Lazy Read: Asynchronous Execution of Synchronous File I/O
Key: LRS23
Author: Ansgar Lößer, Florian Raskob, Björn Scheuermann
Date: December 2023
Kind: In proceedings
Publisher: IEEE
Abstract: In the realm of High-Performance Computing (HPC), the disparity between I/O and processing capabilities can hinder application performance. One source of this I/O gap is the latency of the devices, especially in case of distributed filesystems (DFS). Prior solutions to minimize such negative effects (e.g. using asynchronous operations or separate I/O-Threads), have to be considered when designing an application. This work aims to execute these operations asynchronously for existing applications without necessitating modifications or even recompilation. To attain this objective, we introduce the Lazy Read approach, which alters how the operating system handles read requests. This modification enables the application to start multiple reads or do CPU work in parallel instead of waiting for completion of the read operation. For evaluation, we implemented the Lazy Read approach in the Linux kernel. We then showed that the approach adds overhead, however, multiple read operations can be executed in parallel. In our specific evaluation the maximum possible speedup was achieved, reducing the execution time by up to 50%.
Official URL

The documents distributed by this server have been provided by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, not withstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.