Handle ESRCH when getting pgid of a zombie on OS X

3 files changed, 37 insertions, 1 deletions

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0bfb831..e1495ca 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,5 +6,6 @@
 * Enabled travis.
 * Added error? to check if the command ran successfully. MIXLIB-18.
 * Remove GC.disable hack for non-ruby 1.8.8
+* Handle ESRCH from getpgid of a zombie on OS X
 
 ## Last Release: 1.3.0 (12/03/2013)
diff --git a/lib/mixlib/shellout/unix.rb b/lib/mixlib/shellout/unix.rb
index e8aa26e..03f619b 100644
--- a/lib/mixlib/shellout/unix.rb
+++ b/lib/mixlib/shellout/unix.rb
@@ -63,7 +63,7 @@ module Mixlib
         # CHEF-3390: Marshall.load on Ruby < 1.8.7p369 also has a GC bug related
         # to Marshall.load, so try disabling GC first.
         propagate_pre_exec_failure
-        @child_pgid = -Process.getpgid(@child_pid)
+        get_child_pgid
 
         @result = nil
         @execution_time = 0
@@ -107,6 +107,18 @@ module Mixlib
 
       private
 
+      def get_child_pgid
+        # The behavior of Process.getpgid (see also getpgid(2) ) when the
+        # argument is the pid of a zombie isn't well specified. On Linux it
+        # works, on OS X it returns ESRCH (which ruby turns into Errno::ESRCH).
+        #
+        # If the child dies very quickly, @child_pid may be a zombie, so handle
+        # ESRCH here.
+        @child_pgid = -Process.getpgid(@child_pid)
+      rescue Errno::ESRCH
+        @child_pgid = nil
+      end
+
       def set_user
         if user
           Process.euid = uid
@@ -137,6 +149,10 @@ module Mixlib
 
       # Process group id of the child. Returned as a negative value so you can
       # put it directly in arguments to kill, wait, etc.
+      #
+      # This may be nil if the child dies before the parent can query the
+      # system for its pgid (on some systems it is an error to get the pgid of
+      # a zombie).
       def child_pgid
         @child_pgid
       end
diff --git a/spec/mixlib/shellout_spec.rb b/spec/mixlib/shellout_spec.rb
index 42f2714..03bb47b 100644
--- a/spec/mixlib/shellout_spec.rb
+++ b/spec/mixlib/shellout_spec.rb
@@ -843,6 +843,25 @@ describe Mixlib::ShellOut do
         end
       end
 
+      context "when the child process dies immediately" do
+        let(:cmd) { [ 'exit' ] }
+
+        it "handles ESRCH from getpgid of a zombie" do
+          Process.stub(:setsid) { exit!(4) }
+
+          # there is a small race condition here if the child doesn't get
+          # scheduled and call exit! before the parent can call getpgid, so run
+          # this a few times to make sure we've created the reproduction case
+          # correctly.
+          5.times do
+            s = Mixlib::ShellOut.new(cmd)
+            s.run_command # should not raise Errno::ESRCH
+          end
+
+        end
+
+      end
+
       context 'with subprocess that takes longer than timeout' do
         def ruby_wo_shell(code)
           parts = %w[ruby]