TY - JOUR
T1 - CloudPilot
T2 - Flow acceleration in the cloud
AU - Toledo, Kfir
AU - Breitgand, David
AU - Lorenz, Dean
AU - Keslassy, Isaac
N1 - Publisher Copyright:
© 2023
PY - 2023/4
Y1 - 2023/4
N2 - TCP-split proxies have been previously studied as an efficient mechanism to improve the rate of connections with large round trip times. These works focused on improving a single flow. In this paper, we investigate how strategically deploying TCP-split proxies in the cloud can improve the performance of geo-distributed applications entailing multiple flows interconnecting globally-distributed sources and destinations using different communication patterns, and being subject to budget limitations. We present CloudPilot, a Kubernetes-based system that measures communication parameters across different cloud regions, and uses these measurements to deploy cloud proxies in optimized locations on multiple cloud providers. To this end, we model cloud proxy acceleration and define a novel cloud-proxy placement problem. Since this problem is NP-Hard, we suggest a few efficient heuristics to solve it. Finally, we find that our cloud-proxy optimization can improve flow completion time by an average of 3.6× in four different use cases.
AB - TCP-split proxies have been previously studied as an efficient mechanism to improve the rate of connections with large round trip times. These works focused on improving a single flow. In this paper, we investigate how strategically deploying TCP-split proxies in the cloud can improve the performance of geo-distributed applications entailing multiple flows interconnecting globally-distributed sources and destinations using different communication patterns, and being subject to budget limitations. We present CloudPilot, a Kubernetes-based system that measures communication parameters across different cloud regions, and uses these measurements to deploy cloud proxies in optimized locations on multiple cloud providers. To this end, we model cloud proxy acceleration and define a novel cloud-proxy placement problem. Since this problem is NP-Hard, we suggest a few efficient heuristics to solve it. Finally, we find that our cloud-proxy optimization can improve flow completion time by an average of 3.6× in four different use cases.
KW - Cloud network
KW - Geo-distributed application
KW - TCP-split proxy
UR - http://www.scopus.com/inward/record.url?scp=85148011877&partnerID=8YFLogxK
U2 - 10.1016/j.comnet.2023.109610
DO - 10.1016/j.comnet.2023.109610
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85148011877
SN - 1389-1286
VL - 224
JO - Computer Networks
JF - Computer Networks
M1 - 109610
ER -