Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal Software Engineering and Computer Science (IJSECS)
Muhammad Fadhil Rachman
Universitas Budi Luhur
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Performance Trade-Off Between Windows 10 and Windows 11: A Comparative Analysis of CPU and Memory Behavior Using Performance Monitor and LatencyMon Ekie Revsie Akbar; Muhammad Fadhil Rachman; Tiara Fitriana; Try Mulyoto; Yan Everhard Riwurohi
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 2 (2026): AUGUST 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i2.7560

Abstract

The operating system consumes processor and memory resources and affects kernel-level responsiveness before user applications run, and these resource demands may differ across operating system versions. This study compared Windows 10 and Windows 11 under a realistic and reproducible video transcoding workload performed with HandBrake, measuring CPU utilization, hard page faults, and interrupt-to-process latency. A quantitative experimental method was used. Performance Monitor recorded CPU and memory behavior, while LatencyMon measured kernel timer, interrupt service routine, deferred procedure call, and interrupt-to-process latency. An important constraint is that the two operating systems were tested on physically different devices with processors from different generations: a 6th-generation dual-core Intel Core i7-6600U and an 11th-generation quad-core Intel Core i7-1165G7. Therefore, the measured differences cannot be attributed to the operating system version alone. Windows 11 showed more sustained CPU utilization and recorded fewer hard page faults than Windows 10 (22,480 versus 50,539), although the difference is also subject to the unequal monitoring durations. Windows 10 recorded a lower highest interrupt-to-process latency (1,147.60 µs versus 1,430.70 µs) and a lower average interrupt latency (10.10 µs versus 22.44 µs), while both systems remained within the conventional real-time suitability threshold. The findings indicate that the observed performance differences are entangled with processor generation and other hardware-related effects. Therefore, a dual-boot configuration on identical hardware is recommended in future studies to isolate the effect of the operating system version.
Co-Authors Ekie Revsie Akbar Tiara Fitriana Try Mulyoto Yan Everhard Riwurohi