ec: Fix self-healing issues.

Three problems have been detected:

1. Self healing is executed in background, allowing the fop that
   detected the problem to continue without blocks nor delays.

   While this is quite interesting to avoid unnecessary delays,
   it can cause spurious failures of self-heal because it may
   try to recover a file inside a directory that a previous
   self-heal has not recovered yet, causing the file self-heal
   to fail.

2. When a partial self-heal is being executed on a directory,
   if a full self-heal is attempted, it won't be executed
   because another self-heal is already in process, so the
   directory won't be fully repaired.

3. Information contained in loc's of some fop's is not enough
   to do a complete self-heal.

To solve these problems, I've made some changes:

* Improved ec_loc_from_loc() to add all available information
  to a loc.

* Before healing an entry, it's parent is checked and partially
  healed if necessary to avoid failures.

* All heal requests received for the same inode while another
  self-heal is being processed are queued. When the first heal
  completes, all pending requests are answered using the results
  of the first heal (without full execution), unless the first
  heal was a partial heal. In this case all partial heals are
  answered, and the first full heal is processed normally.

* An special virtual xattr (not physically stored on bricks)
  named 'trusted.ec.heal' has been created to allow synchronous
  self-heal of files.

  Now, the recommended way to heal an entire volume is this:

    find <mount> -d -exec getfattr -h -n trusted.ec.heal {} \;

Some minor changes:

* ec_loc_prepare() has been renamed to ec_loc_update().

* All loc management functions return 0 on success and -1 on
  error.

* Do not delay fop unlocks if heal is needed.

* Added basic ec xattrs initially on create, mkdir and mknod
  fops.

* Some coding style changes

This is a backport of http://review.gluster.org/9072/

Change-Id: I2a5fd9c57349a153710880d6ac4b1fa0c1475985
BUG: 1159484
Signed-off-by: Xavier Hernandez <xhernandez@datalab.es>
Reviewed-on: http://review.gluster.org/9073
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>

1 files changed, 78 insertions, 18 deletions

diff --git a/xlators/cluster/ec/src/ec-inode-read.c b/xlators/cluster/ec/src/ec-inode-read.c
index 8f89224987d..b79fbed7e5b 100644
--- a/xlators/cluster/ec/src/ec-inode-read.c
+++ b/xlators/cluster/ec/src/ec-inode-read.c
@@ -346,6 +346,59 @@ int32_t ec_manager_getxattr(ec_fop_data_t * fop, int32_t state)
     }
 }
 
+int32_t ec_getxattr_heal_cbk(call_frame_t *frame, void *cookie, xlator_t *xl,
+                             int32_t op_ret, int32_t op_errno, uintptr_t mask,
+                             uintptr_t good, uintptr_t bad, dict_t *xdata)
+{
+    ec_fop_data_t *fop = cookie;
+    fop_getxattr_cbk_t func = fop->data;
+    ec_t *ec = xl->private;
+    dict_t *dict = NULL;
+    char *str;
+    char bin1[65], bin2[65];
+
+    if (op_ret >= 0) {
+        dict = dict_new();
+        if (dict == NULL) {
+            op_ret = -1;
+            op_errno = ENOMEM;
+        } else {
+            if (gf_asprintf(&str, "Good: %s, Bad: %s",
+                            ec_bin(bin1, sizeof(bin1), good, ec->nodes),
+                            ec_bin(bin2, sizeof(bin2), mask & ~(good | bad),
+                                   ec->nodes)) < 0) {
+                dict_unref(dict);
+                dict = NULL;
+
+                op_ret = -1;
+                op_errno = ENOMEM;
+
+                goto out;
+            }
+
+            if (dict_set_str(dict, EC_XATTR_HEAL, str) != 0) {
+                GF_FREE(str);
+                dict_unref(dict);
+                dict = NULL;
+
+                op_ret = -1;
+                op_errno = ENOMEM;
+
+                goto out;
+            }
+        }
+    }
+
+out:
+    func(frame, NULL, xl, op_ret, op_errno, dict, NULL);
+
+    if (dict != NULL) {
+        dict_unref(dict);
+    }
+
+    return 0;
+}
+
 void ec_getxattr(call_frame_t * frame, xlator_t * this, uintptr_t target,
                  int32_t minimum, fop_getxattr_cbk_t func, void * data,
                  loc_t * loc, const char * name, dict_t * xdata)
@@ -360,6 +413,14 @@ void ec_getxattr(call_frame_t * frame, xlator_t * this, uintptr_t target,
     GF_VALIDATE_OR_GOTO(this->name, frame, out);
     GF_VALIDATE_OR_GOTO(this->name, this->private, out);
 
+    /* Special handling of an explicit self-heal request */
+    if ((name != NULL) && (strcmp(name, EC_XATTR_HEAL) == 0)) {
+        ec_heal(frame, this, target, EC_MINIMUM_ONE, ec_getxattr_heal_cbk,
+                func, loc, 0, NULL);
+
+        return;
+    }
+
     fop = ec_fop_data_allocate(frame, this, GF_FOP_GETXATTR,
                                EC_FLAG_UPDATE_LOC_INODE, target, minimum,
                                ec_wind_getxattr, ec_manager_getxattr, callback,
@@ -652,9 +713,8 @@ int32_t ec_manager_open(ec_fop_data_t * fop, int32_t state)
             LOCK(&fop->fd->lock);
 
             ctx = __ec_fd_get(fop->fd, fop->xl);
-            if ((ctx == NULL) || !ec_loc_from_loc(fop->xl, &ctx->loc,
-                &fop->loc[0]))
-            {
+            if ((ctx == NULL) ||
+                (ec_loc_from_loc(fop->xl, &ctx->loc, &fop->loc[0])) != 0) {
                 UNLOCK(&fop->fd->lock);
 
                 fop->error = EIO;
@@ -697,24 +757,24 @@ int32_t ec_manager_open(ec_fop_data_t * fop, int32_t state)
                         cbk->op_errno = EIO;
                     }
                 }
-                if (cbk->op_ret < 0)
-                {
-                    ec_fop_set_error(fop, cbk->op_errno);
-                }
-                else
-                {
-                    ec_loc_prepare(fop->xl, &fop->loc[0], cbk->fd->inode,
-                                   NULL);
+                if (cbk->op_ret >= 0) {
+                    if (ec_loc_update(fop->xl, &fop->loc[0], cbk->fd->inode,
+                                      NULL) != 0) {
+                        cbk->op_ret = -1;
+                        cbk->op_errno = EIO;
+                    } else {
+                        LOCK(&fop->fd->lock);
 
-                    LOCK(&fop->fd->lock);
+                        ctx = __ec_fd_get(fop->fd, fop->xl);
+                        if (ctx != NULL) {
+                            ctx->open |= cbk->mask;
+                        }
 
-                    ctx = __ec_fd_get(fop->fd, fop->xl);
-                    if (ctx != NULL)
-                    {
-                        ctx->open |= cbk->mask;
+                        UNLOCK(&fop->fd->lock);
                     }
-
-                    UNLOCK(&fop->fd->lock);
+                }
+                if (cbk->op_ret < 0) {
+                    ec_fop_set_error(fop, cbk->op_errno);
                 }
             }
             else