SteelDB: Diagnosing Kernel-Space Bottlenecks in Cloud OLTP Databases

TL;DR

SteelDB identifies kernel-space I/O bottlenecks in cloud OLTP databases and offers a zero-patch optimization approach that significantly enhances performance and reduces maintenance costs.

Contribution

The paper introduces SteelDB, a novel zero-patch architecture that optimizes kernel-space I/O behavior to improve cloud database performance without requiring kernel or database patches.

Findings

SteelDB achieves up to 9x performance improvement in TPC-C benchmarks.

SteelDB outperforms Amazon Aurora by 3.1x and reduces costs by 58%.

SteelDB reduces software maintenance costs to near zero.

Abstract

Modern cloud OLTP databases have sought performance primarily through user-space optimization - separating storage and compute layers, or distributing transactions across multiple nodes using consensus algorithms. This paper turns attention to a previously unexplored layer: kernel-space I/O behavior. From an on-premises perspective, where a single server with local storage delivers excellent performance, these elaborate designs seem puzzling. Why do cloud databases require such architectural complexity? We investigate this through a pathological analysis of databases that rely on OS-level I/O control in cloud-specific storage environments. We show that bottlenecks widely attributed to network or storage architectures in fact originate in kernel-space I/O behavior. Based on this diagnosis, we derive treatment principles and realize them as SteelDB, a zero-patch architecture that improves database performance on general-purpose cloud distributed block storage through strategic I/O optimization without requiring kernel or database patches. TPC-C evaluations demonstrate that SteelDB achieves up to 9x performance improvement at no additional cost. Against Amazon Aurora, SteelDB achieved 3.1x higher performance while reducing costs by 58%, leading to a 7.3x improvement in cost efficiency. While Aurora requires an average of 254 days for major version upgrades due to applying proprietary patches to newly released OSS databases, our zero-patch architecture reduces these software maintenance costs to near zero.