[Colloquium] Ahsan Pervaiz Candidacy Exam/Mar 9, 2022

[Megan Woodward]

This is an announcement of Ahsan Pervaiz's Candidacy Exam.
===============================================
Candidate: Ahsan Pervaiz

Date: Wednesday, March 09, 2022

Time:  2 pm CST

Remote Location: https://uchicago.zoom.us/j/91311114429?pwd=cGoyY2xWcElwd1RxbEd1SEtiTVd6UT09 Meeting ID: 913 1111 4429 Passcode: 647765

Location: JCL 298

Title: Frameworks for providing support for general -purpose adaptation in computing systems

Abstract: Modern computer systems are becoming increasingly complex. Apart from functional correctness, they are expected to provide strict guarantees on quality-of-service (QoS), expressed as goals, in face of unpredictable changes in operating conditions and workload. Furthermore, these systems have a plethora of configurable variables that, combined with unpredictable external conditions, impact the system's QoS. All aforementioned factors make it difficult to optimally deploy and operate modern systems.
The systems community views adaptation as a crucial capability for systems to deliver reliable quantitative behavior in the presence of dynamic operating conditions. Prior work suggests programming frameworks that can simply be instantiated by system. The framework then monitors the system behavior and changes its configurations on behalf of the system to ensure that the quantifiable goals are met despite unpredictable external changes. However, A major limitation of prior frameworks is that they are implemented for a specific, narrow set of goals and knobs. Hence, they cannot be used for complex adaptive systems that must meet different goals using different sets of knobs for different deployments, or different execution stages of one deployment. For such scenarios developers are expected to embed different frameworks in their systems to support different goals. This, in turn, increases the size of the system code base and makes development and deployment more difficult.
In our research we explore the benefits of providing a single generalized adaptation framework that is agnostic of knobs and goals. We show the deployment and runtime benefits of using such a framework in eight real-world systems including a networked video analytics pipeline.
Our research shows that it is not only possible to implement a generalized adaptation framework but that using such a framework is more favorable from a development, deployment and performance perspective. 

Advisors: Hank Hoffmann

Committee Members: Haryadi Gunawi, Hank Hoffmann, and Shan Lu
-------------- next part --------------
A non-text attachment was scrubbed...
Name: candidacy-document.pdf
Type: application/pdf
Size: 919885 bytes
Desc: candidacy-document.pdf
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20220222/b89f3586/attachment-0001.pdf>