Difference between revisions of "Operations Bulletin Latest"

From GridPP Wiki
Jump to: navigation, search
()
()
Line 480: Line 480:
 
===== =====
 
===== =====
 
<!-- ******************Edit start********************* ----->
 
<!-- ******************Edit start********************* ----->
'''Monday 8th October 2018, 14.30 BST'''<br />
 
42 Open UK Tickets this month.
 
 
'''IPv6 Tickets'''<br />
 
'''BRISTOL:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131613 131613]<br />
 
Last update 4/10. There is some recent conversation of this ticket, servers are v6 configured but things are not quite right - perhaps with the v6 routing?
 
 
'''UCL:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131604 131604]<br />
 
Last update 4/10. Some positive news with hopefully some v6 addresses rolling out soon - but that old bugbear of v6 DNS being a problem is showing up again. Ben finishes his update asking if firewall rules remain the same between v6 and v4.
 
 
'''DURHAM:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131609 131609]<br />
 
Last update 10/7. Any news on this front? There seemed to be a lot of exasperation in the last, short post back in July.
 
 
'''CAMBRIDGE:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131614 131614]<br />
 
Last update 25/9. Some good news here, with the Cambridge perfsonars dualstacked and added to the mesh. Duncan noticed some low throughputs for the v6 traffic, but they are otherwise working.
 
 
'''BIRMINGHAM:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131612 131612]<br />
 
Last update 27/8. At the last update in August Mark mentioned that their Central I.T. was waiting on some shiny new infrastructure before they could provide v6 DNS. Has a timescale on getting this rolled out appeared in the last 6 weeks? Pressure definitely needs to be applied I think.
 
 
'''LIVERPOOL:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131606 131606]<br />
 
Last update 4/6. Steve and Co were waiting on new switches so that their v6 performance wouldn't be terrible, plus there were internal negotiations going on. Any news on any of this?
 
 
'''RHUL:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131603 131603]<br />
 
Last update 10/9 (from Duncan). Any news at all on this? The perfsonar was dual-stacked but as Duncan pointed out no v6 DNS.
 
 
'''OXFORD:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131615 131615]<br />
 
Last update 13/7. Kashif once again mentioned v6 DNS and a blocker. Any progress pressuring them?
 
 
'''GLASGOW:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131611 131611]<br />
 
Last update 4/9. It's not been that long since your last update where your move to Plan B (or is it Plan C, D, or Z?) was mentioned. Any news in that short space of time?
 
 
'''RALPP:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131616 131616]<br />
 
Last (proper) update 16/1. Any news here? Things seemed really positive for a while, but that was 2 seasons ago. Really needs an update.
 
 
'''MANCHESTER:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131607 131607]<br />
 
Last (proper) update 25/4. The perfsonars are dualstacked, but no news on the storage (again due to v6 DNS problems IIRC). Another ticket that really needs any update?
 
 
'''ECDF:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131610 131610]<br />
 
Last update: 6/9. There have been some Ipv6 misadventures at ECDF, but a lot of effort has been put into getting things working. Any luck on getting your pool nodes dualstacked (or finding out when you'll be able to do this)?
 
 
'''SHEFFIELD:''' [https://ggus.eu/?mode=ticket_info&ticket_id=131608 131608]<br />
 
Last update 10/7. Things were looking up for a while in the last update, but I take it from the silence since things haven't made much progress?
 
 
Back to the regular tickets, site-by-site as is the tradition.
 
 
'''RALPP'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137633 137633] (8/10)<br />
 
A very fresh CMS ticket for transfer failures to RALPP. Assigned (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137361 137361] (24/9)<br />
 
A t2k ticket, where a user notices that you can upload a zero-sized file but you cannot then download it. I'm not sure why this is relevant, but Chris can replicate with the Imperial SE and reckons it's a dcache "feature". It might be that this will go unresolved. In progress (26/9)
 
 
'''GLASGOW'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=134689 134689] (23/4)<br />
 
Request to upgrade the Glasgow perfsonars. With the release of 4.1 Gareth is working on it, and would like to build the new perfsonars using the docker images. Duncan has suggested giving it a go with the perfsonar-testpoint image to see how things go. In progress (21/9)
 
 
'''ECDF'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137627 137627] (8/8)<br />
 
A ROD ticket for failed SRM tests, Rob notes likely caused by some storages on a disk server falling over. Being fixed (and indeed the tests are working now). In progress (8/8)
 
 
'''DURHAM'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=134687 134687] (23/4)<br />
 
The Durham request to upgrade perfsonar. Adam has put upgrading onto their todo list in the last update. In progress (26/9)
 
 
'''SHEFFIELD'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137491 137491] (1/10)<br />
 
Atlas transfer failures to Sheffield. Acknowledged by the site, but have you had any luck tackling the issue? From today's update by the DDM shifters it looks like it's ongoing. In progress (8/10)
 
 
'''MANCHESTER'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137112 137112] (11/9)<br />
 
Atlas spotted that SRM space reporting at Manchester was broken. Robert set them straight- it was due to a bug in a draining script moving data outside of the tokens. Fixing this is a slow process, Robert estimated of the order of weeks. On hold (20/9)
 
 
'''LIVERPOOL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137458 137458] (28/9)<br />
 
Liverpool's SE not working for biomed, due to there being no space left on the communal area. Liverpool have a spacetoken for biomed, but it was going unused. John and Stephan helped the VO with how to query these. I suspect this ticket can be closed soon. In progress (4/10)
 
 
'''LANCASTER'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=136635 136635] (9/8)<br />
 
Low availability ticket for Lancaster. Being tough to get a clear 30 days due to a collection of downtimes and the Lancaster SE playing up a bit. On hold (8/10)
 
 
'''QMUL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=132929 132929] (18/1)<br />
 
APEL accounting ticket for QM's slurm batch system. Lots of discussion and a related APEL ticket ([https://ggus.eu/index.php?mode=ticket_info&ticket_id=118969 118969]). I'm not sure if there's much further input to be had from the site for now? In progress (12/9)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137180 137180] (13/9)<br />
 
A t2k ticket complaining about the QM data access being slow. One of several tickets tackling a known issue with the QMUL STORM (particularly SRM). Dan helpfully provided a bunch of alternatives and suggestions to help the user - so useful it should be documented! In progress (14/9)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137631 137631] (8/10)<br />
 
A fresh ROD ticket - all SE based tests... Assigned (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=136719 136719] (15/8)<br />
 
LHCB having file access problems at QM (although I think file metadata access problems would be more exact). The ticket mentions a database move, did you get round to this? In progress (18/9)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137622 137622] (8/10)<br />
 
LHCB FTS transfer problems - Dan notes that a rack had power problems which required physical intervention. The rack is back on so hopefully transfers will work again. In progress (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137617 137617] (7/10)<br />
 
An atlas ticket for the same issues. In progress (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=134573 134573] (17/4)<br />
 
A request to install singularity from CMS. Dan mentioned right at the start that this would be part of their CentOS7 move. Is this on the horizon? On hold (17/4)
 
 
'''IMPERIAL'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137468 137468] (28/9)<br />
 
CMS production job stage outs from Brunel to I.C. failing. Daniela cannot reproduce this by hand even though the problems persist for CMS. An environment to test this out by hand has been provided so Raul could try it out on a WN directly. In progress (5/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137352 137352] (24/9)<br />
 
CMS noticed a few transfers failing - a pool node had fallen over and then had filesystem troubles. All fixed now, so we're in the wait and see if things go green stage. Waiting for reply (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=136687 136687] (28/9)<br />
 
Loosely related to 137468 (this ticket uncovered that issue), CMS stageout failures at Brunel. I didn't quite follow the thread, but diagnostics were being run over the weekend. Did they reveal anything? In progress (5/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137451 137451] (28/9)<br />
 
LHCB data transfer problems at Brunel. A lack of information had made Raul's job debugging this difficult. Vladimir responded with something that could help a bit today. In progress (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=133956 133956] (9/3)<br />
 
CMS xroot config change ticket. In July a multi-point plan was laid out, how goes it? In progress (3/7)
 
 
'''100IT''' have a ticket: [https://ggus.eu/?mode=ticket_info&ticket_id=137306 137306]
 
 
'''Orphaned ticket:''' [https://ggus.eu/?mode=ticket_info&ticket_id=136687 136687]<br />
 
I think this ticket regarding third party http transfers and the FTS can be closed, I'm not sure anyone's looking at it.
 
 
'''THE TIER 1'''<br />
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137195 137195] (14/9)<br />
 
A ROD ticket due to bdii problems causing SRM test failures. The issues are known about and being worked through, but at last check on Friday the problems persist. In progress (5/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137391 137391] (25/9)<br />
 
Atlas seeing poor transfer efficiency to tape and disk at RAL. Tim narrowed the errors down to a pair of sources. One of the sources (TRIUMF) has spotted the cause at their side (a v6 networking issue I failed to fully understand), it may or may not be a similar problem for EELA-UTFSM. In progress (5/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=136701 136701] (14/8)<br />
 
LHCB noticing a high (5%) background failure rate for jobs at RAL. The theory is a network issue or a problem with Castor. Waiting on the submitter to get back from his hols. Waiting for reply (24/9)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=136199 136199] (18/7)<br />
 
LHCB stuck FTS transfers. There's been a long break in looking at this, waiting on Catalin to get back from a well-earned break. On hold (1/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137153 137153] (12/9)<br />
 
A t2k ticket about 0-sized files, asking how to deal with them in the LFC (where they seem to have a bunch of these). It appears to be unrelated to the recent LFC issues. There's some discussion at the Tier 1 about what to do. In progress (25/9)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=137634 137634] (8/10)<br />
 
A fresh CMS ticket regarding some transfer failures to METU (although the error could be at either end). In progress (8/10)
 
 
[https://ggus.eu/?mode=ticket_info&ticket_id=124876 124876] (7/11/16)<br />
 
The old ECHO gridftp test ticket - it's looking now like a simple authorisation problem for the test's robot certificate - so maybe we're nearly there fixing this. In progress (8/10)
 
 
  
  

Revision as of 10:31, 15 October 2018

Bulletin archive


Week commencing Monday 8th October 2018
Task Areas
General updates

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


Monday 17th September

  • The IGTF is about to release a regular update to the trust anchor repository (1.93) on Monday, September 24th 2018 (see RT).
  • A round of CERN account requests is due.
  • There was a GDB last week. Agenda.
  • The current status visible to WLCG on IPv6 deployment and issues is in <https://twiki.cern.ch/twiki/bin/view/LCG/WlcgIpv6%23IPv6Depl> this wiki page. We need to form an accurate UK picture and update the GridPP View by the end of September. Note the offer from JISC for Tim/Duncan to visit sites to assist with IPv6 issues.
  • EGI is running a user satisfaction survey for Federation Services. JC will complete this during the week and welcomes wider input. Areas: Services used; Overall satisfaction; Quality of service rating; Quality of documentation and support and suggestions for improving the services.
  • Sites publishing storage accounting: http://goc-accounting.grid-support.ac.uk/storagetest/storagesitesystems.html.



WLCG Operations Coordination - AgendasWiki Page

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.


Monday 9th July

  • There was a WLCG ops coordination meeting on 5th July. Minutes.

Monday 25th June

Monday 16th April

  • There was a meeting on 12th. Agenda | Minutes.
    • Balazs Konya is new in the role of WLCG Middleware Officer.
    • Next meeting 7th June.
    • Delay for submission of GGUS tickets for recalculation should be respected. It is 10 days after monthly drafts of the availability reports are sent around by WLCG project office. If the GGUS tickets are not submitted respecting 10 days delay, they are not accepted.
    • A/R recalculations will be accepted if they are relevant to the site MoU commitment or concern time ranges of sufficient length.


Tier-1 - Status Page

Tue 9th October Report for the Experiments Liaison Report (08/10/2018) is here.

  • LFC:
    • The LFC is STILL running - hurrah! We now believe that this problem has been correctly resolved.
  • FTS / gfal version issues:
    • The newest version of gfal made changes to the way certificate are processed. This broke transfers to a significant number of sites. Tier-1 was ticketed to role back the FTS service.
  • New Castor tape service:
    • Teir-1 have successfully run ATLAS performance tape test. Excellent results at 2GB/s. This was reported at the WLCG Archival Storage WG[1].
    • We were second only to IN2P3 who got 50% better throughput but had dedicated 36 T10KD drives compared to our 8 T10KD drives.
    • As we migrate more VOs to the new Castor instance we will have more drives available (up to 22) and this should mean we are likely to double our overall throughput.


[1] https://indico.cern.ch/event/756338/attachments/1723845/2784624/update-atlas-data-carousel-wlcg-wg.pdf

Storage & Data Management - Agendas/Minutes

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

Wed 15 August

  • Updates on the forward view for GridPP6
  • Unfortunately Vidyo has been "upgraded" to VidyoConnect which has several work-hindering features.

Wed 08 August

  • Updates on the forward view for GridPP6 - storage technologies, future directions
  • Vidyo annoyances

Wed 01 August

  • IRIS
  • GridPP planning - hack day on DOME?
Tier-2 Evolution - GridPP JIRA

Tuesday 3rd July"

  • "Universal" DIRAC VMs deployed in production for GridPP DIRAC and LHCb

Tuesday 26th Jun

  • LHCb Docker containers in production testing at Manchester
  • "Universal" DIRAC VMs for LHCb and GridPP in production testing at Manchester
  • These VMs include a fix for the LZ GFAL problems


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 9th October


Tuesday 2nd October

  • CVE-2018-14634
  • Security Team meeting this afternoon




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
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