Joint$lambda$: Orchestrating Serverless Workflows on Jointcloud FaaS Systems

2025-05-28

AI Summary

Current serverless workflow orchestration systems are constrained to single-cloud Function-as-a-Service (FaaS) platforms, leading to vendor lock-in and suboptimal trade-offs among performance, cost, and availability. Cross-cloud orchestration faces two key challenges: high overhead from centralized coordination and unreliable failover. This paper introduces Joint$lambda$, a decentralized runtime system that pioneers *function-side orchestration*—a novel paradigm where workflow logic executes alongside functions—and a Backend-Shim compatibility layer enabling seamless scheduling across heterogeneous FaaS platforms (e.g., AWS Lambda, Alibaba Cloud Function Compute) without a central coordinator. Joint$lambda$ guarantees exactly-once execution semantics, strongly consistent state management, and dynamic, reliable failover. Evaluation shows that, compared to commercial single-cloud services, Joint$lambda$ reduces latency by 3.3× and cuts costs by 65%; against existing cross-cloud orchestrators, it improves throughput by 4.0× and reduces costs by 4.5×—significantly enhancing efficiency, resilience, and portability of multi-cloud serverless workflows.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Coordination and Collaboration
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Existing serverless workflow orchestration systems are predominantly designed for a single-cloud FaaS system, leading to vendor lock-in. This restricts performance optimization, cost reduction, and availability of applications. However, orchestrating serverless workflows on Jointcloud FaaS systems faces two main challenges: 1) Additional overhead caused by centralized cross-cloud orchestration; and 2) A lack of reliable failover and fault-tolerant mechanisms for cross-cloud serverless workflows. To address these challenges, we propose Joint$lambda$, a distributed runtime system designed to orchestrate serverless workflows on multiple FaaS systems without relying on a centralized orchestrator. Joint$lambda$ introduces a compatibility layer, Backend-Shim, leveraging inter-cloud heterogeneity to optimize makespan and reduce costs with on-demand billing. By using function-side orchestration instead of centralized nodes, it enables independent function invocations and data transfers, reducing cross-cloud communication overhead. For high availability, it ensures exactly-once execution via datastores and failover mechanisms for serverless workflows on Jointcloud FaaS systems. We validate Joint$lambda$ on two heterogeneous FaaS systems, AWS and ALiYun, with four workflows. Compared to the most advanced commercial orchestration services for single-cloud serverless workflows, Joint$lambda$ reduces up to 3.3$ imes$ latency, saving up to 65% cost. Joint$lambda$ is also faster than the state-of-the-art orchestrators for cross-cloud serverless workflows up to 4.0$ imes$, reducing up to 4.5$ imes$ cost and providing strong execution guarantees.

Problem

• Overcoming vendor lock-in in single-cloud serverless workflows
• Reducing cross-cloud orchestration overhead and costs
• Ensuring reliable failover for cross-cloud serverless workflows

Innovation

• Distributed runtime system for multi-cloud FaaS
• Function-side orchestration reduces communication overhead
• Ensures exactly-once execution with failover mechanisms