Serverless Computing: One Step Forward, Two Steps Back
arXiv:1812.03651
Abstract
Serverless computing offers the potential to program the cloud in an autoscaling, pay-as-you go manner. In this paper we address critical gaps in first-generation serverless computing, which place its autoscaling potential at odds with dominant trends in modern computing: notably data-centric and distributed computing, but also open source and custom hardware. Put together, these gaps make current serverless offerings a bad fit for cloud innovation and particularly bad for data systems innovation. In addition to pinpointing some of the main shortfalls of current serverless architectures, we raise a set of challenges we believe must be met to unlock the radical potential that the cloud---with its exabytes of storage and millions of cores---should offer to innovative developers.
arXiv comment8 pages, draft for CIDR 2019
References in corpus (1)
Cited by in corpus (34)
- Cloudburst: Stateful Functions-as-a-Service
- The Serverless Computing Survey: A Technical Primer for Design Architecture
- Lambada: Interactive Data Analytics on Cold Data using Serverless Cloud Infrastructure
- FaaSdom: A Benchmark Suite for Serverless Computing
- LaSS: Running Latency Sensitive Serverless Computations at the Edge
- How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads
- A Deep Recurrent-Reinforcement Learning Method for Intelligent AutoScaling of Serverless Functions
- AuctionWhisk: Using an Auction-Inspired Approach for Function Placement in Serverless Fog Platforms
- A Review of Serverless Use Cases and their Characteristics
- Function Delivery Network: Extending Serverless Computing for Heterogeneous Platforms
- Benchmarking Parallelism in FaaS Platforms
- Serverless Data Science -- Are We There Yet? A Case Study of Model Serving
- Distributed Double Machine Learning with a Serverless Architecture
- ServerMix: Tradeoffs and Challenges of Serverless Data Analytics
- The Ideal Versus the Real: Revisiting the History of Virtual Machines and Containers
- Faa$T: A Transparent Auto-Scaling Cache for Serverless Applications
- Supporting Multi-Cloud in Serverless Computing
- A FaaS File System for Serverless Computing
- Serverless Workflows with Durable Functions and Netherite
- HiveMind: A Scalable and Serverless Coordination Control Platform for UAV Swarms
- Operator as a Service: Stateful Serverless Complex Event Processing
- Serverless Computing for Scientific Applications
- SyncMesh: Improving Data Locality for Function-as-a-Service in Meshed Edge Networks
- Characterizing Commodity Serverless Computing Platforms
- Starling: A Scalable Query Engine on Cloud Function Services
- Scaling a Variant Calling Genomics Pipeline with FaaS
- Fog Function: Serverless Fog Computing for Data Intensive IoT Services
- No more, no less - A formal model for serverless computing
- FaaSter Troubleshooting -- Evaluating Distributed Tracing Approaches for Serverless Applications
- CausalMesh: A Formally Verified Causally Consistent Distributed Cache with Support for Client Migration
- Utility-based Resource Allocation and Pricing for Serverless Computing
- FlexState: Enabling Innovation in Network Function State Management
- Fault-tolerant and Transactional Stateful Serverless Workflows (extended version)
- New Directions in Cloud Programming