glusterd: To do full heal in different online node when do ec/afr full heal

For example:
    We have 3 nodes and create ec 3*(2+1) volume for
test-disperse-0/test-disperse-1/test-disperse-2 when we do
'gluster v heal test full' in node-1 that can in node-1/
node-2/node-3 glustershd's get op=GF_EVENT_TRANSLATOR_OP
and then do full heal in different disperse group.
    Let us say we have 2X(2+1) disperse with each brick
from different machine m0, m1, m2, m3, m4, m5. and candidate_max is m5.
and do full heal so '*index' is 3 and !gf_uuid_compare(MY_UUID, brickinfo->uuid)
will be true in m3,and then m3's glustershd will be the heal-xlator.

Id: I5c6762e6cfb375aed32d3fc11fe5eae3ee41aab4
Signed-off-by: yinkui <13965432176@163.com>

Change-Id: Ic7ef3ddfd30b5f4714ba99b4e7b708c927d68764
fixes: bz#1724948

1 files changed, 36 insertions, 3 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-op-sm.c b/xlators/mgmt/glusterd/src/glusterd-op-sm.c
index 26a0eb7d20f..0b7ef6d5d40 100644
--- a/xlators/mgmt/glusterd/src/glusterd-op-sm.c
+++ b/xlators/mgmt/glusterd/src/glusterd-op-sm.c
@@ -6474,6 +6474,10 @@ _select_hxlators_for_full_self_heal(xlator_t *this, glusterd_volinfo_t *volinfo,
     glusterd_brickinfo_t *brickinfo = NULL;
     int hxl_children = 0;
     uuid_t candidate = {0};
+    int brick_index = 0;
+    glusterd_peerinfo_t *peerinfo = NULL;
+    int delta = 0;
+    uuid_t candidate_max = {0};
 
     if ((*index) == 0)
         (*index)++;
@@ -6485,13 +6489,40 @@ _select_hxlators_for_full_self_heal(xlator_t *this, glusterd_volinfo_t *volinfo,
 
     cds_list_for_each_entry(brickinfo, &volinfo->bricks, brick_list)
     {
+        if (gf_uuid_compare(brickinfo->uuid, candidate_max) > 0) {
+            if (!gf_uuid_compare(MY_UUID, brickinfo->uuid)) {
+                gf_uuid_copy(candidate_max, brickinfo->uuid);
+            } else {
+                peerinfo = glusterd_peerinfo_find(brickinfo->uuid, NULL);
+                if (peerinfo && peerinfo->connected) {
+                    gf_uuid_copy(candidate_max, brickinfo->uuid);
+                }
+            }
+        }
+    }
+
+    cds_list_for_each_entry(brickinfo, &volinfo->bricks, brick_list)
+    {
         if (gf_uuid_is_null(brickinfo->uuid))
             (void)glusterd_resolve_brick(brickinfo);
 
-        if (gf_uuid_compare(brickinfo->uuid, candidate) > 0)
-            gf_uuid_copy(candidate, brickinfo->uuid);
+        delta %= hxl_children;
+        if ((*index + delta) == (brick_index + hxl_children)) {
+            if (!gf_uuid_compare(MY_UUID, brickinfo->uuid)) {
+                gf_uuid_copy(candidate, brickinfo->uuid);
+            } else {
+                peerinfo = glusterd_peerinfo_find(brickinfo->uuid, NULL);
+                if (peerinfo && peerinfo->connected) {
+                    gf_uuid_copy(candidate, brickinfo->uuid);
+                } else if (peerinfo &&
+                           (!gf_uuid_compare(candidate_max, MY_UUID))) {
+                    _add_hxlator_to_dict(dict, volinfo,
+                                         ((*index) - 1) / hxl_children,
+                                         (*hxlator_count));
+                    (*hxlator_count)++;
+                }
+            }
 
-        if ((*index) % hxl_children == 0) {
             if (!gf_uuid_compare(MY_UUID, candidate)) {
                 _add_hxlator_to_dict(dict, volinfo,
                                      ((*index) - 1) / hxl_children,
@@ -6499,6 +6530,8 @@ _select_hxlators_for_full_self_heal(xlator_t *this, glusterd_volinfo_t *volinfo,
                 (*hxlator_count)++;
             }
             gf_uuid_clear(candidate);
+            brick_index += hxl_children;
+            delta++;
         }
 
         (*index)++;