Usage Report hotel

• Period: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013

• 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: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013
• Cloud(IaaS): nimbus
• Hostname: hotel

VMs count by project

Project	Value
fg-54:Investigating cloud computing as a solution for analyzing particle physics data	1583
Others	517
fg-172:Cloud-TM	516
fg-364:Course: EEL6871 Autonomic Computing	339
fg-362:Course: Cloud Computing and Storage (UF)	223
fg-82:FG General Software Development	216
fg-136:JGC-DataCloud-2012 paper experiments	165
fg-97:FutureGrid and Grid‘5000 Collaboration	94
fg-217:Cloud Computing In Education	55
fg-175:GridProphet, A workflow execution time prediction system for the Grid	34
fg-130:Optimizing Scientific Workflows on Clouds	27
fg-52:Cost-Aware Cloud Computing	24
fg-10:TeraGrid XD TIS(Technology Insertion Service) Technology Evaluation Laboratory	21
fg-371:Characterizing Infrastructure Cloud Performance for Scientific Computing	17
fg-374:Course: Cloud and Distributed Computing	16
fg-213:Course: Cloud Computing class - second edition	13
fg-367:Optimize rapid deployment and updating of VM images at the remote compute cluster	10
fg-201:ExTENCI Testing, Validation, and Performance	3
fg-150:SC11: Using and Building Infrastructure Clouds for Science	3
fg-1:Peer-to-peer overlay networks and applications in virtual networks and virtual clusters	2
fg-60:Wide area distributed file system for MapReduce applications on FutureGrid platform	1
fg-355:Course: Data Center Scale Computing Class	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: July 01 – September 30, 2013
• Cloud(IaaS): nimbus
• Hostname: hotel

VMs count by project leader

Projectleader	Value
Randall Sobie	1583
Others	517
Paolo Romano	516
Meng Han	339
Andy Li	223
Gregor von Laszewski	216
Mats Rynge	165
Mauricio Tsugawa	94
Željko Šeremet	55
Thomas Fahringer	34
Weiwei Chen	27
David Lowenthal	24
John Lockman	21
Theron Voran	17
Philip Rhodes	16
Massimo Canonico	13
Jan Balewski	10
John Bresnahan	3
Preston Smith	3
Renato Figueiredo	2
Dirk Grunwald	1
Lizhe Wang	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: July 01 – September 30, 2013
• Cloud(IaaS): nimbus
• Hostname: hotel

VMs count by institution

Institution	Value
University of Victoria	1583
Others	517
INESC ID	516
University of Florida, ACIS	339
University of Florida, Department of Electrical and Computer Eng	223
Indiana University	217
USC	165
University of Florida	96
University of Mostar	55
University of Innsbruck	34
University of Southern California	27
University of Arizona	24
University of Texas at Austin	21
University of Colorado at Boulder, Computer Science Department	17
University of Mississippi, Department of Computer Science	16
University of Piemonte Orientale	13
Massachusetts Institute of Technology, Laboratory for Nuclear Sc	10
Purdue University	3
Nimbus	3
Univ. of Colorado, Boulder, Computer Science	1

Figure 9: Wall time (hours) by project leader

This chart illustrates proportionate total run times by project leader.

• Period: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013
• 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: July 01 – September 30, 2013
• Cloud(IaaS): nimbus
• Hostname: hotel