ANALISIS KINERJA HADOOP DALAM PENGOLAHAN BIG DATA PADA CLOUD COMPUTING MENGGUNAKAN METODE BENCHMARK

AFIFA, ULLY and Heryanto, Ahmad (2025) ANALISIS KINERJA HADOOP DALAM PENGOLAHAN BIG DATA PADA CLOUD COMPUTING MENGGUNAKAN METODE BENCHMARK. Undergraduate thesis, Sriwijaya University.

	Image RAMA_56201_09011282025093_cover.jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (266kB)
	Text RAMA_56201_09011282025093.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011282025093_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (5MB) | Request a copy
	Text RAMA_56201_09011282025093_0022018703_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_56201_09011282025093_0022018703_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (535kB) | Request a copy
	Text RAMA_56201_09011282025093_0022018703_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (589kB) | Request a copy
	Text RAMA_56201_09011282025093_0022018703_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (683kB) | Request a copy
	Text RAMA_56201_09011282025093_0022018703_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (133kB) | Request a copy
	Text RAMA_56201_09011282025093_0022018703_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (171kB) | Request a copy
	Text RAMA_56201_09011282025093_0022018703_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (52kB) | Request a copy

Abstract

Big Data processing in Cloud Computing requires efficient frameworks such as Hadoop and Spark. This study analyzes their performance using the benchmark method with the Terasort workload, evaluating execution time, throughput, and CPU and memory usage. The testing was conducted using the Terasort workload on a cloud infrastructure based on VirtualBox in cluster mode. The results show that Spark outperforms Hadoop, with execution time up to 4.7 times faster for certain workloads and 92.25% higher throughput compared to Hadoop. However, Spark consumes 10% more memory than Hadoop. On the other hand, Hadoop demonstrates better resource efficiency and greater stability under heavy workloads. This study provides insights for users in selecting the appropriate Big Data processing platform based on specific needs. By understanding the advantages and limitations of each framework, the implementation of Hadoop and Spark can be optimized to enhance efficiency in large-scale data processing.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Big Data, Cloud Computing, Hadoop, Spark, Benchmark, Terasort
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Ully Afifa
Date Deposited:	14 Mar 2025 04:05
Last Modified:	14 Mar 2025 04:05
URI:	http://repository.unsri.ac.id/id/eprint/168680

Actions (login required)

View Item