Week of 170731

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: Gavin (computing), Julia (WLCG), Kate (DB, chair), Paul (storage), Andrea M (MW, FTS), Marian B (network)
• remote: Dario B (ATLAS), Smita D (ATLAS), Luca (CNAF), Onno (NL-T1), Ulf (NDGF), John (RAL), Di Qing (TRIUMF), Dave M (FNAL), Tommaso (CMS), Vincenzo (EGI), Pepe (PIC), Kyle (OSG), Xin Zhao (BNL), Chi-Hsun (ASGC), Victor (JINR)

Experiments round table:

• ATLAS reports ( raw view) -
  • Activities:
    • Grid production continuing with 300k slots on average, plus contributions from HPCs.
  • Issues:
    • Uncontrolled submission of overlay jobs caused problems to Frontier servers in RAL, IN2P3-CC and TRIUMF last few days. Problem understood and in course of resolution.
    • FTS at RAL got stuck with integer overflow after 2 billion files. New version installed but in the meantime services moved to CERN pilot service. It turned out that this server had the RFC proxy installed and several storage sites with dCache or BestMan in the DE and US clouds could not recognise it (too old m/w versions). Temporarily fixed by usage of legacy proxy.

• CMS reports ( raw view) -
  • very calm week - at the limit of being boring
  • data taking resumed after stop, all seems ok. Currently PromptReco stopped on request by Offline, will be resumed on Monday
  • Run2017 MC starting - PreMixing samples on the way
  • heavy activity by upgrade Phase II samples
  • O(3PB) deleted from disks last week - expect some more
  • also expect O(5PB) deletion from tapes. It will not be the last one for 2017, probably, so we are not asking for immediate repacking. Sites can feel free to do it, if they think it makes sense for them.
  • No GGUS ticket worth being noted here

• ALICE -
  • apologies: ALICE operations will not attend today
  • continued very high activity
  • CERN: 3 HTCondor CEs crashed on Sat (GGUS:129837)
    • causing many thousands of ALICE jobs to be lost
    • 2 more CEs crashed on Sunday

• LHCb reports ( raw view) -
  • Activity
    • Lots of user analysis(some failling) and Monte Carlo simulation
  • Site Issues
    • T0: Jobs hold at HTCondor CEs CERN-PROD (GGUS:129147)
    • T1:
      • NTR

Sites / Services round table:

• ASGC: NTR
• BNL: NTR
• CNAF:
  • NTR
• EGI: NTR
• FNAL: NTR
• IN2P3: nc
• JINR: SAM SRM test problem 23-07 & 24-07. Disk dCache was under the pressure and "BUG" appears at some pools, we will fill report to support@dacheNOSPAMPLEASE.org
• KISTI: nc
• KIT: nc
• NDGF: NTR
• NL-T1:
  • dCache had internal communication problems this weekend. Some improvements on Saturday after a restart of some dCache components, but still transfers failing. Today we found more components with issues and restarted them; we hope all is fine now. A possible cause is that 2 of the 5 zookeepers were restarted on Friday evening. They were on the same VM host; we'll spread them better to avoid recurrence. We've also reported this to the dCache developers. GGUS:129830
• NRC-KI: nc
• OSG: Ticket exchange issue. Tickets don't arrive to OIM admin list. Possible an OIM list stored in Europe not in sync.
• PIC: Storage issue due to CMS overload, under investigation
• RAL: In addition to the problems mentioned in the Atlas report, there was a network break to the RAL tier1 last Tuesday (25th July). A switch went 'crazy' and things settled down when the links were manually failed over.
• TRIUMF: NTR

• CERN computing services: ntr
• CERN storage services:
  • FTS:
    • Prod upgrade to v3.6.10, tomorrow 1st Aug from 10:00 to 11:00 CEST. (OTG:0038929). The upgrade fixes an issue with integer overflow which affected RAL last week.
    • Pilot upgrade to v3.7.1, Thu 3rd Aug from 10:00 to 12:00 CEST (OTG:0038864).
  • EOS:
    • Machines not on the network still under investigation for ATLAS and CMS
  • CASTOR:
    • Update to CentOS 7 of LHCB, capacity will be down to 25% as there are already some machines on CentOS 7
• CERN databases: Patching of ALICE and LHCb online databases completed in the last 2 weeks fixed the PGA memory leak bug. No new incidents observed since the patching.
• GGUS: ntr
• Monitoring: ntr
• MW Officer:
  • Transfer issues using RFC proxy to/from dCache storages have been observed during the weekend by ATLAS on the FTS Pilot. All those instances are running dCache 2.13, which reached EOL. As already reported in WLCG ops coord, Sites should start upgrading to a version >= 2.16. EGI is going to open tickets from tomorrow to sites.
  • BeStMan issue under investigation
• Networks:
  • JINR network performance issue (GGUS:129544) - resolved, thanks to JINR for all the work on investigation and upgrades.
• Security: NTR

AOB: