Version 3 (modified by paul, 6 years ago) (diff)


dCache Tier I meeting MONTH DATE, 2013

[part of a series of meetings]

Present, Paul), Triumf(Simon), KIT(Xavier), Fermi(Natalia)


(see box on the other side)

Site reports


Natalia reported that, having reported problems mounting their dCache v2.2 with NFS v4.1, they tried mounting the NFS door using v4.0. This worked better, so they will continue with this mount configuration.

At Fermilab, pool nodes normally have 3 disk systems attached to them. A disk system may be upgraded or some other intervention without restarting the node, but the system group suggest restarting the whole node "just to be sure".

Paul said that, if the OS is not affected by the intervention then the following procedure should be OK: stop the domain hosting the affecting pool; make the disk intervention; start the domain hosting the pool. Rebooting the pool node is not a requirement from dCache.

Natalia also asked about the dCache workshop: when and where will the next one be held? The paper-trail for travel must be started a minimum of two months before travelling and ideally three months. The approximate date is enough: the dates can be changed later on. It wasn't clear how approximate the location needs to be (is "in Germany" sufficient?).

Paul will ask within the team and try to discover how this will be handled.


Xavier joined the meeting to ask about the xrootd door problem. He said that, in the ticket, Phillippe described the problem as a show-stopper; however, as the ticket existed for ~3 weeks, it isn't clear what is the real priority.

Paul will investigate -- and ask Gerd if he has any idea.

The LHCb xrootd door is running dCache version 2.6.33.


Simon is back from vacation: everything looks good so far.

Support tickets for discussion

[Items are added here automagically]


Tuesday and Thursday next week: Tigran will chair the meetings.