Last modified 2 years ago Last modified on 07/24/18 14:57:17

dCache Tier I meeting MONTH DATE, 2013

[part of a series of meetings]

Present, IN2P3(), Sara(), Triumf(), BNL(), NDGF(Dmytro), PIC(Elena), KIT(Xavier), Fermi(), CERN()


(see box on the other side)

Site reports


Things are going fine.

This week is a stress test on the tape. Staging data from tape. Things are running smoothly. Some restores are failing due to some parameters will the default value.

For example, in pinmanager.cell.max-messages-queued. Default is 10,000. ATLAS is sending bulk requests of 50,000 files.

SRM could not connect --

request get max-transfers 20,000 .. increase this

Elena will open a ticket about the stress test.


Things are going fine.

At the downloads page -- the links to 3.2.26 are broken.

Already upgraded our head nodes to 3.2.26 today.

The billing directory read-only by dcache user and that parse the


Things are running fine.


Clean service is not yet replicable.

Split the dCache databases in the optimal way.

Use pg-dump pg-restore in custom format. Does work for some databases -- but not cleanly with Chimera.

Probably copy database and drop tables that are not needed.

Support tickets for discussion

[Items are added here automagically]


Same time, next week (but with Tigran)