Latest news

Decommissioning of GR-10-UOI in NGI_GRNET
  	
Detailed Description:
  	According to EGI Procedure 11 (https://wiki.egi.eu/wiki/PROC11) we would like to start decommission process for GR-10-UOI.

This ticket will be the master ticket for the decommissioning process for this resource centre and for all services at the resource centre.


The VOs currently configured at this Resource Centre are listed below:

alice
atlas
biomed
cms
compchem
drihm.eu
dteam
esr
km3net.org
ops
see
vo.complex-systems.eu


Services affected
====

cream01.grid.uoi.gr (APEL)
cream01.grid.uoi.gr (Site-BDII)
cream01.grid.uoi.gr (CREAM-CE)
se01.grid.uoi.gr (SRM)
mon01.grid.uoi.gr (gLite-APEL)
mon02.grid.uoi.gr (gLite-APEL)
cream01.grid.uoi.gr (eu.egi.MPI)
cream02.grid.uoi.gr (CREAM-CE)
sbdii02.grid.uoi.gr (Site-BDII)
cream02.grid.uoi.gr (APEL)
cream02.grid.uoi.gr (eu.egi.MPI)
argus02.grid.uoi.gr (emi.ARGUS)
apel02.grid.uoi.gr (gLite-APEL)


Timeline
====
20th February 2015
- Broadcast of timeline to VO managers and users, and COD.
- The resource centre and all its services will begin scheduled downtime until 1th April, during which time VO managers and users can retrieve data.

2th April 2015
- *** HARD DEADLINE for VO Managers to retrieve all data from storage elements. ***

3th April 2015
- The resource centre status will be marked "suspended".
- Resource centre hardware and services may become inaccessible without further notice to VO managers, users, etc. from this date.

3th July 2015
- End of log retention period.
- Resource centre will be marked "closed".


Affected ROC/NGI: NGI_GRNET
Affected Site: GR-10-UOI
Dear VO Managers, VO Users and COD Shifters,

We wish to inform you that we are beginning the decommissioning process (https://wiki.egi.eu/wiki/PROC12) for the grid services at Resource Centre BIFI in NGI_IBERGRID.

We stop grid services support after many years of service, but once the GRID site is properly decommissioned the hardware will be reinstalled for cloud usage being added to EGI as FedCloud Resources at BIFI Resource Centre.
The VOs currently configured at this Resource Centre are listed below:

atlas
auger 
chem.vo.ibergrid.eu 
dteam 
earth.vo.ibergrid.eu 
eng.vo.ibergrid.eu 
fusion 
iber.vo.ibergrid.eu 
ict.vo.ibergrid.eu 
lhcb 
life.vo.ibergrid.eu 
ops 
ops.vo.ibergrid.eu 
phys.vo.ibergrid.eu
social.vo.ibergrid.eu
tut.vo.ibergrid.eu
vo.unizar.aragrid.es

The aim is to change the status of the resource centre to "suspended" in GOCDB by 9th April 2015. Below is a list of affected services and a decommissioning timeline.

** DEADLINE for retrieval of all VO data is 9th April 2015***

Please forward this mail to all your VO users.

Best Regards,

     RubEn


Services affected
====
 ui-egee.bifi.unizar.es (UI)

wms-egee.bifi.unizar.es (WMS)

bdii-egee.bifi.unizar.es (Top-BDII)

voms-prg.bifi.unizar.es (VOMS)

lfc-egee.bifi.unizar.es (Central-LFC)

proxy-egee.bifi.unizar.es (MyProxy)

cream01-egi.bifi.unizar.es (CREAM-CE)

wms-egee.bifi.unizar.es (LB)

dpm-egee.bifi.unizar.es (SRM)

mon-egi.bifi.unizar.es (gLite-APEL)

cream01-egi.bifi.unizar.es (APEL)

Timeline
====
16th February 2015
- Broadcast of timeline to VO managers and users, and COD.

27th April 2015
- The resource centre and all its services will begin scheduled downtime until 8th April, during which time VO managers and users can retrieve data.
8th April 2015
- *** HARD DEADLINE for VO Managers to retrieve all data from storage elements. ***

9th April 2015
- The resource centre status will be marked "suspended".
- Resource centre hardware and services may become inaccessible without further notice to VO managers, users, etc. from this date.
9th July 2015
- End of log retention period.
- Resource centre will be marked "closed".
Dear VO Managers, VO Users and COD Shifters,

We wish to inform you that we are beginning the decommissioning process (https://wiki.egi.eu/wiki/PROC11) for the Resource Centre ARAGRID-CIENCIAS in NGI_IBERGRID.


We stop grid services support after many years of service, but once the site is properly decommissioned the hardware will be reinstalled for cloud usage being joined again to EGI as FedCloud Resources at BIFI Resource Centre.
The VOs currently configured at this Resource Centre are listed below:

atlas
auger 
chem.vo.ibergrid.eu 
dteam 
earth.vo.ibergrid.eu 
eng.vo.ibergrid.eu 
fusion 
iber.vo.ibergrid.eu 
ict.vo.ibergrid.eu 
lhcb 
life.vo.ibergrid.eu 
ops 
ops.vo.ibergrid.eu 
phys.vo.ibergrid.eu
social.vo.ibergrid.eu
tut.vo.ibergrid.eu
vo.unizar.aragrid.es

The aim is to change the status of the resource centre to "suspended" in GOCDB by 9th April 2015. Below is a list of affected services and a decommissioning timeline.

** DEADLINE for retrieval of all VO data from ARAGRID-CIENCIAS is 9th April 2015***

Please, forward this mail to all your VO users.

Best Regards,

     RubEn


Services affected
====

sbdiic-iber.bifi.unizar.es (Site-BDII)

creamc-iber.bifi.unizar.es (CREAM-CE)

apelc-iber.bifi.unizar.es (gLite-APEL)

creamc-iber.bifi.unizar.es (APEL)


Timeline
====
16th February 2015
- Broadcast of timeline to VO managers and users, and COD.

27th April 2015
- The resource centre and all its services will begin scheduled downtime until 8th April, during which time VO managers and users can retrieve data.
8th April 2015
- *** HARD DEADLINE for VO Managers to retrieve all data from storage elements. ***

9th April 2015
- The resource centre status will be marked "suspended".
- Resource centre hardware and services may become inaccessible without further notice to VO managers, users, etc. from this date.
9th July 2015
- End of log retention period.
- Resource centre will be marked "closed".
Dear Partners,

BG03-NGCC RC will be turned off on 06.03.2015.
See GGUS ticket #111157

The following RC services registered in GOCDB are affected:

CE: ce02.ngcc.acad.bg
SE se02.ngcc.acad.bg
gLite-APEL: mon.ngcc.acad.bg
Site BDII: sbdii.ngcc.acad.bg

Please take your necessary data from the SE of the site (se02.ngcc.acad.bg).

List of affected VOs:

alice
bg-edu.grid.acad.bg
biomed
biotech.grid.acad.bg
cms
dteam
env.see-grid-sci.eu
esr
meteo.see-grid-sci.eu
mm-comp-chem.grid.acad.bg
national-heritage.grid.acad.bg
new-energy-sources.grid.acad.bg
ops
see
seismo.see-grid-sci.eu

Regards,

Vladimir Dimitrov
(Resource Centre Operations Manager, NGI_BG)
1. Operations Dashboard release.

The new version of operations dashboard will be released soon. The proposed schedule:
- end of development: February 27th 
- test during 2 weeks 
- official release: March 16th

The list of features for this release can be found at http://operations-portal.egi.eu/home/tasksList
If somebody is interested in participation in release testing, please contact ops-portal-atb@mailman.egi.eu 

Best regards,
EGI Operations Support Team
1. Switching of APEL UMD-2/EMI-2 services:

As reported in the EGI Ops meeting [1], the EMI2/UMD2 APEL service was switched off on Friday 16th January 

[1] https://wiki.egi.eu/wiki/Agenda-12-01-2015#2.3_EMI-2_decommissioning 

2. Switching of UMD-2/EMI-2 repositories

Since Aug. 2014 UMD-2/EMI-2 repositories contain obsoleted, unmaintained software - These repositories are officially declared deprecated as of 01.02. 2015.

Best regards,
EGI Operations Support Team

>>> More news <<<

Dear All,
following our first broadcast, this is to remind all WLCG sites to reinstall or upgrade their perfSONAR instances to version 3.4.1 unless they haven't done it already. The deadline for sites to upgrade is 16th of February.  We'd like to stress out, that after updating, it's very important to reconfigure your instances following the instructions at https://twiki.opensciencegrid.org/bin/view/Documentation/InstallUpdatePS

We'd like to also ask ALL sites to reboot their perfSONAR instances in order to ensure that the latest security updates are applied and to check if you have correctly whitelisted the OSG subnet, which is now hosting the core infrastructure for WLCG perfSONAR. 

Finally, we would like to announce availability of the perfSONAR infrastructure monitoring at:
http://pfomd.grid.iu.edu

To access it, you will need to have your personal certificate loaded in the browser. You can check status of your perfSONAR instances by typing hostname (or just domain) in the quick search bar. Detailed information on the metrics and troubleshooting is available at https://twiki.opensciencegrid.org/bin/view/Documentation/TroubleFAQPS

For any issues, please open GGUS ticket for WLCG perfSONAR Support or contact wlcg-perfsonar-support@cern.ch. 

Best regards,
perfSONAR Support Team
Due to maintenance at power stations in the Western Cape, the sites in the Cape Town region are particularly vulnerable to power outages for the foreseable future. Site administrators have been alerted and have been requested to open downtimes as soon as services are affected. Both sites - ZA-CHPC and ZA-UCT-ICTS have adequate UPS, but this depends on the compute load of the jobs at the sites. We cannot guarantee 100 % up time, but will do our best to maintain > 90% reliability.

more information : https://www.capetown.gov.za/en/electricity/Pages/LoadShedding.aspx 

Thanks,
Bruce
Dear VO Manager,

We are revising the overall EGI strategy to lead our activities over the next 5-10 years. The strategy would support the EGI community in realising the 'Open Science Commons' vision that has been recently described in this policy paper: http://www.egi.eu/news-and-media/publications/OpenScienceCommons_v2.pdf.

We would like to hear also your VO community's opinion on how the EGI strategy should look like. We have setup a short, online survey to capture input from you. We would appreciate if you could spend 15 minutes in the next few days to provide input for us through this survey at https://www.surveymonkey.com/r/egi-user-survey-1.

Many thanks.

Gergely Sipos
Technical Outreach Manager, EGI.eu 
e-mail: gergely.sipos@egi.eu 
Dear Partners,

 BG03-NGCC RC will be decommissioned within 2 months after now.
GGUS Ticket #111157 is created.

 The decommissioning timeline is below:

 14.01.2015 - The broadcast message is sent to the affected VO managers and users and the NGI BG manager.
01.02.2015 - The site will enter downtime in which VO users may get their stored data
02.03.2015 - The site status will be changed to SUSPENDED in GOCDB
05.03.2015 - Resource Centre Operations Manager will contact with EGI Operations and EGI CSIRT 
06.03.2015- The RC will be turned off. Log files will be kept for 90 days after that.
04.06.2015-  End of Log retention period. EGI operations team will be notified.
05.06.2015, 18h – Garden party with buffet, Champagne, caviar etc. The best RC admin will be awarded. 

The following RC services registered in GOCDB are affected:

CE: ce02.ngcc.acad.bg
SE se02.ngcc.acad.bg
gLite-APEL: mon.ngcc.acad.bg
Site BDII: sbdii.ngcc.acad.bg

 Please take your necessary data from the SE of the site (se02.ngcc.acad.bg) according to this timeline.

 List of affected VOs:

alice
bg-edu.grid.acad.bg
biomed
biotech.grid.acad.bg
cms
dteam
env.see-grid-sci.eu
esr
meteo.see-grid-sci.eu
mm-comp-chem.grid.acad.bg
national-heritage.grid.acad.bg
new-energy-sources.grid.acad.bg
ops
ops.vo.egee-see.org
see
seegrid
seismo.see-grid-sci.eu

 Regards,

 Vladimir Dimitrov
 (Resource Centre Operations Manager, NGI_BG)
Action: Enable multicore accounting.

Dear NGI managers, Site administrators.

As many EGI user communities are now exploiting multicore hardware it is important for them that accounting correctly reflects the usage made of cores and cpus. At the December Operations Management Board (OMB) it was decided to ask all sites using the APEL client to configure it to publish the number of cores used by jobs.

To enable multicore accounting, you will need to edit the configuration file for the apel parser. This is the software which parses blah logs and batch logs to produce accounting records. The configuration file is usually found at /etc/apel/parser.cfg. In the section labelled [batch], change:

parallel = false
to
parallel = true

This will enable multicore reporting for all future accounting data. Please note that this does not change historical data. Also note that republishing old data is not sufficient to show multicore information - the log files will need to be reparsed. If you wish to republish old data with multicore enabled, please open a GGUS ticket with the APEL team so that we can help you with the process.

If you use the SGE parser, please be aware that it only reports on the number of processors used in a job. It does not report the number of nodes. If you know how to get around this limitation, then please get in touch with the APEL team at apel-admins@stfc.ac.uk.

The multicore accounting data can currently be seen here
http://accounting-devel.egi.eu/show.php?
Drill down to your site and select the grouping  "Show data for: Submitting Host" as a function of: "Number of Processors" Values of 0 mean the parallel option was false when the data were published. The Submitting Host is a new feature in the accounting portal which lets a site see in more detail which CEs are publishing.

Stuart Pullinger
APEL Team Leader

Best regards,
EGI Operations Support Team
The problems affecting access to services at the RAL Tier1 have been resolved. Services were unavailable from 10:30 until 11:40 local time (=UTC) this morning (24th December).
We are investigating a networking problem that is affecting access to services at the RAL Tier1 (including GOC DB).
The APEL repository problem has been fixed. The summaries used by the accounting portal have now been brought up to date. 

The next time the portal updates you should see data received up to today. 

The APEL Team apologise for any inconvenience caused by this break in service.
Over the weekend there has been an error in the APEL repository during the preparation of data to send to the Accounting Portal. This is under investigation. 

Sites are assured that there were no problems receiving data from sites. This is all stored safely in the repository and will appear in the portal soon after the problem is resolved.