2024-08-01 Meeting Notes
Date
Aug 1, 2024
Participants
@James Walder
@Thomas, Jyothish (STFC,RAL,SC)
@Alexander Rogovskiy
@Ian Johnson
@Mariam Demir
@Robert Appleyard
Lancs: Gerard, Steven
Glasgow: Sam
Apologies:
CC:
Goals
List of Epics
New tickets
Consider new functionality / items
Detailed discussion of important topics
Site report activity
Discussion topics
Current status of Echo Gateways / WNs testing
Recent sandbox’s for review / deployments:
Item | Presenter | Notes |
|
---|---|---|---|
Operational Issues | @Thomas, Jyothish (STFC,RAL,SC)
‘Memory allocation errors on WN proxy containers’ | svc18 causing issues for cms SAM tests (davs refuse to connect) memory allocation caused by 2 issues: non-pgrw vector read sizes were too large for direct reads, and the gateway containers were running out of memory. WN container restart order can be improved |
|
Compilation issues with XrdCeph and rocky 8 with 5.6+ |
| Problems compiling XrdCeph alongside core xrootd (warning message → termination of compilation) With standalone XrdCeph crashes @James Walder and @Thomas, Jyothish (STFC,RAL,SC) to review the code and debugging. | . |
CMSD Load balancing | @Thomas Byrne @Thomas, Jyothish (STFC,RAL,SC) | PR: |
|
Gateway Auth failures | @Thomas, Jyothish (STFC,RAL,SC) | Auto-restarting on this failure mode is enable. Still observing occasional cases. |
|
XrootD Workshop plan | @Alastair Dewhurst |
|
|
Shoveler | @Katy Ellis |
Shoveler installation and monitoring CC. for WN to report to Shoveler, not yet implemented. |
|
Future developments ideas planning work | @Ian Johnson @Thomas, Jyothish (STFC,RAL,SC) |
| |
Deletion studies through RDR | @Ian Johnson
|
|
|
Deletions | Preliminary figures, deleting 3000 small files from 10 gateways simultaneously, using 10 workers and 100 workers: Seems encouraging, but small files so far. Need to check results for 100 workers as some target files had already been deleted. Moving on to record timings for deleting larger files in the GB range. |
| |
Planning for ALICE CMSD redirection | @Thomas, Jyothish (STFC,RAL,SC) | restarted activities on this; looking at how server ‘logs in to the CMSD manager’ |
|
Checksums fixes | @Alexander Rogovskiy @Thomas, Jyothish (STFC,RAL,SC) |
|
|
Prefetch studies and WN changes | @Alexander Rogovskiy | Prefetch activities complete. |
|
Tokens Status | @Thomas, Jyothish (STFC,RAL,SC) @Katy Ellis |
|
|
SKA Gateway box | @James Walder | https://stfc.atlassian.net/wiki/spaces/UK/pages/215941180 AQ configuration for Bonded VLANs seems OK. Netbox config for {02,03} seem ok. Issues with PXE booting and OS installation due to routing between AQ and hosts. JC and JA to look into this |
|
Xrootd testing framework | @Mariam Demir |
|
on GGUS:
Site reports
Lancaster: Working on/with Reef; (@Thomas, Jyothish (STFC,RAL,SC) links to ceph-dev: revive centos 8 builds for quincy and reef using vault.centos.org repos by cbodley · Pull Request #2272 · ceph/ceph-build )
Glasgow: Man with Reef on el9
Action items