TY - JOUR
T1 - Flow-Aware Service Function Embedding Algorithm in Programmable Data Plane
AU - Lee, Jaewook
AU - Ko, Haneul
AU - Lee, Hochan
AU - Pack, Sangheon
N1 - Funding Information:
This work was supported in part by the National Research Foundation (NRF) of Korea through the Korean Government under Grant 2020R1A2C3006786, and in part by the Ministry of Science and ICT (MSIT), Korea, through the Information Technology Research Center (ITRC) support program supervised by the Institute for Information and Communications Technology Planning and Evaluation (IITP) under Grant IITP-2020-2017-0-01633.
Publisher Copyright:
© 2013 IEEE.
PY - 2021
Y1 - 2021
N2 - Service function chaining (SFC) is an indispensable technique for Internet service providers to efficiently manage their networks. However, SFC poses requirements of additional processing time of service functions (SFs) and increased routing time owing to detoured paths. In this paper, we introduce the use of a programmable data plane (PDP) to reduce the additional processing and routing times in SFC. We first classify the existing PDP-empowered SFC schemes and analyze their pros and cons. An optimization problem, to find the optimal SF embedding strategy minimizing the SFC completion time while efficiently utilizing the PDP switch resources, is formulated and a flow-aware SF embedding (FASE) algorithm that complementarily combines the redundant SF and re-circulation approaches is devised. FASE is implemented over a commercial PDP switch and experimental results demonstrate that FASE can reduce the SFC completion time by up to 33% compared with conventional approaches while utilizing the switch resources efficiently.
AB - Service function chaining (SFC) is an indispensable technique for Internet service providers to efficiently manage their networks. However, SFC poses requirements of additional processing time of service functions (SFs) and increased routing time owing to detoured paths. In this paper, we introduce the use of a programmable data plane (PDP) to reduce the additional processing and routing times in SFC. We first classify the existing PDP-empowered SFC schemes and analyze their pros and cons. An optimization problem, to find the optimal SF embedding strategy minimizing the SFC completion time while efficiently utilizing the PDP switch resources, is formulated and a flow-aware SF embedding (FASE) algorithm that complementarily combines the redundant SF and re-circulation approaches is devised. FASE is implemented over a commercial PDP switch and experimental results demonstrate that FASE can reduce the SFC completion time by up to 33% compared with conventional approaches while utilizing the switch resources efficiently.
KW - Service function chaining
KW - in-network computing
KW - programmable data plane
UR - http://www.scopus.com/inward/record.url?scp=85099090323&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.3048421
DO - 10.1109/ACCESS.2020.3048421
M3 - Article
AN - SCOPUS:85099090323
SN - 2169-3536
VL - 9
SP - 6113
EP - 6121
JO - IEEE Access
JF - IEEE Access
M1 - 9311727
ER -