afr: all children of AFR must be up to resolve s-brain

Problem:
The various split-brain resolution policies (favorite-child-policy based,
CLI based and mount (get/setfattr) based) attempt to resolve split-brain
even when not all bricks of replica are up. This can be a problem when
say in a replica 3, the only good copy is down and the other 2 bricks
are up and blame each other (i.e. split-brain). We end up healing the
file in such a  case and allow I/O on it.

Fix:
A decision on whether the file is in split-brain or not must be taken
only if we are able to examine the afr xattrs of *all* bricks of a given
replica.

> Reviewed-on: https://review.gluster.org/16476
> Smoke: Gluster Build System <jenkins@build.gluster.org>
> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>

(cherry picked from commit 0e03336a9362e5717e561f76b0c543e5a197b31b)

Change-Id: Icddb1268b380005799990f5379ef957d84639ef9
BUG: 1420984
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: https://review.gluster.org/16589
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Smoke: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>

3 files changed, 61 insertions, 15 deletions

diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index 4d9327b8a11..c324c02c008 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -661,14 +661,17 @@ afr_set_split_brain_choice (int ret, call_frame_t *frame, void *opaque)
         gf_boolean_t        timer_reset      = _gf_false;
         int                 old_spb_choice   = -1;
 
-        if (ret)
-                goto out;
-
         frame = data->frame;
         loc = data->loc;
         this = frame->this;
         priv = this->private;
 
+        if (ret) {
+                op_errno = -ret;
+                ret = -1;
+                goto out;
+        }
+
         delta.tv_sec = priv->spb_choice_timeout;
         delta.tv_nsec = 0;
 
@@ -5264,6 +5267,12 @@ afr_is_split_brain (call_frame_t *frame, xlator_t *this, inode_t *inode,
         if (ret)
                 goto out;
 
+        if (!afr_can_decide_split_brain_source_sinks (replies,
+                                                      priv->child_count)) {
+                ret = -EAGAIN;
+                goto out;
+        }
+
         ret = _afr_is_split_brain (frame, this, replies,
                                     AFR_DATA_TRANSACTION, d_spb);
         if (ret)
@@ -5316,6 +5325,13 @@ afr_get_split_brain_status (void *opaque)
         if (!inode)
                 goto out;
 
+        dict = dict_new ();
+        if (!dict) {
+                op_errno = ENOMEM;
+                ret = -1;
+                goto out;
+        }
+
         /* Calculation for string length :
         * (child_count X length of child-name) + strlen ("    Choices :")
         * child-name consists of :
@@ -5329,13 +5345,9 @@ afr_get_split_brain_status (void *opaque)
                                   &m_spb);
         if (ret) {
                 op_errno = -ret;
-                ret = -1;
-                goto out;
-        }
-
-        dict = dict_new ();
-        if (!dict) {
-                op_errno = ENOMEM;
+                if (ret == -EAGAIN)
+                        ret = dict_set_str (dict, GF_AFR_SBRAIN_STATUS,
+                                            SBRAIN_HEAL_NO_GO_MSG);
                 ret = -1;
                 goto out;
         }
diff --git a/xlators/cluster/afr/src/afr-self-heal-common.c b/xlators/cluster/afr/src/afr-self-heal-common.c
index 40cfd01f4e9..c11ca11fdd9 100644
--- a/xlators/cluster/afr/src/afr-self-heal-common.c
+++ b/xlators/cluster/afr/src/afr-self-heal-common.c
@@ -472,6 +472,19 @@ afr_dict_contains_heal_op (call_frame_t *frame)
         return _gf_true;
 }
 
+gf_boolean_t
+afr_can_decide_split_brain_source_sinks (struct afr_reply *replies,
+                                         int child_count)
+{
+        int i = 0;
+
+        for (i = 0; i < child_count; i++)
+                if (replies[i].valid != 1 || replies[i].op_ret != 0)
+                        return _gf_false;
+
+        return _gf_true;
+}
+
 int
 afr_mark_split_brain_source_sinks_by_heal_op (call_frame_t *frame,
                                    xlator_t *this, unsigned char *sources,
@@ -510,6 +523,14 @@ afr_mark_split_brain_source_sinks_by_heal_op (call_frame_t *frame,
         }
         xdata_rsp = local->xdata_rsp;
 
+        if (!afr_can_decide_split_brain_source_sinks (replies,
+                                                      priv->child_count)) {
+                ret = dict_set_str (xdata_rsp, "sh-fail-msg",
+                                    SBRAIN_HEAL_NO_GO_MSG);
+                ret = -1;
+                goto out;
+        }
+
         for (i = 0 ; i < priv->child_count; i++)
                 if (locked_on[i])
                         sources[i] = 1;
@@ -748,26 +769,35 @@ afr_sh_get_fav_by_policy (xlator_t *this, struct afr_reply *replies,
         int fav_child = -1;
 
         priv = this->private;
+        if (!afr_can_decide_split_brain_source_sinks (replies,
+                                                      priv->child_count)) {
+                return -1;
+        }
+
         switch (priv->fav_child_policy) {
         case AFR_FAV_CHILD_BY_SIZE:
                 fav_child = afr_sh_fav_by_size (this, replies, inode);
-                if (policy_str && fav_child >= 0)
+                if (policy_str && fav_child >= 0) {
                         *policy_str = "SIZE";
+                }
                 break;
         case AFR_FAV_CHILD_BY_CTIME:
                 fav_child = afr_sh_fav_by_ctime (this, replies, inode);
-                if (policy_str && fav_child >= 0)
+                if (policy_str && fav_child >= 0) {
                         *policy_str = "CTIME";
+                }
                 break;
         case AFR_FAV_CHILD_BY_MTIME:
                 fav_child = afr_sh_fav_by_mtime (this, replies, inode);
-                if (policy_str && fav_child >= 0)
+                if (policy_str && fav_child >= 0) {
                         *policy_str = "MTIME";
+                }
                 break;
         case AFR_FAV_CHILD_BY_MAJORITY:
                 fav_child = afr_sh_fav_by_majority (this, replies, inode);
-                if (policy_str && fav_child >= 0)
+                if (policy_str && fav_child >= 0) {
                         *policy_str = "MAJORITY";
+                }
                 break;
         case AFR_FAV_CHILD_NONE:
         default:
diff --git a/xlators/cluster/afr/src/afr-self-heal.h b/xlators/cluster/afr/src/afr-self-heal.h
index 500227abe24..a33905033cc 100644
--- a/xlators/cluster/afr/src/afr-self-heal.h
+++ b/xlators/cluster/afr/src/afr-self-heal.h
@@ -81,7 +81,8 @@
 
 #define IA_EQUAL(f,s,field) (memcmp (&(f.ia_##field), &(s.ia_##field), sizeof (s.ia_##field)) == 0)
 
-
+#define SBRAIN_HEAL_NO_GO_MSG "Failed to obtain replies from all bricks of "\
+                      "the replica (are they up?). Cannot resolve split-brain."
 int
 afr_selfheal (xlator_t *this, uuid_t gfid);
 
@@ -220,6 +221,9 @@ afr_mark_active_sinks (xlator_t *this, unsigned char *sources,
 gf_boolean_t
 afr_dict_contains_heal_op (call_frame_t *frame);
 
+gf_boolean_t
+afr_can_decide_split_brain_source_sinks (struct afr_reply *replies,
+                                         int child_count);
 int
 afr_mark_split_brain_source_sinks (call_frame_t *frame, xlator_t *this,
                                    inode_t *inode,