Perfecting a Video Game with Game Metrics
Vol 17, No 1: February 2019

Performance comparison of transmitting jumbo frame on Windows and Linux System

Supriyanto Praptodiyono (Universitas Sultan Ageng Tirtayasa)
Rian Sofhan (Universitas Sultan Ageng Tirtayasa)
Anggoro S. Pramudyo (Universitas Sultan Ageng Tirtayasa)
Teguh Firmansyah (Universitas Sultan Ageng Tirtayasa)
Azlan Osman (Universiti Sains Malaysia)



Article Info

Publish Date
01 Feb 2019

Abstract

IPv6 is the successor of IPv4, the current Internet Protocol that runs out its address. It offers some improvements including simpler header format and extension header resulting in faster transmission of IP packets. However, IPv6 is a network layer protocol that requires lower layer services. IP packets from the network layer pass to data link layer to be encapsulated by layer 2 headers and trailer to become frames. Ethernet is the most widely used data link layer protocol in the current network devices. The technology is always improved to support high speed transmission. However, from standard Ethernet until ten gigabit Ethernet, the size of MTU remains unchanged at 1500 Bytes. This prevents the network from gaining an optimum performance on transmitting IP packets and operating systems cannot take full advantage of the high-speed performance of Gigabit Ethernet. This research aims to implement the transmission of IPv6 packets using jumbo frame on a test-bed environment. The implementation can be used to justify the impact of jumbo frame on the network as well as operating systems performance. The results prove that the OS used on implementation of jumbo frame affects on the network performance. The highest percentage of increasing throughput is 33.6% when both sender and receiver are running Windows. The decreasing delay by 54.36% was happened when using Linux in sender and Windows in receiver.

Copyrights © 2019






Journal Info

Abbrev

TELKOMNIKA

Publisher

Subject

Computer Science & IT

Description

Submitted papers are evaluated by anonymous referees by single blind peer review for contribution, originality, relevance, and presentation. The Editor shall inform you of the results of the review as soon as possible, hopefully in 10 weeks. Please notice that because of the great number of ...