Usage Report hotel

• Period: April 01 – June 30, 2014
• Hostname: hotel.futuregrid.org
• Services: nimbus
• Metrics: VMs count, Users count, Wall time (hours), Distribution by wall time, project, project leader, and institution, and systems

Histogram

Summary (Monthly)

Figure 1: Average monthly usage data (wall time (hour), launched VMs, users)

This mixed chart represents average monthly usage as to wall time (hour), the number of VM instances and active users.

• Period: April 01 – June 30, 2014

• Cloud(IaaS): nimbus

• Hostname: hotel

• Metric:

  • Runtime (Wall time hours): Sum of time elapsed from launch to termination of VM instances
  • Count (VM count): The number of launched VM instances
  • User count (Active): The number of users who launched VMs

Summary (Daily)

Figure 2: Users count

This time series chart represents daily active user count for cloud services and shows historical changes during the period.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

Figure 3: VMs count

This time series chart represents the number of daily launched VM instances for cloud services and shows historical changes during the period.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

Figure 4: Wall time (hours)

This time series chart represents daily wall time (hours) for cloud services and shows historical changes during the period.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

Distribution

Figure 5: VM count by wall time

This chart illustrates usage patterns of VM instances in terms of running wall time.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

Figure 6: VMs count by project

This chart illustrates the proportion of launched VM instances by project groups. The same data in tabular form follows.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

VMs count by project

Project	Value
fg-54:Investigating cloud computing as a solution for analyzing particle physics data	3564
fg-97:FutureGrid and Grid‘5000 Collaboration	189
fg-314:User-friendly tools to play with cloud platforms	133
fg-418:Course: Cloud Computing Class - fourth edition	119
fg-82:FG General Software Development	74
fg-213:Course: Cloud Computing class - second edition	57
fg-367:Optimize rapid deployment and updating of VM images at the remote compute cluster	37
fg-217:Cloud Computing In Education	25
fg-224:Nimbus Auto Scale	22
fg-13:FutureGrid Systems Development and Prototyping	20
fg-404:Enhancing Usage of cloud Infrastructure	17
fg-257:Particle Physics Data analysis cluster for ATLAS LHC experiment	11
fg-9:Distributed Execution of Kepler Scientific Workflow on Future Grid	10
fg-42:SAGA	8
fg-362:Course: Cloud Computing and Storage (UF)	7
fg-150:SC11: Using and Building Infrastructure Clouds for Science	3
fg-341:Course: Parallel Computing	3
fg-394:Hydroinformatics on the Cloud	3
fg-344:Exploring map/reduce frameworks for users of traditional HPC	1
fg-443:Virtual Machine Live Migration for Disaster Recovery in WANs	1

Figure 7: VMs count by project leader

This chart also illustrates the proportion of launched VM instances by project Leader. The same data in tabular form follows.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

VMs count by project leader

Projectleader	Value
Randall Sobie	3564
Massimo Canonico	309
Mauricio Tsugawa	189
Gregor von Laszewski	74
Jan Balewski	37
Željko Šeremet	25
Pierre Riteau	22
Sharif Islam	20
Rahul Limbole	17
Doug Benjamin	11
Ilkay Altintas	10
Shantenu Jha	8
Andy Li	7
John Bresnahan	3
Wilson Rivera	3
Kate Keahey	3
Tae Seung Kang	1
Glenn K. Lockwood	1

Figure 8: VMs count by institution

This chart illustrates the proportion of launched VM instances by Institution. The same data in tabular form follows.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

VMs count by institution

Institution	Value
University of Victoria	3564
University of Piemonte Orientale, Computer Science Department	252
University of Florida	189
Indiana University	94
University of Piemonte Orientale	57
Massachusetts Institute of Technology, Laboratory for Nuclear Sc	37
University of Mostar	25
University of Chicago	22
Veermata Jijabai Technological Institute Mumbai, Computer Scienc	17
Duke University	11
UCSD	10
Louisiana State University	8
University of Florida, Department of Electrical and Computer Eng	7
University of Chicago, Computation Institute	3
University of Puerto Rico, Electrical and Computer Emgineering D	3
Nimbus	3
University of Florida, Advanced Computing and Information System	1
University of California San Diego, San Diego Supercomputer Cent	1

Figure 9: Wall time (hours) by project leader

This chart illustrates proportionate total run times by project leader.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

System information

System information shows utilization distribution as to VMs count and wall time. Each cluster represents a compute node.

Figure 10: VMs count by systems (compute nodes) in Cluster (hotel)

This column chart represents VMs count among systems.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel

Figure 11: Wall time (hours) by systems (compute nodes) in Cluster (hotel)

This column chart represents wall time among systems.

• Period: April 01 – June 30, 2014
• Cloud(IaaS): nimbus
• Hostname: hotel