Rutgers Hexfarm

Batch System

Status

• Node Status Summary
• Condor status
• Condor queue, all jobs, local submission
• Condor queue, running jobs, local submission
• Condor queue, all jobs, OSG submission
• Condor queue, running jobs, OSG submission

Instructions

• Setup to use Condor, OSG commands, CMSSW, Apptainer, and Rucio
• How to submit a job using the Condor Batch System
• HTCondor best practices and xrdlocal
• GPU resources and how to use them

CMS related

• Twiki for Rutgers HEX newcomers
• CMS disk usage
• Data Aggregation System (DAS)
• Cross section database (XSDB)
• Xrootd/AAA
• Obtaining/renewing a grid certficate

CRAB

• CRAB monitoring overview: select your username
• CRAB monitoring of individual jobs: select your username and task name
• CRAB jobs running vs. time: double click on a username at the bottom
• Hexfarm Rucio / CRAB transfer monitoring
• Additional CRAB transfer monitoring

Rucio

• Rucio subscription summary
• Rucio documentation
• Rucio WebUI
• Instructions for huge datasets (e.g. tape transfers)
• Dataset statistics

System Monitoring

• RAID disks
• PDU outlet use & status
• CPU Utilization: recent, long-term
• GPU Utilization: recent
• Network Utilization
• Current draw
• Room 333 temperature
• Hexserver5 RAID backplane temperature
• hexfm0 backplane temperature

Site status tests

• CMS Site Status
• checkmk
• WLCG SiteMon Latest Tests
• WLCG SiteMon Historical Tests
• CMS Facilities & Services
• CMS Computing Resource Information Catalog