dCache Tier I meeting February 2, 2010

[part of a series of meetings]

Present

dCache.org(Patrick, Owen, Paul), IN2P3(), Sara(), Triumf(Simon), BNL(), NDGF(Gerd), PIC(Gerard), GridKa(Doris, Silke), Fermi(), CERN(Andrea)

Agenda

(see box on the other side)

Site reports

FZK

We are more-or-less at end of Chimera migration. Still doing some final checks, reboots, etc. Looking good

No other issues. Other ..

One more dCache instance.

How many files 6.5 million files

Triumf

CA problem again, at midnight. Restarted SRM and everything was OK.

Other than that, no

Chimera migration: aim for upgrade, migration next week. Everything is down Reda: make decision today or tomorrow. Two days downtime. Probably use about 20 nodes to do the storage info check. Other parts look OK.

Randomise node update CRL 4 times per day; but we can reduce this to only during the day-time.

NDGF did two things.

NDGF

Have been at DESY for half a week. Last week

Minor upgrade to dCache tomorrow: 1.9.6-3 ++

CERN

Nothing to report.

PIC

Things are generally good. Just passing the ATLAS bandwidth tests. Shifted to gridFTP v2 about two weeks ago. Going through

200 MB/s transfer

Now Solaris pool: 750 MB/s. Limit looks it's from CERN.

Tuned the TCP Window Size on the Solaris pool.

6.2 GiB/s to the pools 1.2 GiB/s

1.2 GiB/s is what PIC is doing right now. Outbound 300 MB/s

One open issue:

CMS jobs was unable to read a file on tape. They say they were accessing the file with a certificate that should be

<GGUS ticket URI here>

​https://gus.fzk.de/ws/ticket_info.php?ticket=55121

WLCG activity

dcap and SRM client are upgrading on all WLCG roll-outs.

Support tickets for discussion

[Items are added here automagically]

DTNM

Proposed: same time, next week.