Last modified 3 years ago Last modified on 09/20/16 15:12:07

dCache Tier I meeting September 20, 2016

[part of a series of meetings]

Present, IN2P3(), Sara(), Triumf(), BNL(), NDGF(Ulf), PIC(Marc), KIT(Xavier), Fermi(), CERN()


(see box on the other side)

Site reports


Everything is running smoothly.

Last week upgraded to 2.13.42.


Wanted to enable the replica service.



Running fine for the last two weeks.

ATLAS deletion support

1st Dec. ticket 9043, with statements from billing -- when file was deleted from the pool.

The pool was deleted 37 hours after SRM delete request

Some times the same second.

Some timeouts reported in cleaner log file.

No pool was offline.

tag deletion =

Tigran look into SQL function for deleting tags from database.


We are running 3.0.0-SNAPSHOT. It's not working well. Gerd on vacation, gone for a while.

Trials with two head nodes -- works perfectly until you restart one of them. Works fine, except for pool-to-pool transfer.

Admin interface works, and can remotely restart them.

Communication system isn't working reliably.

The problem appears when there is a long latency between pool and head-node: not seen during test set-up.

Doing "emergency pool evaluation": couldn't evacuation quickly, seems to be slow.

NDGF is running OK.

Single head-node running.

Have not restarted all pools; only the problematic ones.

Support tickets for discussion

[Items are added here automagically]


Proposed: same time, next week.