* The build hooks used to implement distributed builds can now be run

  in parallel.  Hooks are more efficient: locks on output paths are
  only acquired when the hook says that it is willing to accept a
  build job.  Hooks now work in two phases.  First, they should first
  tell Nix whether they are willing to accept a job.  Nix guarantuees
  that no two hooks will ever be in the first phase at the same time
  (this simplifies the implementation of hooks, since they don't have
  to perform locking (?)).  Second, if they accept a job, they are
  then responsible for building it (on the remote system), and copying
  the result back.  These can be run in parallel with other hooks and
  locally executed jobs.

  The implementation is a bit messy right now, though.  

* The directory `distributed' shows a (hacky) example of a hook that
  distributes build jobs over a set of machines listed in a
  configuration file.
  

1 files changed, 119 insertions, 0 deletions

diff --git a/distributed/build-remote.pl b/distributed/build-remote.pl
new file mode 100755
index 0000000000..f1a9b10f4d
--- /dev/null
+++ b/distributed/build-remote.pl
@@ -0,0 +1,119 @@
+#! /usr/bin/perl -w
+
+use strict;
+
+my $amWilling = shift @ARGV;
+my $localSystem = shift @ARGV;
+my $neededSystem = shift @ARGV;
+my $storeExpr = shift @ARGV;
+
+# Decline if the local system can do the build.
+if ($amWilling && ($localSystem eq $neededSystem)) {
+    print "decline\n";
+    exit 0;
+}
+
+# Otherwise find a willing remote machine.
+my %machines;
+my %systemTypes;
+my %sshKeys;
+my %maxJobs;
+my %curJobs;
+
+# Read the list of machines.
+open CONF, "< /home/eelco/nix/distributed/remote-systems.conf" or die;
+
+while (<CONF>) {
+    chomp;
+    next if /^\s*$/;
+    /^\s*(\S+)\s+(\S+)\s+(\S+)\s+(\d+)\s*$/ or die;
+    $machines{$1} = "";
+    $systemTypes{$1} = $2;
+    $sshKeys{$1} = $3;
+    $maxJobs{$1} = $4;
+}
+
+close CONF;
+
+# Read the current load status.
+open LOAD, "< /home/eelco/nix/distributed/current-load" or die;
+while (<LOAD>) {
+    chomp;
+    next if /^\s*$/;
+    /^\s*(\S+)\s+(\d+)\s*$/ or die;
+    $curJobs{$1} = $2;
+}
+close LOAD;
+
+sub sendReply {
+    my $reply = shift;
+    open OUT, ">&3" or die;
+    print OUT "$reply\n";
+    close OUT;
+}
+
+# Find a suitable system.
+my $rightType = 0;
+my $machine;
+foreach my $cur (keys %machines) {
+    if ($neededSystem eq $systemTypes{$cur}) {
+        $rightType = 1;
+        if (!defined $curJobs{$cur} or
+            ($curJobs{$cur} < $maxJobs{$cur}))
+        {
+            $machine = $cur;
+            last;
+        }
+    }
+}
+
+if (!defined $machine) {
+    if ($rightType) {
+        sendReply "postpone";
+        exit 0;
+    } else {
+        sendReply "decline";
+        exit 0;
+    }
+}
+
+sendReply "accept";
+open IN, "<&4" or die;
+my $x = <IN>;
+chomp $x;
+print "got $x\n";  
+close IN;
+
+print "BUILDING REMOTE: $storeExpr on $machine\n";
+
+my $ssh = "ssh -i $sshKeys{$machine} -x";
+
+my $inputs = `cat inputs`;
+$inputs =~ s/\n/ /g;
+
+my $outputs = `cat outputs`;
+$outputs =~ s/\n/ /g;
+
+my $successors = `cat successors`;
+$successors =~ s/\n/ /g;
+
+system "rsync -a -e '$ssh' $storeExpr $inputs $machine:/nix/store";
+die "cannot rsync inputs to $machine" if ($? != 0);
+
+system "$ssh $machine /nix/bin/nix-store --validpath $storeExpr $inputs";
+die "cannot set valid paths on $machine" if ($? != 0);
+
+system "$ssh $machine /nix/bin/nix-store --successor $successors";
+die "cannot set successors on $machine" if ($? != 0);
+
+print "BUILDING...\n";
+
+system "$ssh $machine /nix/bin/nix-store -qnfvvvv $storeExpr";
+die "remote build on $machine failed" if ($? != 0);
+
+print "REMOTE BUILD DONE\n";
+
+foreach my $output (split '\n', $outputs) {
+    system "rsync -a -e '$ssh' $machine:$output /nix/store";
+    die "cannot rsync outputs from $machine" if ($? != 0);
+}