glusterd/snapshot: Adding snap_vol_id and snap_uuid to missed_snap_list

Persisting missing snapshot info on disk as well as in memory in
the following format:
-------------NODE-UUID--------------:--------------SNAP-UUID-------------=---------SNAP-VOL-ID------------:BRICKNUM:-------BRICKPATH--------:OPERATION:STATUS
927cb5fe-63da-48f5-82f6-e6a09ddc81c4:8258b18f-d408-483d-8239-204039dc6397=a17b4fe42c5a45f7a916438643edaa13:   3    :/brick/brick-dirs/brick3:    1    :   1
927cb5fe-63da-48f5-82f6-e6a09ddc81c4:8258b18f-d408-483d-8239-204039dc6397=a17b4fe42c5a45f7a916438643edaa13:   3    :/brick/brick-dirs/brick3:    3    :   1
927cb5fe-63da-48f5-82f6-e6a09ddc81c4:8258b18f-d408-483d-8239-204039dc6397=83a3cc05453b46b2a7eda4c9a9208638:   3    :/brick/brick-dirs/brick3:    1    :   1

This data will be stored on disk at /var/lib/glusterd/snaps/missed_snaps_list

In memory we maintain the data as a list of glusterd_missed_snap_info
in conf, the key for this list are the first two fields,
i.e NODE-UUID:SNAP-UUID.

For every NODE-UUID:SNAP-UUID, there can be multiple operations missed
on multiple bricks. So we maintain a list of glusterd_snap_op_t
for every node of glusterd_missed_snap_info

This list is maintained or updated during snapshot create, delete, and restore
operations which are the only operations that if missed, are recorded in this
list.

During snapshot create, if a node is down, or a brick is down, we don't
receive their mount point infos. snap_status of such bricks is marked as
-1, and their brick details are added to this list.

During snapshot delete, we check from originator node, if any other
nodes, holding bricks of the said snap are down. Those are also added to the list.
Also if the node is up, but the snapshot was pending for a snap
brick, and its snap_status is -1, we add that to the list too.
When a subsequent delete entry is processed for an already existing
create entry, we just mark the create entries status as done (2), and don't
add the delete entry to the list.

During snapshot restore, we check from originator node, if any other
nodes, holding bricks of the said snap are down. Those are also added to the list.
Also if the node is up, but the snapshot was pending for a snap
brick, and its snap_status is -1, we add that to the list too.
Like delete when a subsequent restore entry is processed for an already existing
create entry, we just mark the create entries status as done (2), and don't
add the restore entry to the list.

Change-Id: I54f63e28d3c40555d0f84528f38227103171f594
BUG: 1061685
Signed-off-by: Avra Sengupta <asengupt@redhat.com>
Reviewed-on: http://review.gluster.org/7454
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Rajesh Joseph <rjoseph@redhat.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>

1 files changed, 18 insertions, 27 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-store.c b/xlators/mgmt/glusterd/src/glusterd-store.c
index b803ba28253..9c04aab50c7 100644
--- a/xlators/mgmt/glusterd/src/glusterd-store.c
+++ b/xlators/mgmt/glusterd/src/glusterd-store.c
@@ -2994,6 +2994,7 @@ glusterd_store_retrieve_missed_snaps_list (xlator_t  *this)
 {
         char                   buf[PATH_MAX]    = "";
         char                   path[PATH_MAX]   = "";
+        char                  *snap_vol_id      = NULL;
         char                  *missed_node_info = NULL;
         char                  *brick_path       = NULL;
         char                  *value            = NULL;
@@ -3048,12 +3049,13 @@ glusterd_store_retrieve_missed_snaps_list (xlator_t  *this)
                 }
 
                 /* Fetch the brick_num, brick_path, snap_op and snap status */
-                brick_num = atoi(strtok_r (value, ":", &save_ptr));
+                snap_vol_id = strtok_r (value, ":", &save_ptr);
+                brick_num = atoi(strtok_r (NULL, ":", &save_ptr));
                 brick_path = strtok_r (NULL, ":", &save_ptr);
                 snap_op = atoi(strtok_r (NULL, ":", &save_ptr));
                 snap_status = atoi(strtok_r (NULL, ":", &save_ptr));
 
-                if (!missed_node_info || !brick_path ||
+                if (!missed_node_info || !brick_path || !snap_vol_id ||
                     brick_num < 1 || snap_op < 1 ||
                     snap_status < 1) {
                         gf_log (this->name, GF_LOG_ERROR,
@@ -3062,11 +3064,12 @@ glusterd_store_retrieve_missed_snaps_list (xlator_t  *this)
                         goto out;
                 }
 
-                ret = glusterd_store_missed_snaps_list (missed_node_info,
-                                                        brick_num,
-                                                        brick_path,
-                                                        snap_op,
-                                                        snap_status);
+                ret = glusterd_add_new_entry_to_list (missed_node_info,
+                                                      snap_vol_id,
+                                                      brick_num,
+                                                      brick_path,
+                                                      snap_op,
+                                                      snap_status);
                 if (ret) {
                         gf_log (this->name, GF_LOG_ERROR,
                                 "Failed to store missed snaps_list");
@@ -3145,6 +3148,7 @@ out:
 int32_t
 glusterd_store_write_missed_snapinfo (int32_t fd)
 {
+        char                           key[PATH_MAX]               = "";
         char                           value[PATH_MAX]             = "";
         int32_t                        ret                         = -1;
         glusterd_conf_t               *priv                        = NULL;
@@ -3164,14 +3168,15 @@ glusterd_store_write_missed_snapinfo (int32_t fd)
                 list_for_each_entry (snap_opinfo,
                                      &missed_snapinfo->snap_ops,
                                      snap_ops_list) {
-                        snprintf (value, sizeof(value), "%d:%s:%d:%d",
+                        snprintf (key, sizeof(key), "%s:%s",
+                                  missed_snapinfo->node_uuid,
+                                  missed_snapinfo->snap_uuid);
+                        snprintf (value, sizeof(value), "%s:%d:%s:%d:%d",
+                                  snap_opinfo->snap_vol_id,
                                   snap_opinfo->brick_num,
                                   snap_opinfo->brick_path,
                                   snap_opinfo->op, snap_opinfo->status);
-                        ret = gf_store_save_value
-                                           (fd,
-                                            missed_snapinfo->node_snap_info,
-                                            value);
+                        ret = gf_store_save_value (fd, key, value);
                         if (ret) {
                                 gf_log (this->name, GF_LOG_ERROR,
                                         "Failed to write missed snapinfo");
@@ -3189,7 +3194,7 @@ out:
 /* Adds the missed snap entries to the in-memory conf->missed_snap_list *
  * and writes them to disk */
 int32_t
-glusterd_store_update_missed_snaps (dict_t *dict, int32_t missed_snap_count)
+glusterd_store_update_missed_snaps ()
 {
         int32_t                        fd                          = -1;
         int32_t                        ret                         = -1;
@@ -3198,17 +3203,10 @@ glusterd_store_update_missed_snaps (dict_t *dict, int32_t missed_snap_count)
 
         this = THIS;
         GF_ASSERT(this);
-        GF_ASSERT(dict);
 
         priv = this->private;
         GF_ASSERT (priv);
 
-        if (missed_snap_count < 1) {
-                gf_log (this->name, GF_LOG_DEBUG, "No missed snaps");
-                ret = 0;
-                goto out;
-        }
-
         ret = glusterd_store_create_missed_snaps_list_shandle_on_absence ();
         if (ret) {
                 gf_log (this->name, GF_LOG_ERROR, "Unable to obtain "
@@ -3224,13 +3222,6 @@ glusterd_store_update_missed_snaps (dict_t *dict, int32_t missed_snap_count)
                 goto out;
         }
 
-        ret = glusterd_add_missed_snaps_to_list (dict, missed_snap_count);
-        if (ret) {
-                gf_log (this->name, GF_LOG_ERROR,
-                        "Failed to add missed snaps to list");
-                goto out;
-        }
-
         ret = glusterd_store_write_missed_snapinfo (fd);
         if (ret) {
                 gf_log (this->name, GF_LOG_ERROR,