LCG deployment ============== - Total number of Sites (1): 259 - Status -> Num. Sites (1): ok -> 210 degraded -> 11 down -> 38 - Software -> Num. Sites (2): gLite-3_1_0 -> 220 gLite-3_0_2 -> 23 gLite-3_0_0 -> 1 - Average of concurrently running jobs during this week (3): 29.6k (1) Sites that are Certified, in Production and that have been monitored by SAM during the last week under OPS credentials. SAM is available at: https://lcg-sam.cern.ch:8443/sam/sam.py To see this page one needs a grid certificate loaded in the browser. The calculation of the Site availability (Status) is described at: https://cern.ch/twiki/pub/LCG/GridView/Gridview_Service_Availability_Computation.pdf (2) Software version is coming from the 'CE-sft-softver' CE test. Sites not supporting SAM 'CE' service, or not having sent results for this particular test during the last week, are not counted. (3) Job statistics taken from GStat: http://goc.grid.sinica.edu.tw/gstat/ http://goc.grid.sinica.edu.tw/gstat/total/GIISQuery_Usage_job_.html EGEE Pre-Production Service Coordination: ============================ 2008-08-27: the EMT made the decision to delay the deployment of the CREAM CE (the certified patch). This is because not-ICE-enabeld WMS could accidentally match the Cream CE and cause a submission failure. Waiting for the ICE-WMS to be deployed, as a workaround,Cream will be released with a GlueServiceStatus? = 'Production', to be changed again later. One issue is represented by the old version of WMS on SL3 (unsupported). As they will not be integrated with ICE, once the Cream CE will be advertised again in realproduction mode, they would fail to submit. In order to size this issue up we would like to get from the WLCG EGEE Operation Meeting an estimation of the number of old SL3 WMS still in production. 2008-08-25: release of gLite3.1 Update30 to production in preparation. The update, to be released next Thursday, will affect the vast majority of services. It will contain, notably: * Cream CE and clients * A patch to globus VDT , fixing the issue raised with BUG:37563 (limit in proxy delegation chain) * dCache 1.8.0-15p5 * GFAL/lcg_util bugfix release 2008-08-20: gLite 3.1 Update 29 was released to production The updated version of DPM and LFC , corresponding to PATCH:1987 and PATCH:1988 fixes the following bugs: * return space to pool when removing a replica in a space that no longer exists * disfavour filling filesystems to more than 98 percent of capacity during selection * added ctrl-c handling and an option to limit total drain size in dpm-drain * minor bounds checking changes in dpm, ns and Csec * return a network time out error to client rather than internal error in some circumstances * apply castor ns fix for BUG:31342, for consistency between lcg-dm and castor * several small fixes (see patch for more details) CERN GRID Pre-Production Site (CERN_PPS): ============================= nothing to report CERN ROC: ======= * new test for the alarm ticket to FNAL * business as usual with tickets SAM Service Unavailabilities =================== From: 21-08-2008 (Thurs) 10:00 To: 21-08-2008 (Thurs) 12:30 Description: web service problem on one of the load-balanced servers after reboot Impact: Moderate Details: Some test results might be missing. COD dashboard couldn't get list of alarms. Sites affected: All Solution: re-running NCM component. reason not understood. Testing Report ========== Patches certified; patch #1873: New updates on LCG CE improvement packages patch #1947: proxy renewal update Operational Security ============= The security incident affecting HEP sites (see report from 07 Aug) is still being investigated by the EGEE OSCT and the relevant academic CSIRTs. ETICS ===== Migration of the ETICS worker nodes to new 8-core hardware is almost finished. The frequent failures of the blade nodes seem to be due to the EDAC module. Investigation of the kernel modules being (possibly) at the source of the issue done together with Kernel/Linux support from FIO. A new revision version of the ETICS Client (1.3.10-1) has been released to fix some issues in the generation of the package list build reports. Statistics: Projects registered: 31 Packages available in the repository: 57059 Build/test reports total: 2854 Build/tests executed this week: 593