ec: Fix self-heal issues

Problem: Doing an 'ls' of a directory that has been modified while one
         of the bricks was down, sometimes returns the old directory
         contents.

Cause: Directories are not marked when they are modified as files are.
       The ec xlator balances requests amongst available and healthy
       bricks. Since there is no way to detect that a directory is
       out of date in one of the bricks, it is used from time to time
       to return the directory contents.

Solution: Basically the solution consists in use versioning information
          also for directories, however some additional changes have
          been necessary.

Changes:

 * Use directory versioning:

     This required to lock full directory instead of a single entry for
     all requests that add or remove entries from it. This is needed to
     allow atomic version update. This affects the following fops:

         create, mkdir, mknod, link, symlink, rename, unlink, rmdir

     Another side effect is that opendir requires to do a previous
     lookup to get versioning information and discard out of date
     bricks for subsequent readdir(p) calls.

 * Restrict directory self-heal:

     Till now, when one discrepancy was found in lookup, a self-heal
     was automatically started. This caused the versioning information
     of a bad directory to be healed instantly, making the original
     problem to reapear again.

     To solve this, when a missing directory is detected in one or more
     bricks on lookup or opendir fops, only a partial self-heal is
     performed on it. A partial self-heal basically creates the
     directory but does not restore any additional information.

     This avoids that an 'ls' could repair the directory and cause the
     problem to happen again. With this change, output of 'ls' is
     always consistent. However, since the directory has been created
     in the brick, this allows any other operation on it (create new
     files, for example) to succeed on all bricks and not add additional
     work to the self-heal process.

     To force a self-heal of a directory, any other operation must be
     done on it. For example a getxattr.

     With these changes, the correct healing procedure that would avoid
     inconsistent directory browsing consists on a post-order traversal
     of directoriesi being healed. This way, the directory contents will
     be healed before healing the directory itslef.

 * Additional changes to fix self-heal errors

     - Don't use fop->fd to decide between fd/loc.

         open, opendir and create have an fd, but the correct data is in
         loc.

     - Fix incorrect management of bad bricks per inode/fd.

     - Fix incorrect selection of fop's target bricks when there are bad
       bricks involved.

     - Improved ec_loc_parent() to always return a parent loc as
       complete as possible.

Change-Id: Iaf3df174d7857da57d4a87b4a8740a7048b366ad
BUG: 1149726
Signed-off-by: Xavier Hernandez <xhernandez@datalab.es>
Reviewed-on: http://review.gluster.org/8916
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>

1 files changed, 24 insertions, 14 deletions

diff --git a/xlators/cluster/ec/src/ec-inode-write.c b/xlators/cluster/ec/src/ec-inode-write.c
index 7e557f12aa3..aa3682516ed 100644
--- a/xlators/cluster/ec/src/ec-inode-write.c
+++ b/xlators/cluster/ec/src/ec-inode-write.c
@@ -94,11 +94,11 @@ int32_t ec_manager_removexattr(ec_fop_data_t * fop, int32_t state)
         case EC_STATE_LOCK:
             if (fop->fd == NULL)
             {
-                ec_lock_prepare_inode(fop, &fop->loc[0]);
+                ec_lock_prepare_inode(fop, &fop->loc[0], 1);
             }
             else
             {
-                ec_lock_prepare_fd(fop, fop->fd);
+                ec_lock_prepare_fd(fop, fop->fd, 1);
             }
             ec_lock(fop);
 
@@ -186,7 +186,7 @@ int32_t ec_manager_removexattr(ec_fop_data_t * fop, int32_t state)
 
         case -EC_STATE_LOCK_REUSE:
         case EC_STATE_LOCK_REUSE:
-            ec_lock_reuse(fop, 1);
+            ec_lock_reuse(fop);
 
             return EC_STATE_UNLOCK;
 
@@ -351,6 +351,8 @@ void ec_fremovexattr(call_frame_t * frame, xlator_t * this, uintptr_t target,
         goto out;
     }
 
+    fop->use_fd = 1;
+
     if (fd != NULL)
     {
         fop->fd = fd_ref(fd);
@@ -490,11 +492,11 @@ int32_t ec_manager_setattr(ec_fop_data_t * fop, int32_t state)
         case EC_STATE_LOCK:
             if (fop->fd == NULL)
             {
-                ec_lock_prepare_inode(fop, &fop->loc[0]);
+                ec_lock_prepare_inode(fop, &fop->loc[0], 1);
             }
             else
             {
-                ec_lock_prepare_fd(fop, fop->fd);
+                ec_lock_prepare_fd(fop, fop->fd, 1);
             }
             ec_lock(fop);
 
@@ -598,7 +600,7 @@ int32_t ec_manager_setattr(ec_fop_data_t * fop, int32_t state)
 
         case -EC_STATE_LOCK_REUSE:
         case EC_STATE_LOCK_REUSE:
-            ec_lock_reuse(fop, 1);
+            ec_lock_reuse(fop);
 
             return EC_STATE_UNLOCK;
 
@@ -772,6 +774,8 @@ void ec_fsetattr(call_frame_t * frame, xlator_t * this, uintptr_t target,
         goto out;
     }
 
+    fop->use_fd = 1;
+
     fop->int32 = valid;
 
     if (fd != NULL)
@@ -880,11 +884,11 @@ int32_t ec_manager_setxattr(ec_fop_data_t * fop, int32_t state)
         case EC_STATE_LOCK:
             if (fop->fd == NULL)
             {
-                ec_lock_prepare_inode(fop, &fop->loc[0]);
+                ec_lock_prepare_inode(fop, &fop->loc[0], 1);
             }
             else
             {
-                ec_lock_prepare_fd(fop, fop->fd);
+                ec_lock_prepare_fd(fop, fop->fd, 1);
             }
             ec_lock(fop);
 
@@ -971,7 +975,7 @@ int32_t ec_manager_setxattr(ec_fop_data_t * fop, int32_t state)
 
         case -EC_STATE_LOCK_REUSE:
         case EC_STATE_LOCK_REUSE:
-            ec_lock_reuse(fop, 1);
+            ec_lock_reuse(fop);
 
             return EC_STATE_UNLOCK;
 
@@ -1138,6 +1142,8 @@ void ec_fsetxattr(call_frame_t * frame, xlator_t * this, uintptr_t target,
         goto out;
     }
 
+    fop->use_fd = 1;
+
     fop->int32 = flags;
 
     if (fd != NULL)
@@ -1380,11 +1386,11 @@ int32_t ec_manager_truncate(ec_fop_data_t * fop, int32_t state)
         case EC_STATE_LOCK:
             if (fop->id == GF_FOP_TRUNCATE)
             {
-                ec_lock_prepare_inode(fop, &fop->loc[0]);
+                ec_lock_prepare_inode(fop, &fop->loc[0], 1);
             }
             else
             {
-                ec_lock_prepare_fd(fop, fop->fd);
+                ec_lock_prepare_fd(fop, fop->fd, 1);
             }
             ec_lock(fop);
 
@@ -1497,7 +1503,7 @@ int32_t ec_manager_truncate(ec_fop_data_t * fop, int32_t state)
 
         case -EC_STATE_LOCK_REUSE:
         case EC_STATE_LOCK_REUSE:
-            ec_lock_reuse(fop, 1);
+            ec_lock_reuse(fop);
 
             return EC_STATE_UNLOCK;
 
@@ -1666,6 +1672,8 @@ void ec_ftruncate(call_frame_t * frame, xlator_t * this, uintptr_t target,
         goto out;
     }
 
+    fop->use_fd = 1;
+
     fop->offset = offset;
 
     if (fd != NULL)
@@ -2019,7 +2027,7 @@ int32_t ec_manager_writev(ec_fop_data_t * fop, int32_t state)
         /* Fall through */
 
         case EC_STATE_LOCK:
-            ec_lock_prepare_fd(fop, fop->fd);
+            ec_lock_prepare_fd(fop, fop->fd, 1);
             ec_lock(fop);
 
             return EC_STATE_GET_SIZE_AND_VERSION;
@@ -2125,7 +2133,7 @@ int32_t ec_manager_writev(ec_fop_data_t * fop, int32_t state)
 
         case -EC_STATE_LOCK_REUSE:
         case EC_STATE_LOCK_REUSE:
-            ec_lock_reuse(fop, 1);
+            ec_lock_reuse(fop);
 
             return EC_STATE_UNLOCK;
 
@@ -2171,6 +2179,8 @@ void ec_writev(call_frame_t * frame, xlator_t * this, uintptr_t target,
     fop->offset = offset;
     fop->uint32 = flags;
 
+    fop->use_fd = 1;
+
     if (fd != NULL)
     {
         fop->fd = fd_ref(fd);