Amer Diwan
Research Areas
Authored Publications
Sort By
Meaningful availability
Dan Ardelean
Philipp Emanuel Hoffmann
Tamás Hauer
17th USENIX Symposium on Networked Systems Design and Implementation (NSDI'20) (2020)
Preview abstract
Accurate measurement of service availability is the cornerstone of good service management: it quantifies the gap between user expectation and system performance, and provides actionable data to prioritize development and operational tasks. We propose a novel metric, user-uptime, which is event- based but is time-sensitive and which approximates aggregated user-perceived reliability better than current metrics. For a holistic view of availability across timescales from minutes to months or quarters, we augment user-uptime with a novel aggregation and visualization paradigm: windowed uptime. Using an example from G Suite we demonstrate its effectiveness in differentiating between unreliability caused
by flakiness and an extended outage.
View details
Why you should care about quantile regression
Preview
Augusto Born De Oliveira
Sebastian Fischmeister
Matthias Hauswirth
Peter Sweeney
Architectural Support for Programming Languages and Operating Systems, ASPLOS '13, ACM (2013), pp. 207-218
Measuring Enforcement Windows with Symbolic Trace Interpretation: What Well-Behaved Programs Say
Preview
Devin Coughlin
Bor-Yuh Evan Chang
Jeremy Siek
Proceedings of the 2012 International Symposium on Software Testing and Analysis, ACM, pp. 276-286
Preview abstract
Modern object-oriented languages have complex features that cause
programmers to overspecify their programs. This overspecification
hinders automatic optimizers, since they must preserve the
overspecified semantics. If an optimizer knew which semantics the
programmer intended, it could do a better job.
Making a programmer clarify his intentions by placing assumptions
into the program is rarely practical. This is because the programmer
does not know which parts of the programs' overspecified semantics
hinder the optimizer. Therefore, the programmer has to guess
which assumption to add. Since the programmer can add many
different assumptions to a large program, he will need to place
many such assumptions before he guesses right and helps the optimizer.
We present IOpt, a practical optimizer that uses a
specification of the programmers' intended semantics to enable
additional optimizations. That way, our optimizer can significantly
improve the performance of a program. We present case studies in which
we use IOpt to speed up two programs by over 50%.
To make specifying the intended semantics practical, IOpt
communicates with the programmer. IOpt identifies which
assumptions the programmer textit{should} place, and where he should
place them. IOpt ranks each assumption by (i) the likelyhood that
the assumption conforms to the programmers' intended semantics and
(ii) how much the assumption will help IOpt improve the programs'
performance. IOpt proposes ranked assumptions to the programmer,
who just picks those that conform to his intended semantics. With
this approach, IOpt keeps the programmers' specification burden
low. Our case studies show that the programmer just needs to add a few
assumptions to realize the 50% speedup.
View details
