NSF bib style.
parent
9c9f7e9659
commit
3b3374db64
|
@ -138,27 +138,63 @@ differs from current benchmarks in four ways:
|
|||
|
||||
\section{Research Focus}
|
||||
|
||||
The limited power, cpu, and memory resources of smartphones provides strong motivation for research that makes small, personal-scale computing more efficient. In this proposal, we focus on enabling research on embedded databases specifically. Embedded databases bring a new array of challenges to the database field, and simultaneously represent a considerable part of a smartphone's resource consumption; An Android smartphone answers more than two queries per second using SQLite on average~\cite{pocketdata}.
|
||||
The limited power, cpu, and memory resources of smartphones provides strong
|
||||
motivation for research that makes small, personal-scale computing more
|
||||
efficient. In this proposal, we focus on enabling research on embedded
|
||||
databases specifically. Embedded databases bring a new array of challenges
|
||||
to the database field, and simultaneously represent a considerable part of a
|
||||
smartphone's resource consumption; An Android smartphone answers more than
|
||||
two queries per second using SQLite on average~\cite{pocketdata}.
|
||||
|
||||
The first step in research on embedded databases is identifying efficiency bottlenecks, common usage patterns, and other specific opportunities for improvement. As host to the \PhoneLab project, UB is uniquely positioned to enable analysis of smartphone embedded database usage in the wild. We have already released a preliminary dataset and accompanying analysis~\cite{pocketdata}. If funded, we will be able to continue these efforts by releasing more, higher-quality data to the research community. Using this data, the research community will be able to identify insights into how embedded databases are used, and how they can be improved.
|
||||
The first step in research on embedded databases is identifying efficiency
|
||||
bottlenecks, common usage patterns, and other specific opportunities for
|
||||
improvement. As host to the \PhoneLab project, UB is uniquely positioned to
|
||||
enable analysis of smartphone embedded database usage in the wild. We have
|
||||
already released a preliminary dataset and accompanying
|
||||
analysis~\cite{pocketdata}. If funded, we will be able to continue these
|
||||
efforts by releasing more, higher-quality data to the research community.
|
||||
Using this data, the research community will be able to identify insights
|
||||
into how embedded databases are used, and how they can be improved.
|
||||
|
||||
As opportunities for improvement are identified, it will become necessary to evaluate proposed solutions. Our second goal is to develop and maintain a benchmarking toolkit for pocket-scale data management. By providing our toolkit as a set of modules, we will be able to capture newly discovered limitations of existing pocket data management solutions in the benchmark. In this way, we hope to motivate further research on embedded data management solutions, and also to motivate embedded database developers to integrate these solutions into their products.
|
||||
As opportunities for improvement are identified, it will become necessary to
|
||||
evaluate proposed solutions. Our second goal is to develop and maintain a
|
||||
benchmarking toolkit for pocket-scale data management. By providing our
|
||||
toolkit as a set of modules, we will be able to capture newly discovered
|
||||
limitations of existing pocket data management solutions in the benchmark.
|
||||
In this way, we hope to motivate further research on embedded data management
|
||||
solutions, and also to motivate embedded database developers to integrate
|
||||
these solutions into their products.
|
||||
|
||||
\section{Sample Research Project}
|
||||
|
||||
In our preliminary analysis~\cite{pocketdata}, we noted that known limitations of object-relational mappers were causing a significant increase in the number of queries processed by SQLite. Compiler-based database integrations like LINQ~\cite{Meijer:2006:LRO:1142473.1142552}, LMS~\cite{Rompf:2015:FPS:2784731.2784760}, or StatusQuo~\cite{StatusQuo} begin to address these limitations. To tune and evaluate these solutions, it is necessary to have the real-world app query semantics that the PocketData project can provide.
|
||||
In our preliminary analysis~\cite{pocketdata}, we noted that known
|
||||
limitations of object-relational mappers were causing a significant increase
|
||||
in the number of queries processed by SQLite. Compiler-based database
|
||||
integrations like LINQ~\cite{Meijer:2006:LRO:1142473.1142552},
|
||||
LMS~\cite{Rompf:2015:FPS:2784731.2784760}, or StatusQuo~\cite{StatusQuo}
|
||||
begin to address these limitations. To tune and evaluate these solutions, it
|
||||
is necessary to have the real-world app query semantics that the PocketData
|
||||
project can provide.
|
||||
|
||||
\section{Community Involvement}
|
||||
|
||||
Our preliminary analysis~\cite{pocketdata} was presented to the Transactional Processing Council as part of an argument for an embedded database benchmark during their annual workshop.
|
||||
The TPC is an organization that oversees many of the popular database benchmarks, and can provide feedback, publicity, and a deployment vector for our efforts.
|
||||
Our argument was received favorably, and since then we have been working with the TPC leadership to obtain buy-in from smartphone vendors.
|
||||
|
||||
We have also been discussing our proposal with potential stakeholders. For example, Arnab Nandi from Ohio State has stated an interest in contributing trace data from his efforts on interactive tools for smartphone data management. We have also received further feedback in the form of desiderata from other faculty working on embedded databases. If funded, we will continue both of these outreach efforts.
|
||||
Our preliminary analysis~\cite{pocketdata} was presented to the Transactional
|
||||
Processing Council as part of an argument for an embedded database benchmark
|
||||
during their annual workshop. The TPC is an organization that oversees many
|
||||
of the popular database benchmarks, and can provide feedback, publicity, and
|
||||
a deployment vector for our efforts. Our argument was received favorably,
|
||||
and since then we have been working with the TPC leadership to obtain buy-in
|
||||
from smartphone vendors.
|
||||
|
||||
We have also been discussing our proposal with potential stakeholders. For
|
||||
example, Arnab Nandi from Ohio State has stated an interest in contributing
|
||||
trace data from his efforts on interactive tools for smartphone data
|
||||
management. We have also received further feedback in the form of desiderata
|
||||
from other faculty working on embedded databases. If funded, we will
|
||||
continue both of these outreach efforts.
|
||||
|
||||
{\footnotesize
|
||||
\bibliographystyle{abbrv}
|
||||
\bibliographystyle{nsf}
|
||||
\bibliography{main}
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue