Overhead reduction in the network communication for web computing

Oh Juil, Ju Wook Jang, Tack Don Han

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

One major source of overhead for conventional network communication is the involvement of operating system to allow for virtual sharing of the network interface card among applications and its processing of the UDP/TCP/IP headers on behalf of applications. The involvement of operating system results in overheads such as extra write/read operations to the kernel buffer through which each inbound/outbound messages should pass. Another overhead comes from scheduling which may hinder immediate sending or receiving of messages to and from network interface buffer. Recently, U-Net over Fast Ethernet [9] addressed this problem and proposed a new scheme which circumvents the operating system in processing the network communication. However, since the approach has removed IP header and provides multiplexing in the ethernet layer, it is only applicable to an ethernet LAN. In this paper, we define a new protocol by which messages are allowed to move across routers and the virtual sharing of network interface card is supported with minimal overhead. In a word, we extended the U-Net over Fast Ethernet [9] beyond routers to WAN and hence opening a new way to exploit vast amount of computing resources all over Internet. With our protocol, cluster computing over any part of WAN is realizable as far as total delay caused by intervening routers is tolerable to the application. As a justification of our approach, we show a small part of WAN containing a router exhibits latency comparable to (differ by less than 1 ms) that of a shared ethernet. Another motivation for our approach is the observation that the aggregate bandwidth of two subnets (part of WAN) is greater than that of a single subnet (LAN). With same number of hosts, each connection will experience more available bandwidth with the part of WAN than the LAN. The experiment over WAN involving a router shows reduction of latency comparable to that of U-Net over Fast Ethernet.

Original languageEnglish
Pages (from-to)93-109
Number of pages17
JournalInternational Journal of High Speed Computing
Volume11
Issue number2
DOIs
Publication statusPublished - 2000 Jun 1

Fingerprint

Network Communication
Wide area networks
Ethernet
Telecommunication networks
Router
Routers
Computing
Operating Systems
Local area networks
Interfaces (computer)
Latency
Buffer
Sharing
Bandwidth
Cluster computing
Network protocols
Cluster Computing
TCP/IP
Multiplexing
Processing

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

@article{8c9f424ee4b64070a9e572277ef494e2,
title = "Overhead reduction in the network communication for web computing",
abstract = "One major source of overhead for conventional network communication is the involvement of operating system to allow for virtual sharing of the network interface card among applications and its processing of the UDP/TCP/IP headers on behalf of applications. The involvement of operating system results in overheads such as extra write/read operations to the kernel buffer through which each inbound/outbound messages should pass. Another overhead comes from scheduling which may hinder immediate sending or receiving of messages to and from network interface buffer. Recently, U-Net over Fast Ethernet [9] addressed this problem and proposed a new scheme which circumvents the operating system in processing the network communication. However, since the approach has removed IP header and provides multiplexing in the ethernet layer, it is only applicable to an ethernet LAN. In this paper, we define a new protocol by which messages are allowed to move across routers and the virtual sharing of network interface card is supported with minimal overhead. In a word, we extended the U-Net over Fast Ethernet [9] beyond routers to WAN and hence opening a new way to exploit vast amount of computing resources all over Internet. With our protocol, cluster computing over any part of WAN is realizable as far as total delay caused by intervening routers is tolerable to the application. As a justification of our approach, we show a small part of WAN containing a router exhibits latency comparable to (differ by less than 1 ms) that of a shared ethernet. Another motivation for our approach is the observation that the aggregate bandwidth of two subnets (part of WAN) is greater than that of a single subnet (LAN). With same number of hosts, each connection will experience more available bandwidth with the part of WAN than the LAN. The experiment over WAN involving a router shows reduction of latency comparable to that of U-Net over Fast Ethernet.",
author = "Oh Juil and Jang, {Ju Wook} and Han, {Tack Don}",
year = "2000",
month = "6",
day = "1",
doi = "10.1142/S0129053300000114",
language = "English",
volume = "11",
pages = "93--109",
journal = "International Journal of High Speed Computing",
issn = "0129-0533",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

Overhead reduction in the network communication for web computing. / Juil, Oh; Jang, Ju Wook; Han, Tack Don.

In: International Journal of High Speed Computing, Vol. 11, No. 2, 01.06.2000, p. 93-109.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Overhead reduction in the network communication for web computing

AU - Juil, Oh

AU - Jang, Ju Wook

AU - Han, Tack Don

PY - 2000/6/1

Y1 - 2000/6/1

N2 - One major source of overhead for conventional network communication is the involvement of operating system to allow for virtual sharing of the network interface card among applications and its processing of the UDP/TCP/IP headers on behalf of applications. The involvement of operating system results in overheads such as extra write/read operations to the kernel buffer through which each inbound/outbound messages should pass. Another overhead comes from scheduling which may hinder immediate sending or receiving of messages to and from network interface buffer. Recently, U-Net over Fast Ethernet [9] addressed this problem and proposed a new scheme which circumvents the operating system in processing the network communication. However, since the approach has removed IP header and provides multiplexing in the ethernet layer, it is only applicable to an ethernet LAN. In this paper, we define a new protocol by which messages are allowed to move across routers and the virtual sharing of network interface card is supported with minimal overhead. In a word, we extended the U-Net over Fast Ethernet [9] beyond routers to WAN and hence opening a new way to exploit vast amount of computing resources all over Internet. With our protocol, cluster computing over any part of WAN is realizable as far as total delay caused by intervening routers is tolerable to the application. As a justification of our approach, we show a small part of WAN containing a router exhibits latency comparable to (differ by less than 1 ms) that of a shared ethernet. Another motivation for our approach is the observation that the aggregate bandwidth of two subnets (part of WAN) is greater than that of a single subnet (LAN). With same number of hosts, each connection will experience more available bandwidth with the part of WAN than the LAN. The experiment over WAN involving a router shows reduction of latency comparable to that of U-Net over Fast Ethernet.

AB - One major source of overhead for conventional network communication is the involvement of operating system to allow for virtual sharing of the network interface card among applications and its processing of the UDP/TCP/IP headers on behalf of applications. The involvement of operating system results in overheads such as extra write/read operations to the kernel buffer through which each inbound/outbound messages should pass. Another overhead comes from scheduling which may hinder immediate sending or receiving of messages to and from network interface buffer. Recently, U-Net over Fast Ethernet [9] addressed this problem and proposed a new scheme which circumvents the operating system in processing the network communication. However, since the approach has removed IP header and provides multiplexing in the ethernet layer, it is only applicable to an ethernet LAN. In this paper, we define a new protocol by which messages are allowed to move across routers and the virtual sharing of network interface card is supported with minimal overhead. In a word, we extended the U-Net over Fast Ethernet [9] beyond routers to WAN and hence opening a new way to exploit vast amount of computing resources all over Internet. With our protocol, cluster computing over any part of WAN is realizable as far as total delay caused by intervening routers is tolerable to the application. As a justification of our approach, we show a small part of WAN containing a router exhibits latency comparable to (differ by less than 1 ms) that of a shared ethernet. Another motivation for our approach is the observation that the aggregate bandwidth of two subnets (part of WAN) is greater than that of a single subnet (LAN). With same number of hosts, each connection will experience more available bandwidth with the part of WAN than the LAN. The experiment over WAN involving a router shows reduction of latency comparable to that of U-Net over Fast Ethernet.

UR - http://www.scopus.com/inward/record.url?scp=0034196965&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034196965&partnerID=8YFLogxK

U2 - 10.1142/S0129053300000114

DO - 10.1142/S0129053300000114

M3 - Article

AN - SCOPUS:0034196965

VL - 11

SP - 93

EP - 109

JO - International Journal of High Speed Computing

JF - International Journal of High Speed Computing

SN - 0129-0533

IS - 2

ER -