TY - GEN
T1 - Mini web server clusters for HTTP request splitting
AU - Rawal, Bharat S.
AU - Karne, Ramesh K.
AU - Wijesinha, Alexander L.
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
N2 - HTTP request splitting is a new concept where the TCP connection and data transfer phases are dynamically split between servers without using a central dispatcher or load balancer. Splitting is completely transparent to the client and provides security due to the inaccessibility and invisibility of the data servers. We study the performance of mini Web server clusters with request splitting. With partial delegation in which some requests are split, throughput is better, and response times are only marginally less than for an equivalent non-split system. For example with partial delegation, for a four-node cluster with a single connection server and three data servers serving 64 KB files, and for a three-node cluster with two connection servers and a single data server serving 4 KB files, the respective throughput improvements over non-split systems are 10% and 22%, with only a marginal increase in response time. In practice, the throughput improvement percentages will be higher and response time gaps will be lower since we ignore the overhead of a dispatcher or load balancer in non-split systems. Although these experiments used bare PC Web servers without an operating system/kernel for ease of implementation, splitting and clustering may also be implemented on conventional systems.
AB - HTTP request splitting is a new concept where the TCP connection and data transfer phases are dynamically split between servers without using a central dispatcher or load balancer. Splitting is completely transparent to the client and provides security due to the inaccessibility and invisibility of the data servers. We study the performance of mini Web server clusters with request splitting. With partial delegation in which some requests are split, throughput is better, and response times are only marginally less than for an equivalent non-split system. For example with partial delegation, for a four-node cluster with a single connection server and three data servers serving 64 KB files, and for a three-node cluster with two connection servers and a single data server serving 4 KB files, the respective throughput improvements over non-split systems are 10% and 22%, with only a marginal increase in response time. In practice, the throughput improvement percentages will be higher and response time gaps will be lower since we ignore the overhead of a dispatcher or load balancer in non-split systems. Although these experiments used bare PC Web servers without an operating system/kernel for ease of implementation, splitting and clustering may also be implemented on conventional systems.
UR - http://www.scopus.com/inward/record.url?scp=81555221717&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=81555221717&partnerID=8YFLogxK
U2 - 10.1109/HPCC.2011.22
DO - 10.1109/HPCC.2011.22
M3 - Conference contribution
AN - SCOPUS:81555221717
SN - 9780769545387
T3 - Proc.- 2011 IEEE International Conference on HPCC 2011 - 2011 IEEE International Workshop on FTDCS 2011 -Workshops of the 2011 Int. Conf. on UIC 2011- Workshops of the 2011 Int. Conf. ATC 2011
SP - 94
EP - 100
BT - Proc.- 2011 IEEE International Conference on HPCC 2011 - 2011 IEEE International Workshop on FTDCS 2011 - Workshops of the 2011 Int. Conf. on UIC 2011- Workshops of the 2011 Int. Conf. ATC 2011
T2 - 13th IEEE International Workshop on FTDCS 2011, the 8th International Conference on ATC 2011, the 8th International Conference on UIC 2011 and the 13th IEEE International Conference on HPCC 2011
Y2 - 2 September 2011 through 4 September 2011
ER -