Fix halo-enabled option

Summary:
- This option was broken (or shall we say....not fully implemented? :) ),
  it needs to set the halo-latency to FLT_MAX to
  gaurentee no bricks will be marked down, and all those presently
  marked down @ runtime shall be marked back up upon the transition from
  true to false
- Also fixes tests/bugs/fb2518260.t

Test Plan: Prove tests (paste coming)

Reviewers: cjh, dph, mmckeen

Reviewed By: mmckeen

Differential Revision: https://phabricator.fb.com/D1435264

Conflicts:
	xlators/cluster/afr/src/afr-common.c

Change-Id: I81209d6f2cc9ea7e562eedf44bf3efbe87e01bf7
Signed-off-by: Kevin Vigor <kvigor@fb.com>
Reviewed-on: http://review.gluster.org/16227
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: Shreyas Siravara <sshreyas@fb.com>
Smoke: Gluster Build System <jenkins@build.gluster.org>

1 files changed, 17 insertions, 8 deletions

diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index ed2c6414718..630bee80be3 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -4270,7 +4270,8 @@ _afr_handle_ping_event (xlator_t *this, xlator_t *child_xlator,
                 if (priv->child_up[i] == 1)
                         up_children++;
 
-        if (*child_latency_msec > halo_max_latency_msec &&
+        if (priv->halo_enabled &&
+            *child_latency_msec > halo_max_latency_msec &&
             priv->child_up[idx] == 1 &&
             up_children > priv->halo_min_replicas) {
                 if ((up_children - 1) <
@@ -4288,13 +4289,14 @@ _afr_handle_ping_event (xlator_t *this, xlator_t *child_xlator,
                                 halo_max_latency_msec);
                         *event = GF_EVENT_CHILD_DOWN;
                 }
-        } else if (*child_latency_msec < halo_max_latency_msec &&
+        } else if ((priv->halo_enabled == _gf_false ||
+                    *child_latency_msec < halo_max_latency_msec) &&
                    priv->child_up[idx] == 0) {
                 if (up_children < priv->halo_max_replicas) {
                         gf_log (child_xlator->name, GF_LOG_INFO,
                                 "Child latency (%ld ms) "
-                                "below halo threshold (%ld), "
-                                "marking child up.",
+                                "below halo threshold (%ld) or halo is "
+                                "disabled, marking child up.",
                                 *child_latency_msec,
                                 halo_max_latency_msec);
                         *event = GF_EVENT_CHILD_UP;
@@ -4343,7 +4345,8 @@ _afr_handle_child_up_event (xlator_t *this, xlator_t *child_xlator,
          * halo_min_replicas even though it's latency exceeds
          * halo_max_latency_msec.
          */
-        if (up_children > priv->halo_min_replicas) {
+        if (priv->halo_enabled == _gf_true &&
+                        up_children > priv->halo_min_replicas) {
                 worst_up_child = find_worst_up_child (this);
                 if (worst_up_child >= 0 &&
                     priv->child_latency[worst_up_child] >
@@ -4360,7 +4363,8 @@ _afr_handle_child_up_event (xlator_t *this, xlator_t *child_xlator,
                         up_children--;
                 }
         }
-        if (up_children > priv->halo_max_replicas &&
+        if (priv->halo_enabled == _gf_true &&
+                        up_children > priv->halo_max_replicas &&
             !priv->shd.iamshd) {
                 worst_up_child = find_worst_up_child (this);
                 if (worst_up_child < 0) {
@@ -4440,7 +4444,8 @@ _afr_handle_child_down_event (xlator_t *this, xlator_t *child_xlator,
          * as we want it to be up to date if we are going to
          * begin using it synchronously.
          */
-        if (up_children < priv->halo_min_replicas) {
+        if (priv->halo_enabled == _gf_true &&
+                        up_children < priv->halo_min_replicas) {
                 best_down_child = find_best_down_child (this);
                 if (best_down_child >= 0) {
                         gf_log (this->name, GF_LOG_DEBUG,
@@ -4546,7 +4551,11 @@ afr_notify (xlator_t *this, int32_t event,
         had_quorum = priv->quorum_count && afr_has_quorum (priv->child_up,
                                                            this);
 
-        halo_max_latency_msec = _afr_get_halo_latency (this);
+        if (!priv->halo_enabled) {
+                halo_max_latency_msec = INT64_MAX;
+        } else {
+                halo_max_latency_msec = _afr_get_halo_latency (this);
+        }
 
         if (event == GF_EVENT_CHILD_PING) {
                 /* Calculates the child latency and sets event