Version 2 (modified by paul, 3 years ago) (diff)


dCache Tier I meeting October 4, 2016

[part of a series of meetings]

Present, Paul), PIC(Marc), KIT(Xavier)


(see box on the other side)

Site reports


Everything is really working well; no issues to report.

Upgrade from 2.13 to 2.16

Marc was concerned that he cannot estimate how long to do the upgrade of Chimera. Currently PIC has some 6.6x107 entries in inodes table.

Tigran reported that DESY upgraded last week their CMS instance. There, the database was 30 GiB in size took some 30 minutes to upgrade. This is with 1.3x107 inode entries.


Xavier reported that everything is running fine, no issues.


KIT upgraded their ATLAS instance to v2.13.44 last week. The upgrade exposed some problems.

There was a regression where the transfers.txt format inadvertently changed. This caused problems for KIT's monitoring script.

Xavier will send his script that parses the transfers.txt format.

SQL script

Tigran promised to look into Xavier's SQL script.

Deletion ATLAS

Paul apologised for not having time to investigate further in the slow deletion of replicas on ATLAS pools.

Writing through xrootd

Tigran reported that, apparently, ATLAS decided at a meeting at CERN last week to switch to using xrootd for namespace management operations.

Xavier has not received any such request yet.

We'll wait and see what happens.


Xavier asked if there was any outstanding work on the SRM that Gerd will now be unable to complete.

No, there is nothing immediate that was planned and not available in the latest dCache release.

Support tickets for discussion

[Items are added here automagically]


Because people will be at CHEP next week, the next meeting will be in two weeks time; 2016-10-18.