Merge branch 'master' of http://git.hps.vi4io.org/eugen.betke/mistral-io-datasets into master

paper/main.tex

@@ -213,12 +213,12 @@ We believe this will then allow a near-online analysis of a job.
   \begin{subfigure}{0.31\textwidth}
   \centering
   \includegraphics[width=\textwidth]{progress_4296426-out-boxplot}
-  \caption{Job-S} \label{fig:perf-job-S}
+  \caption{Job-S (runtime=15,551\,s, segments=25)} \label{fig:perf-job-S}
   \end{subfigure}
   \begin{subfigure}{0.31\textwidth}
   \centering
   \includegraphics[width=\textwidth]{progress_5024292-out-boxplot}
-  \caption{Job-M} \label{fig:perf-job-M}
+  \caption{Job-M (runtime=28,828\,s, segments=48)} \label{fig:perf-job-M}
   \end{subfigure}
   \begin{subfigure}{0.31\textwidth}
   \centering
@@ -226,7 +226,7 @@ We believe this will then allow a near-online analysis of a job.
   \caption{Job-L} \label{fig:perf-job-L}
   \end{subfigure}
 
-  \caption{Runtime overview for all algorithms and jobs}
+  \caption{Runtime of the algorithms to compute the similarity to reference jobs}
   \label{fig:performance}
 \end{figure}
 
@@ -333,50 +333,49 @@ For Job-L, the two hex algorithms include with (12 and 13) a bit more diverse us
 \end{subfigure}
 
 
-\caption{User information for each jobs}
+\caption{User information for all 100 top ranked jobs}
 \label{fig:userids}
 \end{figure}
 
 \begin{figure}
-\begin{subfigure}{0.31\textwidth}
-\centering
-\includegraphics[width=\textwidth]{job_similarities_4296426-out/jobs-nodes}
-\caption{Job-S} \label{fig:nodes-job-S}
-\end{subfigure}
-\begin{subfigure}{0.31\textwidth}
+%\begin{subfigure}{0.31\textwidth}
+%\centering
+%\includegraphics[width=\textwidth]{job_similarities_4296426-out/jobs-nodes}
+%\caption{Job-S} \label{fig:nodes-job-S}
+%\end{subfigure}
+\begin{subfigure}{0.48\textwidth}
 \centering
 \includegraphics[width=\textwidth]{job_similarities_5024292-out/jobs-nodes}
-\caption{Job-M} \label{fig:nodes-job-M}
+\caption{Job-M (ref. job runs on 128 nodes)} \label{fig:nodes-job-M}
 \end{subfigure}
-\begin{subfigure}{0.31\textwidth}
+\begin{subfigure}{0.48\textwidth}
 \centering
 \includegraphics[width=\textwidth]{job_similarities_7488914-out/jobs-nodes}
-\caption{Job-L} \label{fig:nodes-job-L}
+\caption{Job-L (reference job runs on 20 nodes)} \label{fig:nodes-job-L}
 \end{subfigure}
 \centering
-\caption{Distribution of node counts}
+\caption{Distribution of node counts (for Job-S nodes=1 in all cases)}
 \label{fig:nodes-job}
 \end{figure}
 
-
 \begin{figure}
 \begin{subfigure}{0.31\textwidth}
 \centering
 \includegraphics[width=\textwidth]{job_similarities_4296426-out/jobs-elapsed}
-\caption{Job-S} \label{fig:runtime-job-S}
+\caption{Job-S ($job=10^{4.19}$)} \label{fig:runtime-job-S}
 \end{subfigure}
 \begin{subfigure}{0.31\textwidth}
 \centering
 \includegraphics[width=\textwidth]{job_similarities_5024292-out/jobs-elapsed}
-\caption{Job-M} \label{fig:runtime-job-M}
+\caption{Job-M ($job=10^{4.46}$)} \label{fig:runtime-job-M}
 \end{subfigure}
 \begin{subfigure}{0.31\textwidth}
 \centering
 \includegraphics[width=\textwidth]{job_similarities_7488914-out/jobs-elapsed}
-\caption{Job-L} \label{fig:runtime-job-L}
+\caption{Job-L ($job=10^{5.3}$)} \label{fig:runtime-job-L}
 \end{subfigure}
 \centering
-\caption{Distribution of elapsed runtime}
+\caption{Distribution of runtime for all 100 top ranked jobs}
 \label{fig:runtime-job}
 \end{figure}
 

scripts/plot-performance.R

@@ -14,8 +14,8 @@ data = read.csv(file)
 
 e = data %>% filter(jobs_done >= (jobs_total - 9998))
 e$time_per_100k = e$elapsed / (e$jobs_done / 100000)
-ggplot(e, aes(alg_name, time_per_100k, fill=alg_name)) + geom_boxplot()  + theme(legend.position=c(0.2, 0.7)) + xlab("Algorithm") + ylab("Runtime in s per 100k jobs") + stat_summary(aes(label=round(..y..,0)), position = position_nudge(x = 0, y = 250), fun=mean, geom="text", size=4)
-ggsave(paste(prefix, "-boxplot.png", sep=""), width=5, height=4)
+ggplot(e, aes(alg_name, time_per_100k, fill=alg_name)) + geom_boxplot()  + theme(legend.position=c(0.2, 0.7)) + xlab("Algorithm") + ylab("Runtime in s per 100k jobs") + stat_summary(aes(label=round(..y..,0)), position = position_nudge(x = 0, y = 200), fun=mean, geom="text", size=4) + theme(legend.title = element_blank())
+ggsave(paste(prefix, "-boxplot.png", sep=""), width=4, height=4)
 
 # Development when adding more jobs
 ggplot(data, aes(x=jobs_done, y=elapsed, color=alg_name)) + geom_point() + ylab("Cummulative runtime in s") + xlab("Jobs processed") + theme(legend.position = "bottom") #+ scale_x_log10() + scale_y_log10()

scripts/plot.R

@@ -122,7 +122,7 @@ for (alg_name in levels(data$alg_name)){
   res.jobs = rbind(res.jobs, cbind(alg_name, metadata[metadata$jobid %in% result[, alg_name],]))
 }
 
-ggplot(res.jobs, aes(alg_name, total_nodes, fill=alg_name)) + geom_boxplot() + scale_y_continuous(trans = log2_trans(), breaks = trans_breaks("log2", function(x) 2^x), labels = trans_format("log2", math_format(2^.x))) + theme(legend.position = "none")
+ggplot(res.jobs, aes(alg_name, total_nodes, fill=alg_name)) + geom_boxplot() + scale_y_continuous(trans = log2_trans(), breaks = trans_breaks("log2", function(x) 2^x), labels = trans_format("log2", math_format(2^.x))) + theme(legend.position = "none") + xlab("Algorithm")
 ggsave("jobs-nodes.png", width=6, height=4)
 
 ggplot(res.jobs, aes(alg_name, elapsed, fill=alg_name)) + geom_boxplot() + scale_y_continuous(trans = log2_trans(), breaks = trans_breaks("log10", function(x) 10^x), labels = trans_format("log10", math_format(10^.x))) + ylab("Runtime in s") + xlab("Algorithm")  + theme(legend.position = "none")