From a84f503d863fd77de9b6ecf149399c2ca7642b75 Mon Sep 17 00:00:00 2001 From: wmertens Date: Sat, 10 May 2014 15:53:01 +0200 Subject: [PATCH] Shortcut already-hardlinked files If an inode in the Nix store has more than 1 link, it probably means that it was linked into .links/ by us. If so, skip. There's a possibility that something else hardlinked the file, so it would be nice to be able to override this. Also, by looking at the number of hardlinks for each of the files in .links/, you can get deduplication numbers and space savings. --- src/libstore/optimise-store.cc | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/src/libstore/optimise-store.cc b/src/libstore/optimise-store.cc index d833f3aa05..1b81f64078 100644 --- a/src/libstore/optimise-store.cc +++ b/src/libstore/optimise-store.cc @@ -71,6 +71,16 @@ void LocalStore::optimisePath_(OptimiseStats & stats, const Path & path) return; } + stats.totalFiles++; + + /* If a store inode has 2 or more links we presume that it was + already linked by us */ + /* TODO: allow overriding this behavior */ + if (st.st_nlink > 1) { + printMsg(lvlDebug, format("`%1%' is already linked, with %2% other file(s).") % path % (st.st_nlink - 2)); + return; + } + /* Hash the file. Note that hashPath() returns the hash over the NAR serialisation, which includes the execute bit on the file. Thus, executable and non-executable files with the same @@ -81,7 +91,6 @@ void LocalStore::optimisePath_(OptimiseStats & stats, const Path & path) contents of the symlink (i.e. the result of readlink()), not the contents of the target (which may not even exist). */ Hash hash = hashPath(htSHA256, path).first; - stats.totalFiles++; printMsg(lvlDebug, format("`%1%' has hash `%2%'") % path % printHash(hash)); /* Check if this is a known hash. */