TU Darmstadt / ULB / TUbiblio

Achieving 10Gbps Line-rate Key-value Stores with FPGAs

Blott, Michaela ; Karras, Kimon ; Liu, Ling ; Vissers, Kees A. ; Bär, Jeremia ; István, Zsolt (2013)
Achieving 10Gbps Line-rate Key-value Stores with FPGAs.
5th USENIX Workshop on Hot Topics in Cloud Computing. San Jose, USA (25.-26.06.2013)
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

Distributed in-memory key-value stores such as memcached have become a critical middleware application within current web infrastructure. However, typical x86-based systems yield limited performance scalability and high power consumption as their architecture with its optimization for single thread performance is not wellmatched towards the memory-intensive and parallel nature of this application. In this paper we present the design of a novel memcached architecture implemented on Field Programmable Gate Arrays (FPGAs) which is the first in literature to achieve 10Gbps line rate processing for all packet sizes. By transformation of the functionality into a dataflow architecture, the implementation can not only provide significant speed-up but also operate at a lower power consumption than any x86. More specifically, with our prototype we have measured an increase of up to a factor of 36x in requests per second per Watt that can be serviced in comparison to the best published numbers for regular servers with optimized software. Additionally, we show that through the tight integration of network interface, memory and compute, round trip latency can be reduced down to below 4.5 microseconds.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2013
Autor(en): Blott, Michaela ; Karras, Kimon ; Liu, Ling ; Vissers, Kees A. ; Bär, Jeremia ; István, Zsolt
Art des Eintrags: Bibliographie
Titel: Achieving 10Gbps Line-rate Key-value Stores with FPGAs
Sprache: Englisch
Publikationsjahr: 25 Juni 2013
Veranstaltungstitel: 5th USENIX Workshop on Hot Topics in Cloud Computing
Veranstaltungsort: San Jose, USA
Veranstaltungsdatum: 25.-26.06.2013
URL / URN: https://www.usenix.org/conference/hotcloud13/workshop-progra...
Kurzbeschreibung (Abstract):

Distributed in-memory key-value stores such as memcached have become a critical middleware application within current web infrastructure. However, typical x86-based systems yield limited performance scalability and high power consumption as their architecture with its optimization for single thread performance is not wellmatched towards the memory-intensive and parallel nature of this application. In this paper we present the design of a novel memcached architecture implemented on Field Programmable Gate Arrays (FPGAs) which is the first in literature to achieve 10Gbps line rate processing for all packet sizes. By transformation of the functionality into a dataflow architecture, the implementation can not only provide significant speed-up but also operate at a lower power consumption than any x86. More specifically, with our prototype we have measured an increase of up to a factor of 36x in requests per second per Watt that can be serviced in comparison to the best published numbers for regular servers with optimized software. Additionally, we show that through the tight integration of network interface, memory and compute, round trip latency can be reduced down to below 4.5 microseconds.

Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Distributed and Networked Systems
Hinterlegungsdatum: 23 Jan 2023 12:43
Letzte Änderung: 02 Mai 2023 09:22
PPN: 507377729
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen