TY - GEN
T1 - RESQ
T2 - 15th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2018
AU - Tootoonchian, Amin
AU - Panda, Aurojit
AU - Lan, Chang
AU - Walls, Melvin
AU - Argyraki, Katerina
AU - Ratnasamy, Sylvia
AU - Shenker, Scott
N1 - Funding Information:
Acknowledgement We would like to thank Andrew Herdrich, Edwin Verplanke, Priya Autee, Christian Maciocco, Charlie Tai, Rich Uhlig, Michael Alan Chang, Yashar Ganjali, David Lie, Hans-Arno Jacobsen, our shepherd Tim Wood, and the NSDI reviewers for their comments and suggestions. This work was funded in part by NSF-1553747, NSF-1704941, and Intel corporation.
Publisher Copyright:
© Proceedings of NSDI 2010: 7th USENIX Symposium on Networked Systems Design and Implementation. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Network Function Virtualization is allowing carriers to replace dedicated middleboxes with Network Functions (NFs) consolidated on shared servers, but the question of how (and even whether) one can achieve performance SLOs with software packet processing remains open. A key challenge is the high variability and unpredictability in throughput and latency introduced when NFs are consolidated. We show that, using processor cache isolation and with careful sizing of I/O buffers, we can directly enforce a high degree of performance isolation among consolidated NFs - for a wide range of NFs, our technique caps the maximum throughput degradation to 2.9% (compared to 44.3%), and the 95th percentile latency degradation to 2.5% (compared to 24.5%). Building on this, we present ResQ, a resource manager for NFV that enforces performance SLOs for multi-tenant NFV clusters in a resource efficient manner. ResQ achieves 60%-236% better resource efficiency for enforcing SLOs that contain contention-sensitive NFs compared to previous work.
AB - Network Function Virtualization is allowing carriers to replace dedicated middleboxes with Network Functions (NFs) consolidated on shared servers, but the question of how (and even whether) one can achieve performance SLOs with software packet processing remains open. A key challenge is the high variability and unpredictability in throughput and latency introduced when NFs are consolidated. We show that, using processor cache isolation and with careful sizing of I/O buffers, we can directly enforce a high degree of performance isolation among consolidated NFs - for a wide range of NFs, our technique caps the maximum throughput degradation to 2.9% (compared to 44.3%), and the 95th percentile latency degradation to 2.5% (compared to 24.5%). Building on this, we present ResQ, a resource manager for NFV that enforces performance SLOs for multi-tenant NFV clusters in a resource efficient manner. ResQ achieves 60%-236% better resource efficiency for enforcing SLOs that contain contention-sensitive NFs compared to previous work.
UR - http://www.scopus.com/inward/record.url?scp=85076794425&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076794425&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85076794425
T3 - Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2018
SP - 283
EP - 297
BT - Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2018
PB - USENIX Association
Y2 - 9 April 2018 through 11 April 2018
ER -