https://wiki.egi.eu/w/api.php?action=feedcontributions&user=Miguelgi&feedformat=atomEGIWiki - User contributions [en]2024-03-29T07:53:10ZUser contributionsMediaWiki 1.37.1https://wiki.egi.eu/w/index.php?title=NGI-VO_WN_tests&diff=39426NGI-VO WN tests2012-08-07T07:38:48Z<p>Miguelgi: </p>
<hr />
<div>The Worker Node ('''WN''') released in '''gLite 3.2''' will be supported for security updates until September 2012. <br />
<br />
*During the coming months the gLite WNs will need to be updated to the EMI-WN released in UMD1, or UMD2 (expected for the UMD2.1 update) <br />
*The main changes in the upgrade are the path to the client libraries. The EMI-WN aligned the libraries path to the linux standard locations, if the job's code has the library path hard coded needs to be corrected. <br />
*Changes in the execution environment of user's payload may affect the code executed by the job, and in general for VOs is useful to have their code tested vs more recent releases of the WN<br />
<br />
<br> NGIs are strongly suggested to provide to the supported VOs the possibility to run their code on EMI-WNs. If no sites have EMI-WN in production a possible solution could be: <br />
<br />
*Choose one or more site and ask the Site Managers to install a couple of EMI-WN, set up a new queue in the CE to submit jobs to those WN <br />
*Enable the queue for the VOs supported by the NGI <br />
**The queue does not need to support the ops VO <br />
*Coordinate with the VO Managers, in order to have some jobs running on those WNs <br />
*Summarize the results in the table<br />
<br />
{| cellspacing="0" cellpadding="3" border="1" style="border-collapse: collapse; border:1px solid black; text-align:center;" class="wikitable"<br />
|-<br />
! NGI <br />
! VOs who tested successfully the EMI-WN <br />
! VOs who tested the EMI-WN with issues <br />
! Comments<br />
|-<br />
| Example <br />
| <br />
*Vo1 <br />
*vo2 <br />
*vo3<br />
<br />
| <br />
*vo4: Issue1 <br />
*vo5: Issue2<br />
<br />
| <br />
|-<br />
| AsiaPacific <br />
| <br />
| <br />
| <br />
|-<br />
| CERN <br />
| <br />
| <br />
| <br />
|-<br />
| EGI.eu <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_AEGIS <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_AL <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_ARMGRID <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_BA <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_BG <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_BY <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_CH <br />
| ATLAS, CMS, LHCb, HONE, OPS<br />
| <br />
| EMI UMD 1 WN (emi-wn-1.0.0-0.sl5) installed as regular WN with no jobs failing. No extra queues for this host.<br />
|-<br />
| NGI_CYGRID <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_CZ <br />
| ATLAS, ALICE, Auger, Belle, MPI, VOCE <br />
| N/A <br />
| <br />
|-<br />
| NGI_DE <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_FI <br />
| <br />
NA <br />
<br />
| <br />
NA <br />
<br />
| <br />
None <br />
<br />
|-<br />
| NGI_FRANCE <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_GE <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_GRNET <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_HR <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_HU <br />
| Alice, CMS: ok on SLC5 EMI-1 <br />
| Alice, CMS: problems on SLC6 EMI-2 <br />
| <br />
|-<br />
| NGI_IBERGRID <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_IE <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_IL <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_IT <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_MARGI <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_MD <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_ME <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_NDGF <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_NL <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_PL <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_RO <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_SI <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_SK <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_TR <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_UA <br />
| <br />
| <br />
| <br />
|-<br />
| NGI_UK <br />
| ATLAS: Able to use EMI-1 and EMI-2 on SL5 <br />
| ATLAS: Unable to use EMI-1 WN <br />
| <br />
Conflicting reports; down to the storage access libs <br />
<br />
|-<br />
| NGI_ZA <br />
| <br />
| <br />
| <br />
|-<br />
| ROC_Canada <br />
| <br />
| <br />
| <br />
|-<br />
| ROC_IGALC <br />
| <br />
| <br />
| <br />
|-<br />
| ROC_LA <br />
| <br />
| <br />
| <br />
|-<br />
| Russia <br />
| <br />
| <br />
| <br />
|}</div>Miguelgihttps://wiki.egi.eu/w/index.php?title=NGI_DE_CH_Operations_Center:Operations_Meeting:02092011&diff=24034NGI DE CH Operations Center:Operations Meeting:020920112011-09-02T12:55:32Z<p>Miguelgi: /* Round the sites */</p>
<hr />
<div>[[NGI_DE_CH_Operations_Center:Operations_Meeting|Operations Meeting Main]]<br />
<br />
== How to connect ==<br />
Connect Via Phone:<br />
<br />
Following DFN ISDN Gateways are available: Germany - Berlin:+49-30-2541080 Germany - Stuttgart:+49-711-6330190<br />
<br />
If requested please enter following conference number: 97922688 <br />
<br />
==Introduction==<br />
<br />
* Minutes of last meeting<br />
<br />
==Announcements==<br />
<br />
* Meetings/conferences<br />
<br />
5-9 September 2011<br />
GridKa School <br />
Karlsruhe, Germany<br />
http://gridka-school.scc.kit.edu/2011) <br />
<br />
8-9 September 2011<br />
Paradiso workshop<br />
Brussels, Belgium <br />
http://www.paradiso-fp7.eu )<br />
<br />
19 -23 September 2011<br />
EGI Technical Forum<br />
Lyon, France (http://tf2011.egi.eu/)<br />
<br />
* Availability/reliability statistics<br />
There was the question from John Alan Kennedy from MPPMU why MPPMU's scheduled downtime [08-07-2011 16:00 to 15-07-2011 16:00 <br />
UTC] was not taken into account. Explanation from Dimitris Zilaskos: Downtime was only marked as 'at warning'.<br />
<br />
For the problem of UNI-Siegen-HEP we will wait untill the statistics of August and we will see if the situation has improved.<br />
* Monitoring<br />
* Staged rollout/updates<br />
<br />
==Round the sites==<br />
<br />
; NGI-DE<br />
* BMRZ-FRANKFURT (Uni Frankfurt)<br />
* DESY-HH<br />
new wn's (exchange the old hardware), now we have 37kHS and ~4800 jobs slots at DESY-HH.<br />
100% occupancy (mostly cms, atlas, but also ilc, and hera).<br />
* DESY-ZN<br />
* FZJuelich<br />
* Goegrid<br />
* GSI<br />
* ITWM<br />
* KIT (GridKa, FZK-LCG2)<br />
Business as usual.<br />
GridKA school next week. <br />
* KIT (Uni Karlsruhe)<br />
* LRZ<br />
* MPI-K<br />
* MPPMU<br />
* RWTH Aachen<br />
* SCAI<br />
* Uni Bonn<br />
* Uni Dortmund<br />
* Uni Dresden<br />
* Uni Freiburg<br />
* Uni Mainz-Maigrid<br />
* Uni Siegen<br />
* Uni Wuppertal<br />
; SwiNG<br />
* CSCS<br />
Business as usual despite some issues with Lustre filesystem (scratch) that we hope to fix in the upcoming weeks by replacing it by GPFS with SSDs for metadata.<br />
* PSI<br />
* Switch<br />
<br />
Note: please update your entry at https://wiki.egi.eu/wiki/NGI_DE:Sites if needed.<br />
<br />
==Status ROD==<br />
<br />
* Any problematic tickets?<br />
* Handover of the ROD shift<br />
(from DESY-HH, week before) - nothing serious to report, but to mention that <br />
In NGI_DE there is discrepancy in the number of published job slots (GoeGrid - two times then <br />
in reality) and in the apel statistics (MPPMU - wrong SI2K). Proposal - can we have the table in NGI_DE<br />
wiki with the actual number of job slots, total HS for all sites in NGI_DE, so that we can compare <br />
this with the information from bddi,gstat,gridview and contact sites in case of disagreement?<br />
<br />
This week:<br />
35 29.08 04.09 Team2, FhG (SCAI)<br />
<br />
Next weeks:<br />
<br />
36 05.09 11.09 Team3, KIT <br />
<br />
37 12.09 18.09 Team4, JUELICH<br />
<br />
38 19.09 25.09 Team5, BADW-LRZ<br />
<br />
* ROD shift schedule https://wiki.egi.eu/wiki/NGI_DE_CH_Operations_Center:Operations_Teams#Shifts_rotation_table<br />
<br />
* ROD Workshop @ EGI TechForum.<br />
ROD team’s session on Thursday September 22nd in afternoon at 4. Have a<br />
look at the agenda at: https://www.egi.eu/indico/contributionDisplay.py?contribId=35&confId=452.<br />
<br />
==AOB==<br />
<br />
If you have additional topics to be discussed during the meeting, please submit them in advance via our email list email list.</div>Miguelgi