greg/stasis-aries-wal
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Camera ready version. (Second try.)

Browse source
This commit is contained in:
Sears Russell 2006-09-06 23:59:39 +00:00
parent 139f5b3fdb
commit cfd2395157
3 changed files with 14 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
doc/paper3/LLADD.tex
View file

@ -590,7 +590,7 @@ system.
\includegraphics[% \includegraphics[%
viewport=0bp 0bp 458bp 225bp, viewport=0bp 0bp 458bp 225bp,
clip, clip,
width=1\columnwidth]{figs/structure} width=1\columnwidth]{figs/structure.pdf}
{\caption{\label{fig:structure} The portions of \yad that directly interact with new operations. Arrows point in the direction of data flow.}} {\caption{\label{fig:structure} The portions of \yad that directly interact with new operations. Arrows point in the direction of data flow.}}
\vspace{-12pt} \vspace{-12pt}
\end{figure} \end{figure}
@ -798,7 +798,7 @@ overhead to be negligible.
\includegraphics[% \includegraphics[%
viewport=-1bp 0bp 460bp 225bp, viewport=-1bp 0bp 460bp 225bp,
clip, clip,
width=1\columnwidth]{figs/lsn-estimation} width=1\columnwidth]{figs/lsn-estimation.pdf}
\caption{\label{fig:lsn-estimation}LSN estimation. If a page was not mentioned in the log, it must have been up-to-date on disk. RecLSN is the LSN of the entry that caused the page to become dirty. Subtracting one gives us a safe estimate of the page LSN.} \caption{\label{fig:lsn-estimation}LSN estimation. If a page was not mentioned in the log, it must have been up-to-date on disk. RecLSN is the LSN of the entry that caused the page to become dirty. Subtracting one gives us a safe estimate of the page LSN.}
\vspace{-12pt} \vspace{-12pt}
\end{figure} \end{figure}
@ -934,7 +934,7 @@ logically consistent.
\includegraphics[% \includegraphics[%
viewport=0bp 0bp 445bp 308bp, viewport=0bp 0bp 445bp 308bp,
clip, clip,
width=1\columnwidth]{figs/torn-page} width=1\columnwidth]{figs/torn-page.pdf}
\caption{\label{fig:torn}Torn pages and LSN-free recovery. \caption{\label{fig:torn}Torn pages and LSN-free recovery.
The page is torn during the crash, but consistent once redo completes. The page is torn during the crash, but consistent once redo completes.
Overwritten sectors are shaded.} Overwritten sectors are shaded.}
@ -1049,7 +1049,7 @@ perform similarly to comparable monolithic implementations.
\graphdbg{\includegraphics[% \graphdbg{\includegraphics[%
viewport=-26bp 28bp 625bp 360bp, viewport=-26bp 28bp 625bp 360bp,
clip, clip,
width=1\columnwidth]{figs/bulk-load}} width=1\columnwidth]{figs/bulk-load.pdf}}
\caption{\label{fig:BULK_LOAD} Performance of \yad and Berkeley DB hash table implementations. The \caption{\label{fig:BULK_LOAD} Performance of \yad and Berkeley DB hash table implementations. The
test is run as a single transaction, minimizing synchronous log writes.} test is run as a single transaction, minimizing synchronous log writes.}
\end{figure} \end{figure}
@ -1058,7 +1058,7 @@ test is run as a single transaction, minimizing synchronous log writes.}
\graphdbg{\includegraphics[% \graphdbg{\includegraphics[%
viewport=-43bp 45bp 490bp 370bp, viewport=-43bp 45bp 490bp 370bp,
clip, clip,
width=1\columnwidth]{figs/tps-extended}} width=1\columnwidth]{figs/tps-extended.pdf}}
\caption{\label{fig:TPS} High-concurrency hash table performance. Our Berkeley DB test can only support 50 threads (see text). \caption{\label{fig:TPS} High-concurrency hash table performance. Our Berkeley DB test can only support 50 threads (see text).
\vspace{-16pt} \vspace{-16pt}
} }
@ -1104,13 +1104,13 @@ as a baseline for our experiments.
\graphdbg{\includegraphics[% \graphdbg{\includegraphics[%
viewport=-25bp 19bp 625bp 400bp, viewport=-25bp 19bp 625bp 400bp,
clip, clip,
width=1\columnwidth]{figs/object-diff}} width=1\columnwidth]{figs/object-diff.pdf}}
\hspace{.2in} \hspace{.2in}
\graphdbg{\includegraphics[% \graphdbg{\includegraphics[%
% viewport=-25bp 23bp 425bp 330bp, % viewport=-25bp 23bp 425bp 330bp,
viewport=-40bp 28bp 450bp 315bp, viewport=-40bp 28bp 450bp 315bp,
clip, clip,
width=1\columnwidth]{figs/mem-pressure}} width=1\columnwidth]{figs/mem-pressure.pdf}}
\caption{\label{fig:OASYS} \caption{\label{fig:OASYS}
The effect of \yad object-persistence optimizations under low and high memory pressure.} The effect of \yad object-persistence optimizations under low and high memory pressure.}
\vspace{-12pt} \vspace{-12pt}
@ -1157,7 +1157,7 @@ produce, not the performance of our own highly tuned implementation.
Both Berkeley DB and \yad can service concurrent calls to commit with Both Berkeley DB and \yad can service concurrent calls to commit with
a single synchronous I/O. a single synchronous I/O.
\yad scaled quite well, delivering over 6000 transactions per \yad scaled quite well, delivering over 6000 transactions per
second,%\endnote{The concurrency test was run without lock managers, and the second, %\endnote{The concurrency test was run without lock managers, and the
% transactions obeyed the A, C, and D properties. Since each % transactions obeyed the A, C, and D properties. Since each
% transaction performed exactly one hash table write and no reads, they also % transaction performed exactly one hash table write and no reads, they also
% obeyed I (isolation) in a trivial sense.} % obeyed I (isolation) in a trivial sense.}
@ -1275,7 +1275,7 @@ the implementation is encouraging.
\label{sec:logging} \label{sec:logging}
\begin{figure} \begin{figure}
\graphdbg{\includegraphics[width=1\columnwidth]{figs/graph-traversal}} \graphdbg{\includegraphics[width=1\columnwidth]{figs/graph-traversal.pdf}}
%\vspace{-12pt} %\vspace{-12pt}
\caption{\label{fig:multiplexor} Locality-based request reordering. \caption{\label{fig:multiplexor} Locality-based request reordering.
Requests are partitioned into queues. Queue are handled Requests are partitioned into queues. Queue are handled
@ -1362,7 +1362,7 @@ the naive traversal.
\begin{figure}[t] \begin{figure}[t]
\graphdbg{\includegraphics[% \graphdbg{\includegraphics[%
viewport=-13bp 19bp 600bp 280bp, viewport=-13bp 19bp 600bp 280bp,
width=1\columnwidth]{figs/oo7}} width=1\columnwidth]{figs/oo7.pdf}}
%\vspace{-12pt} %\vspace{-12pt}
\caption{\label{fig:oo7} OO7 benchmark style graph traversal. The optimization performs well due to the presence of non-local nodes.} \caption{\label{fig:oo7} OO7 benchmark style graph traversal. The optimization performs well due to the presence of non-local nodes.}
%\vspace{-12pt} %\vspace{-12pt}
@ -1372,7 +1372,7 @@ the naive traversal.
\graphdbg{\includegraphics[% \graphdbg{\includegraphics[%
viewport=-10bp 10bp 525bp 346bp, viewport=-10bp 10bp 525bp 346bp,
clip, clip,
width=1\columnwidth]{figs/trans-closure-hotset}} width=1\columnwidth]{figs/trans-closure-hotset.pdf}}
%\vspace{-12pt} %\vspace{-12pt}
\caption{\label{fig:hotGraph} Hot-set based graph traversal for random \caption{\label{fig:hotGraph} Hot-set based graph traversal for random
graphs with out-degrees of 3 and 9. The multiplexer graphs with out-degrees of 3 and 9. The multiplexer
@ -1445,14 +1445,14 @@ could address. However, it is unclear whether a single interface or
conceptual mapping would meet their needs. Based on experiences with conceptual mapping would meet their needs. Based on experiences with
their system, the authors of StreamBase argue that ``one size fits their system, the authors of StreamBase argue that ``one size fits
all'' database engines are no longer appropriate. Instead, they argue that all'' database engines are no longer appropriate. Instead, they argue that
the market will ``fracture into a collection of independent ... engines''~\cite{oneSizeFitsAll}. This is in contrast to the RISC the market will ``fracture into a collection of independent...engines''~\cite{oneSizeFitsAll}. This is in contrast to the RISC
approach, which attempts to build a database in terms of approach, which attempts to build a database in terms of
interchangeable parts. interchangeable parts.
We agree with the motivations behind RISC databases and StreamBase, We agree with the motivations behind RISC databases and StreamBase,
and believe they complement each other and \yad well. However, or and believe they complement each other and \yad well. However, our
goal differs from these systems; we want to support applications that goal differs from these systems; we want to support applications that
are a poor fit for database systems. However, as \yad matures we we are a poor fit for database systems. As \yad matures we
hope that it will enable a wide range of transactional systems, hope that it will enable a wide range of transactional systems,
including improved DBMSs. including improved DBMSs.

BIN
doc/paper3/Stasis-CameraReady.pdf
View file

Binary file not shown.

BIN
doc/paper3/Stasis-html.tar.gz
View file

Binary file not shown.