mds: relax divergent backtrace scrub failures for replicated ancestor inodes

scrub could be verifying backtrace for an inode for which some of its
ancestors might be replicas, e.g. (from a custom debug build) some
ancestors of an inode with divergent backtrace were replicas:

```
[inode 0x3000000502f [...122,head] /volumes/qa/sv_0/b98de6ea-ed40-40d0-8e1a-9433a337a387/client.0/tmp/payload.2/multiple_rsync_payload.190107/firmware/ rep@0.1 fragtree_t(*^3) v6663 f(v493 m2024-05-01T06:38:16.403080+0000 388=289+99) n(v139 rc2024-05-01T06:55:35.239345+0000 b467915716 4880=4534+346) old_inodes=24 (inest mix) (ifile mix) | lock=0 importing=0 dirfrag=1 0x55a85d244680]
```

In such cases, the backpointer version (inode_backpointer_t::version) of the
in-memory (cache) inode can fall behind the on-disk version causing scrub to
consider the inode backtrace as divergent (memory version < on-disk version).

Sample:

```
"ondisk_value":"(2)0x30000005bba:

[<0x3000000502f/mwl8k v2126>,
<0x30000005026/firmware v6663>,
<0x30000005025/multiple_rsync_payload.190107 v3041>,
<0x10000005894/payload.2 v4873>,
<0x10000000005/tmp v6193>,<0x10000000003/client.0 v5964>,
<0x10000000002/b98de6ea-ed40-40d0-8e1a-9433a337a387 v5817>
,<0x10000000001/sv_0 v5837>,
<0x10000000000/qa v6241>,
<0x1/volumes v4036>]

"memoryvalue":"(2)0x30000005bba:

[<0x3000000502f/mwl8k v2126>,
<0x30000005026/firmware v6663>,
<0x30000005025/multiple_rsync_payload.190107 v3041>,
<0x10000005894/payload.2 v4873>,
<0x10000000005/tmp v6081>,
<0x10000000003/client.0 v5942>,
<0x10000000002/b98de6ea-ed40-40d0-8e1a-9433a337a387 v5709>,
<0x10000000001/sv_0 v5819>,
<0x10000000000/qa v6121>,
<0x1/volumes v4022>]
```

Fixes: http://tracker.ceph.com/issues/64730
Signed-off-by: Venky Shankar <vshankar@redhat.com>
(cherry picked from commit b98bb860a899ba86caf2d0e4d82b5882a13ae840)

diff --git a/src/mds/CInode.cc b/src/mds/CInode.cc
index 32050bde261dd3dd2df0726d4a6def5f914c5cef..dfc4d154339b86eee6e621c34dc7a51cb81b889a 100644 (file)
--- a/src/mds/CInode.cc
+++ b/src/mds/CInode.cc
@@ -998,6 +998,19 @@ bool CInode::is_ancestor_of(const CInode *other, std::unordered_map<CInode const
   return false;
 }
 
+bool CInode::is_any_ancestor_inode_a_replica() {
+  CDentry *pdn = get_parent_dn();
+  while (pdn) {
+    CInode *diri = pdn->get_dir()->get_inode();
+    if (!diri->is_auth()) {
+      return true;
+    }
+    pdn = diri->get_parent_dn();
+  }
+
+  return false;
+}
+
 bool CInode::is_projected_ancestor_of(const CInode *other) const
 {
   while (other) {
@@ -4791,7 +4804,11 @@ void CInode::validate_disk_state(CInode::validated_data *results,
           dout(20) << "divergent backtraces are acceptable when dn "
                       "is being purged or has been renamed or moved to a "
                       "different directory " << *in << dendl;
-        }
+        } else if (in->is_any_ancestor_inode_a_replica()) {
+          results->backtrace.passed = true;
+          dout(20) << "divergent backtraces are acceptable when some "
+                     "ancestor inodes are replicas " << *in << dendl;
+       }
       } else {
         results->backtrace.passed = true;
       }

diff --git a/src/mds/CInode.h b/src/mds/CInode.h
index b287c49c18bb088b0c496ad5277b09b350df3353..0012a76b3a2e2bf0072c8643afba2f526ff230bf 100644 (file)
--- a/src/mds/CInode.h
+++ b/src/mds/CInode.h
@@ -704,6 +704,8 @@ class CInode : public MDSCacheObject, public InodeStoreBase, public Counter<CIno
   const CDir *get_projected_parent_dir() const;
   CDir *get_projected_parent_dir();
   CInode *get_parent_inode();
+
+  bool is_any_ancestor_inode_a_replica();
   
   bool is_lt(const MDSCacheObject *r) const override {
     const CInode *o = static_cast<const CInode*>(r);