EGEE-SA1-SWE Meeting

→ Europe/Zurich
VRVS Virtual Room (http://www.vrvs.org)

VRVS Virtual Room (http://www.vrvs.org)

Pacheco, Andreu
Description
Present: Andreu Pacheco (IFAE/PIC), Miguel Cardenas (CIEMAT), Adrià Casajús (UB), Farida Fassi (IFIC), Javier Sanchez (IFIC), Fco. Bernabé (CESGA), Javier Palacios (IFIC), Celso Martínez (IFCA), Mario David (LIP), Javier Lopez (CESGA), Juan Saborido (USC), Carlos Borrego (PIC), Pablo Rey (CESGA), Gonzalo Merino (PIC), Daniel Cano (IFCA), Guillermo Losilla (BIFI), Alvaro Fernandez Casani (IFIC), Kai Neuffer (CAB-INTA)
    • 12:00 → 12:15
      Briefing of activities 15m VRVS

      VRVS

      Speaker: Pacheco, Andreu (IFAE/PIC)
      more information
    • 12:05 → 12:15
      Operational status from sites 10m VRVS

      VRVS

      * From February 1st 2005 all sites must report by mail their operational status each friday if they want Gonzalo Merino to report with accuracy their status to EGEE Operations Meeting * Since the people from CERN is asking the ROCs to write the monday's 11 report following a sort of template, I think it will be useful that the SWE Site Reports that site managers are sending on friday to this list, try to follow a similar template as well. I suggest then that these reports are produced following the template available at: https://services2.pic.org.es/devel/download/txt/SR-SWE-Template.txt * Reports should be sent to: egee.swe.roc.contact@pic.es The reports from SWE are appended to the agenda page of the weekly operation meetings: http://agenda.cern.ch/displayLevel.php?fid=258
      Speaker: Merino, Gonzalo (PIC)
      • BIFI-LCG 15m
        * Guillermo Losilla. * With only one worker node the slot was used by Atlas bloking dteam SFT jobs. Weekly Operations Status Report: BIFI Reporting Period: 12/9/2005 to 16/9/2005 Availability of Core Services Hosted in the Site ================================================== No core services running at BIFI Non-Functional Time ==================== Since last Friday 8th September all SFTs began to fail with random errors in the replica management tests: "lcg_cp: Communication error on send", "lcg_del: Invalid argument", "the server sent an error response: 425 425 Can't open data connection", "lcg_rep: Communication error on send", "lcg_rep: Connection refused", "lcg_del: Communication error on send", "Timeout when executing the test after 900 seconds!!!", "a system call failed (Connection timed out)", "lcg_del: Transport endpoint is not connected"... After long time studying the issue, we found out there was a network problem; the Computer Centre of the University our network belongs to, was priorizing/controlling/filtering our network traffic in some way that produced all those timeouts and so on. After "speaking" with the responsible people at the Computer Centre now everything seems to be quite ok again. Anyway we will keep an eye on it. Scheduled Down Time =================== No scheduled down time intervals during the reporting period nor expected in the coming days. Major Operational Issues Encountered During the Reporting Period ================================================================ none Upgrade to Scientific Linux 3 (or equivalent) ============================================= By when will all service nodes in the Site be upgraded? Already done (running SL 3.0.4) By when will the WNs in the Site be upgraded? Already done (running SL 3.0.4) Points to Raise at the Operations Meeting ========================================= none
        Speaker: Losilla Anadon, Guillermo (BIFI)
      • CESGA-EGEE 15m
        * Javier Lopez reporting. * No real problems during the week.
        Speaker: Lopez, Javier
      • CIEMAT-LCG2 15m
        * Reported by mail. Weekly Operations Status Report: CIEMAT-LCG2 Reporting Period: 12/09/05 to 16/09/05 Availability of Core Services Hosted in the Site ================================================== There is no core services running at CIEMAT at this moment Non-Functional Time ==================== 1.0 days (Monday 12/09/05) Scheduled Down Time =================== * Scheduled Maintenance During the Reporting Period None * Scheduled Maintenance During the Next Reporting Period None Major Operational Issues Encountered During the Reporting Period ================================================================ Due to an unexpected electrical powerdown on past week lcg-bdii daemon was not publishing any information. It was restarted and problem was fixed (GGUS ticket 4361). Upgrade to Scientific Linux 3 (or equivalent) ============================================= By when will all service nodes in the Site be upgraded? Completed, now Scientific Linux 3.0.4 By when will the WNs in the Site be upgraded? Completed, now Scientific Linux 3.0.4 Points to Raise at the Operations Meeting ========================================= We are yet running LCG-2.4.0. As we are involved in SC3 along the next two weeks, we have to postponed our upgrade to LCG-2.6.0 until first week in October
        Speaker: Calonge, Javier
      • CNB-LCG2 15m
        * No report. * In schedulle downtime until tomorrow.
        Speaker: No contact person
      • IFCA-LCG2 15m
        * Dani Cano reporting. * No special issues.
        Speaker: Cano, Dani
      • IFIC-LCG2 15m
        * Javier Sanchez reporting. * Random failures.
        Speaker: Sanchez, Javier
      • INTA-CAB 15m
        * Kai Neufer reporting. * Monitoring jobs are queuing due to overload of other jobs. Weekly Operations Status Report: INTA-CAB Reporting Period: 11/09/05 to 17/09/05 Availability of Core Services Hosted in the Site ================================================ No core services hosted in this site. Non-Functional Time =================== 0 days. Scheduled Down Time =================== * Scheduled Maintenance During the Reporting Period 1.5 days. (14,15/09/2005) * Scheduled Maintenance During the Next Reporting Period 0 days. Major Operational Issues Encountered During the Reporting Period ================================================================ Upbgrade to LCG-2_6_0 Upgrade to Scientific Linux 3 (or equivalent) ============================================= Already done. Points to Raise at the Operations Meeting ========================================= None.
        Speaker: Huedo, Eduardo
      • LIP-LCG2 15m
        * Mario David reporting. * Only two replica management false positives. They have reserved at least one CPU for dteam to prevent overloading. Configured using MAUI. * Atlas and CMS jobs take very long time. They limit of number of jobs in queue (max 1-2 jobs). Weekly Operations Status Report: LIP Reporting Period: 12/09/05 to 18/09/05 Availability of Core Services Hosted in the Site ================================================== RB: rb02.lip.pt PX: px01.lip.pt BDII: ii02.lip.pt LFC: lfc01.lip.pt Non-Functional Time ==================== 1 [JS] during the whole week, We have permanently resrved one CPU for DTEAM, guarantying that the SFT are executed. The one time JS was due that another DTEAM member was running a job and all other CPU's were ocupied, making that the SFT job failled. 2 [CT] during the whole week, this was due to some RM failure, we consider this as false positive since it happened only twice. There are either "Warning" of "Failure" of apel, this is intermintent also. The accouting seems to be working OK. Points to Raise at the Operations Meeting ========================================= None
        Speaker: David, Mario
      • IFAE 15m
        Weekly Operations Status Report: [ IFAE ] Reporting Period: [ 12/09/05 ] to [ 19/09/05 ] Availability of Core Services Hosted in the Site ================================================== RB, BDII: ifaece02.ifae.es [OK] Non-Functional Time ==================== - Total days unavailable: 0 days Scheduled Down Time =================== Major Operational Issues Encountered During the Reporting Period ================================================================ none Upgrade to Scientific Linux 3 (or equivalent) ============================================= By when will all service nodes in the Site be upgraded? done By when will the WNs in the Site be upgraded? done Points to Raise at the Operations Meeting ========================================= none
        Speaker: Borrego, Carlos
      • PIC 15m
        Weekly Operations Status Report: [ PIC ] Reporting Period: [ 12/09/05 ] to [ 19/09/05 ] Availability of Core Services Hosted in the Site ================================================== ce01.ifae.es bdii01.pic.es [OK] Non-Functional Time ==================== - Total days unavailable: 0 Scheduled Down Time =================== Major Operational Issues Encountered During the Reporting Period ================================================================ Upgrade to Scientific Linux 3 (or equivalent) ============================================= By when will all service nodes in the Site be upgraded? Done By when will the WNs in the Site be upgraded? Done Points to Raise at the Operations Meeting ========================================= none
        Speaker: Borrego, Carlos
      • UAM-LCG2 15m
        * Reported by mail. Weekly Operations Status Report: [ UAM-LCG2 ] Reporting Period: [ 09/09/05 ] to [ 16/09/05 ] Availability of Core Services Hosted in the Site ================================================== MyProxy [OK] VOServer [OK] RB [OK] BDII [OK] Non-Functional Time ==================== Problem with globus-mds. I solved this problem restarting the service. Scheduled Down Time =================== Major Operational Issues Encountered During the Reporting Period ================================================================ none Upgrade to Scientific Linux 3 (or equivalent) ============================================= By when will all service nodes in the Site be upgraded? [ - I am installing lcg2.6.0 with quattor in a cluster of test. - I am having problem with the update of SE dcache - about 1'5 week ] Points to Raise at the Operations Meeting ========================================= none
        Speaker: Pardo Navarro, Juan Jose
      • UB-LCG2 15m
        * Adria Casajus reporting. * In schedulle downtime for LCG 2.6 upgrade
        Speaker: Graciani, Ricardo and Casajus, Adrian
      • UPV-GRyCAP 15m
        * No report
        Speaker: Caballer, Miguel
      • USC-LCG2 15m
        * Juan Saborido reporting. * The site is running smoothly.
        Speaker: Saborido, Juan
    • 12:10 → 12:15
      APEL Status Report 5m VRVS

      VRVS

      Speaker: Rey Mayo, Pablo (CESGA)
    • 12:15 → 12:30
      Action lists 15m VRVS

      VRVS

      Speaker: Pacheco, Andreu (IFAE)
      • 5.3.7.4 Mario to deploy gmdat monitoring tools in SWE (OPEN) 15m
        * Mario reporting. * He is still analysing the data to cross-check collected results. He has asked to upgrade the scripts to all sites. Some improvements have been done in the monitoring. * Mario is checking also GridICE. * All sites upgrading please contact Mario.
        Speaker: David, Mario (LIP)
      • 5.9.19.1 All sites to upgrade the gridice sensor in all machines (NEW) 15m
        * Done for CESGA, BIFI, LIP
        Speaker: Francisco Jose Bernabe Pellicer (CESGA)
      • 5.9.19.2 All sites to upgrade fmon2glue in gridice collector (NEW) 15m
        * Done for CESGA, BIFI, LIP
        Speaker: Francisco Jose Bernabe Pellicer (CESGA)
      • 5.9.19.3 Request for volunteers to test network monitoring with GridICE (NEW) 15m
        * LIP and CESGA participating.
        Speaker: Francisco Jose Bernabe Pellicer (CESGA)
      • 5.9.19.4 All sites to feedback about GridICE e-mails (NEW) 15m
        * When a site changes status an email is sent by GridICE.
        Speaker: Francisco Jose Bernabe Pellicer (CESGA)
    • 12:20 → 12:35
      Preproduction Activity Status 15m VRVS

      VRVS

      This section will contain an update about the preproduction activity in SWE where more and more sites will be involved.
      Speaker: Pacheco, Andreu (PIC)
      • PIC Report 15m
        * Carlos Borrego reporting. * Site upgraded to 1.3 * Request by CMS on friday to use the LCG production batch system from the preproduction CE. In progress.
        Speaker: Carlos Borrego (PIC)
      • CESGA 15m
        * Javier Lopez reporting. * Today the worker node will be upgraded to 1.3
        Speaker: Lopez, Javier (CESGA)
      • IFIC 15m
        * Alvaro Fernandez Casani reporting. * No major changes in the testbest. * Last week the VO server was upgraded to Scientific Linux. VOMS server installed also.
        Speaker: Fernandez, Alvaro (IFIC)
      • LIP 15m
        * Mario David reporting. * In gLite 1.3 since two weeks. Minor problems with one worker node.
        Speaker: David, Mario (LIP)