carlnues
/
paper-KeepItSimple
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

added cdf graph for Spotify study

master
carlnues@buffalo.edu 2023-08-24 14:55:46 -04:00
parent d3866ad41b
commit 85f21fcead
2 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
figures/graph_time_per_freq_spot.pdf Normal file
View File

Binary file not shown.

9
sections/evaluation.tex
View File

@ -22,6 +22,13 @@
\label{fig:time_per_freq_yt}
\end{figure*}
\begin{figure*}
\centering
\includegraphics[width=.95\linewidth]{figures/graph_time_per_freq_spot.pdf}
\bfcaption{Average time spent per CPU at a given frequency under the default policy for a :30 scripted Spotify interaction (Average of 10 runs, 90\% confidence)}
\label{fig:time_per_freq_spot}
\end{figure*}
\begin{figure*}
\centering
\includegraphics[width=.95\linewidth]{figures/graph_nonidletime_yt.pdf}
@ -93,7 +100,7 @@ On all workloads, \systemname and truncated \schedutil both outperform regular \
\subsection{Ramp-Up Times}
To attribute the improvement in performance, we measure the CPU frequencies selected by \schedutil and \systemname, respectively.
\Cref{fig:time_per_freq_fb,fig:time_per_freq_yt} plot a CDF of the difference between these two selections.
\Cref{fig:time_per_freq_fb,fig:time_per_freq_yt,fig:time_per_freq_spot} plot a CDF of the difference between these two selections.
We note that for a significant fraction of the workload (5\% for Facebook, 15\% for Youtube), the frequency selected by \schedutil is significantly (up to 50\%) lower.
This is \schedutil's ramp-up period, where it selects frequencies lower than $\fenergy$.
We attribute the improved performance for both governors to eliminating the ramp-up period where \systemname selects speeds below $\fenergy$.