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:403-404
DTSTART;TZID=America/Denver:20231115T110000
DTEND;TZID=America/Denver:20231115T113000
UID:submissions.supercomputing.org_SC23_sess161_pap349@linklings.com
SUMMARY:Design Considerations and Analysis of Multi-Level Erasure Coding i
 n Large-Scale Data Centers
DESCRIPTION:Meng Wang, Jiajun Mao, and Rajdeep Rana (University of Chicago
 ); John Bent (Los Alamos National Laboratory (LANL)); Serkay Olmez (Seagat
 e Research); Anjus George (Oak Ridge National Laboratory (ORNL)); Garrett 
 Wilson Ransom (Los Alamos National Laboratory (LANL)); Jun Li (CUNY Queens
  College & Graduate Center); and Haryadi S. Gunawi (University of Chicago)
 \n\nMulti-level erasure coding (MLEC) has seen large deployments in the fi
 eld, but there is no in-depth study of design considerations for MLEC at s
 cale. In this paper, we provide comprehensive design considerations and an
 alysis of MLEC at scale. We introduce the design space of MLEC in multiple
  dimensions, including various code parameter selections, chunk placement 
 schemes, and various repair methods. We quantify their performance and dur
 ability, and show which MLEC schemes and repair methods can provide the be
 st tolerance against independent/correlated failures and reduce repair net
 work traffic by orders of magnitude. To achieve this, we use various evalu
 ation strategies including simulation, splitting, dynamic programming, and
  mathematical modeling. We also compare the performance and durability of 
 MLEC with other EC schemes such as SLEC and LRC and show that MLEC can pro
 vide high durability with higher encoding throughput and less repair netwo
 rk traffic over both SLEC and LRC.\n\nTag: Accelerators, Architecture and 
 Networks, Data Analysis, Visualization, and Storage, Fault Handling and To
 lerance\n\nRegistration Category: Tech Program Reg Pass\n\nAward Finalist:
  Best Student Paper Finalist\n\nReproducibility Badges: Artifact Available
 , Artifact Functional, Results Reproduced\n\nSession Chair: Ignacio Laguna
  (Lawrence Livermore National Laboratory (LLNL))\n\n
END:VEVENT
END:VCALENDAR