Last modified 8 years ago Last modified on 12/10/14 16:00:44

[part of a series of meetings]


Al, Dmitry, Gerd, Tigran, Karsten, Christian


[see box on the right-hand side]


Up to two minutes (uninterrupted) per person where they can answer two questions:

  • What I did last week (since the last meeting),
  • What I plan to do in the next week.

No questions until we get through everyone :)

Karsten: Smallfiles for DPHep and Docukenmtnation

Christian: Tickets!, pcells -> testing, Patches

Al: Decoupled Alarms from other sercvice

Dmitry: Metawork

Gerd: Helping KIT upgrade

Tigran: Debugging NFS problems with CMS instance

Special topics

KIT upgrade


Successfully upgraded, Spacemanager problems, because of stuff (e.g., indices) in tables Duplicated records, null values - no idea why. Currently restoring 2.6 dump Made a patch to solve those issues for other sites

Issue with duplicated records remaining.



50% of worker nodes use NFS4.1 now From last thursday, maybe caused by network problems, problems started to occur, pool were online but not serving data, patch committed, other patches running but not yet in repo. More problems with network caused new problems -> NFS4.1 offline -> will setup another NFS door for other use cases so users and worker nodes don't interfere. -> split reads and writes and metadata operations

-> open question: why are we falling back to proxy IO


  • we have a case of one direcotry where ls takes some seconds and ls -l takes about 2h.
  • Also GridFTP transfers looks to kill performance and push up IO wait

Trunk activity

Progress with new features...

  • xrootd4j update requires update of plugins.
  • ipv6 patch 7571

Issues from [FIXME: Add link to yesterday's Tier-1 meeting]

PIC: will upgrade to 2.10 on monday KIT: no issues with dCache, will upgrade to 2.11 soon.

Plans for patch-releases

Should we make a new patch release?


Outstanding Documentation

Outstanding RT Tickets - SRM default port - should we change srmclient? -> won't ix - xrootd movers -> we could somehow work around this, but it is not critical. 8509 8499 - ipv6 -> Gerd has a patch, what does it fix? - advice on configuring hot pool replication -> trial and error

Better to spread data in the first place using migration/balance 0.7 might be a good number (Tigran)

8400 -> is documented

Review of RB requests

There are some WebAdmin? patches 7484, 7508 + 7503, please review again Al, Gerd: billing patch

New, noteworthy and other business


Proposed: same time, next week.