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:20181221T160904Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T083000
DTEND;TZID=America/Chicago:20181113T170000
UID:submissions.supercomputing.org_SC18_sess325_spost139@linklings.com
SUMMARY:Identifying Network Data Transfer Bottlenecks in HPC Systems
DESCRIPTION:ACM Student Research Competition, Poster\nTech Program Reg Pas
 s, Exhibits Reg Pass\n\nIdentifying Network Data Transfer Bottlenecks in H
 PC Systems\n\nTu\n\nImproving network data transfer performance is a major
  factor for improving high performance computing systems. Most studies ana
 lyze data transfer and file system IO performance separately, but understa
 nding the relationship between the two is essential for optimizing schedul
 ing and resource management. Intuitively, if data is being transferred to 
 a busy file system the transfer rate would be slower than a file system at
  regular activity levels.\n\nThis study analyzes patterns between file sys
 tem activity and network throughput for several use cases of file writing 
 and data transfers using a parallel file system. The parameters changed am
 ong the use cases were file striping for the file system, and buffer size 
 and parallelism for data transfer. The main bottleneck for network data tr
 ansfer rate was the number of OSTs the data was striped across. For a larg
 e number of OSTs (16 or greater), writing to the file system was the bottl
 eneck.
URL:https://sc18.supercomputing.org/presentation/?id=spost139&sess=sess325
END:VEVENT
END:VCALENDAR