Object as a Service (OaaS): Enabling Object Abstraction in Serverless Clouds

• URL: http://arxiv.org/abs/2206.05361v3
• Date: Tue, 5 Sep 2023 23:16:15 GMT
• Title: Object as a Service (OaaS): Enabling Object Abstraction in Serverless Clouds
• Authors: Pawissanutt Lertpongrujikorn, Mohsen Amini Salehi
• Abstract summary: We propose a new abstraction level atop the function abstraction, known as Object as a Service (O) programming. O encapsulates the application data and function into the object abstraction and relieves the developers from resource and data management burdens. It also unlocks opportunities for built-in optimization features, such as software reusability, data locality, and caching.
• Score: 2.0575037267955305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Function as a Service (FaaS) paradigm is becoming widespread and is envisioned as the next generation of cloud systems that mitigate the burden for programmers and cloud solution architects. However, the FaaS abstraction only makes the cloud resource management aspects transparent but does not deal with the application data aspects. As such, developers have to undergo the burden of managing the application data, often via separate cloud services (e.g., AWS S3). Similarly, the FaaS abstraction does not natively support function workflow, hence, the developers often have to work with workflow orchestration services (e.g., AWS Step Functions) to build workflows. Moreover, they have to explicitly navigate the data throughout the workflow. To overcome these problems of FaaS, we design a higher-level cloud programming abstraction that hides the complexities and mitigate the burden of developing cloud-native application development. We borrow the notion of object from object-oriented programming and propose a new abstraction level atop the function abstraction, known as Object as a Service (OaaS). OaaS encapsulates the application data and function into the object abstraction and relieves the developers from resource and data management burdens. It also unlocks opportunities for built-in optimization features, such as software reusability, data locality, and caching. OaaS natively supports dataflow programming such that developers define a workflow of functions transparently without getting involved in data navigation, synchronization, and parallelism aspects. We implemented a prototype of the OaaS platform and evaluated it under real-world settings against state-of-the-art platforms regarding the imposed overhead, scalability, and ease of use. The results demonstrate that OaaS streamlines cloud programming and offers scalability with an insignificant overhead to the underlying cloud system.

Related papers

• Histrio: a Serverless Actor System [44.99833362998488]
  Histrio is a programming model and execution environment that simplifies the development of stateful applications. It lifts concerns such as state management, database interaction, and programming handling from developers. It guarantees exactly-once-processing consistency, meaning that the application always behaves as if any interaction with external clients was processed once and only once.
  arXiv  Detail & Related papers  (2024-10-29T06:58:56Z)
• Bauplan: zero-copy, scale-up FaaS for data pipelines [4.6797109107617105]
  bauplan is a novel F programming model and serverless runtime designed for data practitioners. bauplan enables users to declaratively define functional Directed Acyclic Graphs (DAGs) along with their runtime environments. We show that bauplan both better performance and a superior developer experience for data workloads by making trade-off of reducing generality in favor of data-awareness.
  arXiv  Detail & Related papers  (2024-10-22T22:49:01Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorFBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures. We also present WorFEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms. We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• SeBS-Flow: Benchmarking Serverless Cloud Function Workflows [51.4200085836966]
  We propose the first serverless workflow benchmarking suite SeBS-Flow. SeBS-Flow includes six real-world application benchmarks and four microbenchmarks representing different computational patterns. We conduct comprehensive evaluations on three major cloud platforms, assessing performance, cost, scalability, and runtime deviations.
  arXiv  Detail & Related papers  (2024-10-04T14:52:18Z)
• Object as a Service: Simplifying Cloud-Native Development through Serverless Object Abstraction [1.7416288134936873]
  We propose a new paradigm, known as Object as a Service (O) that encapsulates application data and functions into the cloud object abstraction. O relieves developers from resource and data management burden while offering built-in optimization features. We develop a platform named Oparaca that offers state abstraction for structured and unstructured data with consistency and fault-tolerant guarantees.
  arXiv  Detail & Related papers  (2024-08-09T06:55:00Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Auto-Split: A General Framework of Collaborative Edge-Cloud AI [49.750972428032355]
  This paper describes the techniques and engineering practice behind Auto-Split, an edge-cloud collaborative prototype of Huawei Cloud. To the best of our knowledge, there is no existing industry product that provides the capability of Deep Neural Network (DNN) splitting.
  arXiv  Detail & Related papers  (2021-08-30T08:03:29Z)
• Exploring the potential of flow-based programming for machine learning deployment in comparison with service-oriented architectures [8.677012233188968]
  We argue that part of the reason is infrastructure that was not designed for activities around data collection and analysis. We propose to consider flow-based programming with data streams as an alternative to commonly used service-oriented architectures for building software applications.
  arXiv  Detail & Related papers  (2021-08-09T15:06:02Z)
• A Privacy-Preserving Distributed Architecture for Deep-Learning-as-a-Service [68.84245063902908]
  This paper introduces a novel distributed architecture for deep-learning-as-a-service. It is able to preserve the user sensitive data while providing Cloud-based machine and deep learning services.
  arXiv  Detail & Related papers  (2020-03-30T15:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.