* `--min-age' flag in nix-store and nix-collect-garbage to only delete

  unreachable paths that haven't been used for N hours.  For instance,
  `nix-collect-garbage --min-age 168' only deletes paths that haven't
  been accessed in the last week.

  This is useful for instance in the build farm where many derivations
  can be shared between consecutive builds, and we wouldn't want a
  garbage collect to throw them all away.  We could of course register
  them as roots, but then we'd to unregister them at some point, which
  would be a pain to manage.  The `--min-age' flag gives us a sort of
  MRU caching scheme.

  BUG: this really shouldn't be in gc.cc since that violates
  mechanism/policy separation.

6 files changed, 70 insertions, 17 deletions

diff --git a/doc/manual/nix-collect-garbage.xml b/doc/manual/nix-collect-garbage.xml
index adc6c1e73..1de50408e 100644
--- a/doc/manual/nix-collect-garbage.xml
+++ b/doc/manual/nix-collect-garbage.xml
@@ -11,6 +11,7 @@
         <arg choice='plain'><option>--print-live</option></arg>
         <arg choice='plain'><option>--print-dead</option></arg>
       </group>
+      <arg><option>--min-age</option> <replaceable>age</replaceable></arg>
     </cmdsynopsis>
   </refsynopsisdiv>
 
@@ -56,6 +57,16 @@
         </listitem>
       </varlistentry>
       
+      <varlistentry>
+        <term><option>--min-age</option> <replaceable>age</replaceable></term>
+        <listitem>
+          <para>
+            This option corresponds to the <option>--min-age</option>
+            option in <command>nix-store <option>--gc</option></command>.
+          </para>
+        </listitem>
+      </varlistentry>
+      
     </variablelist>
 
   </refsection>
diff --git a/doc/manual/nix-store.xml b/doc/manual/nix-store.xml
index febe02fd4..522de60d3 100644
--- a/doc/manual/nix-store.xml
+++ b/doc/manual/nix-store.xml
@@ -147,6 +147,7 @@
           <arg choice='plain'><option>--print-dead</option></arg>
           <arg choice='plain'><option>--delete</option></arg>
         </group>
+        <arg><option>--min-age</option> <replaceable>age</replaceable></arg>
       </cmdsynopsis>
     </refsection>
 
@@ -207,6 +208,17 @@
         Each line should contain exactly one store path.
       </para>
 
+      <para>
+        The option <option>--min-age</option> specifies a minimum time
+        in hours that an unreachable store path must not have been
+        used before it is considered dead.  The default is 0 (consider
+        all unreachable store paths dead).  Whether a store path has
+        been used is determined by looking at its access time
+        (<literal>atime</literal>), so this does not work if the store
+        is located on a file system that has the
+        <literal>noatime</literal> option set.
+      </para>
+
       <warning>
         <para>
           You generally will want to use the command
diff --git a/scripts/nix-collect-garbage.in b/scripts/nix-collect-garbage.in
index 539979cbb..44bcc16bb 100755
--- a/scripts/nix-collect-garbage.in
+++ b/scripts/nix-collect-garbage.in
@@ -9,16 +9,24 @@ my $storeDir = "@storedir@";
 my %alive;
 
 my $gcOper = "--delete";
-my $keepSuccessors = 1;
+my $minAge = 0;
 
 my @roots = ();
 
 
 # Parse the command line.
-foreach my $arg (@ARGV) {
+for (my $i = 0; $i < scalar @ARGV; $i++) {
+    my $arg = $ARGV[$i];
     if ($arg eq "--delete" || $arg eq "--print-live" || $arg eq "--print-dead") {
         $gcOper = $arg;
-    } else { die "unknown argument `$arg'" };
+    }
+    elsif ($arg eq "--min-age") {
+        $i++;
+        $minAge = undef;
+        $minAge = $ARGV[$i];
+        die "invalid minimum age" unless defined $minAge && $minAge =~ /^\d*$/;
+    }
+    else { die "unknown argument `$arg'" };
 }
 
 
@@ -69,7 +77,7 @@ findRoots 1, $rootsDir;
 
 
 # Run the collector with the roots we found.
-my $pid = open2(">&1", \*WRITE, "@bindir@/nix-store --gc $gcOper")
+my $pid = open2(">&1", \*WRITE, "@bindir@/nix-store --gc $gcOper --min-age $minAge")
     or die "cannot run `nix-store --gc'";
 
 foreach my $root (@roots) {
diff --git a/src/libstore/gc.cc b/src/libstore/gc.cc
index aed7c2294..9af957693 100644
--- a/src/libstore/gc.cc
+++ b/src/libstore/gc.cc
@@ -2,6 +2,11 @@
 #include "globals.hh"
 
 
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+
 void followLivePaths(Path nePath, PathSet & live)
 {
     /* Just to be sure, canonicalise the path.  It is important to do
@@ -62,16 +67,26 @@ PathSet findLivePaths(const Paths & roots)
 }
 
 
-PathSet findDeadPaths(const PathSet & live)
+PathSet findDeadPaths(const PathSet & live, time_t minAge)
 {
     PathSet dead;
 
     startNest(nest, lvlDebug, "finding dead paths");
 
+    time_t now = time(0);
+
     Strings storeNames = readDirectory(nixStore);
 
     for (Strings::iterator i = storeNames.begin(); i != storeNames.end(); ++i) {
         Path p = canonPath(nixStore + "/" + *i);
+
+        if (minAge > 0) {
+            struct stat st;
+            if (lstat(p.c_str(), &st) != 0)
+                throw SysError(format("obtaining information about `%1%'") % p);
+            if (st.st_atime + minAge >= now) continue;
+        }
+        
         if (live.find(p) == live.end()) {
             debug(format("dead path `%1%'") % p);
             dead.insert(p);
diff --git a/src/libstore/gc.hh b/src/libstore/gc.hh
index 997057ba9..1ada419da 100644
--- a/src/libstore/gc.hh
+++ b/src/libstore/gc.hh
@@ -17,8 +17,10 @@ PathSet findLivePaths(const Paths & roots);
 
 /* Given a set of "live" store paths, determine the set of "dead"
    store paths (which are simply all store paths that are not in the
-   live set). */
-PathSet findDeadPaths(const PathSet & live);
+   live set).  The value `minAge' specifies the minimum age in seconds
+   for an unreachable file to be considered dead (0 meaning that any
+   unreachable file is dead). */
+PathSet findDeadPaths(const PathSet & live, time_t minAge);
 
 
 #endif /* !__GC_H */
diff --git a/src/nix-store/main.cc b/src/nix-store/main.cc
index 7bc8565d2..e9948c7cf 100644
--- a/src/nix-store/main.cc
+++ b/src/nix-store/main.cc
@@ -212,17 +212,22 @@ static void opIsValid(Strings opFlags, Strings opArgs)
 
 static void opGC(Strings opFlags, Strings opArgs)
 {
-    if (opFlags.size() != 1) throw UsageError("missing flag");
-    if (!opArgs.empty())
-        throw UsageError("no arguments expected");
-
     /* Do what? */
-    string flag = opFlags.front();
     enum { soPrintLive, soPrintDead, soDelete } subOp;
-    if (flag == "--print-live") subOp = soPrintLive;
-    else if (flag == "--print-dead") subOp = soPrintDead;
-    else if (flag == "--delete") subOp = soDelete;
-    else throw UsageError(format("bad sub-operation `%1%' in GC") % flag);
+    time_t minAge = 0;
+    for (Strings::iterator i = opFlags.begin();
+         i != opFlags.end(); ++i)
+        if (*i == "--print-live") subOp = soPrintLive;
+        else if (*i == "--print-dead") subOp = soPrintDead;
+        else if (*i == "--delete") subOp = soDelete;
+        else if (*i == "--min-age") {
+            if (opArgs.size() == 0)
+                throw UsageError("`--min-age' requires an argument");
+            istringstream st(opArgs.front());
+            st >> minAge;
+            if (!st) throw Error("number expected");
+        }
+        else throw UsageError(format("bad sub-operation `%1%' in GC") % *i);
         
     Paths roots;
     while (1) {
@@ -240,7 +245,7 @@ static void opGC(Strings opFlags, Strings opArgs)
         return;
     }
 
-    PathSet dead = findDeadPaths(live);
+    PathSet dead = findDeadPaths(live, minAge * 3600);
 
     if (subOp == soPrintDead) {
         for (PathSet::iterator i = dead.begin(); i != dead.end(); ++i)