\uD83D\uDDD3 Date
07
\uD83D\uDC65 Participants
...
Lancs: Gerard, Matt, Steven
Glasgow: Sam
Apologies:
James
CC:
\uD83E\uDD45 Goals
List of Epics
New tickets
Consider new functionality / items
Detailed discussion of important topics
Site report activity
...
Item | Presenter | Notes | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Operational Issues (Gateway Auth failures) | accidentally broke preprod workernodes - docker had cached old layers for the new image | ||||||||||
cms-aaa naming convention | cms-aaa is the only remaining personality to use proxy/ceph as the xrootd service names Separate naming convention would be more appropriate, to have main/supporting (not so urgent). CC created, but due to be reviewed December | ||||||||||
XRootD Managers De-VMWareification |
Option 2 preferred for efficiency, but Option 1 decided on Option 1 would be simpler to implement for a temporary fix, as the move would be reversed antares tpc nodes to be moved to an echo leafsw, to confirm ipv4 real estate with James | ||||||||||
Compilation and rollout status with XrdCeph and rocky 8: 5.7.x | Upstream merging in process. Branch now exists. Documention (particularly for the Buffered IO is needed). | ||||||||||
Shoveler | |||||||||||
Deletion studies through RDR | |||||||||||
Deletions |
| ||||||||||
periodic hackaton? | XRootD Writable Workernode Gateway Hackaton (XWWGH) Tues 12th Nov 1600 | ||||||||||
Xrootd testing framework | |||||||||||
100 GbE Gateway testing: | /wiki/spaces/UK/pages/215941180 Following up on server installs | ||||||||||
UKSRC Storage Architecture | For v0.1 Requirements: POSIX-like access be provided ‘next to’ the compute. POSIX area ‘should be’ an RSE, to enable the transfers, and lifecylce management. Dissadvantages: Other ideas: Manilla style shares / volumes for each DID / container requested ? | ||||||||||
Tokens Status |
|
...
on GGUS:
Site reports
Lancaster: Still having a rough time with CEPH the MDS servers, having our third switchover in as many weeks. Gerard found some possible bugs, and the workaround is… what we’ve been doing…Gerard updated to the latest reef (18.2.4), it wasn’t a completely smooth process but we got there in the end. Also as discussed in storage on Wednesday, turning off mclock made ceph behave a lot better.
Manchester also noticed similar problems with mclock (3 objects/hour with mclock). changing settings didn’t seem to have an effect,
lots of scrubbing but not updating the scrub date (scrubbing a bit broken on reef)
Reporting bugs flagged upstream
Glasgow: targetting pacific for upgrade, waiting for Reef stability
...
RAL upgrade might go to Quincy
mid-upgrade (pacific mons + nautiluse osd) - osd maps are created very quickly, but can bloat mon stores
✅ Action items
How to replace the original functionality of fstream monitoring, now opensearch has replaced existing solutions.
...