CTA deployment meeting

Monday 16 Nov 2020, 14:00 → 16:00 Europe/Zurich

600/R-001 (CERN)

Michael Davis (CERN)

14:00 → 14:10 ALICE Post-migration

• ALICE Friday 13th post-mortem will be on Wednesday.

TO DO

• Space reporting for the garbage collector (see #905 and notes attached to last week's minutes).
• Julien: ensure that ALICE have tested implicit prepare and are happy with it.
• XrdAliceTokenAcc puppetization and ALICE probe (#105 and #666). After the upgrade, our probe is succeeding, but the ALICE probe is failing. Julien has disabled the reporting for now and will investigate with ALICE.
• Test of >1,000 clients. Steve has e-mailed ALICE to retry their recall with >1,000 clients.

14:10 → 14:20 Getting CMS into Production

• See Putting EOSCTACMS into Production: TO DO List
• See Notes from meeting with CMS 02/10/2020

TO DO

• Repack of public_user to separate CMS files is underway
• Test archiving side of EOS Backup (Elvin's daemon and user backup tools on EOS CMS) (#113).
• Implement xrdfs query prepare in XRoot Python API to allow prepare evict after recall of backup files.
• Reconciliation Rucio ←→ CTA
• OTG for CTA.

Eric Vaandering (11/11/2020) : "Would it be possible to get a more recent version of this meta-data dump or is it only available during migration? The reason for this is that without a dump of the Rucio database from before this file was produced (which we don’t have) we can’t tell the difference between missing files and newly produced files."

Schedule (confirmed with CMS)

• 18 Nov 2020: MWGR#4 (CASTOR only)
• 23 Nov 2020 Put CASTOR CMS into recall-only mode (OTG0060300)
• 30 Nov 2020: Migrate to CTA (OTG0060319)
• 07 Dec 2020: CMS in production
• End Dec 2020? : CMS retires PhEDEx

14:20 → 14:30 Getting LHCb into Production

• See Putting EOSCTALHCB into Production (CodiMD)

TO DO/Schedule

• DAQ test : waiting for network connectivity
• Oliver is following up the Dirac+FTS+TPC issue with Mihai and Chris
• Michael is coordinating a test of XRootD TPC between CTA and T1. Need to configure EOSCTALHCBPPS for XRootD TPC.
• It would be good to do this test before the WLCG workshop if possible (19-24 Nov).

14:30 → 14:40 Getting PUBLIC into Production

• Migration of SMEs from CASTOR to CTA, see Putting EOSCTAPUBLIC into Production

COMPASS

• Metadata check checksum bulk query: they will do it the slow way for now
• DAQ tests on CTA (#69) (ongoing)

NA62

• Recall tests (30 TB) on EOSCTA PPS (#72) (ongoing)

n_TOF

• Between now and Christmas: eliminate Cns_* calls from their DAQ software and replace with standard XRoot calls.

Garbage Collection on EOS PUBLIC

• n_TOF abd other small experiments need a solution for this.
• Proposal that we give them a space in EOS PUBLIC which can be used for tape recalls but is read-only for users, so no danger that any reconstructions etc. end up there. If the garbage collector accidentally deletes files they can be recalled from tape, so no danger of data loss.

15:00 → 15:05 AOB