[[TOC(depth=0)]] [part of a [wiki:developers-meetings series of meetings]] = Participants = Al, Dmitry, Gerd, Tigran, Karsten, Christian = Agenda = [see box on the right-hand side] = Postcards = 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 == Gerd: 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. == CMS NFS == Tigran: 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 Dmitry: - 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 = http://rt.dcache.org/Ticket/Display.html?id=8557 - SRM default port - should we change srmclient? -> won't ix http://rt.dcache.org/Ticket/Display.html?id=8561 - xrootd movers -> we could somehow work around this, but it is not critical. http://rt.dcache.org/Ticket/Display.html?id=8508 8509 8499 - ipv6 -> Gerd has a patch, what does it fix? http://rt.dcache.org/Ticket/Display.html?id=8556 - 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 = = DTNM = Proposed: same time, next week.