Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Apologies:

CC:

...

Item

Presenter

Notes

Operational Issues
Gateways and WNs:
- Current status and upcoming changes

Thomas, Jyothish (STFC,RAL,SC)

RALPP/Oxford issue

upgrade hiccups

OXFORD - fixed (proxy certs at oxford)

RALPP - fixed (routing changes due to sl7)

More upgrade hiccups

network issues coinciding with redirector upgrade

CHEP Abstract ideas

Thomas, Jyothish (STFC,RAL,SC)

(awaiting acceptance notifications)

XrootD Workshop plan

Alastair Dewhurst

The workshop agenda and registration page can be found at:

https://indico.cern.ch/event/1386888/

We would kindly ask you to consider contributing to the workshop in the following areas:

  •  Status, statistics and projected usage of FTS and XRootD for Run3 and beyond.

  • Storage access for analysis use, including performance and CPU efficiency with emphasis on realistic running conditions (e.g., local disk, EOS, Tier2, remote data access, with or without XCache).

  • Data distribution management, needs and use-cases within scientific communities: data management needs of their community, frameworks used and how they integrate FTS and/or XRootD within their workflow.

  • Structured input and future requirements from the experiments and community members on the FTS medium-to-long term evolution.

  • R&D projects in the realm of data management, data access and data distribution within the Grid world are also invited. This could touch on integrating Cloud Storage within scientific data management workflows or Network projects aimed at optimizing data movements.

  • Discussion on connected topics such as Authentication frameworks (IAM, CILogon, etc) and the role of FTS and XRootd for emerging communities (e.g.: SKAO) in the world of scientific data management .

We encourage you to submit the title of your talk, along with how much time you would like to have to present it, using the form at https://indico.cern.ch/event/1386888/abstracts/
deadline 1 August

Should the title not be sufficiently explanatory, please include a sentence or two of context.


data pipeline for another project in SCD (FTS/xrootd/antares)


Oxford Xcache issues

discussed above

Rocky 8 and 9 migration planning

all gateways except the gridftp ones are upgraded,

1 of the managers is upgraded

discussed above

Shoveller

Katy Ellis

Shoveler installation and monitoring

Future developments ideas planning work

Ian Johnson Thomas, Jyothish (STFC,RAL,SC)

https://stfc.atlassian.net/wiki/spaces/X/pages/459997229/Notes+from+planning+meeting+22-04-2024?atlOrigin=eyJpIjoiNDRmNDEwOWI3Y2NhNDg5MDg4ZmZiYTNhNTliOWUwNmUiLCJwIjoiYyJ9

Deletion studies through RDR

Ian Johnson

Deletions

Jira Legacy
serverSystem Jira
serverId929eceee-34b0-3928-beeb-a1a37de31a8b
keyXRD-83

Planning for ALICE CMSD redirection

Thomas, Jyothish (STFC,RAL,SC)

tests to be done

Checksums fixes

Alexander Rogovskiy Thomas, Jyothish (STFC,RAL,SC)

WNs are currently redirecting checksums to external gws

Prefetch studies and WN changes

Alexander Rogovskiy

ipv6 DNS poisoning attempted, but is being rolled back

nullfs testing for xcache hit rate - full scale test on WN TBD

View file
namewn_xcache_efficiency_v2.pdf

Tokens Status

Thomas, Jyothish (STFC,RAL,SC) Katy Ellis

CMSD Load balancing

Thomas Byrne Thomas, Jyothish (STFC,RAL,SC)

PR:
https://github.com/stfc/xrootd/pull/8/files

SKA Gateway box

James Walder

/wiki/spaces/UK/pages/215941180

gws in a working state, aq config port pending

Xrootd testing framework

Mariam Demir

...

on GGUS:

Site reports

Lancaster: Not much to report, we’re unhappy with some of the behaviour we’re seeing in Ceph but haven’t quite put our finger on the issues yet.
slow backfill on new osd

We’re working on how best to separate LSST from Grid without just spinning up a new set of xroot servers for them.

Glasgow:

migration to alma8 on monday, later to pacific > pacific+admRestarting OSDs eventually fixed the backfilling slowness, data moving around at GB/s rather then MB/s. None the wiser for the root cause, or why these OSDs had problems. Some suspicion at QoS, but need to dig.

Glasgow:

Migration started, OS first.

in place upgrade worked well

✅ Action items

⤴ Decisions

...