Abstract
Paxos is a prominent theory of state-machine replication. Recent data intensive systems that implement state-machine replication generally require high throughput. Earlier versions of Paxos as few of them are classical Paxos, fast Paxos, and generalized Paxos have a major focus on fault tolerance and latency but lacking in terms of throughput and scalability. A major reason for this is the heavyweight leader. Through offloading the leader, we can further increase throughput of the system. Ring Paxos, Multiring Paxos, and S-Paxos are few prominent attempts in this direction for clustered data centers. In this paper, we are proposing HT-Paxos, a variant of Paxos that is the best suitable for any large clustered data center. HT-Paxos further offloads the leader very significantly and hence increases the throughput and scalability of the system, while at the same time, among high throughput state-machine replication protocols, it provides reasonably low latency and response time.
Highlights
State-machine replication (SMR) is a fundamental technique for increasing availability of the system [1, 2]
State-machine replication prevalently uses the variants of Paxos
Like classic Paxos, it is assumed that agents communicate by sending messages
Summary
State-machine replication (SMR) is a fundamental technique for increasing availability of the system [1, 2]. HT-Paxos adopts few major concepts as (i) eliminating the work of handling client communications and request dissemination from the leader; that is, leader does not require either receiving or disseminating the client requests; instead it only receives the batch IDs (or request IDs) and orders them (unlike S-Paxos and ring Paxos). This significantly reduces acknowledgement messages at disseminators in large clustered data centers (unlike S-Paxos, where every disseminator sends acknowledgement messages to every other disseminator).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have