Difference between revisions of "Operations Bulletin Latest"

From GridPP Wiki
Jump to: navigation, search
()
()
Line 96: Line 96:
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->
 
<!-- ***********************Start T1 text*********************** ----->
 
<!-- ***********************Start T1 text*********************** ----->
'''Tuesday 31st October'''
+
'''Tuesday 14th October'''
A reminder that there is a weekly [http://www.gridpp.ac.uk/wiki/RAL_Tier1_Experiments_Liaison_Meeting Tier-1 experiment liaison meeting]. Notes from the last meeting [https://www.gridpp.ac.uk/wiki/Tier1_Operations_Report_2017-10-18 here]
+
A reminder that there is a weekly [http://www.gridpp.ac.uk/wiki/RAL_Tier1_Experiments_Liaison_Meeting Tier-1 experiment liaison meeting]. Notes from the last meeting [https://www.gridpp.ac.uk/wiki/Tier1_Operations_Report_2017-11-08 here]
* Last Tuesday CMS was switched to use Echo for SAM tests. There was a problem with this and the change was reverted. The switch was made again on Monday 30th. This time is seems to be working for SAM tests. Chris Brew is to arrange a test on production data in Echo.
+
* There was a problem with CMS Castor service on Tuesday 7th Nov. after one of the "headnodes" failed and had to be replaced. CMS Castor was unavilable for around ten hours.
 +
* Castor will be unavailable for a few hours on Tuesday 14th Nov for patching of the nodes.
 +
* The LHCb Castor SRMs will be unavailable for a while on Wednesday 15th Nov. The Castor SRM version will be updated.
 +
* The "Test" FTS service (used by Atlas) has been enabled for IPv6 (i.e. dual stack enabled). The Production FTS will also have teh dual stack enabled next week.
 
<!-- **********************End T1 text************************** ----->
 
<!-- **********************End T1 text************************** ----->
 
<!-- *********************************************************** ----->
 
<!-- *********************************************************** ----->

Revision as of 16:36, 8 November 2017

Bulletin archive


Week commencing Monday 6th November 2017
Task Areas
General updates

Monday 6th November


Monday 30th October

  • Input for WLCG monthly ops coordination meeting.
  • And the latest weekly update.
  • EGI related items:
    • led NGI/site transition plans to IPv6 - survey.
    • EGI Storage Accounting: Check results | enabling instructions. Deadline was today and tickets will arrive soon.
    • new way for computing the weights for the NGIs average A/R values: computation power | summary.
    • NGIs average A/R values calculation.
  • WLCG reminder
    • The vast majority of Tier-2 sites to provide dual-stack access to their storage resources by the end of Run2 (end of 2018).
  • TB-SUPPORT communications
  • Computing Insight UK 2017 early bird registration closes on Tuesday. This year the theme is "Joining Up the UK e-Infrastructure”.


WLCG Operations Coordination - AgendasWiki Page

Tuesday 7th November

  • The WLCG ops coordination meeting last week (agenda | minutes had as highlights the topics:
    • Security Operations Center WG Workshop/Hackathon
    • Review of EL7 migration plans
    • Providing reliable storage: presentation by BNL


Monday 23rd October

  • The next WLCG ops coordination meeting will be on 2nd November.

Tuesday 10th October

  • There was an ops coordination meeting last Thursday 5th October: Agenda | Minutes.
    • There is one action for us to follow-up: "Collect plans from sites to move to EL7". We could make use of the Batch Systems table.


Tier-1 - Status Page

Tuesday 14th October A reminder that there is a weekly Tier-1 experiment liaison meeting. Notes from the last meeting here

  • There was a problem with CMS Castor service on Tuesday 7th Nov. after one of the "headnodes" failed and had to be replaced. CMS Castor was unavilable for around ten hours.
  • Castor will be unavailable for a few hours on Tuesday 14th Nov for patching of the nodes.
  • The LHCb Castor SRMs will be unavailable for a while on Wednesday 15th Nov. The Castor SRM version will be updated.
  • The "Test" FTS service (used by Atlas) has been enabled for IPv6 (i.e. dual stack enabled). The Production FTS will also have teh dual stack enabled next week.
Storage & Data Management - Agendas/Minutes

Wed 01 Nov

  • (very) modest progress on xcache testing...
  • Except that RALPP has it fully working for dCache - hope to get full report next week

Tuesday 3rd October

  • Looking for small DPM ATLAS site to possibly test xrootd caching
  • Tracking upgrade of SEs to new what will be new baseline versions. (dCache sites updated; 6/14 DPM up-to-date)
  • Alastair D. to give T2 site storage evolution talk 4/10/17 at gridpp-storage meeting

Wednesday 06 Sep

Wednesday 30 Aug

  • How will experiments use object stores in the future? Could the Sept. pre-GDB clarify this?
  • Fair bit of stuff known about advantages and disadvantages of erasure coding data, compressing data, etc. prior to storing it.
  • Bristol's curious missing SE - dropped out of the information system?
Tier-2 Evolution - GridPP JIRA

Tuesday 3 Oct

  • Productions tests of Vac 03.00pre at Manchester.

Tuesday 19 Sep

  • Running LHCb production MC in Docker and Singularity containers on Vac. Since GridPP39, CPU and memory cgroups wrapper around Singularity Containers has been added.

Tuesday 5 Sep

  • Docker and Singularity container support in Vac 03.00pre

Tuesday 29 Aug

  • Prerelease of Vac-in-a-Box (i.e. GitHub master) is now running on CentOS 7, for Vac 02.01.
  • Aiming for combined Vac/Vac-in-a-Box release with CentOS 7, but with continued SL6 support for Vac.


Accounting - UK Grid Metrics HEPSPEC06 Atlas Dashboard HS06

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 26th Sept 2017

  • Safari on macOS autogenerated client certificates fix put into production last week.

Tuesday 19th Sept 2017

  • Bug in Safari on macOS causes random Apple generated client cert to be presented to www.gridpp.ac.uk using a CA we don't know about. The connection is then rejected by Apache. Other browsers ok since we request but do not require that they supply a certificate. Workaround produced by (a) installing the Apple CA root and intermediary CA and (b) whitelisting UK e-Science DNs (+ CERN? Others?) in the HTTPS Wiki plugin. Tested but not yet in production.

Tuesday 5th Sept 2017

New Approved VO. SKA European regional data centre, skatelescope.eu

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

This VO is ramping up and has requested support. Andrew McNab is the contact person for GridPP.

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 9th October

  • MW
    • UMD 4.6 in November
      • UI, CREAM, ARGUS
      • If not before in 4.5.1
    • UMD Preview update on 22/9
      • not rooted 4.7.0 has a bug, wait for update
      • CREAM version in Preview, please test if applicable (leading to release as noted above)
  • Ops
    • cASO (OpenStack Accounting extractor) update: 100%IT done (GGUS ticket 130665)
    • A/R nothing to report
    • Computation Power
      • Sites check data by end of the month
    • EMI WMS
      • mice noted as being enabled on DIRAC
    • IPv6 Readiness
      • Would be useful for us to provide a report
    • webdav probes
      • If you're advertising a webdav endpoint, make sure it's in the GOC DB
    • Storage accounting deployment
      • Enable by 30th October; tickets to follow. Note that per broadcast new data currently not showing, please ticket on errors in logs only

Tuesday 29th August

  • There was an EGI Ops meeting last Monday. Agenda
  • UMD 4.5 is out with CentOS 7 WN package (see broadcast)
  • NGI_UK QoS ticket mentioned in agenda but not in meeting QoS ticket
  • Proposal: WMS will be removed from production starting from 1st January 2018
  • NGIs/ROCs please start discussing with sites and provide suggestions for the overall plan for IPv6
  • WebDAV reporting: The Operations Centres are asked to verify with their sites if the webdav protocol is really (intentional) enabled on their storage elements (if not, the information should be removed from the BDII), and report to EGI Operations
  • Next meeting 11th September https://indico.egi.eu/indico/event/3352/
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

Monday 23rd October

  • Generally quiet. RHUL affected by some transient issues. ECDF triggered low availability alarm a few weeks ago and still has time to go before it clears.
Rollout Status WLCG Baseline

Monday 13th February

  • Please can we hear something from Raul and Sam (or others contributing to the middleware readiness work) about news in this area at the ops meeting next week? Thank you.
  • Does anyone want specific questions in this area tackled in a roundtable discussion?

Tuesday 7th December

  • Raul reports: validation of site BDII on Centos 7 done.

Tuesday 15th September

Tuesday 12th May

  • MW Readiness WG meeting Wed May 6th at 4pm. Attended by Raul, Matt, Sam and Jeremy.


References


Security - Incident Procedure Policies Rota

Monday 30th October

  • EGI SVG ALERT [TLP:WHITE] Up to 'CRITICAL' risk, kernel exploit CVE-2017-7184 and others [EGI-SVG-CVE-2017-7184]
  • Upcoming meetings
    • Details and registration for SOC WG Workshop in December: Advert Indico

Monday 23rd October

  • Nothing to report

Tuesday 10th October

  • ...


Tuesday 3rd October

  • EGI SVG ADVISORY [TLP:WHITE] 'HIGH' risk Linux kernel local root vulnerability CVE-2017-1000253


Services - PerfSonar production dashboard |PerfSonar development dashboard | 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 23rd October

  • The LHCOPN/ONE meeting took place last week at KEK, co-hosted with the HEPiX Fall meeting.
    • You can find a short report of the meeting here.
    • All the slides presented are available in the agenda.

Tuesday 4th July

  • Pete C is preparing another networking forward look document. Note that figures presented in the Manchester workshop were for a Tier-2 (not always a single site).

here

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


Tickets

Monday 6th November 2017, 15.00 GMT
43 Open UK Tickets this month.

There are 15 "IPv6 deployment at WLCG Tier-2 Sites", only 5 have been acknowledged so far- but then the tickets did land on a Friday. We can discuss these in the meeting.

Storage Accounting Deployment
These were the other big blob of tickets to land in the last week, for Oxford, Birmingham, Durham, Manchester and Brunel. The Brunel ticket mentions the latest monitoring page for this:
http://goc-accounting.grid-support.ac.uk/storagetest/storagesitesystems.html

The 23 remaining regular tickets, site by site:

SUSSEX
122772 (11/7/16)
The webdav/xroot ticket - after rebuilding the system from scratch and getting help from Dan it looks like xroot still isn't playing ball. The last update has a few questions in it that could with some storage experts to weigh in on. In progress (18/10)

RALPP
131328 (25/10)
CMS "low hammercloud xroot success rate" ticket. Chris has been working hard on this, but is left in need of some answers looking at his last post. Waiting for reply (30/10)

131565 (2/11)
A CMS ticket for local stageout failures, due to the "unmerged" area filling up by the looks of it. Chris increased the size of this area, and asked some questions on quotas. Waiting for reply (2/11)

130264 (28/8)
Biomed ticket about invalid publishing from the RALPP CEs. The problem seems to have fixed itself despite no joy on the matching Brunel ticket (130263) and Chris not doing anything. Chris asks if Biomed wants to still track the issue. Waiting for reply (30/10)

OXFORD
129931 (4/8)
Failing atlas http SAM tests at Oxford. Have you tried to upgrade your DPM yet? On hold (19/9)

CAMBRIDGE
130787 (28/9)
LHCB jobs dying at Cambridge, John tried to fix the problem by upping the CPU limit, but the ticket needs feedback from LHCB. Waiting for reply (6/11)

BRISTOL
131590 (3/11)
A Friday ticket from CMS, regarding network links or something (I still don't speak CMS). Assigned (3/11) Update - the two issues are likely related, plus Lukasz sees some other errors and is tidying things up. In Progress.

131641 (6/11)
A fresh CMS ticket, that could be related to the previous one - this is about connection problems killing transfers ("connection limit exceeded" errors). Assigned (6/11) Reducing the number of simultaneous connections and allowing the database to catch up fixed things. Solved.

BIRMINGHAM
129930 (4/8)
Failing atlas http SAM tests at Birmingham. Mark put in a handy update this morning, with plans to reinstall in the next couple of weeks to see if that helps. Thanks Mark! On hold (6/11)

SHEFFIELD
131472 (31/10)
Atlas transfers having trouble at Sheffield. Elena notes that she is working on balancing disk servers, which we all know is slow work. In progress (31/10)

MANCHESTER
131171 (18/10)
Atlas VAC jobs failing at Manchester - this has been discussed heavily on lists and in the atlas uk meetings, and I think some conclusions have been made? Or did I dream that? In progress (24/10)

LIVERPOOL
131623 (4/11)
Atlas deletion error ticket - Steve is on it, the problem being on one of the disk servers. In progress (6/11) Update - solved. The server is back from the brink.

QMUL
130262 (28/8)
Biomed complaining that the QM Storm SE publishing invalid glue2 data. Daniel spotted that this is due to storm not publishing glue2 data at all. Biomed wants to know if there's a ticket about this - perhaps we should suggest they submit one? In progress (27/10)

IMPERIAL
(who win kudos for already closing their IPv6 tickets)

131126 (16/10)
Debugging CMS job problems, after some digging it looks like the jobs are having problems accessing files that they should be able to without issue. A mystery. Waiting for reply (is this still the right status?) (2/11) Update - Daniela couldn't replicate the issue so rightly closed the ticket.

131663 (6/11)
A fresh ticket from Brian, asking to check on the status of a file. Assigned (6/11) Solved with the file declared lost

BRUNEL
130263 (28/8)
The other Biomed publishing ticket, waiting on the ARC devs to patch the patch that Raul has been trying out. On hold (13/10)

TIER 1
131652 (6/11)
Jobs failing with gfal-copy errors, although Brian hasn't been able to replicate them. In progress (6/11)

131213 (19/10)
CMS having issues with fallback requests to RAL, tracked down to some dodgy xrootd servers which were restarted. Waiting on hearing if things are fixed. Waiting for reply (23/10)

131299(24/10)
CMS Hammercloud failure ticket. A hint has been dropped that the error message might be due to root CAs being off on the ECHO server. Has this been checked? In progress (24/10)

130949 (6/10)
CMS transfers failing to RAL disk, the root problem caused by their being no room at the disk servers! Chris has been helping, finding about 100TB unaccounted for. Any luck generating those file lists? In progress (25/10)

130207 (24/8)
A MICE ticket regarding Castor, I think all the issues have been solved, this ticket is just being left open whilst "new" disk servers are freed up to go into the disk pool. How goes that process? On hold (25/10)

127597 (7/4)
A CMS request to check the RAL networking. Gareth updated the ticket a few weeks back with news on the state of the firewall. On hold (5/10)

124876 (7/11/16)
ECHO gridftp ops tests failing, due to the tests not having the right path in them. Alastair has poked the ticket to get the tests fixed (125026) On Hold (25/10)

117683(18/11/15)
Castor not publishing glue 2. This is being worked on slowly in the background, but the ticket could do with a quarterly update. On hold (6/7)

Tools - MyEGI Nagios

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.


29th November 2016

LSST monitoring is available through vo-nagios

https://vo-nagios.physics.ox.ac.uk/nagios/cgi-bin/status.cgi?servicegroup=lsst&style=detail

13th September 2016


VOs - GridPP VOMS VO IDs Approved VO table
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