ALISA: An Adaptive Learned Index Structure for Spatial Data on Solid-State Drives

Spatial learned index is becoming popular as a solution to relieve the intense storage demands and high I/O costs of spatial databases. LISA, the original and most prominent spatial learned index structure, is tailored for HDD-resident spatial data and comes with strict data arrangement requirements. Given that direct SSD migration may drastically impair SSD durability especially when page utilization is low, this work aims to adapt this innovative index structure to SSDs to leverage the faster performance and expand application possibilities. We propose an Adaptive Learned Index structure for Spatial dAta on SSDs (ALISA), with mechanisms to persistently monitor updated data distribution and adaptively restructure to align with SSD access characteristics. The evaluation results show that ALISA can significantly extend SSD lifespan and improve low page utilization, thereby enhancing query performance.