cluster/afr : Implementation of command "gluster volume heal vn statistics"

"gluster volume heal volumename statistics" command gives the summary
of the afr crawl done based on the entries present in the xattrop
directory. Whenever afr crawls are attempted, the beginning time of
crawl, end time of crawl, no of files healed, heal-failed count and
number of files in split brain are shown along with the type of the
crawl. If crawl is already in progress then it will give the number
of files healed, heal failed count and number of files in split-brain
from the beginning of the crawl and instead of telling the end time of
the crawl, "CRAWL IN PROGRESS" message will be shown.

Output format:
command: "gluster volume heal volume-name statistics"
Output:
Gathering afr crawl statistics crawl statistics on volume volume-name
has been successful
------------------------------------------------

Crawl statistics for brick no 0
Hostname of brick 192.168.122.248

Starting time of crawl: Wed Jul 10 15:52:38 2013

Ending time of crawl: Wed Jul 10 15:52:38 2013

Type of crawl: INDEX
No. of entries healed: 0
No. of entries in split-brain: 0
No. of heal failed entries: 0

Starting time of crawl: Wed Jul 10 15:52:38 2013

Ending time of crawl: Wed Jul 10 15:52:38 2013

Type of crawl: INDEX
No. of entries healed: 0
No. of entries in split-brain: 0
No. of heal failed entries: 0

------------------------------------------------

Crawl statistics for brick no 1
Hostname of brick 192.168.122.1

Starting time of crawl: Wed Jul 10 15:52:42 2013

Ending time of crawl: Wed Jul 10 15:52:42 2013

Type of crawl: INDEX
No. of entries healed: 0
No. of entries in split-brain: 0
No. of heal failed entries: 0

Starting time of crawl: Wed Jul 10 15:52:42 2013

Ending time of crawl: Wed Jul 10 15:52:42 2013

Type of crawl: INDEX
No. of entries healed: 0
No. of entries in split-brain: 0
No. of heal failed entries: 0

--------------------------------------------------

Change-Id: I10bf9d10b005741db9973fb1352e0dd59ed99aa9
BUG: 949400
Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com>
Reviewed-on: http://review.gluster.org/4790
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

1 files changed, 64 insertions, 3 deletions

diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index 1acbc01ba..d7d786108 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -51,7 +51,7 @@
 
 #define AFR_ICTX_OPENDIR_DONE_MASK     0x0000000100000000ULL
 #define AFR_ICTX_READ_CHILD_MASK       0x00000000FFFFFFFFULL
-
+#define AFR_STATISTICS_HISTORY_SIZE    50
 int
 afr_lookup_done_success_action (call_frame_t *frame, xlator_t *this,
                                 gf_boolean_t fail_conflict);
@@ -1832,7 +1832,8 @@ afr_lookup_perform_self_heal (call_frame_t *frame, xlator_t *this,
 
         afr_lookup_set_self_heal_params (local, this);
         if (afr_can_self_heal_proceed (&local->self_heal, priv)) {
-                if  (afr_is_transaction_running (local))
+                if  (afr_is_transaction_running (local) &&
+                     (!local->allow_sh_for_running_transaction))
                         goto out;
 
                 reason = "lookup detected pending operations";
@@ -2427,7 +2428,7 @@ afr_lookup (call_frame_t *frame, xlator_t *this,
         int               call_count     = 0;
         uint64_t          ctx            = 0;
         int32_t           op_errno       = 0;
-
+        int               allow_sh       = 0;
         priv = this->private;
 
         AFR_LOCAL_ALLOC_OR_GOTO (local, out);
@@ -2499,6 +2500,11 @@ afr_lookup (call_frame_t *frame, xlator_t *this,
         /* By default assume ENOTCONN. On success it will be set to 0. */
         local->op_errno = ENOTCONN;
 
+        ret = dict_get_int32 (xattr_req, "allow-sh-for-running-transaction",
+                              &allow_sh);
+        dict_del (xattr_req, "allow-sh-for-running-transaction");
+        local->allow_sh_for_running_transaction = allow_sh;
+
         ret = afr_lookup_xattr_req_prepare (local, this, xattr_req, &local->loc,
                                             &gfid_req);
         if (ret) {
@@ -4425,6 +4431,16 @@ afr_priv_destroy (afr_private_t *priv)
         if (priv->shd.split_brain)
                 eh_destroy (priv->shd.split_brain);
 
+        for (i = 0; i < priv->child_count; i++)
+        {
+                if (priv->shd.statistics[i])
+                        eh_destroy (priv->shd.statistics[i]);
+        }
+
+        GF_FREE (priv->shd.statistics);
+
+        GF_FREE (priv->shd.crawl_events);
+
         GF_FREE (priv->last_event);
         if (priv->pending_key) {
                 for (i = 0; i < priv->child_count; i++)
@@ -4528,3 +4544,48 @@ afr_handle_open_fd_count (call_frame_t *frame, xlator_t *this)
         }
         UNLOCK (&inode->lock);
 }
+
+int
+afr_initialise_statistics (xlator_t *this)
+{
+        afr_private_t       *priv = NULL;
+        int                 ret = -1;
+        int                 i = 0;
+        int                 child_count = 0;
+        eh_t                *stats_per_brick = NULL;
+        shd_crawl_event_t   ***shd_crawl_events = NULL;
+        priv = this->private;
+
+        priv->shd.statistics = GF_CALLOC (sizeof(eh_t *), priv->child_count,
+                                          gf_common_mt_eh_t);
+        if (!priv->shd.statistics) {
+                ret = -1;
+                goto out;
+        }
+        child_count = priv->child_count;
+        for (i=0; i < child_count ; i++) {
+                stats_per_brick = eh_new (AFR_STATISTICS_HISTORY_SIZE,
+                                          _gf_false,
+                                          _destroy_crawl_event_data);
+                if (!stats_per_brick) {
+                        ret = -1;
+                        goto out;
+                }
+                priv->shd.statistics[i] = stats_per_brick;
+
+        }
+
+        shd_crawl_events = (shd_crawl_event_t***)(&priv->shd.crawl_events);
+        *shd_crawl_events  = GF_CALLOC (sizeof(shd_crawl_event_t*),
+                                        priv->child_count,
+                                        gf_afr_mt_shd_crawl_event_t);
+
+        if (!priv->shd.crawl_events) {
+                ret = -1;
+                goto out;
+        }
+        ret = 0;
+out:
+        return ret;
+
+}