WLCG-OSG-EGEE Operations meeting

Name: WLCG-OSG-EGEE Operations meeting
Start: 2007-02-05T16:00:00+01:00
End: 2007-02-05T18:00:00+01:00
Location: CERN conferencing service (joining details below)

Monday 5 Feb 2007, 16:00 → 18:00 Europe/Zurich

28-R-15 (CERN conferencing service (joining details below))

28-R-15

CERN conferencing service (joining details below)

Description

grid-operations-meeting@cern.ch
Weekly OSG, EGEE, WLCG infrastructure coordination meeting.
We discuss the weekly running of the production grid infrastructure based on weekly reports from the attendees. The reported issues are discussed, assigned to the relevant teams, followed up and escalated when needed. The meeting is also the forum for the sites to get a summary of the weekly WLCG activities and plans
Attendees:

OSG operations team

EGEE operations team

EGEE ROC managers

WLCG coordination representatives

WLCG Tier-1 representatives

other site representatives (optional)

GGUS representatives

VO representatives

To dial in to the conference:
a. Dial +41227676000
b. Enter access code 0157610

OR click HERE

- 16:00 → 16:05
  
  Feedback on last meeting's minutes 5m
  
  Minutes
- 16:05 → 16:30
  EGEE Items 25m
  - <big> Grid-Operator-on-Duty handover </big> 5m
    
    From ROC DECH (backup:ROC SWE) to ROC UKI (backup: ROC Italy)
    Tickets:
    New tickets :
    1st email:
    2nd email:
    Escalated to Ops meeting:
    Qurantine:
    Site OK:
    Unsolvable:
    
    Notes:
  - Note 1.

<big> PPS reports </big> 5m

PPS reports were not received from these ROCs: AsiaPacific Italy NorthernEurope Russia
From CERN ROC: LCG RB pps-rb.cern.ch now available as requested by the experiments new layout of CERN PPS site available in http://www.cern.ch/PPS
From UKI-ROC: We will soon ad a RAL-Tier-1 PPS site. The "Information to be provided for candidate sites for the PPS" asks sites the resources they will provide but we need an indication of the level of the resources required to be useful (WNs and strage) - this is because resources will generally be pulled form the same pool as the production nodes. In being asked about access to the production batch farms it would be useful to know the reasons and implications of the requirements.

Speakers: Antonio Retico, Nicholas Thackray (CERN)

<big> EGEE issues coming from ROC reports </big> 10m

Reports were not received from these ROCs: NorthernEurope
Russia
US-ATLAS
US-CMS
US-OSG

Due to a problem related to Condor, jobs submission has been blocked on 4 LCG RBs (while allowing old jobs to be retrieved). Per node, we wait until the old jobs have drained sufficiently before we apply a patch fixing this problem. Jobs submission should be allowed again before the end of this week.(ROC Cern)
Scheduled downtime for Cern SRM on 7th February(ROC Cern)
documentation is completely out of date: 3 rpm repositories out of 3 advertised in the web documentation are wrong : glite repository, ca repository and glite-WN_sl4compat(ROC France)

ANSWER from Release team:
Your feedback is highly appreciated: Please submit GGUS ticket with the exact name and version of the document and the list of issues you found.
once installed glite-WN_sl4compat & ed glite-WN wish to be removed ASAP (diagnosis of apt-get itself)(ROC France)
ANSWER from release team:
The new WN is still in PPS. We are aware of some particular setup must be done for the apt and it will be in the release notes. If you can provide, via a GGUS ticket, the outcome of your upgrade, that would be valuable feedback for us. Please specify in the GGUS ticket that you are working with software not officially released yet
From DESY-ZN: Hanging GridFTP doors in dCache are now avoided by restarting them once a day.(ROC DECH)
From BIFI: GGUS ticket #17931 was set to "unsolved" without providing any hint or solution. Ticket #1586 was submitted to dcache developers instead. (ROC SWE)

NOTE from OCC:
The ROC could have submitted the ticket to dcache ant put the link in the GGUS ticket before setting it to "unsolved". Please update the GGUS ticket putting the reference to the dcache one
From RAL_LCG2: We will beginning deploying second top-level BDII for RAL on Monday to alleviate BDII problems(ROC UKI)
From LCG-IL-OU: Seems that lcg-bdii.cern.ch is have problems again - probably time to change top level BDII used to bdii.egee-see.or (ROC SEE)

Answer form CERN-PROD:
Last Thursday the number of nodes working on load balancing behind the alias lcg-bdii was increased from 6 to 8. Did you see the problem after that date? However, using a local top-level BDII sounds like a good idea
From INFN-CNAF: Intermittent problems on gLite-CE(ROC Italy)
Fault reports on ROC summary page often not in chronological order, makes it harder to follow and comment on(ROC UKI)

<big>BDII: coming developments and present deployment scenario </big> 5m

<big>Ports table change</big? 5m

Last week there were some comments in bug number 21812 that pointed out that the ports table did not reflect the true situation for the BDII information system. The BDII has site-level BDIIs at each site(!) and then a top-level BDII. The data is pulled by the top-level BDII from the site-level BDIIs that, in turn, pull data from the GRIS. In order for this scheme to work: the GRIS has to accept data to port 2135 from the site-level services (CE, WN, UI etc); the site- level BDII pulls from the GRIS to port 2170 and similarly for the top-level BDII. In addition, a user or service can query the top-level BDII OR the site-level BDII (if they have already decided on that site). Therefore it is necessary for the site and top-level BDIIs to accept connections from anywhere to their port 2170. There should be a discussion about these "*" ports with respect to limiting the high-range port numbers.

Speaker: John White White (Helsinki Institute of Physics HIP)

<big>plug-in for lcg-info-dynamic-scheduler </big> 5m

Speaker: Jeff Templon (NIKHEF)

<big> SRM 2.2 working group? </big> 15m

Speaker: Dr Flavia Donno (CERN AND INFN)

16:30 → 16:50

OSG Items 20m

Item 1

16:50 → 17:35

WLCG Items 45m

<big><a href="https://twiki.cern.ch/twiki/bin/view/LCG/WeeklyServiceReports">WLCG Service Report</a></big> 15m
<big> WLCG Service Commissioning report and upcoming activities </big> 15m

See new and updated information at https://twiki.cern.ch/twiki/bin/view/LCG/SC4ExperimentPlans

Speaker: Harry Renshall

document
<big> WLCG related Issues coming from experiment VOs and Tier-1/Tier-2 reports </big> 15m
Reports were not received from:
> Tier-1 sites: BNL, INFN T1, NDGF, Sara/NIKHEF, Triumf
> VOs: Alice, LHCb, CMS, Atlas
1. ATLAS: post-mortem report on the DPM ACL script
2. Item 2.

17:35 → 17:55

Review of action items 20m

17:55 → 18:00

AOB 5m