BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000712Z
LOCATION:401-402
DTSTART;TZID=America/Denver:20231116T160000
DTEND;TZID=America/Denver:20231116T163000
UID:submissions.supercomputing.org_SC23_sess166_pap190@linklings.com
SUMMARY:Fine-Grained Policy-Driven I/O Sharing for Burst Buffers
DESCRIPTION:Ed Karrels (University of Illinois), Lei Huang (Texas Advanced
  Computing Center (TACC)), Yuhong Kan and Ishank Arora (University of Texa
 s), Yinzhi Wang (Texas Advanced Computing Center (TACC)), Daniel S. Katz a
 nd William Gropp (University of Illinois), and Zhao Zhang (Texas Advanced 
 Computing Center (TACC))\n\nA burst buffer is commonly deployed on large-s
 cale supercomputers to bridge the performance gap between the shared file 
 system and the I/O needs of modern supercomputing applications. Existing I
 /O sharing methods either require resource isolation, offline profiling, o
 r repeated execution that significantly limit the utilization and applicab
 ility of these systems. Here we present ThemisIO, a policy-driven I/O shar
 ing framework for a remote-shared burst buffer. ThemisIO can accurately an
 d efficiently allocate I/O cycles among applications purely based on real-
 time I/O behavior, without requiring user-supplied information or offline-
 profiled application characteristics. By exploiting a statistical token-ba
 sed strategy, ThemisIO can precisely balance I/O cycles between applicatio
 ns via time slicing to enforce processing isolation, enabling a variety of
  fair sharing policies. Our experiments show that ThemisIO sustains 13.5–1
 3.7% higher I/O throughput and 19.5–40.4% lower performance variation than
  existing algorithms. For applications, ThemisIO significantly reduces or 
 nearly eliminates the slowdown caused by I/O interference.\n\nTag: Data An
 alysis, Visualization, and Storage, I/O and File Systems, State of the Pra
 ctice\n\nRegistration Category: Tech Program Reg Pass\n\nReproducibility B
 adges: Artifact Available, Artifact Functional, Results Reproduced\n\nSess
 ion Chair: Sarah Neuwirth (Johannes Gutenberg University Mainz)\n\n
END:VEVENT
END:VCALENDAR