Geospatial decentralization is essential for blockchains, ensuring regulatory resilience, robustness, and fairness. We empirically analyze five major Proof of Stake (PoS) blockchains—Aptos, Avalanche, Ethereum, Solana, and Sui—revealing that a few geographic regions dominate consensus voting power, resulting in limited geospatial decentralization. To address this, we propose Geospatially-aware Proof of Stake (GPoS), which integrates geospatial diversity with stake-based voting power. Experimental evaluation demonstrates an average 45% improvement in geospatial decentralization, as measured by the Gini coefficient of Eigenvector centrality, while incurring minimal performance overhead in BFT protocols, including HotStuff and CometBFT. These results demonstrate that GPoS can improve geospatial decentralization while, in our experiments, incurring minimal overhead to consensus performance.

Conventional consensus algorithms, such as Paxos and Raft, encounter inefficiencies when applied to large-scale distributed systems due to the requirement of waiting for replies from a majority of nodes. To address these challenges, we propose Cabinet, a novel consensus algorithm that introduces dynamically weighted consensus, allocating distinct weights to nodes based on any given failure thresholds. Cabinet dynamically adjusts nodes' weights according to their responsiveness, assigning higher weights to faster nodes. The dynamic weight assignment maintains an optimal system performance, especially in large-scale and heterogeneous systems where node responsiveness varies. We evaluate Cabinet against Raft with distributed MongoDB and PostgreSQL databases using YCSB and TPC-C workloads. The evaluation results show that Cabinet outperforms Raft in throughput and latency under increasing system scales, complex networks, and failures in both homogeneous and heterogeneous clusters, offering a promising high-performance consensus solution.

Passive view-change protocols are widely employed in BFT algorithms; however, they present the risks of selecting unavailable or slow servers as leaders. To tackle these challenges, we propose PrestigeBFT, a novel BFT consensus algorithm that incorporates an active view-change protocol with reputation mechanisms. PrestigeBFT evaluates a server's reputation based on its past behavior and elects more reputable servers as leaders. Our reputation mechanism incentivizes protocol-abiding behavior while penalizing faulty servers by imposing computational work. PrestigeBFT significantly enhances system availability and efficiency by avoiding unavailable or slow servers being assigned as leaders. Under normal operation, PrestigeBFT achieves$5\times$higher throughput than the baseline that uses passive view-change protocols. In addition, PrestigeBFT's throughput remains unaffected under benign faults and witnesses only a 24% drop under a variety of Byzantine faults, whereas the baseline throughput drops by 62% and 69%, respectively. In the long run, while the baseline's availability struggles at 37%, PrestigeBFT progressively improves its availability to over 90%.

Conflict-free replicated data types (CRDTs) are highly available and performant data replication solutions for distributed applications. However, their eventual consistency guarantees are often insufficient for ensuring application correctness, especially in the presence of Byzantine failures. Naively applying traditional consensus and Byzantine fault tolerance (BFT) protocols to CRDT updates for stronger guarantees, while intuitive, negates the performance benefits of CRDTs. We introduce a novel programming model called reliable CRDTs that expands CRDTs with additional guarantees: users can query strongly or eventually consistent values, enforce a total order among selected operations, and define data-type level invariants while remaining operational in the presence of Byzantine failures. Reliable CRDTs enable the use of CRDTs in scenarios where strong consistency is needed while maintaining their performance advantages. We present an implementation of reliable CRDTs named Janus. It enhances CRDTs with the aforementioned features by functioning as a middleware that facilitates CRDT communication and asynchronously runs a BFT consensus protocol. Our evaluation demonstrates that Janus achieves 21× higher throughput than naively applying state-of-the-art BFT protocols such as HotStuff achieves, and it remains responsive even under heavy loads.

The advances in virtualization technologies have sparked a growing transition from virtual machine (VM)-based to container-based infrastructure for cloud computing. From the resource orchestration perspective, containers' lightweight and highly configurable nature not only enables opportunities for more optimized strategies, but also poses greater challenges due to additional uncertainties and a larger configuration parameter search space. Towards this end, we propose Drone, a resource orchestration framework that adaptively configures resource parameters to improve application performance and reduce operational cost in the presence of cloud uncertainties. Built on Contextual Bandit techniques, Drone is able to achieve a balance between performance and resource cost on public clouds, and optimize performance on private clouds where a hard resource constraint is present. We show that our algorithms can achieve sub-linear growth in cumulative regret, a theoretically sound convergence guarantee, and our extensive experiments show that Drone achieves an up to 45% performance improvement and a 20% resource footprint reduction across batch processing jobs and microservice workloads.

Leader-based consensus protocols must undergo a view-change phase to elect a new leader when the current leader fails. The new leader often comes from a candidate server that collects votes from a quorum of servers. However, voting-based election mechanisms intrinsically incite competition in leadership candidacy since candidates may collect only partial votes. This split-vote scenario can result in no leadership winner and thus prolongs the undesired view-change period. In this paper, we investigate a case study of Raft’s leader election and propose a new leader election protocol, called ESCAPE, that fundamentally solves split votes by prioritizing servers based on their log responsiveness. ESCAPE dynamically distributes configurations that offer different priorities to servers through periodic heartbeats. In each assignment, ESCAPE assigns configurations that are more inclined to win an election to servers that have more up-to-date log responsiveness, thereby preparing a pool of prioritized candidates. Consequently, when the next election takes place, the candidate with the highest priority can defeat its counterparts and becomes the next leader without competition. The evaluation results show that ESCAPE progressively reduces the leader election time when the cluster scales up, and the improvement becomes more significant under message loss.

Current leader-based Byzantine fault-tolerant (BFT) protocols aim to improve the efficiency for achieving consensus while tolerating failures; however, Byzantine servers are able to repeatedly impair BFT systems as faulty servers launch attacks without costs. In this paper, leveraging Proof-of-Work and Raft, we propose a new BFT consensus protocol called Prosecutor that dynamically penalizes suspected faulty behavior and suppresses Byzantine servers over time. Prosecutor obstructs Byzantine servers from being elected in leader election by imposing hash computation on new election campaigns. Furthermore, Prosecutor applies message authentication to achieve secure log replication and maintains a similar message-passing scheme as Raft. The evaluation results show that the penalization mechanism progressively suppresses and marginalizes Byzantine servers if they repeatedly launch malicious attacks.