SDCC Liaison Meeting

Thursday 16 Aug 2018, 14:00 → 15:05 US/Eastern

3-192 (Bldg 510)

Tony Wong (Brookhaven National Lab (Physics Department))

BlueJeans Meeting ID: 819 381 923

RACF/SDCC Network Operations

RHIC Migration,ATLAS DCache Migration – Status reports

Preparations for ToR migration – Intervention on Aug 21,2018

ToR switch and cable pre-deployment

Ipv4 layout

Power Interventions in CDCE – Jul 23 – Aug 3

Receptacle work begins on Aug 21

Retirement of the legacy BNL Cloud installation

New HPSS FC Infrastructure Deployment

USATLAS Web infrastructure move to SciZone

Summer/cleanup project – free space in CDCE

 

RHIC Central Storage

Grounding of racks (transparent)

Some issues with the grounding of metal clad receptacles

Shared Pool – Closing some parts

Maintenance – Star Grid, Phenix, GPFS, BlueArc down, NFS down

800 systems being re-iped

AFS work/maintenance needs to be done – RHIC and US Atlas AFS volumes needs to be salvaged.

See slides posted on agenda

 

Storage Group update

Server tests on latest version, tested on SL6/SL7.

Stable operations.

 

HPSS status

HPSS Operations are fine. STAR – 2018 data restricted Ordered LT04 tapes New TSM operational, backup done, will be updating to new system

 

General Services:

NFS appliance upgrade going on

BlueArc system migration to GPFS – Phenix filesystems being moved currently

Other home directories to GPFS were done( resolving some issues with STAR)

NoMachine – Testing upgrade of NX version 6, web-requisition put in for the NX license renewals.

 

RACF Linux Farm

RCF and USATLAS T3 computing facilities - Maintenance Aug 21st

RCF processor farm will be moved to new network equipment and re-IPed.

800 systems to be re-iped and rebooted.

NFS directories will be moved to new equipment.

New ToR switches – can accommodate only certain number of systems – so PHENIX will be losing 4 nodes and and STAR will be losing 5 nodes, so data needs to be backed up

New Address space

Shared Pool – Need to discuss with condor developer to work on time frame for jobs to run.

 

CSI Resources

Stable output
Order for new GPU m/cs went out

AOB

Requirement for CVMFS  File System documentation

14:00 → 14:10 Facility News & Announcements

Speaker: Tony Wong (Brookhaven National Lab (Physics Department))

14:10 → 14:20 Network operations

Speaker: Mr Alexandr Zaytsev (Brookhaven National Laboratory (BNL))

azaytsev_NETOPS_status_16082018_v2.pdf

14:20 → 14:25 Storage Group Update

Speaker: Hironori Ito (Brookhaven National Laboratory)

14:25 → 14:30 HPSS status

Speaker: David Yu (Brookhaven National Lab)

14:30 → 14:35 General Services

Speakers: Jason Smith (RACF/SDCC), Tejas Rao (Brookhaven National Lab)

14:35 → 14:40 RACF Linux Farm

Speakers: Christopher Hollowell (RHIC/ATLAS Computing Facility), William Strecker-Kellogg (BNL)

14:40 → 14:45 CSI resources

Speaker: Mr Costin Caramarcu (BNL-RACF)

14:45 → 14:50 AOB

Speaker: John Hover (Brookhaven National Laboratory)