BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150119Z
LOCATION:C141/143/149
DTSTART;TZID=America/Chicago:20181114T140000
DTEND;TZID=America/Chicago:20181114T143000
UID:submissions.supercomputing.org_SC18_sess177_pap356@linklings.com
SUMMARY:Dynamically Negotiating Capacity Between On-Demand and Batch Clust
 ers
DESCRIPTION:Feng Liu (University of Minnesota), Kate Keahey (Argonne Natio
 nal Laboratory), Pierre Riteau (University of Chicago), and Jon Weissman (
 University of Minnesota)\n\nIn the era of rapid experimental expansion dat
 a analysis needs are rapidly outpacing the capabilities of small instituti
 onal clusters and looking to integrate HPC resources into their workflow. 
 We propose one way of reconciling on-demand needs of experimental analytic
 s with the batch managed HPC resources within a system that dynamically mo
 ves nodes between an on-demand cluster configured with cloud technology (O
 penStack) and a traditional HPC cluster managed by a batch scheduler (Torq
 ue). We evaluate this system experimentally both in the context of real-li
 fe traces representing two years of a specific institutional need, and via
  experiments in the context of synthetic traces that capture generalized c
 haracteristics of potential batch and on-demand workloads. Our results for
  the real-life scenario show that our approach could reduce the current in
 vestment in on-demand infrastructure by 82% while at the same time improvi
 ng the mean batch wait time almost by an order of magnitude (8x).\n\nTag: 
 Clouds and Distributed Computing, Resource Management, Scheduling\n\nRegis
 tration Category: Tech Program Reg Pass\n\nSession Chair: Shantenu Jha (Ru
 tgers University; PPPL, Princeton University)\n\n
END:VEVENT
END:VCALENDAR