WLCG-OSG-EGEE Ops' Minutes Tue 01 Jul 2008

Attendance

  • Kostas Koumantaros (SEE)
  • Clemens Koerdt (DECH)
  • Lev Shamarin (Russian ROC)
  • 0031208884035 -- Ron Trompert (NE ROC)???
  • Jeremy Coles (UKI)
  • Catalin Dumirescu (FNAL)
  • 0033478930880 -- Cyril, Pierre (French ROC)???
  • John Shade, Steve Traylen, Flavia Donno (CERN)
  • Alessandro di Girolamo (ATLAS)
  • Roberto Santinelli (LHCb)
  • Min Tsai (ASGC APROC)
  • Malgorzata Krakowian (CE ROC)

  • Alessandro di Girolamo (ATLAS)
  • Roberto Santinelli (LHCb)

Apologies: ROC Italy: we are unavailable today for the Operations Meeting, due to a telephone/switchboard failure.- Alessandro

[Could those dialing in with anonymous phone numbers please also connect with a web-browser and list the names of those in the room? - Ed.]

Reduced attendance: Due to the EGI Workshop being held today at CERN, there was a lower than usual participation in today's Ops meeting.

Summary

  • Pre production testing of the CREAM CE is now well under way.
  • Requests were made for comments on the proxy renew deamon crashing with the recently released VOMS servers.
  • IN2P3 are investigating 30,000 atlas jobs hitting their site.
  • A report was given on base storage services needed at sites. GSSDCCRCBaseVersions.
  • ATLAS requested gstat should flag up discrepancies between LFCs in GOCDB but not in BDII.

Feedback on Last Week's Minutes

None was given.

EGEE Items

Grid Operator Hand Over on Duty

  Primary Team Secondary Team
From ROC CE ROC UK/I
To ROC SWE ROC AP

  • Nit when collecting weekly reports: CIC portal uses the security certificate of a different site. Cyril will follow-up.

Assigned to Due date Description State Closed Notify  
JohnShade 2008-07-10 CIC portal uses the security certificate of a different site. Cyril will follow-up. John will submit a GGUS ticket.

Update: GGUS:38050 Problem is that Firefox doesn't recognize the French Certificate Authority. Solution is simply to define an exception in Firefox.

2008-07-03 edit

PPS Reports (in Antonio's absence)

  • New SAM DB is being set up for PPS
  • on-going work in PPS on Cream CE

gLite Release News (in Antonio's absence)

  • Release of gLite3.1 PPS Update31 to PPS in preparation (contains glexec installation/configuration + rpath stripping)
  • gLite3.0 Update50 in advanced phase of pre-deployment testing, contains a fix to glite-FTA

EGEE Items From ROC Reports

  • In response to a question from CE ROC: LCG_GFAL_INFOSYS - is not part of official release. SAM does not intend to use this feature. The question about alarms during SE scheduled downtimes is an issue with the presentation layer - in this case, the COD dashboard.
  • DESY wanted to know the procedure to follow when users use site resources in a denial-of-service manner. ROCs should follow this up with their respective sites.
  • NE ROC were inquiring about GGUS:37334. Steve will follow-up.

Assigned to Due date Description State Closed Notify  
SteveTraylen 2008-07-10 Steve to look at GGUS:37334 and escalate to someone.

2nd July - This may be resolved by a fix to BUG:37008, waiting for clarification.

8th July - Mentioned in the EMT yesterday, the fix is in an upcoming patch and
also a bug will be submitted to link to it. Add bug before next week and close.

14th July - Bug now submitted BUG:38820 . As I understand it this already fixed in
an upcoming release. Close the action here after today's meeting since the BUG is
now present.

2008-07-14 edit
  • SE ROC (Antun) seeking to validate running accounting for multiple sites on a single monbox. Clemens said that Italian ROCs do it (but they use DGAS). No one was able to help, but Steve reckoned that, technically, it should be OK. Kostas will keep us posted.

WLCG Items

WLCG issues coming from ROC reports

  • Alessandro volunteered to investigate the 30'000 Atlas jobs at IN2P3 problem, but Cyril said that it was probably an internal problem with IN2P3's batch system.

Upcoming WLCG Service Interventions

  • Steve reported that the VOMS service "went on a migratiion & software upgrade today". The old VOMS service will be decommissioned on Wednesday.

ATLAS Service (Alessandro)

  • Nothing special to report. Question for CNAF: Do they have any news? Power-cut, floor collapsing? According to Roberto, CNAF is not yet back. Steve stated that it was for the COD to decide how they should submit tickets to Italy.

ALICE Service

CMS Service

LHCb Service

  • gsidcap file access issue at IN2P3 has been resolved. The s/w fix (1.8.0-15p8 out next week) will need to be rolled out ASAP.
  • No SRMv1 pools configured at SARA, which is a problem for LHCb. Ron said that he'd attend to the problem immediately after the meeting.

WLCG Service Coordination

Flavia gave the storage service status weekly report. dCache patch 8 is recommended (7 shouldn't be installed). For Castor, the latest patch is 2.1.7-10 which is about to be released. Tier-1s are recommended to upgrade around the 15th of July.

The base versions of services and client software is maintained GSSDCCRCBaseVersions. The link is now included as an integral part of the agenda pages for these meetings.

OSG Items

Action Items

Newly Created Action Items

Review of Open Action Items

Open Action Items

IdSubmitterDescriptionCreationDueAssigned To 

Actions Closed in Last 20 Days

IdSubmitterDescriptionCreationDueAssigned ToClosed 

AOB

Suggestion to use EVO for these meetings was squashed. However, if the CERN callback problems persist, the decision could be reversed.

Kostas complained that there had been no progress with GGUS:37890. UK/I ROC should have a look.

Assigned to Due date Description State Closed Notify  
Main.UKRoc 2008-07-10 UK/I ROC to look at GGUS:37890.

*14th July 2008* Jeremy will take a look.

*21st July 2008* BUG:38320 which was the related item is now fixed and closed.
This item is, consequently, also closed.

2008-07-21 edit

ATLAS mentioned that the LFC from CNAF has disappeared from the infosystem since February. It is hard for experiments to keep track of these things. Steve explained that GSTAT normally checks for discrepancies between GOCDB & BDII. He will submit a ticket to get them to include LFCs in their tests.

Assigned to Due date Description State Closed Notify  
SteveTraylen 2008-07-10 Steve should submit a GGUS requesting that gstat monitors for LFCs not publishing as compared to GOCDB.

*2nd July* GGUS:38053 now submitted, leave action item until a response is given.

2008-07-08 edit

Next Meeting

The next meeting will be Monday, 7 July 2007 15:00 UTC (16:00 Swiss local time).

  • Attendees can join from 13:45 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:

Edit | Attach | Watch | Print version | History: r13 < r12 < r11 < r10 < r9 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r13 - 2008-07-21 - JohnShade
 
    • Cern Search Icon Cern Search
    • TWiki Search Icon TWiki Search
    • Google Search Icon Google Search

    EGEE All webs login

This site is powered by the TWiki collaboration platform Powered by Perl This site is powered by the TWiki collaboration platformCopyright & by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Ask a support question or Send feedback