Blob Blame History Raw
From 85da98b9c54889139822b5c3d351a0249abf75b0 Mon Sep 17 00:00:00 2001
From: Kotresh HR <khiremat@redhat.com>
Date: Fri, 26 Oct 2018 03:45:46 -0400
Subject: [PATCH 437/444] geo-rep: Add more intelligence to automatic error
 handling

Geo-rep's automatic error handling does gfid conflict
resolution. But if there are ENOENT errors because the
parent is not synced to slave, it doesn' handle them.
This patch adds the intelligence to create missing
parent directories on slave. It can create the missing
directories upto the depth of 10.

Backport of:
 > Patch: https://review.gluster.org/21498
 > fixes: bz#1643402
 > Change-Id: Ic97ed1fa5899c087e404d559e04f7963ed7bb54c
 > Signed-off-by: Kotresh HR <khiremat@redhat.com>

BUG: 1638069
Change-Id: Ic97ed1fa5899c087e404d559e04f7963ed7bb54c
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: https://code.engineering.redhat.com/gerrit/155039
Tested-by: RHGS Build Bot <nigelb@redhat.com>
Reviewed-by: Aravinda Vishwanathapura Krishna Murthy <avishwan@redhat.com>
Reviewed-by: Sunny Kumar <sunkumar@redhat.com>
Reviewed-by: Sunil Kumar Heggodu Gopala Acharya <sheggodu@redhat.com>
---
 geo-replication/syncdaemon/master.py | 68 ++++++++++++++++++++++++------------
 1 file changed, 46 insertions(+), 22 deletions(-)

diff --git a/geo-replication/syncdaemon/master.py b/geo-replication/syncdaemon/master.py
index cd135df..bdb4da2 100644
--- a/geo-replication/syncdaemon/master.py
+++ b/geo-replication/syncdaemon/master.py
@@ -693,7 +693,7 @@ class GMasterChangelogMixin(GMasterCommon):
     TYPE_ENTRY = "E "
 
     MAX_EF_RETRIES = 10
-    MAX_OE_RETRIES = 5
+    MAX_OE_RETRIES = 10
 
     # flat directory hierarchy for gfid based access
     FLAT_DIR_HIERARCHY = '.'
@@ -836,11 +836,12 @@ class GMasterChangelogMixin(GMasterCommon):
                     # The file exists on master but with different name.
                     # Probably renamed and got missed during xsync crawl.
                     elif failure[2]['slave_isdir']:
-                        realpath = os.readlink(os.path.join(gconf.local_path,
-                                                            ".glusterfs",
-                                                            slave_gfid[0:2],
-                                                            slave_gfid[2:4],
-                                                            slave_gfid))
+                        realpath = os.readlink(os.path.join(
+                                               gconf.local_path,
+                                               ".glusterfs",
+                                               slave_gfid[0:2],
+                                               slave_gfid[2:4],
+                                               slave_gfid))
                         dst_entry = os.path.join(pfx, realpath.split('/')[-2],
                                                  realpath.split('/')[-1])
                         src_entry = pbname
@@ -881,25 +882,37 @@ class GMasterChangelogMixin(GMasterCommon):
                                  gfid=failure[2]['slave_gfid'],
                                  entry=pbname))
             elif failure[1] == ENOENT:
-                # Ignore ENOENT error for fix_entry_ops aka retry_count > 1
-                if retry_count > 1:
-                    logging.info(lf('ENOENT error while fixing entry ops. '
-                                    'Safe to ignore, take out entry',
+                if op in ['RENAME']:
+                    pbname = failure[0]['entry1']
+                else:
+                    pbname = failure[0]['entry']
+
+                pargfid = pbname.split('/')[1]
+                st = lstat(os.path.join(pfx, pargfid))
+                # Safe to ignore the failure as master doesn't contain
+                # parent directory.
+                if isinstance(st, int):
+                    logging.info(lf('Fixing ENOENT error in slave. Parent '
+                                    'does not exist on master. Safe to '
+                                    'ignore, take out entry',
                                     retry_count=retry_count,
                                     entry=repr(failure)))
                     entries.remove(failure[0])
-                elif op in ('MKNOD', 'CREATE', 'MKDIR'):
-                    pargfid = pbname.split('/')[1]
-                    st = lstat(os.path.join(pfx, pargfid))
-                    # Safe to ignore the failure as master doesn't contain
-                    # parent directory.
-                    if isinstance(st, int):
-                        logging.info(lf('Fixing ENOENT error in slave. Parent '
-                                        'does not exist on master. Safe to '
-                                        'ignore, take out entry',
-                                        retry_count=retry_count,
-                                        entry=repr(failure)))
-                        entries.remove(failure[0])
+                else:
+                    logging.info(lf('Fixing ENOENT error in slave. Create '
+                                    'parent directory on slave.',
+                                    retry_count=retry_count,
+                                    entry=repr(failure)))
+                    realpath = os.readlink(os.path.join(gconf.local_path,
+                                                        ".glusterfs",
+                                                        pargfid[0:2],
+                                                        pargfid[2:4],
+                                                        pargfid))
+                    dir_entry = os.path.join(pfx, realpath.split('/')[-2],
+                                             realpath.split('/')[-1])
+                    fix_entry_ops.append(
+                        edct('MKDIR', gfid=pargfid, entry=dir_entry,
+                             mode=st.st_mode, uid=st.st_uid, gid=st.st_gid))
 
         if fix_entry_ops:
             # Process deletions of entries whose gfids are mismatched
@@ -1077,6 +1090,11 @@ class GMasterChangelogMixin(GMasterCommon):
                         os.path.join(pfx, ec[self.POS_ENTRY1 - 1]))
                     entries.append(edct(ty, gfid=gfid, entry=e1, entry1=en,
                                         stat=st, link=rl))
+                    # If src doesn't exist while doing rename, destination
+                    # is created. If data is not followed by rename, this
+                    # remains zero byte file on slave. Hence add data entry
+                    # for renames
+                    datas.add(os.path.join(pfx, gfid))
                 else:
                     # stat() to get mode and other information
                     if not matching_disk_gfid(gfid, en):
@@ -1100,6 +1118,12 @@ class GMasterChangelogMixin(GMasterCommon):
                                 rl = None
                         entries.append(edct(ty, stat=st, entry=en, gfid=gfid,
                                        link=rl))
+                        # If src doesn't exist while doing link, destination
+                        # is created based on file type. If data is not
+                        # followed by link, this remains zero byte file on
+                        # slave. Hence add data entry for links
+                        if rl is None:
+                            datas.add(os.path.join(pfx, gfid))
                     elif ty == 'SYMLINK':
                         rl = errno_wrap(os.readlink, [en], [ENOENT],
                                         [ESTALE, EINTR])
-- 
1.8.3.1