geo-rep: Fix syncing of hardlink of symlink

Problem:
If there is a hardlink to a symlink on master
and if the symlink file is deleted on master,
geo-rep fails to sync the hardlink.

Typical Usecase:
It's easily hit with rsnapshot use case where
it uses hardlinks.

Example Reproducer:
Setup geo-replication between master and slave
volume and in master mount point, do the following.

 1. mkdir /tmp/symlinkbug
 2. ln -f -s /does/not/exist /tmp/symlinkbug/a_symlink
 3. rsync -a /tmp/symlinkbug ./
 4. cp -al symlinkbug symlinkbug.0
 5. ln -f -s /does/not/exist2 /tmp/symlinkbug/a_symlink
 6. rsync -a /tmp/symlinkbug ./
 7. cp -al symlinkbug symlinkbug.1

Cause:
If the source was not present while syncing hardlink,
it was always packing the blob as regular file.

Fix:
If the source was not present while syncing hardlink,
pack the blob based on the mode.

> Change-Id: Iaa12d6f99de47b18e0650e7c4eb455f23f8390f2
> BUG: 1432046
> Signed-off-by: Kotresh HR <khiremat@redhat.com>
> Reported-by: Christian Lohmaier <lohmaier+rhbz@gmail.com>
> Reviewed-on: https://review.gluster.org/18011
> Smoke: Gluster Build System <jenkins@build.gluster.org>
> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
> Reviewed-by: Aravinda VK <avishwan@redhat.com>
(cherry picked from commit e893962deaabab8e934813f8a0443a8f94e009f2)

Change-Id: Iaa12d6f99de47b18e0650e7c4eb455f23f8390f2
BUG: 1486120
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: https://review.gluster.org/18127
Smoke: Gluster Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Shyamsundar Ranganathan <srangana@redhat.com>

1 files changed, 20 insertions, 6 deletions

diff --git a/geo-replication/syncdaemon/master.py b/geo-replication/syncdaemon/master.py
index 2aae860f5d1..2987bca0601 100644
--- a/geo-replication/syncdaemon/master.py
+++ b/geo-replication/syncdaemon/master.py
@@ -24,7 +24,7 @@ from datetime import datetime
 from gconf import gconf
 from syncdutils import Thread, GsyncdError, boolify, escape_space_newline
 from syncdutils import unescape_space_newline, gauxpfx, md5hex, selfkill
-from syncdutils import lstat, errno_wrap, FreeObject, lf
+from syncdutils import lstat, errno_wrap, FreeObject, lf, matching_disk_gfid
 from syncdutils import NoStimeAvailable, PartialHistoryAvailable
 
 URXTIME = (-1, 0)
@@ -792,6 +792,10 @@ class GMasterChangelogMixin(GMasterCommon):
         fix_entry_ops = []
         failures1 = []
         for failure in failures:
+            if failure[2]['dst']:
+                pbname = failure[0]['entry1']
+            else:
+                pbname = failure[0]['entry']
             if failure[2]['gfid_mismatch']:
                 slave_gfid = failure[2]['slave_gfid']
                 st = lstat(os.path.join(pfx, slave_gfid))
@@ -800,7 +804,6 @@ class GMasterChangelogMixin(GMasterCommon):
                                     ' the entry', retry_count=retry_count,
                                     entry=repr(failure)))
                     #Add deletion to fix_entry_ops list
-                    pbname = failure[0]['entry']
                     if failure[2]['slave_isdir']:
                         fix_entry_ops.append(edct('RMDIR',
                                                   gfid=failure[2]['slave_gfid'],
@@ -836,7 +839,6 @@ class GMasterChangelogMixin(GMasterCommon):
                                         ' Deleting the entry',
                                         retry_count=retry_count,
                                         entry=repr(failure)))
-                        pbname = failure[0]['entry']
                         fix_entry_ops.append(edct('UNLINK',
                                                   gfid=failure[2]['slave_gfid'],
                                                   entry=pbname))
@@ -1024,15 +1026,27 @@ class GMasterChangelogMixin(GMasterCommon):
                                         stat=st, link=rl))
                 else:
                     # stat() to get mode and other information
+                    if not matching_disk_gfid(gfid, en):
+                        logging.debug(lf('Ignoring entry, purged in the '
+                                      'interim', file=en, gfid=gfid))
+                        continue
+
                     go = os.path.join(pfx, gfid)
                     st = lstat(go)
                     if isinstance(st, int):
-                        logging.debug(lf('file got purged in the interim',
-                                         file=go))
+                        logging.debug(lf('Ignoring entry, purged in the '
+                                      'interim', file=en, gfid=gfid))
                         continue
 
                     if ty == 'LINK':
-                        entries.append(edct(ty, stat=st, entry=en, gfid=gfid))
+                        rl = None
+                        if st and stat.S_ISLNK(st.st_mode):
+                            rl = errno_wrap(os.readlink, [en], [ENOENT],
+                                            [ESTALE])
+                            if isinstance(rl, int):
+                                rl = None
+                        entries.append(edct(ty, stat=st, entry=en, gfid=gfid,
+                                       link=rl))
                     elif ty == 'SYMLINK':
                         rl = errno_wrap(os.readlink, [en], [ENOENT], [ESTALE])
                         if isinstance(rl, int):