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

defined "Hot Set" for Oasys experiement,

Browse source
This commit is contained in:
Sears Russell 2006-08-19 20:02:05 +00:00
parent ee3fb4e7a5
commit 3bc8b20920
1 changed files with 18 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
doc/paper3/LLADD.tex
View file

@ -1369,17 +1369,27 @@ linked the benchmark's executable to the {\tt libmysqld} daemon library,
bypassing the RPC layer. In experiments that used the RPC layer, test bypassing the RPC layer. In experiments that used the RPC layer, test
completion times were orders of magnitude slower. completion times were orders of magnitude slower.
Figure~\ref{fig:OASYS} presents the performance of the three Figure~\ref{fig:OASYS} presents the performance of the three \yad
\yad optimizations, and the \oasys plugins implemented on top of other optimizations, and the \oasys plugins implemented on top of other
systems. As we can see, \yad performs better than the baseline systems. In this test, none of the systems were memory bound. As
systems, which is not surprising, since it is not providing the A we can see, \yad performs better than the baseline systems, which is
property of ACID transactions. (Although it is applying each individual operation atomically.) not surprising, since it is not providing the A property of ACID
transactions. (Although it is applying each individual operation
atomically.)
In non-memory bound systems, the optimizations nearly double \yads In non-memory bound systems, the optimizations nearly double \yads
performance by reducing the CPU overhead of object serialization{\rcs different word?} and performance by reducing the CPU overhead of copying marshalling and
the number of log entries written to disk. In the memory bound test, unmarshalling objects, and by reducing the size of log entries written
we see that update/flush indeed improves memory utilization. to disk.
To determine the effect of the optimization in memory bound systems,
we decreased \yads page cache size, and used O\_DIRECT to bypass the
operating system's disk cache. We then partitioned the set of objects
so that 10\% fit in a {\em hot set} that is small enough to fit into
memory. We then measured \yads performance as we varied the
percentage of object updates that manipulate the hot set. In the
memory bound test, we see that update/flush indeed improves memory
utilization.
\subsection{Manipulation of logical log entries} \subsection{Manipulation of logical log entries}