Phoenix Monitoring Overview

Status plots from 2024-04-25 - 05:27 (page is refreshed every 5 minutes). Historical view here.

Note: The now values printed at the bottom of some graphs are not correct.

Current Memory utilization: Current CPU utilization:

Site Tests: Region DE (Nagios, history) / Region CH Nagios / SLTOP / APEL status / Site-View / MyWLCG site availability / WLCG Transfers dashboard

• CMS: Overview / Tiny Panel / CMS hammercloud / Job status / Job Robot / central CMS-Frontier status / Dashboard / WW transfers to CSCS
• ATLAS: Overview / Tiny Panel / Cloud Monitor / Panglia (Analysis , Production) / Dashboard / HammerCloud (Analysis , Production) / ARC (Cloud monitor, Panda)
• LHCb: Overview / Tiny Panel / Dirac Site status / Queues length

Batch jobs

sltop

slurmerrors

Worker nodes

<img src="http://ganglia.lcg.cscs.ch/ganglia3/graph.php?g=load_report&z=medium&c=PHOENIX-workers&m=&r=day&s=descending&hc=4&st=now" /> <img src="http://ganglia.lcg.cscs.ch/ganglia3/graph.php?g=cpu_report&z=medium&c=PHOENIX-workers&m=&r=day&s=descending&hc=4&st=now" /> <img src="http://ganglia.lcg.cscs.ch/ganglia3/graph.php?g=mem_report&z=medium&c=PHOENIX-workers&m=&r=day&s=descending&hc=4&st=now" />

Storage Element

Links:

• dCache GUI / Ganglia dCache Headnode/dCache pools
• CMS: used space (local monitoring) / dashboard summary view / List all hosted datasets/requests / subscriptions / accounting per phys. group (also see victor tool)
• ATLAS: DQ2 accounting on srm tokens

Networking and File Transfers

Links:

• CMS CMS PhEDEx downloads (detailed) / exports / Status prod / Debug / PhEDEx links
• ATLAS ATLAS FZK Cloud Data activity last 7 days
• FTS Channels all-CSCS / CSCS-FZK

<img src="http://ganglia.lcg.cscs.ch/ganglia3/graph.php?g=network_report&z=medium&c=PHOENIX-workers&m=&r=day&s=descending&hc=4&st=now" /> <img src="http://ganglia.lcg.cscs.ch/ganglia3/graph.php?g=network_report&z=medium&c=PHOENIX-fileservers&m=&r=day&s=descending&hc=4&st=now" /> <img src="http://ganglia.lcg.cscs.ch/ganglia/graph.php?g=iconnect_report&z=medium&c=PHOENIX-gpfs&m=&r=day&s=descending&hc=4&st=now" /> <img src="http://ganglia.lcg.cscs.ch/ganglia3/graph.php?g=network_report&z=medium&c=PHOENIX-services&m=&r=day&s=descending&hc=4&st=now" />

Number of active dCache movers (transfers) on the WAN (gridftp, srm) / LAN ("regular",dcap):

Number of queued dCache movers (waiting transfers) on the WAN (gridftp, srm) / LAN ("regular",dcap):

Number of pending dCache requests:

External monitoring

• CSCS external network (shared with other projects, only visible from SWITCH network):

• EGI Nagios from FZK, last 5 days (hover mouse to see hostname)

• Power consumption (Island 1)

• Gridview current status graphs

Other links

• EGI Discussion Forum

• A/R official metrics
• GSTAT
• CSCS Internal VLAN64
• EGI Accounting
• Operations Portal - Dashboard
• SMSCG Swiss sites
• SWITCH weather map
• IRC: irc:gridchat.cscs.ch:994#lcg
• GGUS tickets this year