Rename bookkeeping -> virtual in graphs.

[loba-papers.git] / supercomp11 / supercomp11.tex

diff --git a/supercomp11/supercomp11.tex b/supercomp11/supercomp11.tex
index d03a1d523c85eddcfdcd22280be978cf171a5fb2..36964d1b91b4cd1f6eb05adb146fd0cd3938293b 100644 (file)
--- a/supercomp11/supercomp11.tex
+++ b/supercomp11/supercomp11.tex
@@ -189,11 +189,14 @@ $3$.   If  it  sends  load  to  processor $1$  it  will  not  satisfy  condition
 $x_3^2(t)$.  So we consider that the \emph{ping-pong} condition is probably to
 strong. Currently, we did not try to make another convergence proof without this
 condition or with a weaker condition.
 $x_3^2(t)$.  So we consider that the \emph{ping-pong} condition is probably to
 strong. Currently, we did not try to make another convergence proof without this
 condition or with a weaker condition.

-%
-\FIXME{Develop: We have the feeling that such a weaker condition
-  exists, because (it's not a proof, but) we have never seen any
-  scenario that is not leading to convergence, even with LB-strategies
-  that are not fulfilling these two conditions.}
+
+Nevertheless, we conjecture that such a weaker condition exists.  In fact, we
+have never seen any scenario that is not leading to convergence, even with
+load-balancing strategies that are not exactly fulfilling these two conditions.
+
+It may be the subject of future work to express weaker conditions, and to prove
+that they are sufficient to ensure the convergence of the load-balancing
+algorithm.

 
 \section{Best effort strategy}
 \label{Best-effort}
 
 \section{Best effort strategy}
 \label{Best-effort}


@@ -361,13 +364,25 @@ During the simulation, each processor concurrently runs three threads:
 a \emph{receiving thread}, a \emph{computing thread}, and a
 \emph{load-balancing thread}, which we will briefly describe now.
 
 a \emph{receiving thread}, a \emph{computing thread}, and a
 \emph{load-balancing thread}, which we will briefly describe now.
 

-\paragraph{Receiving thread} The receiving thread is in charge of
-waiting for messages to come, either on the control channel, or on the
-data channel.  Its behavior is sketched by Algorithm~\ref{algo.recv}.
-When a message is received, it is pushed in a buffer of
-received message, to be later consumed by one of the other threads.
-There are two such buffers, one for the control messages, and one for
-the data messages.  The buffers are implemented with a lock-free FIFO
+For the sake of simplicity, a few details were voluntary omitted from
+these descriptions.  For an exhaustive presentation, we refer to the
+actual source code that was used for the experiments%
+\footnote{As mentioned before, our simulator relies on the SimGrid
+  framework~\cite{casanova+legrand+quinson.2008.simgrid}.  For the
+  experiments, we used a pre-release of SimGrid 3.7 (Git commit
+  67d62fca5bdee96f590c942b50021cdde5ce0c07, available from
+  \url{https://gforge.inria.fr/scm/?group_id=12})}, and which is
+available at
+\url{http://info.iut-bm.univ-fcomte.fr/staff/giersch/software/loba.tar.gz}.
+
+\subsubsection{Receiving thread}
+
+The receiving thread is in charge of waiting for messages to come, either on the
+control channel, or on the data channel.  Its behavior is sketched by
+Algorithm~\ref{algo.recv}.  When a message is received, it is pushed in a buffer
+of received message, to be later consumed by one of the other threads.  There
+are two such buffers, one for the control messages, and one for the data
+messages.  The buffers are implemented with a lock-free FIFO

 \cite{sutter.2008.writing} to avoid contention between the threads.
 
 \begin{algorithm}
 \cite{sutter.2008.writing} to avoid contention between the threads.
 
 \begin{algorithm}


@@ -392,9 +407,10 @@ the data messages.  The buffers are implemented with a lock-free FIFO
   }
 \end{algorithm}
 
   }
 \end{algorithm}
 

-\paragraph{Computing thread} The computing thread is in charge of the
-real load management.  As exposed in Algorithm~\ref{algo.comp}, it
-iteratively runs the following operations:
+\subsubsection{Computing thread}
+
+The computing thread is in charge of the real load management.  As exposed in
+Algorithm~\ref{algo.comp}, it iteratively runs the following operations:

 \begin{itemize}
 \item if some load was received from the neighbors, get it;
 \item if there is some load to send to the neighbors, send it;
 \begin{itemize}
 \item if some load was received from the neighbors, get it;
 \item if there is some load to send to the neighbors, send it;


@@ -433,10 +449,11 @@ example, when the current load is near zero).
   }
 \end{algorithm}
 
   }
 \end{algorithm}
 

-\paragraph{Load-balancing thread} The load-balancing thread is in
-charge of running the load-balancing algorithm, and exchange the
-control messages.  As shown in Algorithm~\ref{algo.lb}, it iteratively
-runs the following operations:
+\subsubsection{Load-balancing thread}
+
+The load-balancing thread is in charge of running the load-balancing algorithm,
+and exchange the control messages.  As shown in Algorithm~\ref{algo.lb}, it
+iteratively runs the following operations:

 \begin{itemize}
 \item get the control messages that were received from the neighbors;
 \item run the load-balancing algorithm;
 \begin{itemize}
 \item get the control messages that were received from the neighbors;
 \item run the load-balancing algorithm;


@@ -463,19 +480,7 @@ runs the following operations:
   }
 \end{algorithm}
 
   }
 \end{algorithm}
 

-\paragraph{}
-For the sake of simplicity, a few details were voluntary omitted from
-these descriptions.  For an exhaustive presentation, we refer to the
-actual source code that was used for the experiments%
-\footnote{As mentioned before, our simulator relies on the SimGrid
-  framework~\cite{casanova+legrand+quinson.2008.simgrid}.  For the
-  experiments, we used a pre-release of SimGrid 3.7 (Git commit
-  67d62fca5bdee96f590c942b50021cdde5ce0c07, available from
-  \url{https://gforge.inria.fr/scm/?group_id=12})}, and which is
-available at
-\url{http://info.iut-bm.univ-fcomte.fr/staff/giersch/software/loba.tar.gz}.
-
-\FIXME{ajouter des détails sur la gestion de la charge virtuelle ?
+\paragraph{}\FIXME{ajouter des détails sur la gestion de la charge virtuelle ?

 par ex, donner l'idée générale de l'implémentation.  l'idée générale est déja décrite en section~\ref{Virtual load}}
 
 \subsection{Experimental contexts}
 par ex, donner l'idée générale de l'implémentation.  l'idée générale est déja décrite en section~\ref{Virtual load}}
 
 \subsection{Experimental contexts}


@@ -485,7 +490,7 @@ In order to assess the performances of our algorithms, we ran our
 simulator with various parameters, and extracted several metrics, that
 we will describe in this section.
 
 simulator with various parameters, and extracted several metrics, that
 we will describe in this section.
 

-\paragraph{Load balancing strategies}
+\subsubsection{Load balancing strategies}

 
 Several load balancing strategies were compared.  We ran the experiments with
 the \emph{Best effort}, and with the \emph{Makhoul} strategies.  \emph{Best
 
 Several load balancing strategies were compared.  We ran the experiments with
 the \emph{Best effort}, and with the \emph{Makhoul} strategies.  \emph{Best


@@ -504,7 +509,7 @@ To summarize the different load balancing strategies, we have:
 %
 This gives us as many as $4\times 2\times 2 = 16$ different strategies.
 
 %
 This gives us as many as $4\times 2\times 2 = 16$ different strategies.
 

-\paragraph{End of the simulation}
+\subsubsection{End of the simulation}

 
 The simulations were run until the load was nearly balanced among the
 participating nodes.  More precisely the simulation stops when each node holds
 
 The simulations were run until the load was nearly balanced among the
 participating nodes.  More precisely the simulation stops when each node holds


@@ -517,7 +522,7 @@ real application we would have chosen a decentralized convergence detection
 algorithm, like the one described by Bahi, Contassot-Vivier, Couturier, and
 Vernier in \cite{10.1109/TPDS.2005.2}.
 
 algorithm, like the one described by Bahi, Contassot-Vivier, Couturier, and
 Vernier in \cite{10.1109/TPDS.2005.2}.
 

-\paragraph{Platforms}
+\subsubsection{Platforms}

 
 In order to show the behavior of the different strategies in different
 settings, we simulated the executions on two sorts of platforms.  These two
 
 In order to show the behavior of the different strategies in different
 settings, we simulated the executions on two sorts of platforms.  These two


@@ -543,7 +548,7 @@ processor speeds were normalized, and we arbitrarily chose to fix them to
 Then we derived each sort of platform with four different number of computing
 nodes: 16, 64, 256, and 1024 nodes.
 
 Then we derived each sort of platform with four different number of computing
 nodes: 16, 64, 256, and 1024 nodes.
 

-\paragraph{Configurations}
+\subsubsection{Configurations}

 
 The distributed processes of the application were then logically organized along
 three possible topologies: a line, a torus or an hypercube.  We ran tests where
 
 The distributed processes of the application were then logically organized along
 three possible topologies: a line, a torus or an hypercube.  We ran tests where


@@ -586,7 +591,7 @@ time.
 Anyway, all these the experiments represent more than 240 hours of computing
 time.
 
 Anyway, all these the experiments represent more than 240 hours of computing
 time.
 

-\paragraph{Metrics}
+\subsubsection{Metrics}

 
 In order to evaluate and compare the different load balancing strategies we had
 to define several metrics.  Our goal, when choosing these metrics, was to have
 
 In order to evaluate and compare the different load balancing strategies we had
 to define several metrics.  Our goal, when choosing these metrics, was to have


@@ -630,6 +635,27 @@ With these constraints in mind, we defined the following metrics:
 \subsection{Validation of our approaches}
 \label{Results}
 
 \subsection{Validation of our approaches}
 \label{Results}
 

+\begin{figure}
+  \centering
+  \includegraphics[width=.5\linewidth]{data/graphs/R1-10:1-cluster-line}
+  \includegraphics[width=.5\linewidth]{data/graphs/R1-10:1-cluster-torus}%
+  \hfill%%
+  \includegraphics[width=.5\linewidth]{data/graphs/R1-10:1-cluster-hcube}
+  \caption{Results \textbf{[FIXME]}}
+  \label{fig.results}
+\end{figure}
+
+Dans cet ordre:
+...
+- comparer be/makhoul -> be tient la route
+        -> en réel uniquement
+- valider l'extension virtual load -> c'est 'achement bien
+- proposer le -k -> ça peut aider dans certains cas
+- conclure avec la version entière -> on n'a pas l'effet d'escalier !
+Q: comment inclure les types/tailles de platesformes ?
+Q: comment faire des moyennes ?
+Q: comment introduire les distrib 1/N ?
+...

 
 On constate quoi (vérifier avec les chiffres)?
 \begin{itemize}
 
 On constate quoi (vérifier avec les chiffres)?
 \begin{itemize}


@@ -647,11 +673,11 @@ On constate quoi (vérifier avec les chiffres)?
 
 \item volume de comm? souvent, besteffort/plain en fait plus. pourquoi?
 
 
 \item volume de comm? souvent, besteffort/plain en fait plus. pourquoi?
 

+\item répartition initiale de la charge ?
+

 \item integer mode sur topo. line n'a jamais fini en plain? vérifier si ce n'est
   pas à cause de l'effet d'escalier que bk est capable de gommer.
 
 \item integer mode sur topo. line n'a jamais fini en plain? vérifier si ce n'est
   pas à cause de l'effet d'escalier que bk est capable de gommer.
 

-\item répartition initiale de la charge ?
-

 \end{itemize}
 
 \begin{itshape}
 \end{itemize}
 
 \begin{itshape}


@@ -692,6 +718,7 @@ Taille : 10 100 très gros
   the Mésocentre de calcul de Franche-Comté.
 \end{acknowledgements}
 
   the Mésocentre de calcul de Franche-Comté.
 \end{acknowledgements}
 

+\FIXME{find and add more references}

 \bibliographystyle{spmpsci}
 \bibliography{biblio}
 
 \bibliographystyle{spmpsci}
 \bibliography{biblio}