Last modified 7 years ago Last modified on 10/28/14 14:50:27

dCache Tier I meeting MONTH DATE, 2013

[part of a series of meetings]

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


(see box on the other side)

Site reports


Everything is OK at PIC -- went smoothly

xrootd plugin

CMS and ATLAS plugins

This November.

Issue with NFS v4 -- bug

Current PIC is running v2.6.29, with some doors are v2.6.34. The problem is that -- little project (one pool). When they fill the space something becomes blocked. There's a fix in 2.10 for this problem.

Have NFS mounted on some worker nodes. This problem affected.


Where do you get the

WLCG repository

ATLAS: n2n on door, monitoring on pool.


ATLAS plugin from WLCG repository: Illya <..>

Get release out pcells

Testing latest enstore version to deploy.

Everything is fine, except xrootd plugin, pcells.

Eline will try to connect.


Things are running fine -- no issues for the past two weeks.

Do you know anything about 2.6 to 2.10 upgrade guide?

HEPix might be issues with NFS <>

Robot certificate.

Two weeks from now: CMS running du job on NFS v3. Significant impact on service responsiveness.

Constantly checking whether the user was allowed to access the file.

With 2.10 there's the option to cache this information, but doesn't help with du-like operations.

If no

Directory listing and entering still need to be checked, but might be able

User doing du several times, accessing the same

Exercising this every day.

Support tickets for discussion

[Items are added here automagically]


Same time, next week.