Serverless is More: From PaaS to Present Cloud Computing

Abstract

In the late-1950s, leasing time on an IBM 704 cost hundreds of dollars per minute. Today, cloud computing, that is, using IT as a service, on-demand and pay-per-use, is a widely used computing paradigm that offers large economies of scale. Born from a need to make platform as a service (PaaS) more accessible, fine-grained, and affordable, serverless computing has garnered interest from both industry and academia. This article aims to give an understanding of these early days of serverless computing: what it is, where it comes from, what is the current status of serverless technology, and what are its main obstacles and opportunities. The 1950s saw the emergence of two technologies that are currently shaping the world: containerization in shipping and timesharing in computing. By allowing shipping to become standardized and automated, the former gave rise to manufacturing and retail ecosystems, and ultimately to the economic phenomenon of globalization 1. By enabling multiple clients to share the same physical infrastructure, time-sharing gave rise to cloud computing and the modern digital ecosystems, which are key drivers for growth in knowledge-based societies 2. Whereas few could afford the costs of time-sharing services and paid dearly for simple computer simulations in the late-1950s, today over 80% of companies use the hundreds of services accessible as cloud computing (source: Studies by European Commission 3 and Cloudability (2018)), along with many private individuals. Following with remarkable regularity the evolution observed in the history of containerization, cloud services have adapted to offer better fitting containers that require less time to load (boot) and provide higher automation in handling (orchestrating) containers on behalf of the client. Serverless computing promises more: to achieve full-automation in managing fine-grained containers. Already,

Towards cloud-native simulations – lessons learned from the front-line of cloud computing

“…The studies and surveys 23,[50][51][52] deal mainly with containerization and its accompanying resource efficiency. Although FaaS is quite young and is not reflected extensively in research so far, there exist first survey papers 33,[53][54][55][56] dealing with FaaS approaches deriving some open research questions regarding tool support, performance, patterns for serverless solutions, enterprise suitability, and whether serverless architectures will extend beyond traditional cloud platforms and architectures.…”

Beyond Microbenchmarks: The SPEC-RG Vision for a Comprehensive Serverless Benchmark

“…The key insight that started our design is an understanding of what elements should be part of a benchmark to enable it to be comprehensive. Based on our prior work of surveying existing serverless platforms [12], we mapped the lifecycle of a function execution to multiple aspects, grouped in three operational layersthe Resource Orchestration, Function Management, and Workflow Composition layers in Figure 1. We want to capture and characterize the interplay between the various components depicted in the figure . For example, besides the function runtime overhead itself, there are other aspects that influence the performance of the overall function execution: event-trigger propagation, function configuration, code propagation, and the overhead of function deployment.…”

“…Serverless computing and its ecosystem are rapidly evolving [4,12,14], with an increasing number of open-source and managed serverless platforms available to cloud users. AWS, Google, Microsoft, and other tech giants compete in this space, and tens of open-and closed-source serverless platforms already exist [10].…”

The AtLarge Vision on the Design of Distributed Systems and Ecosystems

“…We then revisited and expanded the performance challenges introduced in the initial vision paper, identifying promising approaches towards addressing them [102]. To further separate hype from reality and leverage our decades of expertise in distributed systems, in another publication we reflected on the motivations, concepts, technologies, and practices that have led to the emergence of serverless computing [60]. Our main finding was clear: though serverless technologies leverages and overlaps many historical efforts, its emergence could not have happened ten years ago.…”