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:20260522T150120Z
LOCATION:D173
DTSTART;TZID=America/Chicago:20181114T143000
DTEND;TZID=America/Chicago:20181114T150000
UID:submissions.supercomputing.org_SC18_sess276_exforum111@linklings.com
SUMMARY:Cassandra in Dockers Deployment Using an NVMe Fabric
DESCRIPTION:Kais Belgaied and David Paulsen (Viking Enterprise Solutions)\
 n\nThe Cassandra distributed database achieves high throughput and large c
 apacity at an unparalleled resiliency by scaling linearly to a large numbe
 r of nodes, while keeping multiple copies of the data. This comes at the p
 rice of increased latency and inefficient use of CPU and storage. Viking E
 nterprise Solutions has developed an approach whereby storage is decoupled
  from the nodes that run the database by deploying a Cassandra Cluster ove
 r dockers that is connected to NVMeoF and served by the Viking Enterprise 
 Solutions NSS-2248 NVME target appliance. We achieve significantly lower l
 atency by using NVMe and reducing the replication factors. The decoupling 
 of the volumes from the database nodes enables much more efficient use of 
 CPU resources by allowing multiple instances to share CPU and memory resou
 rces on the same servers, while improving the overall flexibility and resi
 liency of the system.\n\nTag: Data Management, Machine Learning, Container
 s\n\nSession Chair: Preston Smith (Purdue University)\n\n
END:VEVENT
END:VCALENDAR