wiki:tier-one-meeting-20161213
Last modified 2 years ago Last modified on 12/13/16 15:06:22

dCache Tier I meeting December 13, 2016

[part of a series of meetings]

Present

dCache.org(Tigran, Paul), IN2P3(), Sara(), Triumf(), BNL(), NDGF(Ulf), PIC(Marc), KIT(Xavier), Fermi(), CERN()

Agenda

(see box on the other side)

Site reports

PIC

No problems; everything running fine.

Currently upgrading to 2.13.50 and PostgreSQL 9.5

Plan to upgrade to 2.16 on January.

KIT

No issues for the last week -- nothing to report.

No concrete plans for upgrading to 2.16; other tasks have higher priority.

NDGF

We have had two issues:

  1. ALICE have been trying to overload dCache -- 490 MiB file, 50 TiB in one day. 40GiB NIC, 40 GiB switch, to 2x 10GiB to CERN.
  1. Running 3.0.2 on head nodes; upgrade from 3.0. without any down-time. One head-node; changed 24 GiB --> 12 GiB, dCache runs fine but billing needs more memory when querying, so currently draining to allow an upgrade.

Started upgrading pool nodes to CentOS 7.3, so upgrading dCache to 3.0.x at the same time.

Support tickets for discussion

[Items are added here automagically]

DTNM

Proposed: same time, next week.