From 4de7ac60232d521d7b31bddc0768002894cecf9d Mon Sep 17 00:00:00 2001 From: Alex Auvolat Date: Mon, 22 Jan 2024 18:52:14 +0100 Subject: FOSDEM'24 talk WIP --- doc/talks/2024-02-03-fosdem/.gitignore | 17 + doc/talks/2024-02-03-fosdem/Makefile | 30 + doc/talks/2024-02-03-fosdem/abstract.md | 39 + doc/talks/2024-02-03-fosdem/assets/AGPLv3_Logo.png | Bin 0 -> 32497 bytes doc/talks/2024-02-03-fosdem/assets/aerogramme.png | Bin 0 -> 117865 bytes doc/talks/2024-02-03-fosdem/assets/aerogramme.svg | 1241 ++++++ .../assets/aerogramme_components1.drawio.pdf | Bin 0 -> 31966 bytes .../assets/aerogramme_components1.png | Bin 0 -> 26898 bytes .../assets/aerogramme_components2.drawio.pdf | Bin 0 -> 31688 bytes .../assets/aerogramme_components2.png | Bin 0 -> 27405 bytes .../assets/aerogramme_datatype.drawio.pdf | Bin 0 -> 31073 bytes .../assets/aerogramme_datatype.png | Bin 0 -> 9090 bytes .../assets/aerogramme_keys.drawio.pdf | Bin 0 -> 25145 bytes .../2024-02-03-fosdem/assets/aerogramme_keys.png | Bin 0 -> 17869 bytes .../2024-02-03-fosdem/assets/compatibility.png | Bin 0 -> 84505 bytes doc/talks/2024-02-03-fosdem/assets/consensus.svg | 137 + .../2024-02-03-fosdem/assets/garage.drawio.pdf | Bin 0 -> 26098 bytes .../2024-02-03-fosdem/assets/garage.drawio.png | Bin 0 -> 13463 bytes .../assets/garage_sync.drawio.pdf | Bin 0 -> 34372 bytes .../assets/garage_sync.drawio.png | Bin 0 -> 31184 bytes doc/talks/2024-02-03-fosdem/assets/lattice1.svg | 433 ++ doc/talks/2024-02-03-fosdem/assets/lattice2.svg | 514 +++ doc/talks/2024-02-03-fosdem/assets/lattice3.svg | 515 +++ doc/talks/2024-02-03-fosdem/assets/lattice4.svg | 525 +++ doc/talks/2024-02-03-fosdem/assets/lattice5.svg | 536 +++ doc/talks/2024-02-03-fosdem/assets/lattice6.svg | 553 +++ doc/talks/2024-02-03-fosdem/assets/lattice7.svg | 581 +++ doc/talks/2024-02-03-fosdem/assets/lattice8.svg | 581 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_1.svg | 576 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_10.svg | 715 ++++ doc/talks/2024-02-03-fosdem/assets/latticeB_2.svg | 576 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_3.svg | 576 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_4.svg | 587 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_5.svg | 604 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_6.svg | 632 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_7.svg | 654 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_8.svg | 671 +++ doc/talks/2024-02-03-fosdem/assets/latticeB_9.svg | 699 ++++ doc/talks/2024-02-03-fosdem/assets/rust_logo.png | Bin 0 -> 14835 bytes .../2024-02-03-fosdem/assets/scr_garage_stats.png | Bin 0 -> 133013 bytes .../2024-02-03-fosdem/assets/scr_garage_status.png | Bin 0 -> 75685 bytes .../assets/scr_garage_status_broken.png | Bin 0 -> 54964 bytes .../assets/scr_garage_worker_get.png | Bin 0 -> 76007 bytes .../assets/scr_garage_worker_list.png | Bin 0 -> 115654 bytes doc/talks/2024-02-03-fosdem/assets/slideB1.png | Bin 0 -> 86072 bytes doc/talks/2024-02-03-fosdem/assets/slideB2.png | Bin 0 -> 83399 bytes doc/talks/2024-02-03-fosdem/assets/slideB3.png | Bin 0 -> 82581 bytes doc/talks/2024-02-03-fosdem/assets/slides.svg | 4326 ++++++++++++++++++++ doc/talks/2024-02-03-fosdem/assets/slidesB.svg | 444 ++ doc/talks/2024-02-03-fosdem/talk.pdf | Bin 0 -> 3919347 bytes doc/talks/2024-02-03-fosdem/talk.tex | 1104 +++++ 51 files changed, 17866 insertions(+) create mode 100644 doc/talks/2024-02-03-fosdem/.gitignore create mode 100644 doc/talks/2024-02-03-fosdem/Makefile create mode 100644 doc/talks/2024-02-03-fosdem/abstract.md create mode 100644 doc/talks/2024-02-03-fosdem/assets/AGPLv3_Logo.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.drawio.pdf create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.drawio.pdf create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.drawio.pdf create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.drawio.pdf create mode 100644 doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/compatibility.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/consensus.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/garage.drawio.pdf create mode 100644 doc/talks/2024-02-03-fosdem/assets/garage.drawio.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.pdf create mode 100644 doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice1.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice2.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice3.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice4.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice5.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice6.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice7.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/lattice8.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_1.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_10.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_2.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_3.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_4.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_5.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_6.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_7.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_8.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/latticeB_9.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/rust_logo.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/scr_garage_stats.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/scr_garage_status.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/scr_garage_status_broken.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_get.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_list.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/slideB1.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/slideB2.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/slideB3.png create mode 100644 doc/talks/2024-02-03-fosdem/assets/slides.svg create mode 100644 doc/talks/2024-02-03-fosdem/assets/slidesB.svg create mode 100644 doc/talks/2024-02-03-fosdem/talk.pdf create mode 100644 doc/talks/2024-02-03-fosdem/talk.tex (limited to 'doc/talks/2024-02-03-fosdem') diff --git a/doc/talks/2024-02-03-fosdem/.gitignore b/doc/talks/2024-02-03-fosdem/.gitignore new file mode 100644 index 00000000..9f1f00e6 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/.gitignore @@ -0,0 +1,17 @@ +* + +!*.txt +!*.md + +!assets + +!.gitignore +!*.svg +!*.png +!*.jpg +!*.tex +!Makefile +!.gitignore +!assets/*.drawio.pdf + +!talk.pdf diff --git a/doc/talks/2024-02-03-fosdem/Makefile b/doc/talks/2024-02-03-fosdem/Makefile new file mode 100644 index 00000000..1440057c --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/Makefile @@ -0,0 +1,30 @@ +ASSETS=assets/consensus.pdf_tex \ + assets/lattice1.pdf_tex \ + assets/lattice2.pdf_tex \ + assets/lattice3.pdf_tex \ + assets/lattice4.pdf_tex \ + assets/lattice5.pdf_tex \ + assets/lattice6.pdf_tex \ + assets/lattice7.pdf_tex \ + assets/lattice8.pdf_tex \ + assets/latticeB_1.pdf_tex \ + assets/latticeB_2.pdf_tex \ + assets/latticeB_3.pdf_tex \ + assets/latticeB_4.pdf_tex \ + assets/latticeB_5.pdf_tex \ + assets/latticeB_6.pdf_tex \ + assets/latticeB_7.pdf_tex \ + assets/latticeB_8.pdf_tex \ + assets/latticeB_9.pdf_tex \ + assets/latticeB_10.pdf_tex \ + ../assets/deuxfleurs.pdf \ + ../assets/timeline-22-24.pdf + +talk.pdf: talk.tex $(ASSETS) + pdflatex talk.tex + +%.pdf: %.svg + inkscape -D -z --file=$^ --export-pdf=$@ + +%.pdf_tex: %.svg + inkscape -D -z --file=$^ --export-pdf=$@ --export-latex diff --git a/doc/talks/2024-02-03-fosdem/abstract.md b/doc/talks/2024-02-03-fosdem/abstract.md new file mode 100644 index 00000000..b2658868 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/abstract.md @@ -0,0 +1,39 @@ +### (fr) Garage, un système de stockage de données géo-distribué léger et robuste + +Garage est un système de stockage de données léger, géo-distribué, qui +implémente le protocole de stockage S3 de Amazon. Garage est destiné +principalement à l'auto-hébergement sur du matériel courant d'occasion. À ce +titre, il doit tolérer un grand nombre de pannes: coupures de courant, coupures +de connexion Internet, pannes de machines, ... Il doit également être facile à +déployer et à maintenir, afin de pouvoir être facilement utilisé par des +amateurs ou des petites organisations. + +Cette présentation vous proposera un aperçu de Garage et du choix technique +principal qui rend un système comme Garage possible: le refus d'utiliser des +algorithmes de consensus, remplacés avantageusement par des méthodes à +cohérence faible. Notre modèle est fortement inspiré de la base de donnée +Dynamo (DeCandia et al, 2007), et fait usage des types de données CRDT (Shapiro +et al, 2011). Nous exploreront comment ces méthodes s'appliquent à la +construction de l'abstraction "stockage objet" dans un système distribué, et +quelles autres abstractions peuvent ou ne peuvent pas être construites dans ce +modèle. + +### (en) Garage, a lightweight and robust geo-distributed data storage system + +Garage is a lightweight geo-distributed data store that implements the Amazon +S3 object storage protocol. Garage is meant primarily for self-hosting at home +on second-hand commodity hardware, meaning it has to tolerate a wide variety of +failure scenarios such as power cuts, Internet disconnections and machine +crashes. It also has to be easy to deploy and maintain, so that hobbyists and +small organizations can use it without trouble. + +This talk will present Garage and the key technical choice that made Garage +possible: refusing to use consensus algorithms and using instead weak +consistency methods, with a model that is loosely based on that of the Dynamo +database (DeCandia et al, 2007) and that makes heavy use of conflict-free +replicated data types (Shapiro et al, 2011). We will explore how these methods +are suited to building the "object store" abstraction in a distributed system, +and what other abstractions are possible or impossible to build in this model. + + + diff --git a/doc/talks/2024-02-03-fosdem/assets/AGPLv3_Logo.png b/doc/talks/2024-02-03-fosdem/assets/AGPLv3_Logo.png new file mode 100644 index 00000000..445284a3 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/AGPLv3_Logo.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme.png b/doc/talks/2024-02-03-fosdem/assets/aerogramme.png new file mode 100644 index 00000000..3aabe3ad Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme.svg b/doc/talks/2024-02-03-fosdem/assets/aerogramme.svg new file mode 100644 index 00000000..0c1ee127 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/aerogramme.svg @@ -0,0 +1,1241 @@ + + + + + + K2V APIS3 APIAerogramme + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +IMAPIMAPIMAPMessageindexMessagebodies diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.drawio.pdf b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.drawio.pdf new file mode 100644 index 00000000..71a90f26 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.drawio.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.png b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.png new file mode 100644 index 00000000..fb81b460 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components1.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.drawio.pdf b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.drawio.pdf new file mode 100644 index 00000000..87e42eed Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.drawio.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.png b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.png new file mode 100644 index 00000000..f9e2df14 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_components2.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.drawio.pdf b/doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.drawio.pdf new file mode 100644 index 00000000..0606e059 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.drawio.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.png b/doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.png new file mode 100644 index 00000000..c3b015a1 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_datatype.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.drawio.pdf b/doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.drawio.pdf new file mode 100644 index 00000000..8fea81c7 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.drawio.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.png b/doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.png new file mode 100644 index 00000000..ed2077d9 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/aerogramme_keys.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/compatibility.png b/doc/talks/2024-02-03-fosdem/assets/compatibility.png new file mode 100644 index 00000000..ce364a9b Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/compatibility.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/consensus.svg b/doc/talks/2024-02-03-fosdem/assets/consensus.svg new file mode 100644 index 00000000..8321e383 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/consensus.svg @@ -0,0 +1,137 @@ + + + + + + + + + + + + + + $\bot$ + + + + $x$ + + + $propose(x) / x$ + $propose(y) / x$ + + + diff --git a/doc/talks/2024-02-03-fosdem/assets/garage.drawio.pdf b/doc/talks/2024-02-03-fosdem/assets/garage.drawio.pdf new file mode 100644 index 00000000..a54a163c Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/garage.drawio.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/assets/garage.drawio.png b/doc/talks/2024-02-03-fosdem/assets/garage.drawio.png new file mode 100644 index 00000000..386dd862 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/garage.drawio.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.pdf b/doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.pdf new file mode 100644 index 00000000..a94b3572 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.png b/doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.png new file mode 100644 index 00000000..2e7b5af0 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/garage_sync.drawio.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice1.svg b/doc/talks/2024-02-03-fosdem/assets/lattice1.svg new file mode 100644 index 00000000..8bfa5aa7 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice1.svg @@ -0,0 +1,433 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice2.svg b/doc/talks/2024-02-03-fosdem/assets/lattice2.svg new file mode 100644 index 00000000..adcd92cb --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice2.svg @@ -0,0 +1,514 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice3.svg b/doc/talks/2024-02-03-fosdem/assets/lattice3.svg new file mode 100644 index 00000000..640dc468 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice3.svg @@ -0,0 +1,515 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice4.svg b/doc/talks/2024-02-03-fosdem/assets/lattice4.svg new file mode 100644 index 00000000..b2a99e28 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice4.svg @@ -0,0 +1,525 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + return OK + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice5.svg b/doc/talks/2024-02-03-fosdem/assets/lattice5.svg new file mode 100644 index 00000000..bc6b7195 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice5.svg @@ -0,0 +1,536 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $read()$: + $\sqsupseteq \{a\} \to$ OK + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + return OK + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice6.svg b/doc/talks/2024-02-03-fosdem/assets/lattice6.svg new file mode 100644 index 00000000..176b1715 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice6.svg @@ -0,0 +1,553 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $read()$: + $\sqsupseteq \{a\} \to$ OK + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + + $\to \{\}$ + return OK + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice7.svg b/doc/talks/2024-02-03-fosdem/assets/lattice7.svg new file mode 100644 index 00000000..7ce8bda8 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice7.svg @@ -0,0 +1,581 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $read()$: + $\sqsupseteq \{a\} \to$ OK + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + + $\to \{\}$ + return OK + return $\{\}\sqcup\{a\}=\{a\}$ + + $\to \{a\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/lattice8.svg b/doc/talks/2024-02-03-fosdem/assets/lattice8.svg new file mode 100644 index 00000000..c94a69b2 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/lattice8.svg @@ -0,0 +1,581 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $read()$: + $\sqsupseteq \{a\} \to$ OK + $\sqsupseteq \{a\} \to$ OK + $\sqsupseteq \{a\}$ + + $\to \{\}$ + return OK + return $\{\}\sqcup\{a\}=\{a\}$ + + $\to \{a\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_1.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_1.svg new file mode 100644 index 00000000..92232a1b --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_1.svg @@ -0,0 +1,576 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $\not\sqsupseteq \{b\}$ + $\not\sqsupseteq \{b\}$ + $\not\sqsupseteq \{b\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_10.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_10.svg new file mode 100644 index 00000000..34c24e0d --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_10.svg @@ -0,0 +1,715 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + $\to \{a\}$ + return $\{a\}$ + + $\to \{\}$ + + $\to \{\}$ + $read()$: + ; + return $\{b\}$ + + $\to \{b\}$ + ${\Large\textbf{??!}}$~~~~~$\{a\} \not\sqsubseteq \{b\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_2.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_2.svg new file mode 100644 index 00000000..c07cba2b --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_2.svg @@ -0,0 +1,576 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $\not\sqsupseteq \{b\}$ + $\not\sqsupseteq \{b\}$ + $\not\sqsupseteq \{b\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_3.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_3.svg new file mode 100644 index 00000000..198d1f5d --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_3.svg @@ -0,0 +1,576 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_4.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_4.svg new file mode 100644 index 00000000..c5f6148d --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_4.svg @@ -0,0 +1,587 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_5.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_5.svg new file mode 100644 index 00000000..c2b668be --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_5.svg @@ -0,0 +1,604 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + $\to \{a\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_6.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_6.svg new file mode 100644 index 00000000..980823fc --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_6.svg @@ -0,0 +1,632 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + $\to \{a\}$ + return $\{a\}$ + + $\to \{\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_7.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_7.svg new file mode 100644 index 00000000..154c0b7d --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_7.svg @@ -0,0 +1,654 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + $\to \{a\}$ + return $\{a\}$ + + $\to \{\}$ + $read()$: + ; + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_8.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_8.svg new file mode 100644 index 00000000..21766415 --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_8.svg @@ -0,0 +1,671 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + $\to \{a\}$ + return $\{a\}$ + + $\to \{\}$ + + $\to \{\}$ + $read()$: + ; + + diff --git a/doc/talks/2024-02-03-fosdem/assets/latticeB_9.svg b/doc/talks/2024-02-03-fosdem/assets/latticeB_9.svg new file mode 100644 index 00000000..b60f8afe --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/latticeB_9.svg @@ -0,0 +1,699 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + $\{\}$ + $\{a,b,c\}$ + + $\{a\}$ + $\{b\}$ + $\{c\}$ + + + $\{a,c\}$ + $\{a,b\}$ + $\{b,c\}$ + + + + + + + + + + + + + + + + + + + $write(\{a\})$: + $\sqsupseteq \{a\} \to$ OK + $\not\sqsupseteq \{a\}$ + $\not\sqsupseteq \{a\}$ + + + + $write(\{b\})$: + $read()$: + $\not\sqsupseteq \{b\}$ + $\sqsupseteq \{b\} \to$ OK + $\not\sqsupseteq \{b\}$ + + + $\to \{a\}$ + return $\{a\}$ + + $\to \{\}$ + + $\to \{\}$ + $read()$: + ; + return $\{b\}$ + + $\to \{b\}$ + + diff --git a/doc/talks/2024-02-03-fosdem/assets/rust_logo.png b/doc/talks/2024-02-03-fosdem/assets/rust_logo.png new file mode 100644 index 00000000..0e4809ec Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/rust_logo.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/scr_garage_stats.png b/doc/talks/2024-02-03-fosdem/assets/scr_garage_stats.png new file mode 100644 index 00000000..c92f0774 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/scr_garage_stats.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/scr_garage_status.png b/doc/talks/2024-02-03-fosdem/assets/scr_garage_status.png new file mode 100644 index 00000000..849b8336 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/scr_garage_status.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/scr_garage_status_broken.png b/doc/talks/2024-02-03-fosdem/assets/scr_garage_status_broken.png new file mode 100644 index 00000000..86dcce89 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/scr_garage_status_broken.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_get.png b/doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_get.png new file mode 100644 index 00000000..e7d4e288 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_get.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_list.png b/doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_list.png new file mode 100644 index 00000000..472312a0 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/scr_garage_worker_list.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/slideB1.png b/doc/talks/2024-02-03-fosdem/assets/slideB1.png new file mode 100644 index 00000000..b14b6070 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/slideB1.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/slideB2.png b/doc/talks/2024-02-03-fosdem/assets/slideB2.png new file mode 100644 index 00000000..a881a796 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/slideB2.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/slideB3.png b/doc/talks/2024-02-03-fosdem/assets/slideB3.png new file mode 100644 index 00000000..830709d2 Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/assets/slideB3.png differ diff --git a/doc/talks/2024-02-03-fosdem/assets/slides.svg b/doc/talks/2024-02-03-fosdem/assets/slides.svg new file mode 100644 index 00000000..9946c6fb --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/slides.svg @@ -0,0 +1,4326 @@ + + + + + + + + + + + + + + + + + + + + + + User-facing application + Database + Filesystem + + + + + + + + + + diff --git a/doc/talks/2024-02-03-fosdem/assets/slidesB.svg b/doc/talks/2024-02-03-fosdem/assets/slidesB.svg new file mode 100644 index 00000000..c0a6e97c --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/assets/slidesB.svg @@ -0,0 +1,444 @@ + + + +User-facing applicationDatabase*K2VObject storage*(not really a database)Database diff --git a/doc/talks/2024-02-03-fosdem/talk.pdf b/doc/talks/2024-02-03-fosdem/talk.pdf new file mode 100644 index 00000000..03fa8fcc Binary files /dev/null and b/doc/talks/2024-02-03-fosdem/talk.pdf differ diff --git a/doc/talks/2024-02-03-fosdem/talk.tex b/doc/talks/2024-02-03-fosdem/talk.tex new file mode 100644 index 00000000..4c4dcdbc --- /dev/null +++ b/doc/talks/2024-02-03-fosdem/talk.tex @@ -0,0 +1,1104 @@ +\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, the low-tech storage platform for geo-distributed clusters} +\author{Alex Auvolat, Deuxfleurs} +\date{FOSDEM'24, 2024-02-03} + +\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}\\ + PhD; co-founder of Deuxfleurs + \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{Our objective at Deuxfleurs} + + \begin{center} + \textbf{Promote self-hosting and small-scale hosting\\ + as an alternative to large cloud providers} + \end{center} + \vspace{2em} + \visible<2->{ + Why is it hard? + } + \visible<3->{ + \vspace{2em} + \begin{center} + \textbf{\underline{Resilience}}\\ + {\footnotesize (we want good uptime/availability with low supervision)} + \end{center} + } +\end{frame} + +\begin{frame} + \frametitle{How to make a \underline{stable} system} + + 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} + $\to$ it's costly and only worth it at DC scale +\end{frame} + +\begin{frame} + \frametitle{How to make a \underline{resilient} system} + + \only<1,4-5>{ + Instead, we use: + \vspace{1em} + \begin{itemize} + \item \textcolor<2->{gray}{Commodity hardware (e.g. old desktop PCs)} + \vspace{.5em} + \item<4-> \textcolor<5->{gray}{Commodity Internet (e.g. FTTB, FTTH) and power grid} + \vspace{.5em} + \item<5-> \textcolor<6->{gray}{\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<6>{ + \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/Amazon-S3.jpg} + \hspace{3em} + \includegraphics[height=5em]{../assets/minio.png} + \hspace{3em} + \includegraphics[height=6em]{../../logo/garage_hires_crop.png} + \end{center} + \vspace{1em} + S3: a de-facto standard, many compatible applications + + \vspace{1em} + + MinIO is self-hostable but not suited for geo-distributed deployments + + \vspace{1em} + + \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} + Consensus can be implemented reasonably well in practice, so why avoid it? + \vspace{1em} + \begin{itemize} + \item \textbf{Software complexity} + \vspace{1em} + \item \textbf{Performance issues:} + \vspace{.5em} + \begin{itemize} + \item The leader is a \textbf{bottleneck} for all requests\\ + \vspace{.5em} + \item \textbf{Sensitive to higher latency} between nodes + \vspace{.5em} + \item \textbf{Takes time to reconverge} when disrupted (e.g. node going down) + \end{itemize} + \end{itemize} + \vspace{2em} + $\to$ Garage uses only CRDTs internally (conflict-free replicated data types) +\end{frame} + +\begin{frame} + \frametitle{The data model of object storage} + Object storage is basically a key-value store: + \vspace{1em} + + {\footnotesize + \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{} \\ + \hline + \texttt{img/logo.svg} & + \texttt{Content-Type: text/svg+xml} \newline + \texttt{Content-Length: 13429} \newline + \texttt{} \\ + \hline + \texttt{download/index.html} & + \texttt{Content-Type: text/html; charset=utf-8} \newline + \texttt{Content-Length: 26563} \newline + \texttt{} \\ + \hline + \end{tabular} + \end{center} + } + + \vspace{1em} + Simple interface, compatible with many existing applications + + \vspace{1em} + Maps well to CRDT data types +\end{frame} + +\begin{frame} + \frametitle{Performance gains in practice} + \begin{center} + \includegraphics[width=.8\linewidth]{../assets/endpoint_latency_0.7_0.8_minio.png} + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Timeline} + \begin{center} + \includegraphics[width=.8\linewidth]{../assets/timeline-22-24.pdf} + \end{center} +\end{frame} + +% ====================== v0.7.0 =============================== + +\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 Alternative replication modes with 1 or 2 copies,\\ + modes with weaker consistency + \vspace{1em} + \item Kubernetes integration + \vspace{1em} + \item Admin API (v0.7.2) + \vspace{1em} + \item Experimental K2V API (v0.7.2) + \end{itemize} +\end{frame} + +\begin{frame} + \frametitle{Metrics (Prometheus + Grafana)} + \begin{center} + \includegraphics[width=.9\linewidth]{../assets/grafana_dashboard.png} + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Traces (Jaeger)} + \begin{center} + \includegraphics[width=.8\linewidth]{../assets/jaeger_listobjects.png} + \end{center} +\end{frame} + +% ====================== v0.8.0 =============================== + +\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} + Issues with Sled: + \vspace{2em} + \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} + LMDB: very stable, good performance, reasonably small files on disk + + \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/db_engine.png} + \end{center} + NB: Sqlite was slow due to synchronous journaling 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/ttfb.png} + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Throughput benchmark} + \begin{center} + \includegraphics[width=.7\linewidth]{../assets/io-0.7-0.8-minio.png} + \end{center} +\end{frame} + +% ====================== v0.9.0 =============================== + +\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{center} + \includegraphics[width=\linewidth]{../assets/location-aware.png} + \end{center} + \vspace{2em} + Garage replicates data on different zones when possible +\end{frame} + +\begin{frame} + \frametitle{Layout computation} + \begin{center} + \includegraphics[width=.8\linewidth]{../assets/map.png} + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Optimal layout computation} + \begin{center} + \includegraphics[width=.6\linewidth]{../assets/geodistrib_paper.png} + \end{center} +\end{frame} + +\begin{frame} + \frametitle{What a "layout" is} + \textbf{A layout is a precomputed index table} + \vspace{2em} + + \begin{center} + \begin{tabular}{|l|l|l|l|} + \hline + \textbf{Partition} & \textbf{Node 1} & \textbf{Node 2} & \textbf{Node 3} \\ + \hline + \hline + Partition 0 & Io (jupiter) & Drosera (atuin) & Courgette (neptune) \\ + \hline + Partition 1 & Datura (atuin) & Courgette (neptune) & Io (jupiter) \\ + \hline + Partition 2 & Io(jupiter) & Celeri (neptune) & Drosera (atuin) \\ + \hline + \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ & \hspace{1em}$\vdots$ \\ + \hline + Partition 255 & Concombre (neptune) & Io (jupiter) & Drosera (atuin) \\ + \hline + \end{tabular} + \end{center} + + \vspace{1em} + The index table is built centrally using an optimal algorithm,\\ + then propagated to all nodes +\end{frame} + +\begin{frame} + \frametitle{The relationship between \emph{partition} and \emph{partition key}} + \begin{center} + \begin{tabular}{|l|l|l|l|} + \hline + \textbf{Partition key} & \textbf{Partition} & \textbf{Sort key} & \textbf{Value} \\ + \hline + \hline + \texttt{website} & Partition 12 & \texttt{index.html} & (file data) \\ + \hline + \texttt{website} & Partition 12 & \texttt{img/logo.svg} & (file data) \\ + \hline + \texttt{website} & Partition 12 &\texttt{download/index.html} & (file data) \\ + \hline + \hline + \texttt{backup} & Partition 42 & \texttt{borg/index.2822} & (file data) \\ + \hline + \texttt{backup} & Partition 42 & \texttt{borg/data/2/2329} & (file data) \\ + \hline + \texttt{backup} & Partition 42 & \texttt{borg/data/2/2680} & (file data) \\ + \hline + \hline + \texttt{private} & Partition 42 & \texttt{qq3a2nbe1qjq0ebbvo6ocsp6co} & (file data) \\ + \hline + \end{tabular} + \end{center} + \vspace{1em} + \textbf{To read or write an item:} hash partition key + \\ \hspace{5cm} $\to$ determine partition number (first 8 bits) + \\ \hspace{5cm} $\to$ find associated nodes +\end{frame} + +% ====================== v0.10.0 =============================== + +\begin{frame} + \frametitle{October 2023 - Garage v0.10.0 beta} + Focus on \underline{consistency} + \vspace{2em} + \begin{itemize} + \item Fix consistency issues when reshuffling data + \end{itemize} +\end{frame} + + + + +% -------------------------------------------------------------------- +% ================================================================================= +% ================================================================================= +% -------------------------------------------------------------------- +% -------------------------------------------------------------------- +% -------------------------------------------------------------------- +% ================================================================================= +% ================================================================================= +% -------------------------------------------------------------------- + + + + +\begin{frame} + \frametitle{Two big problems} + \begin{enumerate} + \item \textbf{How to place data on different nodes?}\\ + \vspace{1em} + \underline{Constraints:} heterogeneous hardware\\ + \underline{Objective:} $n$ copies of everything, maximize usable capacity, maximize resilience\\ + \vspace{1em} + $\to$ the Dynamo model + optimization algorithms + \vspace{2em} + \item<2-> \textbf{How to guarantee consistency?}\\ + \vspace{1em} + \underline{Constraints:} slow network (geographical distance), node unavailability/crashes\\ + \underline{Objective:} maximize availability, read-after-write guarantee\\ + \vspace{1em} + $\to$ CRDTs, monotonicity, read and write quorums + \end{enumerate} +\end{frame} + +\section{Problem 1: placing data} + +\begin{frame} + \frametitle{Key-value stores, upgraded: the Dynamo model} + \textbf{Two keys:} + \begin{itemize} + \item Partition key: used to divide data into partitions {\small (a.k.a.~shards)} + \item Sort key: used to identify items inside a partition + \end{itemize} + + \vspace{1em} + + \begin{center} + \begin{tabular}{|l|l|p{3cm}|} + \hline + \textbf{Partition key: bucket} & \textbf{Sort key: filename} & \textbf{Value} \\ + \hline + \hline + \texttt{website} & \texttt{index.html} & (file data) \\ + \hline + \texttt{website} & \texttt{img/logo.svg} & (file data) \\ + \hline + \texttt{website} & \texttt{download/index.html} & (file data) \\ + \hline + \hline + \texttt{backup} & \texttt{borg/index.2822} & (file data) \\ + \hline + \texttt{backup} & \texttt{borg/data/2/2329} & (file data) \\ + \hline + \texttt{backup} & \texttt{borg/data/2/2680} & (file data) \\ + \hline + \hline + \texttt{private} & \texttt{qq3a2nbe1qjq0ebbvo6ocsp6co} & (file data) \\ + \hline + \end{tabular} + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Key-value stores, upgraded: the Dynamo model} + \begin{itemize} + \item Data with different partition keys is stored independently,\\ + on a different set of nodes\\ + \vspace{.5em} + $\to$ no easy way to list all partition keys\\ + $\to$ no cross-shard transactions\\ + \vspace{2em} + \item Placing data: hash the partition key, select nodes accordingly\\ + \vspace{.5em} + $\to$ distributed hash table (DHT) + \vspace{2em} + \item For a given value of the partition key, items can be listed using their sort keys + \end{itemize} +\end{frame} + + +\begin{frame} + \frametitle{Issues with consistent hashing} + \begin{itemize} + \item Consistent hashing doesn't dispatch data based on geographical location of nodes + \vspace{1em} + \item<2-> Geographically aware adaptation, try 1:\\ + data quantities not well balanced between nodes + \vspace{1em} + \item<3-> Geographically aware adaptation, try 2:\\ + too many reshuffles when adding/removing nodes + \end{itemize} +\end{frame} + + +\section{Problem 2: ensuring consistency} + +\begin{frame} + \frametitle{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 \textbf{Linearizability} of all operations\\ + (strongest consistency guarantee) + \vspace{1em} + \item Any sequential specification can be implemented as a \textbf{replicated state machine} + \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{Read-after-write consistency} with quorums, + eventual consistency without + \vspace{1em} + \item \textbf{Operations have to commute}, i.e.~we + can only implement CRDTs + \vspace{1em} + \item \textbf{Fast}, no single bottleneck;\\ + works the same with offline nodes + \end{itemize} + } \end{minipage} + \hspace{1em} +\end{frame} + +\begin{frame} + \frametitle{Consensus vs weak consistency} + \begin{center} + \textbf{From a theoretical point of view:}\\ + + \end{center} + \vspace{2em} + + \hspace{1em} + \begin{minipage}{6.5cm} + \underline{Consensus-based systems:} + + \vspace{1em} + + Require \textbf{additional assumptions} such as a fault detector or a strong RNG\\ + (FLP impossibility theorem) + \end{minipage} + \hfill + \begin{minipage}{6.5cm} + \underline{Weakly consistent systems:} + + \vspace{1em} + + Can be implemented in \textbf{any\\asynchronous message passing\\distributed system} with node crashes + \end{minipage} + \hspace{1em} + + \vspace{3em} + \begin{center} + They represent \textbf{different classes of computational capability}\\ + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Consensus vs weak consistency} + \begin{center} + \textbf{The same objects cannot be implemented in both models.} + \end{center} + \vspace{2em} + + \hspace{1em} + \begin{minipage}{6.5cm} + \underline{Consensus-based systems:} + + \vspace{1em} + + \textbf{Any sequential specification}\\~ + + \vspace{1em} + \textbf{Easier to program for}: just write your program as if it were sequential on a single machine + + \end{minipage} + \hfill + \begin{minipage}{6.5cm} + \underline{Weakly consistent systems:} + + \vspace{1em} + + \textbf{Only CRDTs}\\(conflict-free replicated data types) + + \vspace{1em} + Part of the complexity is \textbf{reported to the consumer of the API}\\~ + \end{minipage} + \hspace{1em} +\end{frame} + +\begin{frame} + \frametitle{Understanding the power of consensus} + \textbf{Consensus:} an API with a single operation, $propose(x)$ + \begin{enumerate} + \item nodes all call $propose(x)$ with their proposed value; + \item nodes all receive the same value as a return value, which is one of the proposed values + \end{enumerate} + \vspace{1em} + + \visible<2->{ + \textbf{Equivalent to} a distributed algorithm that gives a total order on all requests + } + \vspace{1em} + + \visible<3->{ + \textbf{Implemented by} this simple replicated state machine: + \vspace{.5em} + \begin{figure} + \centering + \def\svgwidth{.5\textwidth} + \large + \import{assets/}{consensus.pdf_tex} + \end{figure} + \vspace{1em} + } +\end{frame} + +\begin{frame} + \frametitle{Can my object be implemented without consensus?} + \underline{Given the specification of an API:} + \vspace{2em} + \begin{itemize} + \item \textbf{Using this API, we can implement the consensus object} (the $propose$ function)\\ + $\to$ the API is equivalent to consensus/total ordering of messages\\ + $\to$ the API cannot be implemented in a weakly consistent system + \vspace{2em} + \item<2-> \textbf{This API can be implemented using only weak primitives}\\ + (e.g. in the asynchronous message passing model with no further assumption)\\ + $\to$ the API is strictly weaker than consensus\\ + $\to$ we can implement it in Garage! + \end{itemize} +\end{frame} + + +\begin{frame} + \frametitle{What can we implement without consensus?} + \begin{itemize} + \item Any \textbf{conflict-free replicated data type} (CRDT) + \vspace{1em} + \item<2-> Non-transactional key-value stores such as S3 are equivalent to a simple CRDT:\\ + a map of \textbf{last-writer-wins registers} (each key is its own CRDT) + \vspace{1em} + \item<3-> \textbf{Read-after-write consistency} can be implemented + using quorums on read and write operations + \vspace{1em} + \item<4-> \textbf{Monotonicity of reads} can be implemented with repair-on-read\\ + (makes reads more costly, not implemented in Garage) + \end{itemize} +\end{frame} + +\begin{frame} + \frametitle{CRDTs and quorums: read-after-write consistency} + \begin{figure} + \centering + \def\svgwidth{.8\textwidth} + \only<1>{\import{assets/}{lattice1.pdf_tex}}% + \only<2>{\import{assets/}{lattice2.pdf_tex}}% + \only<3>{\import{assets/}{lattice3.pdf_tex}}% + \only<4>{\import{assets/}{lattice4.pdf_tex}}% + \only<5>{\import{assets/}{lattice5.pdf_tex}}% + \only<6>{\import{assets/}{lattice6.pdf_tex}}% + \only<7>{\import{assets/}{lattice7.pdf_tex}}% + \only<8>{\import{assets/}{lattice8.pdf_tex}}% + \end{figure} +\end{frame} + +\begin{frame} + \frametitle{CRDTs and quorums: read-after-write consistency} + \textbf{Property:} If node $A$ did an operation $write(x)$ and received an OK response,\\ + \hspace{2cm} and node $B$ starts an operation $read()$ after $A$ received OK,\\ + \hspace{2cm} then $B$ will read a value $x' \sqsupseteq x$. + + \vspace{1em} + + \hspace{1em} + \begin{minipage}{6.8cm} + \textbf{Algorithm $write(x)$:} + \begin{enumerate} + \item Broadcast $write(x)$ to all nodes + \item Wait for $k > n/2$ nodes to reply OK + \item Return OK + \end{enumerate} + \end{minipage} + \hfill + \begin{minipage}{6.8cm} + \vspace{1em} + \textbf{Algorithm $read()$:} + \begin{enumerate} + \item Broadcast $read()$ to all nodes + \item Wait for $k > n/2$ nodes to reply\\ + with values $x_1, \dots, x_k$ + \item Return $x_1 \sqcup \dots \sqcup x_k$ + \end{enumerate} + \end{minipage} + \hspace{1em} + + \vspace{2em} + \textbf{Why does it work?} There is at least one node at the intersection between the two sets of nodes that replied to each request, that ``saw'' $x$ before the $read()$ started ($x_i \sqsupseteq x$). +\end{frame} + +\begin{frame} + \frametitle{CRDTs and quorums: monotonic-reads consistency} + \begin{figure} + \centering + \def\svgwidth{.8\textwidth} + \only<1>{\import{assets/}{latticeB_1.pdf_tex}}% + \only<2>{\import{assets/}{latticeB_2.pdf_tex}}% + \only<3>{\import{assets/}{latticeB_3.pdf_tex}}% + \only<4>{\import{assets/}{latticeB_4.pdf_tex}}% + \only<5>{\import{assets/}{latticeB_5.pdf_tex}}% + \only<6>{\import{assets/}{latticeB_6.pdf_tex}}% + \only<7>{\import{assets/}{latticeB_7.pdf_tex}}% + \only<8>{\import{assets/}{latticeB_8.pdf_tex}}% + \only<9>{\import{assets/}{latticeB_9.pdf_tex}}% + \only<10>{\import{assets/}{latticeB_10.pdf_tex}}% + \end{figure} +\end{frame} + +\begin{frame} + \frametitle{CRDTs and quorums: monotonic-reads consistency} + \textbf{Property:} If node $A$ did an operation $read()$ and received $x$ as a response,\\ + \hspace{2cm} and node $B$ starts an operation $read()$ after $A$ received $x$,\\ + \hspace{2cm} then $B$ will read a value $x' \sqsupseteq x$. + + \vspace{1em} + + \textbf{Algorithm $monotonic\_read()$:} {\small (a.k.a. repair-on-read)} + \begin{enumerate} + \item Broadcast $read()$ to all nodes + \item Wait for $k > n/2$ nodes to reply with values $x_1, \dots, x_k$ + \item If $x_i \ne x_j$ for some nodes $i$ and $j$,\\ + \hspace{1cm}then call $write(x_1 \sqcup \dots \sqcup x_k)$ and wait for OK from $k' > n/2$ nodes + \item Return $x_1 \sqcup \dots \sqcup x_k$ + \end{enumerate} + + \vspace{1em} + + This makes reads slower in some cases, and is \textbf{not implemented in Garage}. +\end{frame} + +\begin{frame} + \frametitle{A hard problem: layout changes} + \begin{itemize} + \item We rely on quorums $k > n/2$ within each partition:\\ + $$n=3,~~~~~~~k\ge 2$$ + \item<2-> When rebalancing, the set of nodes responsible for a partition can change:\\ + $$\{n_A, n_B, n_C\} \to \{n_A, n_D, n_E\}$$ + \vspace{.01em} + \item<3-> During the rebalancing, $D$ and $E$ don't yet have the data,\\ + ~~~~~~~~~~~~~~~~~~~and $B$ and $C$ want to get rid of the data to free up space\\ + \vspace{.2em} + $\to$ quorums only within the new set of nodes don't work\\ + $\to$ how to coordinate? \textbf{currently, we don't...} + + \end{itemize} +\end{frame} + +\section{Operating big Garage clusters} + +\begin{frame} + \frametitle{Operating Garage} + \begin{center} + \only<1-2>{ + \includegraphics[width=.9\linewidth]{assets/scr_garage_status.png} + \\\vspace{1em} + \visible<2>{\includegraphics[width=.85\linewidth]{assets/scr_garage_status_broken.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/scr_garage_stats.png}} + \only<2>{\includegraphics[width=.6\linewidth]{assets/scr_garage_worker_list.png}} + \only<3>{\includegraphics[width=.6\linewidth]{assets/scr_garage_worker_get.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 + \item Multi-HDD support not yet released (soon!) + \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 Wait for v0.9 with 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} + Current deployments: $< 10$ TB, we don't have much experience with more +\end{frame} + +\section{Going further than the S3 API} + +\begin{frame} + \frametitle{Using Garage for everything} + \begin{center} + \only<1>{\includegraphics[width=.8\linewidth]{assets/slideB1.png}}% + \only<2>{\includegraphics[width=.8\linewidth]{assets/slideB2.png}}% + \only<3>{\includegraphics[width=.8\linewidth]{assets/slideB3.png}}% + \end{center} +\end{frame} + +\begin{frame} + \frametitle{K2V Design} + \begin{itemize} + \item A new, custom, minimal API\\ + \vspace{.5em} + \begin{itemize} + \item Single-item operations + \item Operations on ranges and batches of items + \item Polling operations to help implement a PubSub pattern + \end{itemize} + \vspace{1em} + \item<2-> Exposes the partitoning mechanism of Garage\\ + K2V = partition key / sort key / value (like Dynamo) + \vspace{1em} + \item<3-> Weakly consistent, CRDT-friendly\\ + $\to$ no support for transactions (not ACID) + \vspace{1em} + \item<4-> Cryptography-friendly: values are binary blobs + \end{itemize} +\end{frame} + +\begin{frame} + \frametitle{Handling concurrent values} + \textbf{How to handle concurrency?} Example: + \vspace{1em} + \begin{enumerate} + \item Client $A$ reads the initial value of a key, $x_0$ + \vspace{1em} + \item<2-> Client $B$ also reads the initial value $x_0$ of that key + \vspace{1em} + \item<3-> Client $A$ modifies $x_0$, and writes a new value $x_1$ + \vspace{1em} + \item<4-> Client $B$ also modifies $x_0$, and writes a new value $x'_1$,\\ + without having a chance to first read $x_1$\\ + \vspace{1em} + $\to$ what should the final state be? + \end{enumerate} +\end{frame} + +\begin{frame} + \frametitle{Handling concurrent values} + \begin{itemize} + \item If we keep only $x_1$ or $x'_1$, we risk \textbf{loosing application data} + \vspace{1.5em} + \item<2-> Values are opaque binary blobs, \textbf{K2V cannot resolve conflicts} by itself\\ + (e.g. by implementing a CRDT) + \vspace{1.5em} + \item<3-> Solution: \textbf{we keep both!}\\ + $\to$ the value of the key is now $\{x_1, x'_1\}$\\ + $\to$ the client application can decide how to resolve conflicts on the next read + \end{itemize} +\end{frame} + +\begin{frame} + \frametitle{Keeping track of causality} + How does K2V know that $x_1$ and $x'_1$ are concurrent? + \vspace{1em} + \begin{itemize} + \item $read()$ returns \textbf{a set of values} and an associated \textbf{causality token}\\ + \vspace{1.5em} + \item<2-> When calling $write()$, the client sends \textbf{the causality token from its last read} + \vspace{1.5em} + \item<3-> The causality token represents the set of values \textbf{already seen by the client}\\ + $\to$ those values are the \textbf{causal past} of the write operation\\ + $\to$ K2V can keep concurrent values and overwrite all ones in the causal past + \vspace{1.5em} + \item<4-> Internally, the causality token is \textbf{a vector clock} + \end{itemize} +\end{frame} + +\begin{frame} + \frametitle{Application: an e-mail storage server} + \begin{center} + \only<1>{\includegraphics[width=.9\linewidth]{assets/aerogramme.png}}% + \end{center} +\end{frame} + +\begin{frame} + \frametitle{Aerogramme data model} + \begin{center} + \only<1->{\includegraphics[width=.4\linewidth]{assets/aerogramme_datatype.drawio.pdf}}% + \end{center} + \visible<2->{Aerogramme encrypts all stored values for privacy\\ + (Garage server administrators can't read your mail)} +\end{frame} + +\begin{frame} + \frametitle{Different deployment scenarios} + \begin{center} + \only<1>{\includegraphics[width=.9\linewidth]{assets/aerogramme_components1.drawio.pdf}}% + \only<2>{\includegraphics[width=.9\linewidth]{assets/aerogramme_components2.drawio.pdf}}% + \end{center} +\end{frame} + +\begin{frame} + \frametitle{A new model for building resilient software} + How to build an application using only Garage as a data store: + \vspace{1em} + \begin{enumerate} + \item Design a data model suited to K2V\\ + {\footnotesize (see Cassandra docs on porting SQL data models to Cassandra)} + \vspace{1em} + \begin{itemize} + \item Use CRDTs or other eventually consistent data types (see e.g. Bayou) + \vspace{1em} + \item Store opaque binary blobs to provide End-to-End Encryption\\ + \end{itemize} + \vspace{1em} + \item<2-> Store big blobs (files) using the S3 API + \vspace{1em} + \item<3-> Let Garage manage sharding, replication, failover, etc. + \end{enumerate} +\end{frame} + +\section{Conclusion} + +\begin{frame} + \frametitle{Perspectives} + \begin{itemize} + \item Fix the consistency issue when rebalancing + \vspace{1em} + \item Write about Garage's architecture and properties,\\ + and about our proposed architecture for (E2EE) apps over K2V+S3 + \vspace{1em} + \item Continue developing Garage; finish Aerogramme; build new applications... + \vspace{1em} + \item Anything else? + \end{itemize} +\end{frame} + +\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/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 : -- cgit v1.2.3