Tier1 Operations Report 2018-10-08

From GridPP Wiki
Jump to: navigation, search

RAL Tier1 Operations Report for 8th October 2018

Review of Issues during the week 2nd October 2018 to the 8th October 2018.
  • The on-going LFC issue appeared to have had been resolved early in the week (w/e 30th), as such the service was returned to Production.
  • First breakage of database = 19th August Fixed 21st September Second breakage of database = Tuesday 25th September 1pm.
  • Currently we have reasonable confidence that LFC issues are now understood and there is a fix:
    • In conjunction with Fabrizio Furano (former LFC code developer at CERN), we have identified a flaw in the Oracle to MySQL migration process.
    • An Oracle SEQUENCE had not been migrated into a MySQL table therefore it was only possible to register 6820 new records in the new MYSQL backend each time before a crash.
    • This is explanation also accounts for the fact that rolling back the database to an earlier backup also worked
    • Fabrizio provided a simple solution to fix the problem.
  • We are now planning to implement the fix and restore the LFC to a full production service by close of business 02/10/2018.
Current operational status and issues
Resolved Castor Disk Server Issues
Machine VO DiskPool dxtx Comments
- - - - -
Ongoing Castor Disk Server Issues
Machine VO DiskPool dxtx Comments
gdss747 Atlas atlasStripInput d1t0 Currently in intervention.
gdss753 Atlas atlasStripInput d1t0 Currently in intervention.
gdss738 LHCb LHCb_FAILOVER,LHCb-Disk d1t0 Currently in intervention.
Limits on concurrent batch system jobs.
Notable Changes made since the last meeting.
  • None.
Entries in GOC DB starting since the last report.
Service ID Scheduled? Outage/At Risk Start End Duration Reason
- - - - - - - -
Declared in the GOC DB
Service ID Scheduled? Outage/At Risk Start End Duration Reason
- - - - - - - -
  • No ongoing downtime
  • No downtime scheduled in the GOCDB for next 2 weeks
Advanced warning for other interventions
The following items are being discussed and are still to be formally scheduled and announced.

Listing by category:

  • Castor:
    • Disk only storage will end in Castor. A new single tape-only Castor instance (called WLCGTape) is being tested. This is using generic Catsor headnodes on SL7 configured by Quattor/Aquilon with a slightly newer Castor version.
    • Update systems to use SL7 and configured by Quattor/Aquilon. (Tape servers done)
  • Internal
    • DNS servers will be rolled out within the Tier1 network.


Open

GGUS Tickets (Snapshot taken during morning of the meeting).

Request id Affected vo Status Priority Date of creation Last update Type of problem Subject Scope
137619 cms in progress urgent 07/10/2018 08/10/2018 CMS_AAA WAN Access T1_UK_RAL xrootd read failures WLCG
137391 atlas in progress urgent 25/09/2018 05/10/2018 Network problem UK RAL-LCG2 transfer errors with Communication error on send WLCG
137195 ops in progress less urgent 14/09/2018 05/10/2018 Operations [Rod Dashboard] Issues detected at RAL-LCG2 EGI
137153 t2k.org in progress urgent 12/09/2018 25/09/2018 Data Management - generic LFC entry has file size 0, preventsw registering of additional replicas EGI
136701 lhcb waiting for reply very urgent 14/08/2018 03/10/2018 File Transfer background of transfer errors WLCG
136199 lhcb on hold very urgent 18/07/2018 01/10/2018 File Transfer Lots of submitted transfers on RAL FTS WLCG
124876 ops in progress less urgent 07/11/2016 23/07/2018 Operations [Rod Dashboard] Issue detected : hr.srce.GridFTP-Transfer-ops@gridftp.echo.stfc.ac.uk EGI
GGUS Tickets Closed Last week
Request id Affected vo Status Priority Date of creation Last update Type of problem Subject Scope
137565 atlas solved less urgent 03/10/2018 05/10/2018 Other failing handshake for transfers from CA-VICTORIA-WESTGRID-T2_DATADISK to UK RAL-LCG2-ECHO WLCG
137498 cms solved urgent 01/10/2018 05/10/2018 CMS_AAA WAN Access Xrootd FileOpenErrors in production jobs WLCG
137416 none verified top priority 26/09/2018 01/10/2018 Other This TEST ALARM has been raised for testing GGUS alarm work flow after a new GGUS release. WLCG
137398 cms solved urgent 26/09/2018 03/10/2018 CMS_Data Transfers Transfers failing from SPRACE to RAL - No data available WLCG
137294 snoplus.snolab.ca closed very urgent 20/09/2018 05/10/2018 File Access No copy on tape error on Castor at RAL EGI
137267 atlas closed urgent 19/09/2018 03/10/2018 Other RAL-LCG2 transfer fail with "Communication error on send" WLCG
137254 ops verified less urgent 18/09/2018 04/10/2018 Operations [Rod Dashboard] Issue detected : ch.cern.LFC-Write-ops@lfc.gridpp.rl.ac.uk EGI
137047 t2k.org closed less urgent 06/09/2018 04/10/2018 File Access Connection to RAL tape storage fails EGI
136840 snoplus.snolab.ca solved very urgent 23/08/2018 03/10/2018 Other Cannot upload files to LFN from Storage node EGI

Availability Report

Day Atlas Atlas-Echo CMS LHCB Alice OPS Comments
2018-09-24 100 100 100 100 100 100
2018-09-25 100 100 100 100 100 100
2018-09-26 100 100 100 100 100 100
2018-09-27 100 100 100 100 100 100
2018-09-28 100 100 100 100 100 100
2018-09-29 100 100 100 100 100 100
2018-09-30 100 100 100 100 100 100
2018-10-01 53 100 100 100 100 100
Hammercloud Test Report
Target Availability for each site is 97.0% Red <90% Orange <97%
Day Atlas HC CMS HC Comment
2018-08-24 100 99
2018-08-25 100 99
2018-08-26 100 100
2018-08-27 100 100
2018-08-28 100 100
2018-08-29 100 99
2018-08-30 100 99
2018-08-01 100 99

Key: Atlas HC = Atlas HammerCloud (Queue RAL-LCG2_UCORE, Template 841); CMS HC = CMS HammerCloud

Notes from Meeting.