BEGIN:VCALENDAR PRODID:-//eluceo/ical//2.0/EN VERSION:2.0 CALSCALE:GREGORIAN BEGIN:VEVENT UID:2fe98bb32c87cd4e79853a01b23dd3d5 DTSTAMP:20260720T163622Z SUMMARY:Digital twins and control of disk-performance in small-scale Linux- based systems DESCRIPTION:Contact: bjorn.olofsson@control.lth.se\n\nTitle: \;Digital twins and control of disk-performance in small-scale Linux-based systemsAu thor: \;Oskar StenbergDate &\; Time: June 10th\, 13:15-14:15Locatio n: \;Seminar Room M 3170-73 in the M-building\, LTHSupervisor: Björn Olofsson\, \;Anders BlomdellExaminer: \; Bo BernhardssonAbstract:P erformance control in servers is important for maintaining responsiveness and efficient resource usage\, particularly in smaller computing environme nts where resource bottlenecks are more noticeable. This creates a need fo r mechanisms to measure and control the performance of common bottlenecks such as disk I/O and networking.This thesis investigates and compares two different methods for controlling disk I/O performance in virtualised Linu x environments\; Linux control groups (cgroups) and the QEMU virtual block layer. The goal is to prioritise high-priority workloads by throttling lo w-priority background tasks.Experimental results show that both methods su ccessfully enforce performance limits and improve the performance of prior itised workloads. In the evaluated scenarios\, user-induced tasks were acc elerated by up to 20% when low-priority background workloads were throttle d. When measuring sequential read performance\, cgroup-based limits achiev ed an average error of 2% compared to the set performance limits\, while Q EMU-based limits achieved an average error of 3%. QEMU-based limits were f ound to provide slightly higher accuracy and efficiency overall\, while a combination of QEMU and cgroup-based limits would provide the best granula rity of disk I/O control.This thesis also investigates the deployment of a digital twin of a computer environment.The deployed twin was found to clo sely match the real environment\, with only minor deviations in hardware s pecifications. To enable communication between the twin and the real envir onment without modifying either system\, a virtual router was designed and evaluated. The router achieved a maximum throughput of approximately 9.1 Gbit/s over a 10 Gbit/s connection while introducing negligible additional latency.In addition\, several performance analysis tools were developed f or monitoring CPU\, memory\, networking and disk performance. These includ e a tool for distributed data collection as well as eBPF-based debugging a nd tracing utilities for Linux network and storage subsystems.Together\, t hese components provide mechanisms for performance control\, monitoring an d validation of virtualised Linux environments\n\nMore information about t he event: https://www.control.lth.se/calendar/digital-twins-and-control-di sk-performance-small-scale-linux-based-systems DTSTART;TZID=GMT:20260610T111500 DTEND;TZID=GMT:20260610T121500 LOCATION:Seminar Room M 3170-73 in the M-building\, LTH END:VEVENT END:VCALENDAR