WLCG-OSG-EGEE Ops' Minutes Mon 21 Apr 2008

• Date: Mon 28 Apr 2008
• Agenda: 32602
• Chair: NicholasThackray
• Minutes: JohnShade
• Minutes from previous meetings: WlcgOsgEgeeOpsMeetingMinutes

Attendance

EGEE

• Asia Pacific ROC: Absent
• Central Europe ROC: Marcin Radecki
• OCC / CERN ROC: Nick Thackray, Antonio Retico, John Shade
• French ROC: ??
• German/Swiss ROC: Sven Hermann
• Italian ROC: Alessandro Cavalli
• Northern Europe ROC: Jules Wolfrat
• Russian ROC: Lev Shamardin
• South East Europe ROC: Kostas Koumantaros
• South West Europe ROC: Kai Neuffer
• UK/Ireland ROC: Jeremy Coles
• GGUS: Helmut Dres

WLCG

• WLCG Service Cordination: Harry Renshall, Jamie Shiers

WLCG Tier 1 Sites

• ASGC: Absent
• BNL: Absent
• CERN site: Ignacio Reguero (FIO), Alessandro di Girolamo (ATLAS)
• FNAL: Absent
• FZK: Sven Hermann
• IN2P3: Pierre
• INFN: Alessandro Cavalli
• NDGF: Absent
• PIC: Kai Neuffer
• RAL: Matt Hodges
• SARA/NIKHEF: Absent
• TRIUMF: Absent

16:05 Apologies for the late start of the meeting; there were some squatters in the conference room. Attendance is reduced this week due to the WLCG workshop currently taking place at CERN.

If you access the tele-conference anonymously (e.g. Sunrise & 0033478930880), please give the list of attendees to the minute taker. In the future, the chair will try and make a point of asking.

Reports Not Received

• VOs:
• EGEE ROCs (Prod Sites):

Feedback on Last Week's Minutes

None were given.

EGEE Items

Grid Operator Hand Over on Duty

	Primary Team	Secondary Team
From	ROC DECH	ROC Russia
To	ROC South East	ROC asia-Pacific

• 1) YerPhI (ticket 26634): Deadline for resolution will be extended by a week to allow time for network investigation. Nick pointed out that the long-term solution to problems like these will be provided by the SLD, which specifies that SAM tests must be passed successfully and continuously.

• 2) Australia-UNIMELB-LCG2 (ticket 34393): a week’s extension granted prior to escalation to Ops meeting. Nick: this is a heads-up for SE/AP ticket handlers, and AP ROC.

PPS Reports

No particular issues. Read the agenda for the details of the releases. In particular, Antonio mentioned update 42 which has been released to production with high priority:

1. New certificate for lcg-voms
2. new version of FTA for FTS service needed for CCRC’08 exercise.

In PPS, updates 23 & 24 are currently being tested. They include important WMS bug fixes, and a new set of clients on WNs (GFAL & lcg-utils). Release to production could be as early as tomorrow.

Antonio mentioned that “PPS is being updated to something already pushed out to prod”. This seems a back-to-front state of affairs, but is due to CCRC08 requiring things to be fast-tracked. Please see the meeting agenda for details.

Nick: Announcement about new CIC portal release, which will have noticeable changes – tomorrow 09-09:30 UTC. Gilles had nothing to add, but confirmed that the changes would be noticeable.

EGEE Items From ROC Reports

Nothing special to report other than a comment from CE ROC concerning Atlas’s request for 100GB s/w areas & SL4 updates. CE would like the experiment to raise one GGUS ticket per ROC (for tracking purposes). They felt that tracking progress through GGUS was more appropriate that using the ROC managers’ meeting for this. Alessandro explained that ATLAS didn’t really want to have to figure out which ROC to contact for a particular site, but Nick said that there is probably a way to clone a ticket for all ROCs. Action: Nick to see with Antonio how to do this.

Marcin added that documentation for the new Atlas SAM tests would be nice, and Alessandro agreed that it should be provided. Marcin then mentioned that for test by the “ops” VO, SAM documentation is automatically generated, and this could be useful for ATLAS. Alessandro expressed excitement, and Marcin follow-up with Marcin off-line.

WLCG Items

WLCG issues coming from ROC reports

* None

Upcoming WLCG Service Interventions

Nick tracked all broadcasts for the week, and went through the list (they’re conveniently listed in the agenda), briefly interrupted by entertaining music from Helmut’s phone system. In addition, John mentioned that one of the SAM UIs was going to be upgraded tomorrow, with the result that the 10 o’Clock battery of tests would not be submitted (minor impact, any state changes during that period could potentially take an hour longer to detect). If interested, one can check the broadcast history in the CIC portal to find all announcements. A German switchboard operator piped-up at this point, and took a little while to understand Nick’s “please hang-up”

CCRC08 Operations Review

Virtually everyone is at the WLCG meeting. See agenda for the short CMS report, and the ATLAS report sent prior to meeting.

ATLAS Service

Some sites (see list in agenda) need to update their version of lcg-utils. Action: ROCs please chase the relevant sites.

Rolf (ROC France): classic SE will be suppressed in mid-May, so some sites can’t upgrade until then. John was confused as to why sites couldn’t upgrade even if they didn’t use the new functionality, but it seems that ATLAS wish to use space-tokens and other new features.

Kai (ROC SW): one site has lcg-utils 1.6.8. Is this a problem? Nick: using 1.6.10 from PPS should probably be used to avert potential problems.

ALICE Service

Kai: EELA site from ALICE (not in GOCDB). Is SWE ROC meant to deal with EELA sites? Nick will take this off-line.

CMS Service

LHCb Service

OSG Items

Rob (OSG) is at CERN but at WLCG workshop. Therefore, we’re assuming no items.

Action Items

Newly Created Action Items

Assigned to	Due date	Description	State	Closed	Notify
Main.OCC	2007-03-05	Example Action Item	openclosed	2007-03-06 SteveTraylen		edit

Review of Open Action Items

Open Action Items

Id	Submitter	Description	Creation	Due	Assigned To

Actions Closed in Last 20 Days

Id	Submitter	Description	Creation	Due	Assigned To	Closed

AOB

SE ROC – Kostas: Orthodox Easter, so slower responses can be expected (this Friday & next Monday are holidays).

ATLAS - Alessandro: Performance problems with LFC server at CERN were not detected by any monitoring tools (querying lfc-ls couldn’t see degradation, but real services were working poorly). ATLAS had no way of seeing that the lfc service was defgraded. Ignacio said that the problem was solved this morning. It was due to a replica table & an index missing after the latest DB intervention. SLS functionality was OK, but performance was “crap”. Alessandro was worried that it was due to the new h/w, and was relieved to hear that it was simply an index issue. Would be good to have a performance sensor...

No more AOB. Meeting closed at 16:52.

Next Meeting

The next meeting will be Monday, dd mmm 2007 15:00 UTC (16:00 Swiss local time).

• Attendees can join from 14:45 UTC (15:45 Swiss local time) onwards.
• The meeting will start promptly at 15:00 UTC (16:00 Swiss local time).
• The WLCG section will start at the fixed time of 15:30 UTC (16:30 Swiss local time).
• To dial in to the conference:
  • Dial +41227676000
  • Enter access code 0157610

---

These minutes can only be changed by members of:

• Set ALLOWTOPICCHANGE = WLCGOpsMeetGroup