WLCG-OSG-EGEE Ops Minutes Mon 25 Feb 2008



  • Asia Pacific ROC: Min Tsai
  • Central Europe ROC: Matgorzata Krakowian
  • OCC / CERN ROC: Maite Barroso, John Shade, Antonio Retico, Steve Traylen
  • French ROC: Rolf Rumler, Cyril L'Orphelin, Pierre-Emmanuel Brinette
  • German/Swiss ROC: Sven Hermann
  • Italian ROC: Alessandro Cavalli
  • Northern Europe ROC: Jules Wolfrat
  • Russian ROC: Lev
  • South East Europe ROC: Kostas Koumantaros
  • South West Europe ROC: Kai Neuffer, Gonzalo Merino
  • UK/Ireland ROC: Jeremy Coles, Derek Ross
  • GGUS: Helmut Dres
  • OSCT: Absent


  • WLCG Service Cordination: Harry Renshall, Jamie Shiers

WLCG Tier 1 Sites

  • ASGC: Min Tsai
  • BNL: Absent
  • CERN site: Alessandro di Girolamo, Simone Campana, Patricia Mendez
  • FNAL: Joe Kaiser
  • FZK/GridKa: Sven Hermann
  • IN2P3: Rolf Rumler
  • INFN: Alessandro Cavalli
  • NDGF: Anders Rhod Gregersen
  • PIC: Gonzalo
  • RAL: Matt Hodges, Derek Ross
  • SARA/NIKHEF: Absent
  • TRIUMF: Absent

Reports Not Received

  • VOs: not a single report received!
  • EGEE ROCs (Prod Sites): France, Russia, SWE

Feedback on Last Week's Minutes

None were given, perhaps due to their tardy publication.

EGEE Items

Grid Operator Hand Over on Duty

  Primary Team Secondary Team
From ROC France ROC UKI

  • SAM portal slowness (10-minute delays): not observed at CERN. Nevertheless, Judit is working on optimizing some of the SQL queries.
  • YerPhI responded to the escalation step and are upgrading their SE.

PPS Reports

  • Antonio: PPS is being reorganized to make the service more suitable for use by HEP VOs & to extend the scope of pre-deployment testing. Antonio circulated an inventory spreadsheet last week, and renewed his request for feedback (within the week, please!). The goal is the redistribution of tasks within PPS.
  • The lcg-utils bug (GGUS:33262) reported by CE ROC is currently being investigated by the developers.
  • Glite 3.1.0 PPS Update 19 is currently being tested. See the agenda page for a brief description, and the release notes for the details.

EGEE Items From ROC Reports

  1. Problems with SAM job submissions. Judit: the specification is too vague, clarification needed (e.g. parameters for queue). Maite: "Please always ask sites to provide GGUS ticket numbers!" Update: ticket in question identified by Sven as being GGUS:33099.
  2. Input sandoxes on WMS. GGUS:33136 WMS experts + Maarten will look at the ticket & interact with the site (problem not seen at CERN).
  3. Accounting problems. John Gordon replied (see agenda page), but a GGUS ticket would have been useful. The APEL folks maintain a useful FAQ to help with publishing problems.
  4. MON on SL4. This is addressed by the latest release to PPS which will soon be made available.

gLite Release News
Antonio: gLite 3.1 update 15 with new certificates for two VOs (biomed & egeode) is coming. Rolf: any timeline for gLite WMS for SL4? Oliver: currently under heavy testing (WMS & LB). Release Candidate is ready, but a 5-day stability period is required, hence the delay. EMT minutes give all the details.

Support for gLite 3.0 services
Oliver: One month of proven good performance is the criteria for being able to withdraw the previous version (3.0). Please react now to this announcement! Withdrawl of support means no more bug fixes or functional updates (other than for security issues). Lev has sites with old lcg-CEs but doesn't anticipate any problems. Sites can either upgrade or face the consequences of no support. Oliver requested that a reminder of the policy (1 month of good behaviour) be sent out so that future retirals come as no surprise. Kostas requested a web-page with a rough timeline as being more efficient than having everyone do their own calculations. Support for all the 3.0 packages listed on the agenda page will stop next week. Nb. the gLite 3.1 node tracker page is available here.

Oliver asked whether there was a need to include DPM Oracle in the distribution alongside DPM MySQL. Action: ROC Managers to check with their respective sites.

Input for consolidated prioritization of 64-bit porting is both accepted & requested (Action: ROC managers). Action: Oliver will provide the list for 32-bit releases.

Migration from RB to WMS: lcg-RB has been in maintenance for some time. WMS is the functional equivalent. SL4 WMS would be a good moment to make the switch for those who have not already done so. Nb. Network Server (edg-job-submit & friends) is no longer there. Action: Broadcast to VOs (including link to user documentation). RBs should henceforth be considered obsolete and unmaintained.

Judit: There is a new pre-release version of the SAM web services installed on the SAM Validation instance. Detailed information is available here. Judit urged people to check that their existing calls using the programmatic interface still work. In addition, notification was given that Host Certificate tests will henceforth run at 6hr intervals rather than hourly.

The two SAM UI nodes were upgraded last week, so tests were run at half the normal frequency. As of tomorrow, all should be back to normal. Some SRM tests last week weren't run due to a bug (details of all SAM outages here).

GLUE V2 draft:
A broadcast has been sent with the new Glue v2 draft specification. Please send any feedback directly to Laurence Field.

WLCG Items

This is the last full week of CCRC'08.

Harry reminded the audience to use dcache.org for getting updates.

3 eLog items were entered over the weekend:

  • proxy corruption at RAL (now fixed)
  • ALICE VObox at Lyon invisible to CERN (but not for everybody), possibly due to the gridmap file.
  • LHCb space problems at Lyon (not recovering space when deleting files - need latest version of dCache)

Rolf: Lyon plan to upgrade dcache tomorrow, and he suspects that a firewall configuration is the cause of ALICE's VO box woes.

WLCG issues coming from ROC reports

  • None

Upcoming WLCG Service Interventions

ATLAS Service (Simone)

Since the end of last week, the full matrix of Tier1-Tier1 transfers is being tested. Impossible to get files from NIKHEF (Flavia investigating). SRM V1 end-points are still being used in several places rather than v2.

Tests of Tier2 clouds should start this week. Rate of export reached >2GB for a few hours on Friday. Problems injecting files into Castor on Friday slowed things down. Machinery is running at 70% of peak rate (problem should be fixed now). ATLAS will stop at end of the week in order to prepare for a muon challenge.

ALICE Service (Patricia)

Core services and DB services all OK.

CMS Service

No one present, but Harry reported stable, 800mbs exports.

LHCb Service

WLCG Service Coordination

OSG Items

From Joe Kaiser:
  • File transfer issue to BNL being worked on (GGUS:32463)
  • GGUS:33220 is not detailed enough. Something about LDAP searches in Spain and word counts (no mention of OSG). Update: Maria checked, and reassigned to GSTAT.

US-ATLAS VOMS server issue (OSG CC'd) from Maria. Joe confirmed that the BNL instance of VOMS should be deprecated (GOC uses CERN, not BNL).

Review of Action Items

102: Nick is absent this week, so no progress.

136,137: ATLAS: will check next Monday to see how many sites need to upgrade (end of March deadline). Clarification: we're talking about upgrades from existing SL3 to SL4.


Kostas: SE has a 64-bit site. Simone confirmed that Atlas s/w must run in 32-bit compatibility mode. This means that 64-bit machines must also install the 32-bit libraries. Alessandro de Salvo is the main man.

Next Meeting

The next meeting will be Monday, 03 March 2008 15:00 UTC (16:00 Swiss Mountain 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:

Edit | Attach | Watch | Print version | History: r8 < r7 < r6 < r5 < r4 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r8 - 2008-02-27 - 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