BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160054Z
LOCATION:Track 5
DTSTART;TZID=America/New_York:20201118T100000
DTEND;TZID=America/New_York:20201118T103000
UID:submissions.supercomputing.org_SC20_sess168_pap536@linklings.com
SUMMARY:RDMP-KV: Designing Remote Direct Memory Persistence Based Key-Valu
 e Stores with PMEM
DESCRIPTION:Paper\n\nRDMP-KV: Designing Remote Direct Memory Persistence B
 ased Key-Value Stores with PMEM\n\nLi, Shankar, Gugnani, Lu\n\nByte-addres
 sable persistent memory (PMEM) can be directly manipulated by Remote Direc
 t Memory Access (RDMA) capable networks. However, existing studies to comb
 ine RDMA and PMEM can not deliver the desired performance due to their PME
 M-oblivious communication protocols. In this paper, we propose novel PMEM-
 aware RDMA-based communication protocols for persistent key-value stores, 
 referred to as Remote Direct Memory Persistence based Key-Value stores (RD
 MP-KV). RDMP-KV employs a hybrid 'server-reply/server-bypass' approach to 
 'durably' store individual key-value objects on PMEM-equipped servers. RDM
 P-KV's runtime can easily adapt to existing (server-assisted durability) a
 nd emerging (appliance durability) RDMA-capable interconnects, while ensur
 ing server scalability through a lightweight consistency scheme. Performan
 ce evaluations show that RDMP-KV can improve the server-side performance w
 ith different persistent key-value storage architectures by up to 22x, as 
 compared with PMEM-oblivious RDMA-'Server-Reply' protocols. Our evaluation
 s also show that RDMP-KV outperforms a distributed PMEM-based filesystem b
 y up to 65% and a recent RDMA-to-PMEM framework by up to 71%.\n\nTag: Comp
 ilers Analysis and Optimization, Debugging, Storage\n\nRegistration Catego
 ry: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR