Merge branch 'main' into next-0.10

4 files changed, 390 insertions, 0 deletions

diff --git a/doc/talks/2024-01-12-seed/.gitignore b/doc/talks/2024-01-12-seed/.gitignore
new file mode 100644
index 00000000..b7e0ced2
--- /dev/null
+++ b/doc/talks/2024-01-12-seed/.gitignore
@@ -0,0 +1,10 @@
+*
+
+!*.txt
+!*.md
+!*.tex
+
+!talk.pdf
+!Makefile
+!.gitignore
+
diff --git a/doc/talks/2024-01-12-seed/Makefile b/doc/talks/2024-01-12-seed/Makefile
new file mode 100644
index 00000000..5f0befbe
--- /dev/null
+++ b/doc/talks/2024-01-12-seed/Makefile
@@ -0,0 +1,10 @@
+ASSETS=../assets/deuxfleurs.pdf
+
+talk.pdf: talk.tex $(ASSETS)
+	pdflatex talk.tex
+
+assets/%.pdf: assets/%.svg
+	inkscape -D -z --file=$^ --export-pdf=$@
+
+assets/%.pdf_tex: assets/%.svg
+	inkscape -D -z --file=$^ --export-pdf=$@ --export-latex
diff --git a/doc/talks/2024-01-12-seed/talk.pdf b/doc/talks/2024-01-12-seed/talk.pdf
new file mode 100644
index 00000000..85c3bcde
--- /dev/null
+++ b/doc/talks/2024-01-12-seed/talk.pdf
diff --git a/doc/talks/2024-01-12-seed/talk.tex b/doc/talks/2024-01-12-seed/talk.tex
new file mode 100644
index 00000000..cd6c4681
--- /dev/null
+++ b/doc/talks/2024-01-12-seed/talk.tex
@@ -0,0 +1,370 @@
+\nonstopmode
+\documentclass[aspectratio=169]{beamer}
+\usepackage[utf8]{inputenc}
+% \usepackage[frenchb]{babel}
+\usepackage{amsmath}
+\usepackage{mathtools}
+\usepackage{breqn}
+\usepackage{multirow}
+\usetheme{boxes}
+\usepackage{graphicx}
+\usepackage{import}
+\usepackage{adjustbox}
+%\useoutertheme[footline=authortitle,subsection=false]{miniframes}
+%\useoutertheme[footline=authorinstitute,subsection=false]{miniframes}
+\useoutertheme{infolines}
+\setbeamertemplate{headline}{}
+
+\beamertemplatenavigationsymbolsempty
+
+\definecolor{TitleOrange}{RGB}{255,137,0}
+\setbeamercolor{title}{fg=TitleOrange}
+\setbeamercolor{frametitle}{fg=TitleOrange}
+
+\definecolor{ListOrange}{RGB}{255,145,5}
+\setbeamertemplate{itemize item}{\color{ListOrange}$\blacktriangleright$}
+
+\definecolor{verygrey}{RGB}{70,70,70}
+\setbeamercolor{normal text}{fg=verygrey}
+
+
+\usepackage{tabu}
+\usepackage{multicol}
+\usepackage{vwcol}
+\usepackage{stmaryrd}
+\usepackage{graphicx}
+
+\usepackage[normalem]{ulem}
+
+\AtBeginSection[]{
+  \begin{frame}
+  \vfill
+  \centering
+  \begin{beamercolorbox}[sep=8pt,center,shadow=true,rounded=true]{title}
+    \usebeamerfont{title}\insertsectionhead\par%
+  \end{beamercolorbox}
+  \vfill
+  \end{frame}
+}
+
+\title{Garage}
+\subtitle{a lightweight and robust geo-distributed data storage system}
+\author{Alex Auvolat, Deuxfleurs}
+\date{SEED webinar, 2024-01-12}
+
+\begin{document}
+
+% \begin{frame}
+% 	\centering
+% 	\includegraphics[width=.3\linewidth]{../../sticker/Garage.png}
+% 	\vspace{1em}
+% 
+% 	{\large\bf Alex Auvolat, Deuxfleurs Association}
+% 	\vspace{1em}
+% 
+% 	\url{https://garagehq.deuxfleurs.fr/}
+% 
+% 	%Matrix channel: \texttt{\#garage:deuxfleurs.fr}
+% \end{frame}
+
+\begin{frame}
+	%\frametitle{Who I am}
+	\begin{columns}[t]
+		\begin{column}{.2\textwidth}
+			\centering
+			\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/alex.jpg}
+		\end{column}
+		\begin{column}{.6\textwidth}
+			\textbf{Alex Auvolat}\\
+			Member of Deuxfleurs, lead developer of Garage
+		\end{column}
+		\begin{column}{.2\textwidth}
+			~
+		\end{column}
+	\end{columns}
+	\vspace{.5em}
+
+	\begin{columns}[t]
+		\begin{column}{.2\textwidth}
+			\centering
+			\adjincludegraphics[width=.6\linewidth, valign=t]{../../logo/garage-notext.png}
+		\end{column}
+		\begin{column}{.6\textwidth}
+			\\\textbf{Garage}\\
+			A self-hosted alternative to S3 for object storage
+		\end{column}
+		\begin{column}{.2\textwidth}
+			~
+		\end{column}
+	\end{columns}
+	\vspace{2em}
+
+	\begin{columns}[t]
+		\begin{column}{.2\textwidth}
+			\centering
+			\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/deuxfleurs.pdf}
+		\end{column}
+		\begin{column}{.6\textwidth}
+			\textbf{Deuxfleurs}\\
+			A non-profit self-hosting collective,\\
+			member of the CHATONS network
+		\end{column}
+		\begin{column}{.2\textwidth}
+			\centering
+			\adjincludegraphics[width=.7\linewidth, valign=t]{../assets/logo_chatons.png}
+		\end{column}
+	\end{columns}
+
+\end{frame}
+
+\begin{frame}
+	\frametitle{Stable vs Resilient}
+
+	\hspace{1em}
+	\begin{minipage}{7cm}
+		\textbf{Building a "stable" system:}
+		\vspace{1em}
+
+		Enterprise-grade systems typically employ:
+		\vspace{1em}
+		\begin{itemize}
+			\item RAID
+			\item Redundant power grid + UPS
+			\item Redundant Internet connections
+			\item Low-latency links
+			\item ... 
+		\end{itemize}
+		\vspace{1em}
+		$\to$ costly, only worth at DC scale\\
+		$\to$ still risk of DC-level incident...
+	\end{minipage}
+	\hfill
+	\begin{minipage}{7cm}
+		\textbf{Building a \underline{resilient} system:}
+		\vspace{1em}
+
+		An alternative, cheaper way:
+		\vspace{1em}
+		\begin{itemize}
+			\item Commodity hardware \\(e.g. old desktop PCs)
+				\vspace{.5em}
+			\item Commodity Internet \\(e.g. FTTB, FTTH) and power grid
+				\vspace{.5em}
+			\item \textbf{Geographical redundancy} \\(multi-site replication)
+		\end{itemize}
+		\vspace{1.5em}
+	\end{minipage}
+	\hspace{1em}
+\end{frame}
+
+\begin{frame}
+	\frametitle{Example: our infrastructure at Deuxfleurs}
+	\only<1>{
+		\begin{center}
+			\includegraphics[width=.8\linewidth]{../assets/neptune.jpg}
+		\end{center}
+	}
+	\only<2>{
+		\begin{center}
+			\includegraphics[width=.8\linewidth]{../assets/atuin.jpg}
+		\end{center}
+	}
+	\only<3>{
+		\begin{center}
+			\includegraphics[width=.8\linewidth]{../assets/inframap_jdll2023.pdf}
+		\end{center}
+	}
+\end{frame}
+
+\begin{frame}
+	\frametitle{Object storage: simpler than file systems}
+
+	\begin{minipage}{6cm}
+		Only two operations:
+		\vspace{1em}
+		\begin{itemize}
+			\item Put an object at a key
+				\vspace{1em}
+			\item Retrieve an object from its key
+		\end{itemize}
+		\vspace{1em}
+		{\footnotesize (and a few others)}
+
+		\vspace{1em}
+		Sufficient for many applications!
+	\end{minipage}
+	\hfill
+	\begin{minipage}{8cm}
+		\begin{center}
+			\vspace{2em}
+			\includegraphics[height=6em]{../2020-12-02_wide-team/img/Amazon-S3.jpg}
+			\hspace{2em}
+			\includegraphics[height=5em]{../assets/minio.png}
+
+			\vspace{2em}
+			\includegraphics[height=6em]{../../logo/garage_hires_crop.png}
+		\end{center}
+		\vspace{1em}
+	\end{minipage}
+\end{frame}
+
+
+\begin{frame}
+	\frametitle{The data model of object storage}
+	Object storage is basically a key-value store:
+	\vspace{1em}
+
+		\begin{center}
+		\begin{tabular}{|l|p{8cm}|}
+			\hline
+			\textbf{Key: file path + name} & \textbf{Value: file data + metadata} \\
+			\hline
+			\hline
+			\texttt{index.html} &
+				\texttt{Content-Type: text/html; charset=utf-8} \newline
+				\texttt{Content-Length: 24929} \newline
+				\texttt{<binary blob>} \\ 
+			\hline
+			\texttt{img/logo.svg} &
+				\texttt{Content-Type: text/svg+xml} \newline
+				\texttt{Content-Length: 13429} \newline
+				\texttt{<binary blob>} \\ 
+			\hline
+			\texttt{download/index.html} &
+				\texttt{Content-Type: text/html; charset=utf-8} \newline
+				\texttt{Content-Length: 26563} \newline
+				\texttt{<binary blob>} \\ 
+			\hline
+		\end{tabular}
+		\end{center}
+\end{frame}
+
+\begin{frame}
+	\frametitle{Implementation: consensus vs weak consistency}
+
+	\hspace{1em}
+	\begin{minipage}{7cm}
+		\textbf{Consensus-based systems:}
+		\vspace{1em}
+		\begin{itemize}
+			\item \textbf{Leader-based:} a leader is elected to coordinate
+				all reads and writes
+				\vspace{1em}
+			\item Allows for \textbf{sequential reasoning}:
+				program as if running on a single machine
+				\vspace{1em}
+			\item Serializability is one of the \\
+				\textbf{strongest consistency guarantees}
+				\vspace{1em}
+			\item \textbf{Costly}, the leader is a bottleneck;
+				leader elections on failure take time
+		\end{itemize}
+	\end{minipage}
+	\hfill
+	\begin{minipage}{7cm} \visible<2->{
+		\textbf{Weakly consistent systems:}
+		\vspace{1em}
+		\begin{itemize}
+			\item \textbf{Nodes are equivalent}, any node
+				can originate a read or write operation
+				\vspace{1em}
+			\item \textbf{Operations must be independent},
+				conflicts are resolved after the fact
+				\vspace{1em}
+			\item Strongest achievable consistency:\\
+				\textbf{read-after-write consistency}\\(using quorums)
+				\vspace{1em}
+			\item \textbf{Fast}, no single bottleneck;\\
+				works transparently with offline nodes
+		\end{itemize}
+	} \end{minipage}
+	\hspace{1em}
+\end{frame}
+
+\begin{frame}
+	\frametitle{Why avoid consensus?}
+	Consensus can be implemented reasonably well in practice, so why avoid it?
+	\vspace{2em}
+	\begin{itemize}
+		\item \textbf{Software complexity:} RAFT and PAXOS are complex beasts;\\
+			harder to prove, harder to reason about
+			\vspace{1.5em}
+		\item \textbf{Performance issues:}
+			\vspace{1em}
+			\begin{itemize}
+				\item Taking a decision may take an \textbf{arbitrary number of steps} (in adverse scenarios)
+					\vspace{1em}
+				\item The leader is a \textbf{bottleneck} for all requests;\\
+					even in leaderless approaches, \textbf{all nodes must process all operations in order}
+					\vspace{1em}
+				\item Particularly \textbf{sensitive to higher latency} between nodes
+			\end{itemize}
+	\end{itemize}
+\end{frame}
+
+\begin{frame}
+	\frametitle{Objective: the right level of consistency for Garage}
+
+	\underline{Constraints:} slow network (geographical distance), node unavailability/crashes\\
+	\underline{Objective:} maximize availability, maintain an \emph{appropriate level of consistency}\\
+	\vspace{1em}
+	\begin{enumerate}
+		\item<2-> \textbf{Weak consistency for most things}\\
+			\vspace{1em}
+			\underline{Example:} \texttt{PutObject}\\
+			\vspace{.5em}
+			If two clients write the same
+			object at the same time, one of the two is implicitly overwritten.
+			No need to coordinate, use a \emph{last-writer-wins register}.
+			\vspace{1em}
+		\item<3-> \textbf{Stronger consistency only when necessary}\\
+			\vspace{1em}
+			\underline{Example:} \texttt{CreateBucket}\\
+			\vspace{.5em}
+			A bucket is a reserved name in a shared namespace,
+			two clients should be prevented from both creating the same bucket
+			(\emph{mutual exclusion}).
+	\end{enumerate}
+\end{frame}
+
+\begin{frame}
+	\frametitle{The possibility of \emph{leaderless consensus}}
+	Currently, Garage \emph{only has weak consistency}. Is fast, but \texttt{CreateBucket} is broken!
+
+	\visible<2->{
+		\vspace{1em}
+		Leaderless consensus (Antoniadis et al., 2023) alleviates issues with RAFT and PAXOS:
+			\vspace{1em}
+		\begin{itemize}
+			\item \textbf{No leader.} All nodes participate equally at each time step,
+				and different nodes can be unavailable at different times without issues.
+				\\ \vspace{.5em} $\to$ better tolerance to the high latency (remove bottleneck issue)
+				\\ $\to$ tolerates crash transparently
+				\vspace{1em}
+			\item \textbf{Simpler formalization.} The algorithm is very simple to express and to analyze in mathematical terms.
+		\end{itemize}
+	}
+	\visible<3->{
+		\vspace{1em}
+		One of the possible subjects for this PhD:
+		\\$\to$ \emph{integration of leaderless consensus in Garage} + testing + perf eval, etc.
+	}
+\end{frame}
+
+\begin{frame}
+	\begin{center}
+			\includegraphics[width=.25\linewidth]{../../logo/garage_hires.png}\\
+			\vspace{-1em}
+		\url{https://garagehq.deuxfleurs.fr/}\\
+		\url{mailto:garagehq@deuxfleurs.fr}\\
+		\texttt{\#garage:deuxfleurs.fr} on Matrix
+
+		\vspace{1.5em}
+			\includegraphics[width=.06\linewidth]{../assets/rust_logo.png}
+			\includegraphics[width=.13\linewidth]{../assets/AGPLv3_Logo.png}
+	\end{center}
+\end{frame}
+
+\end{document}
+
+%% vim: set ts=4 sw=4 tw=0 noet spelllang=en :