Week of 170220

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: Kate (chair, DB), Vladimir (LHCb), Julia (WLCG), Maarten (ALICE + GGUS), Gavin (computing), Vincent (security), Andrea M. (MW Officer + storage), Jesus (storage), Giuseppe (storage), Ivan G. (ATLAS), Alberto A. (monitoring)
• remote: Andrew (NLT1), David B (IN2P3), David C (ATLAS), John K. (RAL), Pepe (PIC), Tommaso (CMS), Luca (CNAF), Jens (NDGF), Xin (BNL), Vincenzo (EGI), Victor (JINR), David M. (FNAL), Kyle (OSG), Fa Hui Lin (ASGC), Sang Un (KISTI)

Experiments round table:

• ATLAS reports ( raw view) -
  • Smooth operations, running on ~300k job slots. New production campaign MC16a continues.
  • Reprocessing is to start by the beginning of March with data16 first then data15. Staging of RAW files from Tier1 tapes started last week.
    • UPDATE: The information for the RAW staging was announced on the "ADC Weekly" meeting on Tuesday, 14.02.2017 where representative from each cloud are expected to be present. The topic will be discussed once again on the next "ADC Weekly" tomorrow, 21.02.2017.
  • CERN NoAFS day - no immediate effect on ADC. Too short to see increased job failure rate.
  • Tape staging tests: PIC & NDGF has increased the internal timeout above the 48 limit of FTS. Ticketing other sites to do the same.
  • We are looking at the Frontier server loads in more detail (index relevant variables and upload them to ElasticSearch and monitor in Kibana) to understand better which jobs cause the server loads and their corresponding database queries to optimize the condition database accesses required by such jobs.

• CMS reports ( raw view) -
  • nearly uneventful week, Computing Run Coordinator mostly hands-off
  • big MC production for Moriond 17 done, now mostly
    • Phase II simulations (2026+)
    • Phase I simulations (2017 and 2021)
    • Analysis continuing at a good pace (more than 60k jobs at any time...)
    • All spot-like, which means T1/2s can experience moments of lower activity (as expected ...)
  • Many alarms from CMSWEB, most transient, some requiring service restart
    • annoying, but we are getting used to them, the system is under pressure since many weeks
    • All in all, the system is coping with the load
  • Some tickets open, none beyond usual business.

• ALICE -
  • High activity
  • CERN: all CEs were failing the SAM tests of ALICE and CMS Fri evening (GGUS:126689)
    • Starting ~15:00 CET, fixed by ~21:00
    • Gavin commented issue is understood and related to Puppet 4 migration (old config file picked up)

• LHCb reports ( raw view) -
  • Activity
    • MC Simulation, user analysis and data reconstruction jobs
  • Site Issues
    • Some issues with file access at NRC-KI

Sites / Services round table:

• ASGC: ntr
• BNL: BNL FTS is now IPv6 enabled (dual stack).
• CNAF:
  • We noticed a huge activity on tape from atlas, it's not far from being a DoS (see recall success rate).
  • Future operations of this size should be announced to the site in order to cope with the requests, same goes for the foreseen campaign of analysis that will be run directly on scratch disk. (ATLAS has confirmed the load. The matter will be discussed again with the sites on "ADC Weekly". More details in ATLAS'es report).
• EGI: ntr
• FNAL: downtime tomorrow
• GridPP: nc
• IN2P3: the site will be in maintenance downtime on March 21st, a Tuesday. As usual details will be available one week before the event.
• JINR: NTR. But still low CMS jobs load.
• KISTI: ntr
• KIT: nc
• NDGF: ntr
• NL-T1: ntr
• NRC-KI: nc
• OSG: ntr
• PIC: Enstore will be upgraded tomorrow.
• RAL: Some work planned for Wednesday but shouldn't be service affecting.
• TRIUMF: NTR

• CERN computing services: Some issues with Argus.
• CERN storage services:
  • Castor Alice will be in downtime on Thursday, Feb 23rd between 13:30 and 16:00 due to a database migration to new HW. Similar intervention should be expected for other experiments in the coming weeks.
  • Diskservers need to be updated to CentOS7. It can be done in one go with downtime, or part by part over a period of time. ALICE probably would prefer an update in one go.
• CERN databases:
  • CMSR instance 1 rebooted on Wednesday due to high load
  • HW migration ongoing
    • ADCR was migrated today
    • ATONR was migrated last Tuesday
    • ATLR migration is tentatively scheduled for next week
    • CMSONR ADG (just alias migration) proposed for Tuesday next week
    • CMSARC migration proposed for Tuesday next week
• GGUS: NTR
• Monitoring:
  • Distributed final A/R reports for January.
• MW Officer:
  • 2 issues are affecting the latest Xrootd release (v4.6.0 available in the xrootd repository ) both client and server side. We suggest Sites and Experiments not to use this version.
    • https://github.com/xrootd/xrootd/issues/463,
    • https://github.com/xrootd/xrootd/issues/465
• Networks: absent
• Security: ntr

AOB: