Abstract

The massive growth of the current internet network has triggered an increase in the number of users connected to various server services. These conditions must be handled with a good server system. This can be accomplished through the implementation of many servers, because with many servers the incoming load will be unraveled. One method that can be used in distributing the received load to a number of servers is load balancing. This study aims to obtain the best throughput value from the load balancing method using round-robin and least-connection algorithms. The results of the connection test with a request value of 500 connections/second for 1000 requests, 600 connections/second for 1200 requests, load balancing with the least-connection algorithm looks a little better. This condition is caused by the distribution of active connections that can still be handled by each server. However, during the test period of 700 connections/sec for 1400 requests, 800 connections/sec for 1600 requests, and 900 connections/sec for 1800 requests there was a change in the ability to respond to incoming requests. This certainly has a significant impact on the throughput provided by the server when processing a request.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call