2024-04-11 Meeting Notes

Date

Mar 7, 2024

Participants

@Thomas, Jyothish (STFC,RAL,SC)
@Thomas Byrne
@Alastair Dewhurst
@Alexander Rogovskiy
Mariam Demir
Lancs: Gerard, Steven, Matt
Glasgow: Sam
@Ian Johnson

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

Item	Presenter	Notes
Operational Issues Gateways and WNs: - Current status and upcoming changes	@Thomas, Jyothish (STFC,RAL,SC)	wk 19th March, moving gateways to the new network. gw10,12,13,15 moved cms-aaa had a brief issue with incorrect CA chains for x509 gw11,14,16,8 moving
XrootD Workshop plan	@Alastair Dewhurst
Further observations from Data Challenge Future testing plans (RAL initiated / VO initiated) ?	All
Rocky 8 and 9 migration planning		gridftp to be decommissioned
Deletion studies through RDR	@Ian Johnson	Multi-thread deletions with known file sizes temporarily suspended for work with DC24 deletion times and LHCb dark file deletions. WIll resume, recording deletion times both from client side and server side for indication of “overhead” in server.
Deletions	https://stfc.atlassian.net/browse/XRD-83	load balancing algorithm seems to have improved this Deletion times during DC24 - combining gateway logs for analysis of file size vs deletion time. After DC24 finished- LHCb dark file deletions - recorded file size and deletion times for 158589 files, typical rate ~6Hz, via single-thread client. Not started - hijack “rados bench” cleanup routine to work from a list of files, rather than its auto-generated sequence
Planning for ALICE CMSD redirection	@Thomas, Jyothish (STFC,RAL,SC)	INC-163994 - DNS ip additions
Checksums fixes	@Alexander Rogovskiy @Thomas, Jyothish (STFC,RAL,SC)	Noscript checksum by Jo-stfc · Pull Request #9 · stfc/xrootd deployed, lhcb ticket closed
Prefetch studies and WN changes	@Alexander Rogovskiy
Tokens Status	@Thomas, Jyothish (STFC,RAL,SC) @Katy Ellis	Looking into tokens through redirection; (i.e. redacting the release of a token). TPC still can see tokens in certain cases.
CMSD Load balancing	@Thomas Byrne @Thomas, Jyothish (STFC,RAL,SC)	PR: revised load balancing algorithm - weighed random selection by Jo-stfc · Pull Request #8 · stfc/xrootd
SKA Gateway box	@James Walder	https://stfc.atlassian.net/wiki/spaces/UK/pages/215941180 4 Nodes awaiting installation: 2 for Exit pod (+ 1 existing) 1 for cloud 1 for Tier-1 usage
5.6.x root TPC issue		root:// TPC transfer fail with xrootd 5.6.x · Issue #2202 · xrootd/xrootd issue found to be dcache side, mitigation possible in xrootd config to use the old md algorithm

on GGUS:

Site reports

Lancaster: Smooth running over Easter. Gearing up for an update to the “top of Pacific”. Steven noticed a correlation between drive errors and drive manufacturer, unsure if this is just one type of drive doing a better job of reporting.

(hard to see, but almost all the orange blobs are TOSHIBA drives, this data is pulled from SMART) -

Tom B - reported metrics might mean different things

Glasgow: Sam build newer versions of xrootd on CC7 and 8. (anticipating 5.6.9), and awaiting any updates for LB.

Action items

@James Walder to schedule a ‘hackathon’ within a F2F to have a session on architectural planning.
@James Walder to prepare an outline of the expected roadmap for XRootD developments in 2024.