bitbake: server/process: Add bitbake.sock race handling

We've seen cases where the bitbake.sock file appears to disappear but the
server continues to hold bitbake.lock. The most likely explaination is
that some previous build directory was moved out the way, a server there
kept running, eventually exited and removed the sock file from the wrong
directory.

To guard against this, save the inode information for the sock file and check
it before deleting the file. The new code isn't entirely race free but should
guard against what is a rare but annoying potential issue.

(Bitbake rev: 52b6b099a47555811b8d0b311f62af712dd6eb8e)

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
(cherry picked from commit b02ebbffdae27e564450446bf84c4e98d094ee4a)
Signed-off-by: Steve Sakoman <steve@sakoman.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

1 files changed, 11 insertions, 1 deletions

diff --git a/bitbake/lib/bb/server/process.py b/bitbake/lib/bb/server/process.py
index 2a9fb6623c..3668a32b71 100644
--- a/bitbake/lib/bb/server/process.py
+++ b/bitbake/lib/bb/server/process.py
@@ -28,6 +28,7 @@ import datetime
 import pickle
 import traceback
 import gc
+import stat
 import bb.server.xmlrpcserver
 from bb import daemonize
 from multiprocessing import queues
@@ -64,6 +65,9 @@ class ProcessServer():
         self.bitbake_lock_name = lockname
         self.sock = sock
         self.sockname = sockname
+        # It is possible the directory may be renamed. Cache the inode of the socket file
+        # so we can tell if things changed.
+        self.sockinode = os.stat(self.sockname)[stat.ST_INO]
 
         self.server_timeout = server_timeout
         self.timeout = self.server_timeout
@@ -246,8 +250,14 @@ class ProcessServer():
 
         serverlog("Exiting")
         # Remove the socket file so we don't get any more connections to avoid races
+        # The build directory could have been renamed so if the file isn't the one we created
+        # we shouldn't delete it.
         try:
-            os.unlink(self.sockname)
+            sockinode = os.stat(self.sockname)[stat.ST_INO]
+            if sockinode == self.sockinode:
+                os.unlink(self.sockname)
+            else:
+                serverlog("bitbake.sock inode mismatch (%s vs %s), not deleting." % (sockinode, self.sockinode))
         except Exception as err:
             serverlog("Removing socket file '%s' failed (%s)" % (self.sockname, err))
         self.sock.close()