From 06eb3d0b8488d12a92ea21b92727497c585bae4b Mon Sep 17 00:00:00 2001
From: Harpreet Kaur <hlalwani@redhat.com>
Date: Mon, 7 Jan 2019 16:38:25 +0530
Subject: geo-rep: Fix for "Transport End Point not connected" issue

problem: Geo-rep gsyncd process mounts the master and slave volume
         on master nodes and slave nodes respectively and starts
         the sync. But it doesn't wait for the mount to be in ready
         state to accept I/O. The gluster mount is considered to be
         ready when all the distribute sub-volumes is up. If the all
         the distribute subvolumes are not up, it can cause ENOTCONN
         error, when lookup on file comes and file is on the subvol
         that is down.

solution: Added a Virtual Xattr "dht.subvol.status" which returns "1"
          if all subvols are up and "0" if all subvols are not up.
          Geo-rep then uses this virtual xattr after a fresh mount, to
          check whether all subvols are up or not and then starts the
          I/O.

fixes: bz#1664335
Change-Id: If3ad01d728b1372da7c08ccbe75a45bdc1ab2a91
Signed-off-by: Harpreet Kaur <hlalwani@redhat.com>
Signed-off-by: Kotresh HR <khiremat@redhat.com>
---
 xlators/cluster/dht/src/dht-common.c | 59 ++++++++++++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)

(limited to 'xlators/cluster/dht/src/dht-common.c')

diff --git a/xlators/cluster/dht/src/dht-common.c b/xlators/cluster/dht/src/dht-common.c
index b762f1a358d..ce211e6c642 100644
--- a/xlators/cluster/dht/src/dht-common.c
+++ b/xlators/cluster/dht/src/dht-common.c
@@ -4865,6 +4865,60 @@ out:
     return 0;
 }
 
+/* Virtual Xattr which returns 1 if all subvols are up,
+   else returns 0. Geo-rep then uses this virtual xattr
+   after a fresh mount and starts the I/O.
+*/
+
+enum dht_vxattr_subvol {
+    DHT_VXATTR_SUBVOLS_UP = 1,
+    DHT_VXATTR_SUBVOLS_DOWN = 0,
+};
+
+int
+dht_vgetxattr_subvol_status(call_frame_t *frame, xlator_t *this,
+                            const char *key)
+{
+    dht_local_t *local = NULL;
+    int ret = -1;
+    int op_errno = ENODATA;
+    int value = DHT_VXATTR_SUBVOLS_UP;
+    int i = 0;
+    dht_conf_t *conf = NULL;
+
+    conf = this->private;
+    local = frame->local;
+
+    if (!key) {
+        op_errno = EINVAL;
+        goto out;
+    }
+    local->xattr = dict_new();
+    if (!local->xattr) {
+        op_errno = ENOMEM;
+        goto out;
+    }
+    for (i = 0; i < conf->subvolume_cnt; i++) {
+        if (!conf->subvolume_status[i]) {
+            value = DHT_VXATTR_SUBVOLS_DOWN;
+            gf_msg_debug(this->name, 0, "subvol %s is down ",
+                         conf->subvolumes[i]->name);
+            break;
+        }
+    }
+    ret = dict_set_int8(local->xattr, (char *)key, value);
+    if (ret < 0) {
+        op_errno = -ret;
+        ret = -1;
+        goto out;
+    }
+    ret = 0;
+
+out:
+    DHT_STACK_UNWIND(getxattr, frame, ret, op_errno, local->xattr, NULL);
+    return 0;
+}
+
 int
 dht_getxattr(call_frame_t *frame, xlator_t *this, loc_t *loc, const char *key,
              dict_t *xdata)
@@ -4922,6 +4976,11 @@ dht_getxattr(call_frame_t *frame, xlator_t *this, loc_t *loc, const char *key,
         goto err;
     }
 
+    if (strncmp(key, DHT_SUBVOL_STATUS_KEY, SLEN(DHT_SUBVOL_STATUS_KEY)) == 0) {
+        dht_vgetxattr_subvol_status(frame, this, key);
+        return 0;
+    }
+
     /* skip over code which is irrelevant if !DHT_IS_DIR(layout) */
     if (!DHT_IS_DIR(layout))
         goto no_dht_is_dir;
-- 
cgit