healed themselves, but John has asked some team members to check the logs. In progress (5/11)

https://ggus.eu/?mode=ticket_info&ticket_id=138103 (5/11)
CMS transfers failing - the cause looks to be a zero-sized "stub file" causing issues, and it's being investigated. In progress (5/11)

https://ggus.eu/?mode=ticket_info&ticket_id=138002 (29/10)
CMS problems with the FTS, with a lot of sites seeing "bad transfer quality". Investigations pointed to a IPv6 problem that has since been fixed. However Gareth couldn't see an endemic issue with the RAL FTS whilst looking through the plots, and has asked for clarification. Waiting for reply (5/11)

https://ggus.eu/?mode=ticket_info&ticket_id=137897 (23/10)
enmr.eu jobs have zero normalised CPU hours in the accounting portals. It seems to have been a problem with the data the site reported. Catalin has asked the VO if anything changed around the 16th of October, and to resubmit some more jobs so they can watch them. Waiting for reply (5/11)

https://ggus.eu/?mode=ticket_info&ticket_id=137752 (15/10)
A request to replicate the OSG cvmfs repositories on the EGI stratum 1s. These have been replicated to the RAL servers, so I don't know what the next steps are. In progress (2/11)

https://ggus.eu/?mode=ticket_info&ticket_id=136199 (18/7)
One of a few LHCB FTS tickets, it looks like the work here has progressed nicely so maybe this ticket can be closed? Or is it waiting on all LHCB FTS issues to be solved? In progress (1/11)

https://ggus.eu/?mode=ticket_info&ticket_id=137822 (18/10)
FTS servers seemingly in a bad state for LHCB. I think this is being worked on, but no news in this particular ticket. In progress (22/10)

https://ggus.eu/?mode=ticket_info&ticket_id=138028 (1/11)
LHCB noticing files cannot be staged from tape to disk. The issue is somewhat understood (there is a copy of the file on disk elsewhere), but it's unsure why the resulting disk-to-disk transfer fails so the ticket is being kept open. In progress (1/11)

https://ggus.eu/?mode=ticket_info&ticket_id=136701 (14/8)
LHCB ticket regarding the high background rate of failures putting job output into RAL. I don't think a conclusion has been reached, the last update has Chris from LHCB collecting some more stats and saying that LHCB hope to be using direct xroot connections in the not too distant future. In progress (17/10)

https://ggus.eu/?mode=ticket_info&ticket_id=137153 (12/9)
T2K having trouble with zero sized files in the LFC. The LFC devs have been contacted for help, but that was a few weeks back. Any news from them? In progress (10/10)

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