FaaSFlow: enable efficient workflow execution for function-as-a-service
Zijun Li, Yushi Liu, Linsong Guo, Quan Chen, Jiagan Cheng, Wenli Zheng, Minyi Guo
Abstract
Serverless computing (Function-as-a-Service) provides fine-grain resource sharing by running functions (or Lambdas) in containers. Data-dependent functions are required to be invoked following a pre-defined logic, which is known as serverless workflows. However, our investigation shows that the traditional master-worker based workflow execution architecture performs poorly in serverless context. One significant overhead results from the master-side workflow schedule pattern, with which the functions are triggered in the master node and assigned to worker nodes for execution. Besides, the data movement between workers also reduces the throughput.
Topics & Concepts
WorkflowComputer scienceOverhead (engineering)ScheduleDistributed computingNode (physics)Context (archaeology)Function (biology)Workflow technologyService (business)Operating systemDatabaseEngineeringPaleontologyBiologyEvolutionary biologyStructural engineeringEconomicsEconomyCloud Computing and Resource ManagementScientific Computing and Data ManagementDistributed and Parallel Computing Systems