BtrLog: Low-Latency Logging for Cloud Database Systems

2026-06-25

AI Summary

This work addresses the challenge of achieving low-latency, cost-efficient write-ahead logging (WAL) durability in cloud databases. Existing approaches face trade-offs: remote block storage incurs high latency, object storage is ill-suited for OLTP workloads, and specialized log backends lack generality. To overcome these limitations, the authors propose BtrLog, a reusable, cloud-native log service built on a single-writer architecture that leverages SSD-based log nodes for low-latency durable appends and asynchronously archives segmented logs to object storage for cost efficiency. Its key innovation is a majority-acknowledged replication protocol requiring only a single network round trip, which ensures strong durability while significantly reducing tail latency. Experimental results demonstrate that BtrLog substantially lowers log-write latency compared to Amazon EBS and improves end-to-end transaction throughput when integrated with mainstream DBMSs.

Abstract

Cloud database systems cannot rely on instance-local disks for write-ahead logging (WAL) durability, forcing WAL onto remote storage. Existing options are unsatisfying: remote block storage like EBS is easy to adopt but adds substantial write latency and cost, while object storage offers excellent durability and low storage cost but is impractical for OLTP due to high latency and per-append cost. Many cloud-native databases, therefore, depend on purpose-built logging backends, which are typically proprietary and tightly coupled to engine-specific replication and recovery protocols, limiting reuse. We present BtrLog, a reusable cloud logging service that combines low-latency durable appends with low-cost archival for the common single-writer architecture. BtrLog replicates log records across a quorum of SSD-backed log nodes in a single network round trip, reducing sensitivity to stragglers in commit latency. To minimize storage cost, log nodes archive records to object storage as large segments, which are written asynchronously and off the latency-critical write path. In our evaluation, BtrLog achieves lower latency than EBS and enables higher end-to-end transaction throughput when integrated into a DBMS.

Problem

• cloud database
• write-ahead logging
• remote storage
• low-latency
• durability

Innovation

• cloud logging
• write-ahead logging
• low-latency durability
• asynchronous archiving
• quorum replication