\nonstopmode
\documentclass[aspectratio=169,xcolor={svgnames}]{beamer}
\usepackage[utf8]{inputenc}
% \usepackage[frenchb]{babel}
\usepackage{amsmath}
\usepackage{mathtools}
\usepackage{breqn}
\usepackage{multirow}
\usetheme{boxes}
\usepackage{graphicx}
\usepackage{import}
\usepackage{adjustbox}
\usepackage[absolute,overlay]{textpos}
%\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, an S3 backend as reliable as possible}
\author{Garage Authors}
\date{JoSy S3, 2025-10-08}

\begin{document}

\begin{frame}
	\centering
	\includegraphics[width=.3\linewidth]{../../sticker/Garage.png}
	\vspace{1em}

	{\large\bf Garage, an S3 backend as reliable as possible}
	\vspace{1em}

		\url{https://garagehq.deuxfleurs.fr/}\\
		\url{mailto:garagehq@deuxfleurs.fr}\\
		\texttt{\#garage:deuxfleurs.fr} on Matrix
\end{frame}


\section{Meet Garage}

\begin{frame}
	\frametitle{A non-profit initiative}


	\begin{columns}[t]
		\begin{column}{.2\textwidth}
			\centering
			\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/logos/deuxfleurs.pdf}
		\end{column}
		\begin{column}{.8\textwidth}
			\textbf{Part of a degrowth initiative}\\
			Garage has been created at Deuxfleurs where we experiment running Internet services without datacenter on commodity and refurbished hardware.
		\end{column}

	\end{columns}
	\vspace{2em}
	\begin{columns}[t]
		\begin{column}{.2\textwidth}
			\centering
			\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/community.png}
		\end{column}
		\begin{column}{.8\textwidth}
			\textbf{Developed by a community}\\
			{\small Some recent contributors: Arthur C, Charles H, dongdigua, Etienne L, Jonah A, Julien K, Lapineige, MagicRR, Milas B, Niklas M, RockWolf, Schwitzd, trinity-1686a, Xavier S,  babykart, Baptiste J, eddster2309, James O'C, Joker9944, Maximilien R, Renjaya RZ, Yureka...}
		\end{column}

	\end{columns}
	\vspace{2em}
	\begin{columns}[t]
		\begin{column}{.2\textwidth}
			\centering
			\adjincludegraphics[width=.5\linewidth, valign=t]{../assets/logos/AGPLv3_Logo.png}
		\end{column}
		\begin{column}{.8\textwidth}
			\textbf{Owned by nobody, open-core is impossible, zero VC money}\\
			AGPL + no Contributor License Agreement = Garage ownership spreads among hundredth of contributors.
		\end{column}

	\end{columns}
\end{frame}

\begin{frame}
	\frametitle{Getting support for Garage}
	\begin{columns}[t]
		\begin{column}{.2\textwidth}
			\centering
			\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/alex.jpg}
		\end{column}
		\begin{column}{.4\textwidth}
			\textbf{Alex Auvolat}\\
			PhD; co-founder of Deuxfleurs\\
			Garage maintainer, Freelance
		\end{column}
		\begin{column}{.3\textwidth}
			\centering
			\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/support.png}
		\end{column}
		\begin{column}{.1\textwidth}
			~
		\end{column}
	\end{columns}
	\vspace{2em}
	\begin{columns}[t]
		\begin{column}{.2\textwidth}
			\centering
			\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/quentin.jpg}
		\end{column}
		\begin{column}{.4\textwidth}
			\textbf{Quentin Dufour}\\
			PhD; co-founder of Deuxfleurs\\
			Garage contributor, Freelance
		\end{column}
		\begin{column}{.4\textwidth}
			For support requests, write at: \\
			\url{garagehq@deuxfleurs.fr}
		\end{column}
	\end{columns}
	\vspace{2em}
	\begin{columns}[t]
		\begin{column}{.2\textwidth}
			\centering
			\adjincludegraphics[width=.4\linewidth, valign=t]{../assets/armael.jpg}
		\end{column}
		\begin{column}{.4\textwidth}
			\textbf{Armaël Guéneau}\\
			PhD; member of Deuxfleurs\\
			Garage contributor, Freelance
		\end{column}
		\begin{column}{.4\textwidth}
			Eligible: email support, architecture design, specific feature development, etc.
		\end{column}
	\end{columns}


\end{frame}

\begin{frame}
	\frametitle{Our initial goal}

	\centering
	\Large

	Being a self-sovereign community to be free of our degrowth choice

	$\big\downarrow$

	As web citizens, datacenters are big black boxes. \\
	We want to leave them to autonoumously manage our servers.

	$\big\downarrow$

	We want reliable services without relying on dedicated hardware or places.

\end{frame}

\begin{frame}
	\frametitle{Building a resilient system with cheap stuff}

	\only<1,4-7>{
		\begin{itemize}
			\item \textcolor<5->{gray}{Commodity hardware (e.g. old desktop PCs)\\
				\vspace{.5em}
				\visible<4->{{\footnotesize (can die at any time)}}}
				\vspace{1.5em}
			\item<5-> \textcolor<7->{gray}{Regular Internet (e.g. FTTB, FTTH) and power grid connections\\
				\vspace{.5em}
				\visible<6->{{\footnotesize (can be unavailable randomly)}}}
				\vspace{1.5em}
			\item<7-> \textbf{Geographical redundancy} (multi-site replication)
		\end{itemize}
	}
	\only<2>{
		\begin{center}
			\includegraphics[width=.8\linewidth]{../assets/neptune.jpg}
		\end{center}
	}
	\only<3>{
		\begin{center}
			\includegraphics[width=.8\linewidth]{../assets/atuin.jpg}
		\end{center}
	}
	\only<8>{
		\begin{center}
			\includegraphics[width=.8\linewidth]{../assets/inframap_jdll2023.pdf}
		\end{center}
	}
\end{frame}

\begin{frame}
	\frametitle{Object storage: a crucial component}
		\begin{center}
			\includegraphics[height=6em]{../assets/logos/Amazon-S3.jpg}
			\hspace{3em}
			\visible<2->{\includegraphics[height=5em]{../assets/logos/minio.png}}
			\hspace{3em}
			\visible<3>{\includegraphics[height=6em]{../../logo/garage_hires_crop.png}}
		\end{center}
		\vspace{1em}
	S3: a de-facto standard, many compatible applications

	\vspace{1em}
	\visible<2->{MinIO is self-hostable but not suited for geo-distributed deployments}

	\vspace{1em}
	\visible<3->{\textbf{Garage is a self-hosted drop-in replacement for the Amazon S3 object store}}
\end{frame}

\begin{frame}
	\frametitle{CRDTs / weak consistency instead of consensus}

	\underline{Internally, Garage uses only CRDTs} (conflict-free replicated data types)

	\vspace{2em}
	Why not Raft, Paxos, ...? Issues of consensus algorithms:

	\vspace{1em}
	\begin{itemize}
		\item<2-> \textbf{Software complexity}
			\vspace{1em}
		\item<3-> \textbf{Performance issues:}
			\vspace{.5em}
			\begin{itemize}
				\item<4-> The leader is a \textbf{bottleneck} for all requests\\
					\vspace{.5em}
				\item<5-> \textbf{Sensitive to higher latency} between nodes
					\vspace{.5em}
				\item<6-> \textbf{Takes time to reconverge} when disrupted (e.g. node going down)
			\end{itemize}
	\end{itemize}
\end{frame}

\begin{frame}
	\frametitle{The data model of object storage}
	Object storage is basically a \textbf{key-value store}:
	\vspace{.5em}

	{\scriptsize
		\begin{center}
		\begin{tabular}{|l|p{7cm}|}
			\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}
		}

	\vspace{1em}
	\begin{itemize}
		\item<2> Maps well to CRDT data types
	\end{itemize}
\end{frame}

\begin{frame}
	\frametitle{Performance gains in practice}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/perf/endpoint_latency_0.7_0.8_minio.png}
	\end{center}
\end{frame}

% ======================================== OPERATING
% ======================================== OPERATING
% ======================================== OPERATING


\section{Production clusters}

\begin{frame}
	\frametitle{Deployment kinds}

	\includegraphics[width=.9\linewidth]{../assets/cluster_kind.png}
	\vspace{1em}
	
\end{frame}

\begin{frame}
	\frametitle{How big they are?}

	\includegraphics[width=.9\linewidth]{../assets/cluster_size.png}
	\vspace{1em}

	\textit{"Petabyte storage setup for a video site. Nginx as CDN in-front using garage-s3-website feature. Each storage node has ~64TB storage with raid10, no replication within garage. 25gbit nic. haproxy to loadbalance across 5 nodes. mostly reads with very few writes."}

	\vspace{1em}
	\textit{"We currently manage 7 Garage nodes, 28TB total storage, 6M blocks for 3M objects and 4TB of object data. We have been running Garage in production for 2.5 years."}

\end{frame}

\begin{frame}
	\frametitle{Operating Garage}
	\begin{center}
		\only<1-2>{
			\includegraphics[width=.9\linewidth]{../assets/screenshots/garage_status_0.10.png}
			\\\vspace{1em}
			\visible<2>{\includegraphics[width=.9\linewidth]{../assets/screenshots/garage_status_unhealthy_0.10.png}}
		}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{Garage's architecture}
	\begin{center}
		\only<1>{\includegraphics[width=.45\linewidth]{../assets/garage.drawio.pdf}}%
		\only<2>{\includegraphics[width=.6\linewidth]{../assets/garage_sync.drawio.pdf}}%
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{Digging deeper}
	\begin{center}
		\only<1>{\includegraphics[width=.9\linewidth]{../assets/screenshots/garage_stats_0.10.png}}
		\only<2>{\includegraphics[width=.5\linewidth]{../assets/screenshots/garage_worker_list_0.10.png}}
		\only<3>{\includegraphics[width=.6\linewidth]{../assets/screenshots/garage_worker_param_0.10.png}}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{Potential limitations and bottlenecks}
	\begin{itemize}
		\item Global:
			\begin{itemize}
				\item Max. $\sim$100 nodes per cluster (excluding gateways)
			\end{itemize}
			\vspace{1em}
		\item Metadata:
			\begin{itemize}
				\item One big bucket = bottleneck, object list on 3 nodes only
			\end{itemize}
			\vspace{1em}
		\item Block manager:
			\begin{itemize}
				\item Lots of small files on disk
				\item Processing the resync queue can be slow
			\end{itemize}
	\end{itemize}
\end{frame}

\begin{frame}
	\frametitle{Deployment advice for very large clusters}
	\begin{itemize}
		\item Metadata storage:
			\begin{itemize}
				\item ZFS mirror (x2) on fast NVMe
				\item Use LMDB storage engine
			\end{itemize}
			\vspace{.5em}
		\item Data block storage:
			\begin{itemize}
				\item Use Garage's native multi-HDD support
				\item XFS on individual drives
				\item Increase block size (1MB $\to$ 10MB, requires more RAM and good networking)
				\item Tune \texttt{resync-tranquility} and \texttt{resync-worker-count} dynamically
			\end{itemize}
			\vspace{.5em}
		\item Other :
			\begin{itemize}
				\item Split data over several buckets
				\item Use less than 100 storage nodes
				\item Use gateway nodes
			\end{itemize}
			\vspace{.5em}
	\end{itemize}
\end{frame}


\begin{frame}
	\frametitle{Focus on Deuxfleurs}

	Host institutional websites, partnership with a web agency.
	Matrix media backend.

	Plan to use it as an email backend for an internally developed email server.

\end{frame}


% ======================================== TIMELINE
% ======================================== TIMELINE
% ======================================== TIMELINE

\section{Recent developments}

% ====================== v0.7.0 ===============================

\begin{frame}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{April 2022 - Garage v0.7.0}
	Focus on \underline{observability and ecosystem integration}
	\vspace{2em}
	\begin{itemize}
		\item \textbf{Monitoring:} metrics and traces, using OpenTelemetry
			\vspace{1em}
		\item Replication modes with 1 or 2 copies / weaker consistency
			\vspace{1em}
		\item Kubernetes integration for node discovery
			\vspace{1em}
		\item Admin API (v0.7.2)
	\end{itemize}
\end{frame}

\begin{frame}
	\frametitle{Metrics (Prometheus + Grafana)}
	\begin{center}
		\includegraphics[width=.9\linewidth]{../assets/screenshots/grafana_dashboard.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{Traces (Jaeger)}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/screenshots/jaeger_listobjects.png}
	\end{center}
\end{frame}

% ====================== v0.8.0 ===============================

\begin{frame}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{November 2022 - Garage v0.8.0}
	Focus on \underline{performance}
	\vspace{2em}
	\begin{itemize}
		\item \textbf{Alternative metadata DB engines} (LMDB, Sqlite)
			\vspace{1em}
		\item \textbf{Performance improvements:} block streaming, various optimizations...
			\vspace{1em}
		\item Bucket quotas (max size, max \#objects)
			\vspace{1em}
		\item Quality of life improvements, observability, etc.
	\end{itemize}
\end{frame}

\begin{frame}
	\frametitle{About metadata DB engines}
	\textbf{Issues with Sled:}
	\vspace{1em}
	\begin{itemize}
		\item Huge files on disk
			\vspace{.5em}
		\item Unpredictable performance, especially on HDD
			\vspace{.5em}
		\item API limitations
			\vspace{.5em}
		\item Not actively maintained
	\end{itemize}

	\vspace{2em}
	\textbf{LMDB:} very stable, good performance, file size is reasonable\\
	\textbf{Sqlite} also available as a second choice

	\vspace{1em}
	Sled will be removed in Garage v1.0
\end{frame}

\begin{frame}
	\frametitle{DB engine performance comparison}
	\begin{center}
		\includegraphics[width=.6\linewidth]{../assets/perf/db_engine.png}
	\end{center}
	NB: Sqlite was slow due to synchronous mode, now configurable
\end{frame}

\begin{frame}
	\frametitle{Block streaming}
	\begin{center}
		\only<1>{\includegraphics[width=.8\linewidth]{../assets/schema-streaming-1.png}}
		\only<2>{\includegraphics[width=.8\linewidth]{../assets/schema-streaming-2.png}}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{TTFB benchmark}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/perf/ttfb.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{Throughput benchmark}
	\begin{center}
		\includegraphics[width=.7\linewidth]{../assets/perf/io-0.7-0.8-minio.png}
	\end{center}
\end{frame}

% ====================== v0.9.0 ===============================

\begin{frame}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{October 2023 - Garage v0.9.0}
	Focus on \underline{streamlining \& usability}
	\vspace{2em}
	\begin{itemize}
		\item Support multiple HDDs per node
			\vspace{1em}
		\item S3 compatibility: 
			\vspace{1em}
			\begin{itemize}
				\item support basic lifecycle configurations
					\vspace{.5em}
				\item allow for multipart upload part retries
			\end{itemize}
			\vspace{1em}
		\item LMDB by default, deprecation of Sled
			\vspace{1em}
		\item New layout computation algorithm
	\end{itemize}
\end{frame}


\begin{frame}
	\frametitle{Layout computation}
	\begin{overprint}
		\onslide<1>
		\begin{center}
			\includegraphics[width=\linewidth, trim=0 0 0 -4cm]{../assets/screenshots/garage_status_0.9_prod_zonehl.png}
		\end{center}
		\onslide<2>
		\begin{center}
			\includegraphics[width=.7\linewidth]{../assets/map.png}
		\end{center}
	\end{overprint}
	\vspace{1em}
	Garage stores replicas on different zones when possible
\end{frame}

\begin{frame}
	\frametitle{What a "layout" is}
		\textbf{A layout is a precomputed index table:}
		\vspace{1em}

		{\footnotesize
			\begin{center}
			\begin{tabular}{|l|l|l|l|}
				\hline
				\textbf{Partition} & \textbf{Node 1} & \textbf{Node 2} & \textbf{Node 3} \\
				\hline
				\hline
				Partition 0 & df-ymk (bespin) & Abricot (scorpio) & Courgette (neptune) \\
				\hline
				Partition 1 & Ananas (scorpio) & Courgette (neptune) & df-ykl (bespin) \\
				\hline
				Partition 2 & df-ymf (bespin) & Celeri (neptune) & Abricot (scorpio) \\
				\hline
				\hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ \\
				\hline
				Partition 255 & Concombre (neptune) & df-ykl (bespin) & Abricot (scorpio) \\
				\hline
			\end{tabular}
			\end{center}
		}

	\vspace{2em}
	\visible<2->{
		The index table is built centrally using an optimal algorithm,\\
		then propagated to all nodes
	}

	\vspace{1em}
	\visible<3->{
		\footnotesize
		Oulamara, M., \& Auvolat, A. (2023). \emph{An algorithm for geo-distributed and redundant storage in Garage}.\\ arXiv preprint arXiv:2302.13798.
	}
\end{frame}



% ====================== v1.0.0 ===============================

\begin{frame}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{April 2024 - Garage v1.0.0}
	Focus on \underline{consistency, security \& stability}
	\vspace{2em}
	\begin{itemize}
		\item Fix consistency issues when reshuffling data (Jepsen testing)
			\vspace{1em}
		\item \textbf{Security audit} by Radically Open Security
			\vspace{1em}
		\item Misc. S3 features (SSE-C, checksums,  ...) and compatibility fixes
	\end{itemize}
\end{frame}

% ====================== v2.0.0 ===============================

\begin{frame}
	\begin{center}
		\includegraphics[width=.8\linewidth]{../assets/tl.drawio.png}
	\end{center}
\end{frame}

\begin{frame}
	\frametitle{Garage v2.0.0}
	Focus on \underline{}
	\vspace{2em}
	\begin{itemize}
		\item TODO
	\end{itemize}
\end{frame}


\begin{frame}
	\frametitle{Currently funding...}

	\textit{...}
\end{frame}

\begin{frame}
	\frametitle{We run community surveys}
	\begin{center}
		\includegraphics[width=.6\linewidth]{../assets/survey_requested_features.png}
	\end{center}
\end{frame}

% ======================================== END
% ======================================== END
% ======================================== END

\begin{frame}
	\frametitle{Where to find us}
	\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/logos/rust_logo.png}
			\includegraphics[width=.13\linewidth]{../assets/logos/AGPLv3_Logo.png}
	\end{center}
\end{frame}

\end{document}

%% vim: set ts=4 sw=4 tw=0 noet spelllang=en :