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:20230124T171525Z
LOCATION:C140-142
DTSTART;TZID=America/Chicago:20221114T095200
DTEND;TZID=America/Chicago:20221114T100000
UID:submissions.supercomputing.org_SC22_sess438_misc236@linklings.com
SUMMARY:Lightning Talk: A Case of Multi-Resource Fairness for Serverless W
 orkflows
DESCRIPTION:Workshop\n\nLightning Talk: A Case of Multi-Resource Fairness 
 for Serverless Workflows\n\nSamanta, Stutsman\n\nServerless platforms have
  exploded in popularity in recent years, but, today, these platforms are s
 till unsuitable for large classes of applications. They perform well for b
 atch-oriented workloads that perform coarse transformations over data asyn
 chronously, but their lack of clear service level agreements (SLAs), high 
 per-invocation overheads, and interference make deploying online applicati
 ons with stringent response time demands impractical. Our assertion is tha
 t beyond the glaring issues like cold start costs, a more fundamental shif
 t is needed in how serverless function invocations are provisioned and sch
 eduled in order to support these more demanding applications. Specifically
 , we propose a platform that leverages the observability and predictabilit
 y of serverless functions to enforce multi-resource fairness. Finally, we 
 propose a new distributed and hierarchical function scheduling architectur
 e that combines lessons from multi-resource fair scheduling to create an a
 pproach that we believe will enable tighter SLAs on serverless platforms t
 han has been possible in the past.\n\nSession Format: Recorded\n\nRegistra
 tion Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR