Query Cost Model Calibration in Confidential Virtual Machines

2026-06-24

AI Summary

This work addresses the significant performance degradation of analytical queries in confidential virtual machines (CVMs), which stems from traditional query optimizers relying on cost models designed for non-encrypted environments and thus ignoring CVM-specific hardware overheads—such as RMP address translation and data movement. To bridge this gap, the authors propose the first CVM-aware cost calibration method that incorporates these hardware costs into the optimizer’s cost model without requiring modifications to the database kernel. Their lightweight approach leverages existing physical proxy metrics already tracked by the optimizer to model CVM-induced overheads and dynamically adjust execution plans. Experimental evaluation on AMD SEV-SNP demonstrates that the method recovers up to 48% of the lost performance, with some workloads even surpassing KVM baselines, thereby substantially narrowing the performance gap between CVMs and conventional virtual machines.

Abstract

With the growing adoption of Confidential Computing, running databases in confidential virtual machines (CVMs) such as AMD SEV-SNP has become an attractive way to protect sensitive cloud data with minimal changes to legacy DBMSs. However, analytical queries in such CVMs often suffer substantial overhead, and prior database work has largely stopped at benchmarking these slowdowns rather than optimizing them. We show that this problem stems from a hardware-software mismatch: query optimizers still rely on KVM-oriented (non-encrypted VM) cost assumptions that no longer hold in CVMs. To address this, we propose a lightweight CVM-aware cost calibration. It models two dominant sources of optimizer-facing overhead: data movement and RMP-related translation using simple physical proxies already available to the optimizer. Experiments show that the calibration significantly narrows the KVM/CVM performance gap, recovering up to 48 percent performance and even outperforming the KVM baseline on some workloads.

Problem

• Confidential Virtual Machines
• Query Cost Model
• Hardware-Software Mismatch
• Database Performance
• Cost Calibration

Innovation

• Confidential Virtual Machines
• Query Cost Model
• Cost Calibration
• AMD SEV-SNP
• Query Optimization