cluster/afr: [Feature] Command implementation to get heal-count

Currently to know the number of files to be healed, either user
has to go to backend and check the number of entries present in
indices/xattrop directory. But if a volume consists of large
number of bricks, going to each backend and counting the number
of entries is a time-taking task. Otherwise user can give
gluster volume heal vol-name info command but with this
approach if no. of entries are very hugh in the indices/
xattrop directory, it will comsume time.

So as a feature, new command is implemented.

Command 1: gluster volume heal vn statistics heal-count
This command will get the number of entries present in
every brick of a volume. The output displays only entries
count.

Command 2: gluster volume heal vn statistics heal-count
           replica 192.168.122.1:/home/user/brickname

           Here if we are concerned with just one replica.
So providing any one of the brick of a replica will get
the number of entries to be healed for that replica only.

Example:
Replicate volume with replica count 2.

Backend status:
--------------
[root@dhcp-0-17 xattrop]# ls -lia | wc -l
1918

NOTE: Out of 1918, 2 entries are <xattrop-gfid> dummy
entries so actual no. of entries to be healed are
1916.

[root@dhcp-0-17 xattrop]# pwd
/home/user/2ty/.glusterfs/indices/xattrop

Command output:
--------------
Gathering count of entries to be healed on volume volume3 has been successful

Brick 192.168.122.1:/home/user/22iu
Status: Brick is Not connected
Entries count is not available

Brick 192.168.122.1:/home/user/2ty
Number of entries: 1916

Change-Id: I72452f3de50502dc898076ec74d434d9e77fd290
BUG: 1015990
Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com>
Reviewed-on: http://review.gluster.org/6044
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

4 files changed, 178 insertions, 25 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-op-sm.c b/xlators/mgmt/glusterd/src/glusterd-op-sm.c
index 15cb3d83e..06e7fc718 100644
--- a/xlators/mgmt/glusterd/src/glusterd-op-sm.c
+++ b/xlators/mgmt/glusterd/src/glusterd-op-sm.c
@@ -4532,24 +4532,95 @@ out:
 }
 
 int
+get_replica_index_for_per_replica_cmd (glusterd_volinfo_t *volinfo,
+                                       dict_t *dict) {
+        int                     ret = 0;
+        char                    *hostname = NULL;
+        char                    *path = NULL;
+        int                     index = 0;
+        glusterd_brickinfo_t   *brickinfo = NULL;
+        int                     cmd_replica_index = -1;
+        int                     replica_count = -1;
+
+
+        if (!dict)  {
+                ret = -1;
+                goto out;
+        }
+
+        ret = dict_get_str (dict, "per-replica-cmd-hostname", &hostname);
+        if (ret)
+                goto out;
+        ret = dict_get_str (dict, "per-replica-cmd-path", &path);
+        if (ret)
+                goto out;
+
+        replica_count = volinfo->replica_count;
+
+        list_for_each_entry (brickinfo, &volinfo->bricks, brick_list) {
+                if (uuid_is_null (brickinfo->uuid))
+                        (void)glusterd_resolve_brick (brickinfo);
+                if (!strcmp (brickinfo->path,  path) &&
+                    !strcmp (brickinfo->hostname, hostname)) {
+                        cmd_replica_index = index/(replica_count);
+                        goto out;
+                }
+                index++;
+        }
+
+
+out:
+        if (ret)
+                cmd_replica_index = -1;
+
+        return cmd_replica_index;
+}
+
+int
 _select_rxlators_with_local_bricks (xlator_t *this, glusterd_volinfo_t *volinfo,
-                                    dict_t *dict)
+                                    dict_t *dict, cli_cmd_type type)
 {
         glusterd_brickinfo_t    *brickinfo = NULL;
         glusterd_conf_t         *priv   = NULL;
-        int                     index = 1;
+        int                     index = 0;
         int                     rxlator_count = 0;
         int                     replica_count = 0;
         gf_boolean_t            add     = _gf_false;
+        int                     ret = 0;
+        int                     cmd_replica_index = -1;
 
         priv = this->private;
         replica_count = volinfo->replica_count;
+
+        if (type == PER_REPLICA) {
+
+                cmd_replica_index = get_replica_index_for_per_replica_cmd
+                                    (volinfo, dict);
+                if (cmd_replica_index == -1) {
+                        ret = -1;
+                        goto err;
+                }
+        }
+
+        index = 1;
+
         list_for_each_entry (brickinfo, &volinfo->bricks, brick_list) {
                 if (uuid_is_null (brickinfo->uuid))
                         (void)glusterd_resolve_brick (brickinfo);
 
-                if (!uuid_compare (MY_UUID, brickinfo->uuid))
-                        add = _gf_true;
+                switch (type) {
+                        case ALL_REPLICA:
+                                if (!uuid_compare (MY_UUID, brickinfo->uuid))
+                                        add = _gf_true;
+                                break;
+                        case PER_REPLICA:
+                                if (!uuid_compare (MY_UUID, brickinfo->uuid) &&
+                                 ((index-1)/replica_count == cmd_replica_index))
+
+                                                add = _gf_true;
+                                break;
+                }
+
                 if (index % replica_count == 0) {
                         if (add) {
                                 _add_rxlator_to_dict (dict, volinfo->volname,
@@ -4562,6 +4633,10 @@ _select_rxlators_with_local_bricks (xlator_t *this, glusterd_volinfo_t *volinfo,
 
                 index++;
         }
+err:
+        if (ret)
+                rxlator_count = -1;
+
         return rxlator_count;
 }
 
@@ -4659,7 +4734,8 @@ out:
 #endif
 
 static int
-fill_shd_status_for_local_bricks (dict_t *dict, glusterd_volinfo_t *volinfo)
+fill_shd_status_for_local_bricks (dict_t *dict, glusterd_volinfo_t *volinfo,
+                                  cli_cmd_type type, dict_t *req_dict)
 {
         glusterd_brickinfo_t    *brickinfo = NULL;
         char                    msg[1024] = {0,};
@@ -4668,10 +4744,22 @@ fill_shd_status_for_local_bricks (dict_t *dict, glusterd_volinfo_t *volinfo)
         int                     index = 0;
         int                     ret = 0;
         xlator_t               *this = NULL;
+        int                     cmd_replica_index = -1;
 
         this = THIS;
         snprintf (msg, sizeof (msg), "self-heal-daemon is not running on");
 
+        if (type == PER_REPLICA) {
+                cmd_replica_index = get_replica_index_for_per_replica_cmd
+                                    (volinfo, req_dict);
+                if (cmd_replica_index == -1) {
+                        gf_log (THIS->name, GF_LOG_ERROR, "Could not find the "
+                                "replica index for per replica type command");
+                        ret = -1;
+                        goto out;
+                }
+        }
+
         list_for_each_entry (brickinfo, &volinfo->bricks, brick_list) {
                 if (uuid_is_null (brickinfo->uuid))
                         (void)glusterd_resolve_brick (brickinfo);
@@ -4680,6 +4768,14 @@ fill_shd_status_for_local_bricks (dict_t *dict, glusterd_volinfo_t *volinfo)
                         index++;
                         continue;
                 }
+
+                if (type == PER_REPLICA) {
+                      if (cmd_replica_index != (index/volinfo->replica_count)) {
+                              index++;
+                              continue;
+                        }
+
+                }
                 snprintf (key, sizeof (key), "%d-status",index);
                 snprintf (value, sizeof (value), "%s %s",msg,
                           uuid_utoa(MY_UUID));
@@ -4748,21 +4844,49 @@ glusterd_bricks_select_heal_volume (dict_t *dict, char **op_errstr,
                 goto out;
         }
 
+        switch (heal_op) {
+                case GF_AFR_OP_INDEX_SUMMARY:
+                case GF_AFR_OP_STATISTICS_HEAL_COUNT:
+                if (!glusterd_is_nodesvc_online ("glustershd")) {
+                        if (!rsp_dict) {
+                                gf_log (this->name, GF_LOG_ERROR, "Received "
+                                        "empty ctx.");
+                                goto out;
+                        }
 
-        if (!glusterd_is_nodesvc_online ("glustershd") &&
-            (heal_op == GF_AFR_OP_INDEX_SUMMARY)) {
-
-                if (!rsp_dict) {
-                        gf_log (this->name, GF_LOG_ERROR, "Received empty "
-                                "ctx.");
+                        ret = fill_shd_status_for_local_bricks (rsp_dict,
+                                                                volinfo,
+                                                                ALL_REPLICA,
+                                                                dict);
+                        if (ret)
+                                gf_log (this->name, GF_LOG_ERROR, "Unable to "
+                                        "fill the shd status for the local "
+                                        "bricks");
                         goto out;
+
                 }
+                break;
+                case GF_AFR_OP_STATISTICS_HEAL_COUNT_PER_REPLICA:
+                if (!glusterd_is_nodesvc_online ("glustershd")) {
+                        if (!rsp_dict) {
+                                gf_log (this->name, GF_LOG_ERROR, "Received "
+                                        "empty ctx.");
+                                goto out;
+                        }
+                        ret = fill_shd_status_for_local_bricks (rsp_dict,
+                                                                volinfo,
+                                                                PER_REPLICA,
+                                                                dict);
+                        if (ret)
+                                gf_log (this->name, GF_LOG_ERROR, "Unable to "
+                                        "fill the shd status for the local"
+                                        " bricks.");
+                        goto out;
 
-                ret = fill_shd_status_for_local_bricks (rsp_dict, volinfo);
-                if (ret)
-                        gf_log (this->name, GF_LOG_ERROR, "Unable to fill the shd"
-                                " status for the local bricks");
-                goto out;
+                }
+                break;
+                default:
+                        break;
         }
 
 
@@ -4772,14 +4896,28 @@ glusterd_bricks_select_heal_volume (dict_t *dict, char **op_errstr,
                                                                      volinfo,
                                                                      dict);
                 break;
+        case GF_AFR_OP_STATISTICS_HEAL_COUNT_PER_REPLICA:
+                rxlator_count = _select_rxlators_with_local_bricks (this,
+                                                                   volinfo,
+                                                                   dict,
+                                                                   PER_REPLICA);
+                break;
         default:
                 rxlator_count = _select_rxlators_with_local_bricks (this,
                                                                     volinfo,
-                                                                    dict);
+                                                                    dict,
+                                                                   ALL_REPLICA);
                 break;
         }
         if (!rxlator_count)
                 goto out;
+        if (rxlator_count == -1){
+                gf_log (this->name, GF_LOG_ERROR, "Could not determine the"
+                        "translator count");
+                ret = -1;
+                goto out;
+        }
+
         ret = dict_set_int32 (dict, "count", rxlator_count);
         if (ret)
                 goto out;
diff --git a/xlators/mgmt/glusterd/src/glusterd-op-sm.h b/xlators/mgmt/glusterd/src/glusterd-op-sm.h
index 321c5c484..17d666c73 100644
--- a/xlators/mgmt/glusterd/src/glusterd-op-sm.h
+++ b/xlators/mgmt/glusterd/src/glusterd-op-sm.h
@@ -162,6 +162,12 @@ typedef struct glusterd_gsync_status_temp {
         glusterd_volinfo_t *volinfo;
         char *node;
 }glusterd_gsync_status_temp_t;
+
+typedef enum cli_cmd_type_ {
+        PER_REPLICA,
+        ALL_REPLICA,
+ } cli_cmd_type;
+
 int
 glusterd_op_sm_new_event (glusterd_op_sm_event_type_t event_type,
                           glusterd_op_sm_event_t **new_event);
diff --git a/xlators/mgmt/glusterd/src/glusterd-utils.c b/xlators/mgmt/glusterd/src/glusterd-utils.c
index 80ec7155c..21b5d746c 100644
--- a/xlators/mgmt/glusterd/src/glusterd-utils.c
+++ b/xlators/mgmt/glusterd/src/glusterd-utils.c
@@ -7390,6 +7390,7 @@ glusterd_heal_volume_brick_rsp (dict_t *req_dict, dict_t *rsp_dict,
         else
                 dict_foreach (rsp_dict, _heal_volume_add_shd_rsp, &rsp_ctx);
 
+
 out:
         return ret;
 }
diff --git a/xlators/mgmt/glusterd/src/glusterd-volume-ops.c b/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
index c1aea4136..d47951f73 100644
--- a/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
+++ b/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
@@ -1211,14 +1211,22 @@ glusterd_op_stage_heal_volume (dict_t *dict, char **op_errstr)
                 goto out;
         }
 
-        if ((heal_op != GF_AFR_OP_INDEX_SUMMARY) &&
-            !glusterd_is_nodesvc_online ("glustershd")) {
-                ret = -1;
-                *op_errstr = gf_strdup ("Self-heal daemon is not running."
-                                        " Check self-heal daemon log file.");
-                gf_log (this->name, GF_LOG_WARNING, "%s", "Self-heal daemon is "
-                        "not running. Check self-heal daemon log file.");
-                goto out;
+        switch (heal_op) {
+                case GF_AFR_OP_INDEX_SUMMARY:
+                case GF_AFR_OP_STATISTICS_HEAL_COUNT:
+                case GF_AFR_OP_STATISTICS_HEAL_COUNT_PER_REPLICA:
+                        break;
+                default:
+                        if (!glusterd_is_nodesvc_online("glustershd")){
+                                ret = -1;
+                                *op_errstr = gf_strdup ("Self-heal daemon is "
+                                                "not running. Check self-heal "
+                                                "daemon log file.");
+                                gf_log (this->name, GF_LOG_WARNING, "%s",
+                                        "Self-heal daemon is not running."
+                                        "Check self-heal daemon log file.");
+                                goto out;
+                        }
         }
 
         ret = 0;