# Reconfigurable Atomic Transaction Commit (Extended Version)

## TL;DR

This paper introduces new atomic commit protocols for distributed data stores that require fewer replicas, reconfigure upon failures, and are proven correct in both asynchronous and RDMA models, improving scalability and fault tolerance.

## Contribution

It presents novel atomic commit protocols that reduce replica requirements to f+1, incorporate reconfiguration, and are rigorously proven correct in multiple models.

## Key findings

- Protocols require only f+1 replicas, reducing overhead.
- Protocols are proven correct under the TCS specification.
- Work highlights trade-offs of using RDMA in distributed commit protocols.

## Abstract

Modern data stores achieve scalability by partitioning data into shards and fault-tolerance by replicating each shard across several servers. A key component of such systems is a Transaction Certification Service (TCS), which atomically commits a transaction spanning multiple shards. Existing TCS protocols require 2f+1 crash-stop replicas per shard to tolerate f failures. In this paper we present atomic commit protocols that require only f+1 replicas and reconfigure the system upon failures using an external reconfiguration service. We furthermore rigorously prove that these protocols correctly implement a recently proposed TCS specification. We present protocols in two different models--the standard asynchronous message-passing model and a model with Remote Direct Memory Access (RDMA), which allows a machine to access the memory of another machine over the network without involving the latter's CPU. Our protocols are inspired by a recent FARM system for RDMA-based transaction processing. Our work codifies the core ideas of FARM as distributed TCS protocols, rigorously proves them correct and highlights the trade-offs required by the use of RDMA.