The AtLarge Vision on the Design of Distributed Systems and Ecosystems

Abstract

High-quality designs of distributed systems and services are essential for our digital economy and society. Threatening to slow down the stream of working designs, we identify the mounting pressure of scale and complexity of (eco-)system, of ill-defined and wicked problems, and of unclear processes, methods, and tools. We envision design itself as a core research topic in distributed systems, to understand and improve the science and practice of distributed (eco-)system design. Toward this vision, we propose the ATLARGE design framework, accompanied by a set of 8 core design principles. We also propose 10 key challenges, which we hope the community can address in the following 5 years. In our experience so far, the proposed framework and principles are practical, and lead to pragmatic and innovative designs for large-scale distributed systems. arXiv:1902.05416v1 [cs.DC] 14 Feb 2019 2. Why Focus on MCS Design?We argue in this section for the timely and important need to focus on MCS design. Not only is (good) design needed (Section 2.1), but we identify an increasing need for good design (Section 2.2) and designers (Section 2.3).We also analyze what good design needs to address, that is, complex challenges from system design (Section 2.4) and from MCS design (Section 2.5).3. We anonymize the venue, but consider it relevant because its held year is after 2014, the venue is a conference, and its ranking is A in CORE18 and green in MSAR14. For comparison, ICDCS has these rankings too.4. We anonymize the university, but consider the course relevant because it is large, it took place after 2014, and the university is ranked in the top-150 (in computer science) in both the THE and the QS 2018 World University Rankings (out of nearly 1,000 universities), and in Webometrics of July 18 (out of over 28,000).

The future is big graphs

“…1940s concept of personal memex, and by a 2010s specialization into a Distributed Systems Memex, 19 we posit that it would be both interesting and useful to create a Big Graph Memex for collecting, archiving, and retrieving meaningful operational information about such systems. This could be beneficial for learning about and eradicating performance and related issues, to enable more creative designs and extend automation, and for meaningful and reproducible testing, such as feedback building-block in smart graph processing.…”

An Empirical Evaluation of the Performance of Video Conferencing Systems

“…Therefore, the requirements are classified as Must have, Should have, Could have, and Won't have. The requirements are derived from iterative group discussions following the AtLarge Design Cycle [5]. Furthermore, the requirements are grouped into functional requirements (Section 3.1) and quality requirements (Section 3.2).…”

The Workflow Trace Archive: Open-Access Data From Public and Private Computing Infrastructures

“…Similarly to how the overall design of experiments is now commonly described in publications in our field, as the setup leading to experimental results, we include here an overview of the design process that led to the design presented in this section. Outlining the design and the process that led to the design is important for understanding how the final design came to be and how it fits the intended goal [26].…”

“…The overall design of the archive and the detailed design that results in the unified format are done iteratively, using a process that draws from the AtLarge systematic design-process [26]. We started by listing initial requirements (see Section 3.1) that the WTA had to fulfill, and co-evolved the requirements with the development of the solution (the archive).…”