glusterd : glusterd fails to start when peer's network interface is down

Problem:
glusterd fails to start on nodes where glusterd tries to come up even
before network is up.

Fix:
On startup glusterd tries to resolve brick path which is based on
hostname/ip, but in the above scenario when network interface is not
up, glusterd is not able to resolve the brick path using ip_address or
hostname With this fix glusterd will use UUID to resolve brick path.

Change-Id: Icfa7b2652417135530479d0aa4e2a82b0476f710
BUG: 1472267
Signed-off-by: Gaurav Yadav <gyadav@redhat.com>
Reviewed-on: https://review.gluster.org/17813
Smoke: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Prashanth Pai <ppai@redhat.com>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>

3 files changed, 17 insertions, 2 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-store.c b/xlators/mgmt/glusterd/src/glusterd-store.c
index 2dc35174f95..4b80186fb70 100644
--- a/xlators/mgmt/glusterd/src/glusterd-store.c
+++ b/xlators/mgmt/glusterd/src/glusterd-store.c
@@ -372,6 +372,10 @@ glusterd_store_brickinfo_write (int fd, glusterd_brickinfo_t *brickinfo)
         GF_ASSERT (brickinfo);
         GF_ASSERT (fd > 0);
 
+        ret = gf_store_save_value (fd, GLUSTERD_STORE_KEY_BRICK_UUID,
+                                   uuid_utoa(brickinfo->uuid));
+        if (ret)
+                goto out;
         ret = gf_store_save_value (fd, GLUSTERD_STORE_KEY_BRICK_HOSTNAME,
                                    brickinfo->hostname);
         if (ret)
@@ -2518,6 +2522,9 @@ glusterd_store_retrieve_bricks (glusterd_volinfo_t *volinfo)
                                              GLUSTERD_STORE_KEY_BRICK_FSID,
                                              strlen (GLUSTERD_STORE_KEY_BRICK_FSID))) {
                                 gf_string2uint64 (value, &brickinfo->statfs_fsid);
+                        } else if (!strcmp(key,
+                                    GLUSTERD_STORE_KEY_BRICK_UUID)) {
+                                gf_uuid_parse (value, brickinfo->uuid);
                         } else {
                                 gf_msg (this->name, GF_LOG_ERROR, 0,
                                         GD_MSG_UNKNOWN_KEY, "Unknown key: %s",
diff --git a/xlators/mgmt/glusterd/src/glusterd-store.h b/xlators/mgmt/glusterd/src/glusterd-store.h
index b515ca6c554..603151a361d 100644
--- a/xlators/mgmt/glusterd/src/glusterd-store.h
+++ b/xlators/mgmt/glusterd/src/glusterd-store.h
@@ -98,6 +98,7 @@ typedef enum glusterd_store_ver_ac_{
 #define GLUSTERD_STORE_KEY_BRICK_MNTOPTS        "mnt-opts"
 #define GLUSTERD_STORE_KEY_BRICK_ID             "brick-id"
 #define GLUSTERD_STORE_KEY_BRICK_FSID           "brick-fsid"
+#define GLUSTERD_STORE_KEY_BRICK_UUID           "uuid"
 
 #define GLUSTERD_STORE_KEY_PEER_UUID            "uuid"
 #define GLUSTERD_STORE_KEY_PEER_HOSTNAME        "hostname"
diff --git a/xlators/mgmt/glusterd/src/glusterd-utils.c b/xlators/mgmt/glusterd/src/glusterd-utils.c
index fe1d16865ef..522872d4815 100644
--- a/xlators/mgmt/glusterd/src/glusterd-utils.c
+++ b/xlators/mgmt/glusterd/src/glusterd-utils.c
@@ -1122,15 +1122,22 @@ glusterd_get_next_available_brickid (glusterd_volinfo_t *volinfo)
 int32_t
 glusterd_resolve_brick (glusterd_brickinfo_t *brickinfo)
 {
-        int32_t                 ret = -1;
-        xlator_t                *this = NULL;
+        int32_t                  ret      = -1;
+        xlator_t                *this     = NULL;
 
         this = THIS;
         GF_ASSERT (this);
 
         GF_ASSERT (brickinfo);
+        if (!gf_uuid_compare(brickinfo->uuid, MY_UUID) ||
+            (glusterd_peerinfo_find_by_uuid (brickinfo->uuid) != NULL)) {
+                ret = 0;
+                goto out;
+        }
 
         ret = glusterd_hostname_to_uuid (brickinfo->hostname, brickinfo->uuid);
+
+out:
         gf_msg_debug (this->name, 0, "Returning %d", ret);
         return ret;
 }