geo-replication: Use a md5 based unique control path

A hostname fqdn can be of length 255 according to RFC1123
------------------------->
/usr/include/bits/posix1_lim.h:#define _POSIX_HOST_NAME_MAX  255
<-------------------------
On linux this length is 64
------------------------->
/usr/include/bits/local_lim.h:#define HOST_NAME_MAX 64
<-------------------------

When a given hostname is > 45 (characters) - SSH fails with

-------------------------->
"ControlPath too long for Unix domain socket".
<--------------------------

Indicating that the total length of ControlPath which is
on linux should be 108

------------------------->
/usr/include/linux/un.h:#define UNIX_PATH_MAX   108
<-------------------------

This leads to "faulty" geo-replication status.

This patch brings in a new file called manifest which carries
given a geo-rep session some unique information - with which
a unique `md5` is generated in a 32length digest, this ensures
that we don't exceed UNIX_PATH_MAX limitations instead we use
a conservative approach and still be able to provide a unique
socket path.

Change-Id: I3a6a27d605d751a86e7c82eace4561d9b0134fe1
BUG: 990330
Signed-off-by: Harshavardhana <harsha@harshavardhana.net>
Reviewed-on: http://review.gluster.org/5681
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Csaba Henk <csaba@redhat.com>

3 files changed, 41 insertions, 7 deletions

diff --git a/geo-replication/syncdaemon/gconf.py b/geo-replication/syncdaemon/gconf.py
index 146c72a1825..fe5795f16e2 100644
--- a/geo-replication/syncdaemon/gconf.py
+++ b/geo-replication/syncdaemon/gconf.py
@@ -12,9 +12,4 @@ class GConf(object):
     permanent_handles = []
     log_metadata = {}
 
-    @classmethod
-    def setup_ssh_ctl(cls, ctld):
-        cls.ssh_ctl_dir = ctld
-        cls.ssh_ctl_args = ["-oControlMaster=auto", "-S", os.path.join(ctld, "gsycnd-ssh-%r@%h:%p")]
-
 gconf = GConf()
diff --git a/geo-replication/syncdaemon/resource.py b/geo-replication/syncdaemon/resource.py
index 4b0183b981d..401bca7f8e9 100644
--- a/geo-replication/syncdaemon/resource.py
+++ b/geo-replication/syncdaemon/resource.py
@@ -1115,9 +1115,15 @@ class SSH(AbstractUrl, SlaveRemote):
         """
         if go_daemon == 'done':
             return self.start_fd_client(*self.fd_pair)
-        gconf.setup_ssh_ctl(tempfile.mkdtemp(prefix='gsyncd-aux-ssh-'))
+
+        syncdutils.setup_ssh_ctl(tempfile.mkdtemp(prefix='gsyncd-aux-ssh-'),
+                                 self.remote_addr,
+                                 self.inner_rsc.url)
+
         deferred = go_daemon == 'postconn'
-        ret = sup(self, gconf.ssh_command.split() + gconf.ssh_ctl_args + [self.remote_addr], slave=self.inner_rsc.url, deferred=deferred)
+        ret = sup(self, gconf.ssh_command.split() + gconf.ssh_ctl_args + [self.remote_addr],
+                  slave=self.inner_rsc.url, deferred=deferred)
+
         if deferred:
             # send a message to peer so that we can wait for
             # the answer from which we know connection is
diff --git a/geo-replication/syncdaemon/syncdutils.py b/geo-replication/syncdaemon/syncdutils.py
index 720200018e5..c09b2505ddd 100644
--- a/geo-replication/syncdaemon/syncdutils.py
+++ b/geo-replication/syncdaemon/syncdutils.py
@@ -12,6 +12,7 @@ from signal import signal, SIGTERM, SIGKILL
 from time import sleep
 import select as oselect
 from os import waitpid as owaitpid
+
 try:
     from cPickle import PickleError
 except ImportError:
@@ -78,6 +79,38 @@ def update_file(path, updater, merger = lambda f: True):
             if fx:
                 fx.close()
 
+def create_manifest(fname, content):
+    """
+    Create manifest file for SSH Control Path
+    """
+    fd = None
+    try:
+        fd = os.open(fname, os.O_CREAT|os.O_RDWR)
+        try:
+            os.write(fd, content)
+        except:
+            os.close(fd)
+            raise
+    finally:
+        if fd != None:
+            os.close(fd)
+
+def setup_ssh_ctl(ctld, remote_addr, resource_url):
+    """
+    Setup GConf ssh control path parameters
+    """
+    gconf.ssh_ctl_dir = ctld
+    content = "SLAVE_HOST=%s\nSLAVE_RESOURCE_URL=%s" % (remote_addr,
+                                                            resource_url)
+    content_md5 = md5hex(content)
+    fname = os.path.join(gconf.ssh_ctl_dir,
+                         "%s.mft" % content_md5)
+
+    create_manifest(fname, content)
+    ssh_ctl_path = os.path.join(gconf.ssh_ctl_dir,
+                                "%s.sock" % content_md5)
+    gconf.ssh_ctl_args = ["-oControlMaster=auto", "-S", ssh_ctl_path]
+
 def grabfile(fname, content=None):
     """open @fname + contest for its fcntl lock