- Compact style
- Indico style
- Indico style - inline minutes
- Indico style - numbered
- Indico style - numbered + minutes
- Indico Weeks View
Topic: WLCG DOMA TPC Meeting
Join Zoom Meeting
https://cern.zoom.us/j/99836057922?pwd=ZFhWN3NpYi9oZmwvM3pIRE9zdzFnZz09
Meeting ID: 998 3605 7922
Passcode: 733660
One tap mobile
+41315280988,,99836057922# Switzerland
+41432107042,,99836057922# Switzerland
Dial by your location
+41 31 528 09 88 Switzerland
+41 43 210 70 42 Switzerland
+41 43 210 71 08 Switzerland
+33 1 7037 2246 France
+33 1 7037 9729 France
+33 1 8699 5831 France
Meeting ID: 998 3605 7922
Find your local number: https://cern.zoom.us/u/aeB4ArMgmT
We went through the tests (link in the section minutes). There is development to do and not everyone has clear what are the priorities. There are also differences because different storage providers use different libraries underneath,We are going to wait for the WLCG workshop and the next authz meeting to understand what is the time scale to work on this and what we want to go with first.
However organised the work storage developers can now look at the testbed results on amnesiac and that should make it easier to evaluate changes.
ATLAS is putting online the T1s it has increased the number of sites in production to 26. The reason to do this is to better understand the bottlenecks that appear in Petr's stress tests. He reports an order of magnitude difference with INFN-T1 between webdav and gsiftp. INFN-T1 will be enabled next Monday in ATLAS production. EOSATLAS was in the pipeline to be enabled but we need to quantify the effects of the checksum race condition.
Andrea reported about the ESCAPE tests which highlighted a checksum problem when uploading using the rucio clients. There is already a rucio ticket.
CMS has made the big move to rucio last Wednesday. Not using it yet for WEBdav but it'll make things easier in the future.
EOSCMS is not yet open to the outside. elvin will look into it.
FTS/gfal changes
Mihai reports that the changes we talked about are less straightforward than we thought and it is not enough to move block of codes from FTS to gfal. Problem is that all the information needed to request a token is not available to gfal but to FTS so that will need to be redressed. Also we need to decide if we want tokens to work for all the use cases or only for TPC. Andrea says there shouldn't be a problem because the tokens can be parsed so the code always know what they are for. Alessandra asks if there is a ticket that can be used to track this if it takes longer than expected. There is a JIRA ticket Mihai will circulate it.
Will adjourn on these topic to after the WLCG workshop.