diff --git a/common/images/2019-06-archive-growth.png b/common/images/2019-06-archive-growth.png new file mode 100644 index 0000000..11ba86c Binary files /dev/null and b/common/images/2019-06-archive-growth.png differ diff --git a/common/images/general-architecture.pdf b/common/images/general-architecture.pdf new file mode 100644 index 0000000..dd8af9e Binary files /dev/null and b/common/images/general-architecture.pdf differ diff --git a/common/images/general-architecture.svg b/common/images/general-architecture.svg new file mode 100644 index 0000000..8dcbc31 --- /dev/null +++ b/common/images/general-architecture.svg @@ -0,0 +1,3687 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + image/svg+xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ObjStorage + API + + + + + Object Storage + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Web App + + + + + + + + + + + + + + + + + + + Scheduler + API + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Deposit + API + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Vault + API + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Indexer + API + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Storage + API + + + + + + + + + + + + + + + Journal + + + + Lister + + + + + + + + + + + + + + + + + + + + + + + + + + + Celery Broker + + + Scheduler + + + + + + + + + + listener + workers + + + + Scheduler + + + + + + + + + + runner + + + + + + + + + + + + + Loader + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Indexer + + + + + + + + + + + + + + + workers + workers + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Kafka + topics + diff --git a/common/images/swh-data-model-h.pdf b/common/images/swh-data-model-h.pdf new file mode 100644 index 0000000..e45b26c Binary files /dev/null and b/common/images/swh-data-model-h.pdf differ diff --git a/common/images/swh-data-model-h.svg b/common/images/swh-data-model-h.svg new file mode 100644 index 0000000..9f5fdfe --- /dev/null +++ b/common/images/swh-data-model-h.svg @@ -0,0 +1,1048 @@ + + + + + + image/svg+xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Origin + + + Origin + + + + + + + + url: str + + + + url: str + + + + + + + + + branches + + + branches + + + + + + + + + + + + Snapshot + + + Snapshot + + + + + + + * + + + * + + + + + + + * + + + * + + + + + + + + + + + + Release + + + Release + + + + + + + + directory + + + directory + + + + + + + + + + Revision + + + Revision + + + + + + + * + + + * + + + + + + + * + + + * + + + + + + + * + + + * + + + + + + + * + + + * + + + + + + + + Merkle DAG + + + Merkle DAG + + + + + + + branches + + + branches + + + + + + + * + + + + 1 + + + + + + + + entries + + + entries + + + + + + + + directory + + + parents + + + + + + + branches + + + snapshots + + + + + + + + url: str + + + + id: str + + + + + + + + + + Directory + + + Directory + + + + + + + entries + + + entries + + + + + + + + url: str + + + + id: str + + + + id: str+ author: str+ name: str+ message: str+ timestamp: datetime + + id: str+ author: str+ message: str+ timestamp: datetime + + + + + + + + + Directory + + + Content + + + + + + + + url: str + + + + + sha1: str + + + + diff --git a/common/images/swh-merkle-dag-small-visit1.pdf b/common/images/swh-merkle-dag-small-visit1.pdf new file mode 100644 index 0000000..bdecae2 Binary files /dev/null and b/common/images/swh-merkle-dag-small-visit1.pdf differ diff --git a/common/images/swh-merkle-dag-small-visit1.svg b/common/images/swh-merkle-dag-small-visit1.svg new file mode 100644 index 0000000..de4898e --- /dev/null +++ b/common/images/swh-merkle-dag-small-visit1.svg @@ -0,0 +1,1493 @@ + + + + + + image/svg+xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + origin + + + visit + + + https://forge.softwareheritage.org/source/helloworld.git + + + snapshot + + + 1 + + + timestamp + + + Fri Feb 9 12:38:45 2018 +0100 + + + 0861db5e… + + + + + <<Revision>> + a3ee21ad… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "add build toolchain …" + +timestamp = Thu Feb 8 10:49:29 2018 +0100 + +directory: Directory + +parents: Revision list + + + + <<Directory>> + b94a90cd… + + +entries + ".gitignore" + "Makefile" + "hello.c" + + + + <<Content>> + 225ae01b… + + +data = "all: hello\n\n…" + + + + <<Revision>> + 43ef7dcd… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "add licensing information and README" + +timestamp = Thu Feb 8 10:54:09 2018 +0100 + +directory: Directory + +parents: Revision list + + + + + <<Directory>> + fa8c0908… + + +entries + ".gitignore" + "COPYING" + "Makefile" + "README.md" + "hello.c" + + + + <<Content>> + a1afd006… + + +data = "…Yet another…" + + + + <<Release>> + edf82f21… + + +author = "Stefano Zacchiroli <zack@…>" + +name = "1.0" + +message = "1.0 release" + +timestamp = Thu Feb 8 15:51:00 2018 +0100 + +target + + + + <<Snapshot>> + 0861db5e… + + +branches + HEAD + refs/heads/master + refs/tags/1.0 + + + Archive content + after visit 1 + + + + <<Content>> + c839dea9… + + +data = "#include …" + + + + <<Directory>> + 6ca2e444… + + +entries + "hello.c" + + + + <<Revision>> + 1886826f… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "implement a trivial …" + +timestamp = Thu Feb 8 10:44:35 2018 +0100 + +directory: Directory + +parents: Revision list = None + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/common/images/swh-merkle-dag-small-visit2.pdf b/common/images/swh-merkle-dag-small-visit2.pdf new file mode 100644 index 0000000..d46c6c1 Binary files /dev/null and b/common/images/swh-merkle-dag-small-visit2.pdf differ diff --git a/common/images/swh-merkle-dag-small-visit2.svg b/common/images/swh-merkle-dag-small-visit2.svg new file mode 100644 index 0000000..f92d2e8 --- /dev/null +++ b/common/images/swh-merkle-dag-small-visit2.svg @@ -0,0 +1,1584 @@ + + + + + + image/svg+xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + origin + + + visit + + + https://forge.softwareheritage.org/source/helloworld.git + + + snapshot + + + 1 + + + https://forge.softwareheritage.org/source/helloworld.git + + + 2 + + + timestamp + + + Fri Feb 9 12:38:45 2018 +0100 + + + Fri Feb 9 13:29:00 2018 +0100 + + + 0861db5e… + + + 0861db5e… + + + + + <<Revision>> + a3ee21ad… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "add build toolchain …" + +timestamp = Thu Feb 8 10:49:29 2018 +0100 + +directory: Directory + +parents: Revision list + + + + <<Directory>> + b94a90cd… + + +entries + ".gitignore" + "Makefile" + "hello.c" + + + + <<Content>> + 225ae01b… + + +data = "all: hello\n\n…" + + + + <<Revision>> + 43ef7dcd… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "add licensing information and README" + +timestamp = Thu Feb 8 10:54:09 2018 +0100 + +directory: Directory + +parents: Revision list + + + + + <<Directory>> + fa8c0908… + + +entries + ".gitignore" + "COPYING" + "Makefile" + "README.md" + "hello.c" + + + + <<Content>> + a1afd006… + + +data = "…Yet another…" + + + + <<Release>> + edf82f21… + + +author = "Stefano Zacchiroli <zack@…>" + +name = "1.0" + +message = "1.0 release" + +timestamp = Thu Feb 8 15:51:00 2018 +0100 + +target + + + + <<Snapshot>> + 0861db5e… + + +branches + HEAD + refs/heads/master + refs/tags/1.0 + + + Archive content after visits 1 and 2 + + + + <<Content>> + c839dea9… + + +data = "#include …" + + + + <<Directory>> + 6ca2e444… + + +entries + "hello.c" + + + + <<Revision>> + 1886826f… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "implement a trivial …" + +timestamp = Thu Feb 8 10:44:35 2018 +0100 + +directory: Directory + +parents: Revision list = None + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/common/images/swh-merkle-dag-small.pdf b/common/images/swh-merkle-dag-small.pdf new file mode 100644 index 0000000..7c75469 Binary files /dev/null and b/common/images/swh-merkle-dag-small.pdf differ diff --git a/common/images/swh-merkle-dag-small.svg b/common/images/swh-merkle-dag-small.svg new file mode 100644 index 0000000..802e5f9 --- /dev/null +++ b/common/images/swh-merkle-dag-small.svg @@ -0,0 +1,2012 @@ + + + + + + image/svg+xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + origin + + + visit + + + https://forge.softwareheritage.org/source/helloworld.git + + + snapshot + + + 1 + + + https://forge.softwareheritage.org/source/helloworld.git + + + 2 + + + timestamp + + + Fri Feb 9 12:38:45 2018 +0100 + + + Fri Feb 9 13:29:00 2018 +0100 + + + https://forge.softwareheritage.org/source/helloworld.git + + + 3 + + + Fri Feb 9 15:52:50 2018 +0100 + + + 510aa88b… + + + 0861db5e… + + + 0861db5e… + + + + + + <<Revision>> + a3ee21ad… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "add build toolchain …" + +timestamp = Thu Feb 8 10:49:29 2018 +0100 + +directory: Directory + +parents: Revision list + + + + <<Directory>> + b94a90cd… + + +entries + ".gitignore" + "Makefile" + "hello.c" + + + + <<Content>> + 225ae01b… + + +data = "all: hello\n\n…" + + + + <<Revision>> + 43ef7dcd… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "add licensing information and README" + +timestamp = Thu Feb 8 10:54:09 2018 +0100 + +directory: Directory + +parents: Revision list + + + + + <<Revision>> + c7640e8d… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "move source code to src/\n…" + +timestamp = Thu Feb 8 15:26:08 2018 +0100 + +directory: Directory + +parents: Revision list + + + + <<Directory>> + fa8c0908… + + +entries + ".gitignore" + "COPYING" + "Makefile" + "README.md" + "hello.c" + + + + <<Content>> + a1afd006… + + +data = "…Yet another…" + + + + <<Directory>> + 45f0c078… + + +entries + "COPYING" + "Makefile" + "README.md" + "src" + + + + + + + <<Release>> + edf82f21… + + +author = "Stefano Zacchiroli <zack@…>" + +name = "1.0" + +message = "1.0 release" + +timestamp = Thu Feb 8 15:51:00 2018 +0100 + +target + + + + <<Snapshot>> + 0861db5e… + + +branches + HEAD + refs/heads/master + refs/tags/1.0 + + + + <<Snapshot>> + 510aa88b… + + +branches + HEAD + refs/heads/master + refs/heads/doc + refs/tags/1.0 + + + Archive content after visits 1 and 2 + + + + <<Content>> + c839dea9… + + +data = "#include …" + + + + <<Directory>> + 6ca2e444… + + +entries + "hello.c" + + + + <<Revision>> + 1886826f… + + +author = "Stefano Zacchiroli <zack@…>" + +message = "implement a trivial …" + +timestamp = Thu Feb 8 10:44:35 2018 +0100 + +directory: Directory + +parents: Revision list = None + + + + + + + + + + + + + + + + + + + + ... + + + + + Archive content + after visits 1, 2 and 3 + + + + + + + + + + + + + + + + + + diff --git a/common/modules/status-extended.org b/common/modules/status-extended.org index 54d1435..ea88ac3 100644 --- a/common/modules/status-extended.org +++ b/common/modules/status-extended.org @@ -1,461 +1,489 @@ #+COLUMNS: %40ITEM %10BEAMER_env(Env) %9BEAMER_envargs(Env Args) %10BEAMER_act(Act) %4BEAMER_col(Col) %10BEAMER_extra(Extra) %8BEAMER_opt(Opt) #+INCLUDE: "prelude.org" :minlevel 1 # not to be included as a whole, just pick individual slides as you see fit * Status :PROPERTIES: :CUSTOM_ID: main :END: ** The people :PROPERTIES: :CUSTOM_ID: people :END: *** The core team :B_picblock: :PROPERTIES: :CUSTOM_ID: core-team-formal :BEAMER_env: picblock :BEAMER_opt: pic=team,width=.4\linewidth :END: - Roberto Di Cosmo - Stefano Zacchiroli - Nicolas Dandrimont (Engineer) - Antoine Dumont (Engineer) # - and /Jordi, Quentin and Guillaume/ *** Scientific advisors - Serge Abiteboul (French Science Academy) - Jean-François Abramatic (former W3C director) - Gerard Berry (CNRS Gold Medal, French Science Academy) - Julia Lawall (Coccinelle, Linux Kernel, Outreachy) ** Archive coverage --- archive.softwareheritage.org :PROPERTIES: :CUSTOM_ID: archive :END: #+BEAMER: \vspace{-1mm} - #+BEAMER: \begin{center}\includegraphics[width=\extblockscale{1.1\linewidth}]{2019-01-archive-growth.png}\end{center} + #+BEAMER: \begin{center}\includegraphics[width=\extblockscale{1.1\linewidth}]{2019-06-archive-growth.png}\end{center} #+BEAMER: \vspace{-2mm} -*** +*** #+BEAMER: \includegraphics[width=0.19\linewidth]{coverage/github} \hfill #+BEAMER: \includegraphics[width=0.2\linewidth]{coverage/debian} \hfill #+BEAMER: \includegraphics[width=0.2\linewidth]{coverage/gitlab} \hfill #+BEAMER: \includegraphics[width=0.2\linewidth]{coverage/googlecode} \\ #+BEAMER: \includegraphics[width=0.2\linewidth]{coverage/gitorious} \hfill #+BEAMER: \includegraphics[width=0.15\linewidth]{coverage/gnu} \hfill #+BEAMER: \includegraphics[width=0.13\linewidth]{coverage/hal} \hfill #+BEAMER: \includegraphics[width=0.16\linewidth]{coverage/inria} \hfill #+BEAMER: \includegraphics[width=0.13\linewidth]{coverage/pypi} #+BEAMER: \pause -*** - - 200 TB (compressed) blobs, 6 TB database (as a graph: 10 B nodes + 100 B edges) +*** + - 410 TB (uncompressed) blobs, 20 B nodes, 280 B edges - The /richest/ public source code archive, ... and growing daily! ** The structure of the archive :noexport: *** On-disk storage - flat file storage for contents - postgres database for the metadata *** Data model: /one/ big Merkle DAG, inspired by the git model - Origins (= repositories) - Occurrences (= branches) - Releases (= tags) - Revisions (= commits) - Directories (= trees) - Contents (= blobs) ** Archiving goals :PROPERTIES: :CUSTOM_ID: archivinggoals :END: Targets: VCS repositories & source code releases (e.g., tarballs) *** We DO archive - file *content* (= blobs) - *revisions* (= commits), with full metadata - *releases* (= tags), ditto - where (*origin*) & when (*visit*) we found any of the above # - time-indexed repo *snapshots* (i.e., we never delete anything) … in a VCS-/archive-agnostic *canonical data model* *** We DON'T archive # - diffs → derived data from related contents - homepages, wikis - BTS/issues/code reviews/etc. - mailing lists Long term vision: play our part in a /"semantic wikipedia of software"/ ** Architecture :PROPERTIES: :CUSTOM_ID: architecture :END: *** Data flow :PROPERTIES: :CUSTOM_ID: dataflow :END: # #+BEAMER: \begin{center}\includegraphics[width=\extblockscale{1.2\textwidth}]{swh-dataflow.pdf}\end{center} ** Data model :noexport: *** General schema - VCS-independent - fully deduplicated + files, directories and commits are /shared/ - biggest git-like /graph/ in the world *** \begin{center} \url{http://deb.li/swhdm} \end{center} *** full hash index (sha1, sha256, ...) Some funny facts: - the GPL2 licence appears under more than 500 names + including /aa.css.txt/ and /FullSync.txt/ ~ :-) ** Merkle DAG *** Merkle structure :PROPERTIES: :CUSTOM_ID: merkle :END: **** Merkle trees :PROPERTIES: :CUSTOM_ID: merkletree :END: # R. C. Merkle, A digital signature based on a conventional encryption # function, Crypto '87 #+BEAMER: \vspace{-3mm} ***** Merkle tree (R. C. Merkle, Crypto 1979) :B_picblock: :PROPERTIES: :BEAMER_opt: pic=merkle, leftpic=true, width=.7\linewidth :BEAMER_env: picblock :BEAMER_act: :END: Combination of - tree - hash function #+BEAMER: \pause #+BEAMER: \footnotesize ***** Classical cryptographic construction - fast, parallel signature of large data structures - widely used (e.g., Git, blockchains, IPFS, ...) - built-in deduplication #+BEAMER: \vspace{-1mm} +**** Data Model + :PROPERTIES: + :CUSTOM_ID: datamodel + :END: +***** The archive: a (giant) Merkle DAG + #+BEAMER: \vspace{-3mm} + #+BEAMER: \centering \includegraphics[width=\textwidth]{swh-data-model-h} + **** The archive in a few pictures :PROPERTIES: :CUSTOM_ID: merkledemo :END: ***** A giant (extended) Merkle DAG #+LATEX: \only<1>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/merkle_1.pdf}}} #+LATEX: \only<2>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/contents.pdf}}} #+LATEX: \only<3>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/merkle_2_contents.pdf}}} #+LATEX: \only<4>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/directories.pdf}}} #+LATEX: \only<5>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/merkle_3_directories.pdf}}} #+LATEX: \only<6>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/revisions.pdf}}} #+LATEX: \only<7>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/merkle_4_revisions.pdf}}} #+LATEX: \only<8>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/releases.pdf}}} #+LATEX: \only<9>{\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/merkle_5_releases.pdf}}} # #+LATEX: {\colorbox{white}{\includegraphics[width=\extblockscale{.9\linewidth}]{git-merkle/merkle_1.pdf}}} *** A revision node :PROPERTIES: :CUSTOM_ID: merklerevision :END: **** Example: a Software Heritage revision ***** #+BEAMER: \vspace{-.5cm}\centering\includegraphics[width=0.9\textwidth]{git-merkle/revisions} ***** Note: most object kinds currently have Git-compatible identifiers *** Giant DAG :PROPERTIES: :CUSTOM_ID: giantdag :END: **** The archive: a (giant) Merkle DAG # Using an empty frame because the image is difficult to read on swh bg. # Finding a way to override image bg for just this frame would be better. ***** #+BEAMER: \centering \includegraphics[width=\extblockscale{\textwidth}]{git-merkle/merkle_5_releases} *** Giant DAG (single slide) :PROPERTIES: :CUSTOM_ID: giantdag1slide :END: **** The Software Heritage archive: a gigantic Merkle DAG #+LATEX: \centering\forcebeamerstart{} #+LATEX: \only<1>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/merkle_1}}} #+LATEX: \only<2>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/contents}}} #+LATEX: \only<3>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/merkle_2_contents}}} #+LATEX: \only<4>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/directories}}} #+LATEX: \only<5>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/merkle_3_directories}}} #+LATEX: \only<6>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/revisions}}} #+LATEX: \only<7>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/merkle_4_revisions}}} #+LATEX: \only<8>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/releases}}} #+LATEX: \only<9>{\colorbox{white}{\includegraphics[width=.75\linewidth]{git-merkle/merkle_5_releases}}} #+LATEX: \forcebeamerend{} *** Giant DAG (detailed) :PROPERTIES: :CUSTOM_ID: dagdetail :END: **** The archive: a (giant) Merkle DAG #+BEAMER: \vspace{-3mm} #+BEAMER: \centering \includegraphics[width=\textwidth]{swh-merkle-dag-wide} +*** Giant DAG (detailed) + :PROPERTIES: + :CUSTOM_ID: dagdetailsmall + :END: +**** The archive: a (giant) Merkle DAG + #+BEAMER: \vspace{-3mm} + #+BEAMER: \centering \includegraphics[width=\textwidth]{swh-merkle-dag-small-visit1} +**** The archive: a (giant) Merkle DAG + #+BEAMER: \vspace{-3mm} + #+BEAMER: \centering \includegraphics[width=\textwidth]{swh-merkle-dag-small-visit2} +**** The archive: a (giant) Merkle DAG + #+BEAMER: \vspace{-3mm} + #+BEAMER: \centering \includegraphics[width=\textwidth]{swh-merkle-dag-small} ** Technology :noexport: :PROPERTIES: :CUSTOM_ID: technology :END: *** Software stack **** 3rd party - Debian, Puppet, Ceph - PostgreSQL for metadata storage, with barman & pglogical - Celery (RabbitMQ backend) for task scheduling - Python3 and psycopg2 for the backend - Django, Bootstrap, D3.js for Web stuff **** in house - /ad hoc/ object storage (to avoid imposing tech to mirrors) - data model implementation, listers, loaders, scheduler - ~60 Git repositories (~20 Python packages, ~30 Puppet modules) - - ~30 kSLOC Python / ~12 kSLOC SQL / ~4 kSLOC Puppet + - ~60 kSLOC Python / ~12 kSLOC SQL / ~4 kSLOC Puppet - licence choice: GPLv3 (backend) / AGPLv3 (frontend) *** Hardware stack **** in house - 2x hypervisors with ~20 VMs + - 1x high performance database server + - 2x dedicated storage server using - 2x high density storage array (60 * 6TB => 300TB usable each) - - Prototype: ceph storage cluster for blobs + - 3x nodes for a kafka+elasticsearch cluster **** on Azure - full object storage mirror - full mirror of the database containing the graph - workers for content indexing - workers for download bundle preparation -**** at the University of Bologna - - backend storage (60TB) for the bundles available for download + +*** Deployment architecture + :PROPERTIES: + :CUSTOM_ID: deployment-architecture + :END: + #+BEAMER: \vspace{1mm} + #+BEAMER: \centering \includegraphics[height=.9\textheight]{general-architecture} *** Software architecture :noexport: **** Module dependencies (internal + external) :B_picblock: :PROPERTIES: :BEAMER_env: picblock :BEAMER_opt: pic=swh-modules-deps-all,width=\linewidth :END: **** let's zoom in: http://deb.li/swhdeps ** Technology :noexport: :PROPERTIES: :CUSTOM_ID: technology-short :END: *** Deployment and resource usage **** Software - - around 30k SLOC of custom Python code, running on Debian Stable + - around 60k SLOC of custom Python code, running on Debian Stable - PostgreSQL database for the metadata storage - Full docker-compose development environment - Work in progress: scale-out metadata storage (Cassandra?) - Work in progress: mirroring infrastructure (Kafka) **** Hardware - 12 servers (hypervisors, database, storage, staging and testing infrastructure) / 40 virtual machines with mass storage and a backup server at Inria - In-kind sponsorship of cloud and storage resources (Microsoft, University of Bologna) ** Software development :noexport: :PROPERTIES: :CUSTOM_ID: development :END: *** Software development **** classic FOSS development - language: English - development mailing list #+BEAMER: \\{\small \url{https://sympa.inria.fr/sympa/info/swh-devel}} - IRC #+BEAMER: \\ #swh-devel / FreeNode - Forge #+BEAMER: \\{\small \url{https://forge.softwareheritage.org}} - Git, tasks, code review, etc. **** for more information #+BEAMER: \scriptsize https://www.softwareheritage.org/community/developers/ ** Roadmap :PROPERTIES: :CUSTOM_ID: features :END: *** Features... - (done) *lookup* by content hash - (done) *browsing*: "wayback machine" for source code (API + UI) - (early access) *deposit* of source code bundles directly to the archive - (early access) *save code now*, on-demand archive - (done) *download*: =wget= / =git clone= from the archive - (todo) *provenance* lookup for all archived content - (todo) *full-text search* on all archived source code files #+BEAMER: \pause *** ... and much more than one could possibly imagine all the world's software development history at hand's reach! ** Web API :noexport: :PROPERTIES: :CUSTOM_ID: api :END: *** Web API :PROPERTIES: :CUSTOM_ID: apiintro :END: **** RESTful API to programmatically access the Software Heritage archive \\ *\url{https://archive.softwareheritage.org/api/}* **** Features - pointwise *browsing* of the archive - … snapshots → revisions → directories → contents … - full access to the *metadata* of archived objects - *crawling* information - /when have you last visited this Git repository I care about?/ - /where were its branches/tags pointing to at the time?/ # - derived information about archived contents (WIP) # - MIME type, programming language, license, etc. **** Endpoint index \url{https://archive.softwareheritage.org/api/1/} *** A tour of the Web API --- origins & visits :PROPERTIES: :CUSTOM_ID: apitourvisits :END: #+BEAMER: \footnotesize #+BEGIN_SRC GET https://archive.softwareheritage.org/api/1/origin/ \ git/url/https://github.com/hylang/hy { "id": 1, "origin_visits_url": "/api/1/origin/1/visits/", "type": "git", "url": "https://github.com/hylang/hy" } #+END_SRC #+BEAMER: \vfill #+BEGIN_SRC GET https://archive.softwareheritage.org/api/1/origin/ \ 1/visits/ [ ..., { "date": "2016-09-14T11:04:26.769266+00:00", "origin": 1, "origin_visit_url": "/api/1/origin/1/visit/13/", "status": "full", "visit": 13 }, ... ] #+END_SRC *** A tour of the Web API --- snapshots :PROPERTIES: :CUSTOM_ID: apitoursnapshots :END: #+BEAMER: \footnotesize #+BEGIN_SRC GET https://archive.softwareheritage.org/api/1/origin/ \ 1/visit/13/ { ..., "occurrences": { ..., "refs/heads/master": { "target": "b94211251...", "target_type": "revision", "target_url": "/api/1/revision/b94211251.../" }, "refs/tags/0.10.0": { "target": "7045404f3...", "target_type": "release", "target_url": "/api/1/release/7045404f3.../" }, ... }, "origin": 1, "origin_url": "/api/1/origin/1/", "status": "full", "visit": 13 } #+END_SRC *** A tour of the Web API --- releases :noexport: :PROPERTIES: :CUSTOM_ID: apitourreleases :END: #+BEAMER: \footnotesize #+BEGIN_SRC GET https://archive.softwareheritage.org/api/1/release/ \ 7045404f3d1c54e6473c71bbb716529fbad4be24/ { "author": { "email": "tag@pault.ag", "fullname": "Paul Tagliamonte ", "id": 96, "name": "Paul Tagliamonte" }, "date": "2014-04-10T23:01:28-04:00", "message": "0.10: The Oh f*ck it's PyCon release", "name": "0.10.0", "synthetic": false, "target": "6072557b6...", "target_type": "revision", "target_url": "/api/1/revision/6072557b6.../", ... } #+END_SRC *** A tour of the Web API --- revisions :PROPERTIES: :CUSTOM_ID: apitourrevisions :END: #+BEAMER: \footnotesize #+BEGIN_SRC GET https://archive.softwareheritage.org/api/1/revision/ \ 6072557b6c10cd9a21145781e26ad1f978ed14b9/ { "author": { "email": "tag@pault.ag", "fullname": "Paul Tagliamonte ", "id": 96, "name": "Paul Tagliamonte" }, "committer": { ... }, "date": "2014-04-10T23:01:11-04:00", "committer_date": "2014-04-10T23:01:11-04:00", "directory": "2df4cd84e...", "directory_url": "/api/1/directory/2df4cd84e.../", "history_url": "/api/1/revision/6072557b6.../log/", "merge": false, "message": "0.10: The Oh f*ck it's PyCon release", "parents": [ { "id": "10149f66e...", "url": "/api/1/revision/10149f66e.../" } ], ... } #+END_SRC *** A tour of the Web API --- contents :PROPERTIES: :CUSTOM_ID: apitourcontents :END: #+BEAMER: \footnotesize #+BEGIN_SRC GET https://archive.softwareheritage.org/api/1/content/ \ adc83b19e793491b1c6ea0fd8b46cd9f32e592fc/ { "data_url": "/api/1/content/sha1:adc83b19e.../raw/", "filetype_url": "/api/1/content/sha1:.../filetype/", "language_url": "/api/1/content/sha1:.../language/", "length": 1, "license_url": "/api/1/content/sha1:.../license/", "sha1": "adc83b19e...", "sha1_git": "8b1378917...", "sha256": "01ba4719c...", "status": "visible" } #+END_SRC #+BEAMER: \normalsize \vfill \pause **** Caveats - rate limits apply throughout the API - raw download available for textual contents ** Accessing the archive :noexport: :PROPERTIES: :CUSTOM_ID: accessing-short :END: *** Browse :B_block:BMCOL: :PROPERTIES: :BEAMER_col: 0.4 :BEAMER_env: block :END: #+BEAMER: \begin{center}\includegraphics[width=0.5\textwidth]{archive-browse}\end{center} - https://archive.softwareheritage.org/browse - way back machine for software source code #+BEAMER: \pause *** Web API :B_block:BMCOL: :PROPERTIES: :BEAMER_col: 0.4 :BEAMER_env: block :END: #+BEAMER: \begin{center}\includegraphics[width=0.5\textwidth]{archive-webapi}\end{center} - https://archive.softwareheritage.org/api - point-wise navigation of the archive as a graph ** Some technical challenges :PROPERTIES: :CUSTOM_ID: techchallenges :END: *** Expanding the archive - discover and classify /all/ the software sources - importers for other VCSs (SVN, Hg, ...) \hfill /We need your help!/ *** Staying current get new repositories and commits ASAP\\ \hfill /We need reliable, standardised event feeds./ *** Handling the backlog ingesting all the pre-existing data\\ \hfill /Decades of software development are waiting!/