Week of 151207

WLCG Operations Call details

• At CERN the meeting room is 513 R-068.

• For remote participation we use the Vidyo system. Instructions can be found here.

General Information

• The purpose of the meeting is:
  • to report significant operational issues (i.e. issues which can or did degrade experiment or site operations) which are ongoing or were resolved after the previous meeting;
  • to announce or schedule interventions at Tier-1 sites;
  • to inform about recent or upcoming changes in the experiment activities or systems having a visible impact on sites;
  • to provide important news about the middleware;
  • to communicate any other information considered interesting for WLCG operations.
• The meeting should run from 15:00 until 15:20, exceptionally to 15:30.
• The SCOD rota for the next few weeks is at ScodRota
• General information about the WLCG Service can be accessed from the Operations Web
• Whenever a particular topic needs to be discussed at the daily meeting requiring information from site or experiments, it is highly recommended to announce it by email to wlcg-operations@cernSPAMNOTNOSPAMPLEASE.ch to make sure that the relevant parties have the time to collect the required information or invite the right people at the meeting.

Tier-1 downtimes

Experiments may experience problems if two or more of their Tier-1 sites are inaccessible at the same time. Therefore Tier-1 sites should do their best to avoid scheduling a downtime classified as "outage" in a time slot overlapping with an "outage" downtime already declared by another Tier-1 site supporting the same VO(s). The following procedure is recommended:

1. A Tier-1 should check the downtimes calendar to see if another Tier-1 has already an "outage" downtime in the desired time slot.
2. If there is a conflict, another time slot should be chosen.
3. In case stronger constraints cannot allow to choose another time slot, the Tier-1 will point out the existence of the conflict to the SCOD mailing list and at the next WLCG operations call, to discuss it with the representatives of the experiments involved and the other Tier-1.

As an additional precaution, the SCOD will check the downtimes calendar for Tier-1 "outage" downtime conflicts at least once during his/her shift, for the current and the following two weeks; in case a conflict is found, it will be discussed at the next operations call, or offline if at least one relevant experiment or site contact is absent.

Links to Tier-1 downtimes

ALICE	ATLAS	CMS	LHCB
	BNL	FNAL

Monday

Attendance:

• local: Maria Alandes (chair,minutes), Maarten Litmaath (ALICE), Christoph Wissing (CMS), Ulrich Schwickerath and Krystof Borkovec (Grid&Batch), Prasanth (IT-DB), Asa Hsu (ASGC)
• remote: David Cameron (ATLAS), Andrei Tsaregorodtsev(LHCb), Michael Ernst (BNL), Lisa Giachetti (FNAL), Rolf Rumler (INP3), Dimitri (KIT), Ulf Tigerstedt (NDGF), Onno Zweers (NL-T1), Kyle Gross (OSG), John Kelly (RAL), Di Qing (TRIUMF)

Experiments round table:

• ATLAS reports ( raw view) -
  • HI processing is proving challenging (esp memory)
  • Otherwise regular activities, nothing special to report

• CMS reports ( raw view)
  • Transfer problems at KIT: GGUS:118169, GGUS:118171 + tickets from other VOs
    • CRL outdated and fixed over the weekend
    • Did not help to improve working through the existing backlog of stage requests: GGUS:117910
  • Still issues with EOS file access: GGUS:118082
    • Several files appear to have only one replica at Wigner
    • Particular server not online
    • Causes delays in Heavy Ion data PromptRECO

• ALICE -
  • KIT: team ticket GGUS:118170 Saturday evening about expired CRL for CERN Grid CA
    • Fixed Sunday morning, thanks!
  • CERN: team ticket GGUS:118177 Sunday evening about CASTOR issue affecting reco jobs
    • Converted to alarm ticket when the DAQ could no longer write.
    • Quickly fixed by the CASTOR team, thanks!

• LHCb reports ( raw view) -
  • Data Processing
    • Heavy Ion data processing ongoing, almost complete
    • Monte Carlo at low pace, user analysis at T0/1/2D sites
    • Lead-Lead data replication ongoing
  • Issues: nothing significant
    • CNAF: CVMFS access ticket to be closed after reverification
    • GridKa: no SRM access on the week-end up until Sunday morning, no report on the issue resolution
    • GridKa /PIC: issues with access to some local data - being checked
    • RRCKI data replication is resumed

Sites / Services round table:

• ASGC: NTR
• BNL: NTR
• CNAF: NA
• FNAL: NTR
• GridPP: NA
• IN2P3: Full day site maintenance from 07.12 at 21h to 08.12 at 18h30. GOCDB.
• JINR: NA
• KISTI: NA
• KIT: As reported by several experiments affected by the issue, the CRL problem was fixed on Sunday.
• NDGF: Several tapes run out of physical space during the weekend. This has been now solved.
• NL-T1: NTR
• NRC-KI: NA
• OSG: NTR
• PIC: NA
• RAL:
  • Several network interventions scheduled this week. Check GOCDB 1 and 2
  • Due to a DoS attack in the UK Academic Network, data transfers to RAL may be affected.
• TRIUMF: NTR

• CERN batch and grid services: Lost about 3000 worker nodes over the weekend and 20k associated jobs running on them. A SIR is available with the details of the issue here.
• CERN storage services: Absent due to a meeting clash with CMS to discuss the EOS performance issues.
• Databases: /Applications/Oracle DFS volume was unavailable for 30 min starting from 11:00, since tnsnames.ora resides there this could have caused applications using this tnsnames.ora not able to connect to databases
• GGUS: NA
• Grid Monitoring: NA
• MW Officer: NA

AOB:

Thursday

Attendance:

• local: Maria Alandes (chair,minutes), Krystof Borkovec (Grid&Batch)
• remote: Peter Love (ATLAS), Andrei Tsaregorodtsev(LHCb), Michael Ernst (BNL), Lisa Giachetti (FNAL), Rolf Rumler (INP3), Ulf Tigerstedt (NDGF), Andrew Pickford (NL-T1), Kyle Gross (OSG), John Kelly (RAL), Di Qing (TRIUMF), Sang Un Ahn (KISTI), Eric Vaandering (CMS)

Experiments round table:

• ATLAS reports ( raw view) -
  • FTS issue in BNL. GGUS:118285.

• CMS reports ( raw view) -
  • The issue with the poor performance in EOS transfers have been now fixed and root cause has been understood.
  • NDGF reports about failed file transfers into a T2 in Finland that result in CMS opening tickets to the site because the files are not available, as CMS believes the transfers have been successful. Ulf suggests that CMS follows up better on failed transfers. This happens one or twice every month. Ulf has tried to contact CMS experts without success. Eric will follow up.

• ALICE -
  • NTR

• LHCb reports ( raw view) -
  • Data Processing
    • Heavy Ion data reconstruction almost complete
    • Monte Carlo at low pace, user analysis at T0/1/2D sites
    • Lead-Lead data replication ongoing, no reconstruction yet
    • Data prestaging for the Restripping 15 ( Run II data ) is started
  • Issues:
    • IN2P3: downtime on 8th Dec was announced not to include SEs, but they were also unavailable
    • RRCKI: problem with recalling a file from the tape storage
    • CNAF: CVMFS not accessible on some WNs, probably due to a low activity at CNAF, being checked

Sites / Services round table:

• ASGC: NA
• BNL: The FTS https daemon has just been restarted to try to fix the issue reported by ATLAS. [NB: Further analysis has shown that prior to the restart the FTS service was fully functional. The reason as to why job submission from Rucio wasn't working was, as far as we understand things, that the certificate on the client side at CERN was changed, but the CRLs on the server side at BNL were not yet updated. Therefore all job submissions from this/these particular host(s) was/were rejected. We have contacted the FTS developers and they suggested the following: "fetch-crl renews the certificate revocation lists on disk, but neither mod_ssl nor mod_gridsite reload them while running. It is necessary to issue a service httpd reload/restart/graceful to trigger the refresh. Otherwise, the in-memory crls eventually expire and you get that error. So you need to make sure that periodically, you run service httpd graceful to trigger a reload of the crls. This period has to be lower than the crl expiration time, so once/twice a day should suffice". Note we consider restarting the http daemon periodically a stop gap and not a viable solution.]
• CNAF: NA
• FNAL: NTR
• GridPP: NA
• IN2P3: NTR
• JINR: NA
• KISTI: NTR
• KIT: NA
• NDGF: All danish pools are currently offline due to a fiber cut.
• NL-T1: NTR
• NRC-KI: NA
• OSG: Transition from OSG CA to CERN CA is now in place for US ATLAS. US ATLAS users are now pointed to the CERN CA to obtain a personal certificate.
• PIC: NA
• RAL: Recording tape issues seem to be fixed now. Network degraded at RAL due to broadcast storm.
• TRIUMF: Intervention scheduled on 13th December to upgrade router for 20 minutes.

• CERN batch and grid services: NTR
• CERN storage services: NA
• Databases: NA
• GGUS:
  • GGUS Release deployed on 9th of December, with a new support unit (WLCG HTTP Deployment Task Force), and some minor changes on the UI
• Grid Monitoring:
  • Draft availability reports for November sent, and available at the SAM3 UI
• MW Officer: NA

AOB: