cluster/dht: Do layout self healing of directory for nameless lookup

Problem: Currently in the  nameless lookup code path, if at the
         end of the lookup, even if it detects that layout
         anamolies are there, layout healing will not be done as
         there is no code to heal it.
         So there can be race between mkdir and lookup.

         Assume mkdir is going on from some other mount point,
         Say, M1. Directories are created on some nodes but layout
         is not set yet.

         Now from M2, nameless lookup goes, lookup will be success
         full as the directory is present on some of the nodes, but
         it won't heal layout. Now if create goes after lookup fop,
         because layout is absent, file creation will fail.

Fix:     Included the code of layout self-heal in the nameless
         lookup path. At the end of lookup, layout will be computed
         as it would have been in the named lookup, but it will be
         set to those node only, where directory is present.
         So after that if create fop goes, the probabiliy to get the
         subvolume with proper hash-range is high now, so reduces
         the race window.

Other:  Whenever a directory is created, we have to choose a brick
        from which we start allocating layout in a circular fashion.
        To calculate this starting brick, I have changed the candidate
        from name of the directory to gfid of the directory

        But to compute where a given file belongs, we will still
        use the name of the file. Hash computed from the name of the
        file should belong to any one of the directory-hash-range

        Calculation of hash for a file is acting as a consumer and the
        setting of directory layout based on gfid is acting as a producer,
        which are independent from each other.

Change-Id: I3808c55082cd1b5c72d2c77cbbc063f55aa38bee
BUG: 1095888
Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com>
Reviewed-on: http://review.gluster.org/7493
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra Bhat <raghavendra@redhat.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>

1 files changed, 197 insertions, 0 deletions

diff --git a/xlators/cluster/dht/src/dht-selfheal.c b/xlators/cluster/dht/src/dht-selfheal.c
index 04e58903147..1e2d7438350 100644
--- a/xlators/cluster/dht/src/dht-selfheal.c
+++ b/xlators/cluster/dht/src/dht-selfheal.c
@@ -332,6 +332,144 @@ out:
         return 0;
 }
 
+gf_boolean_t
+dht_is_subvol_part_of_layout (dht_layout_t *layout, xlator_t *xlator)
+{
+        int               i = 0;
+        gf_boolean_t    ret = _gf_false;
+
+        for (i = 0; i < layout->cnt; i++) {
+                if (!strcmp (layout->list[i].xlator->name, xlator->name)) {
+                        ret = _gf_true;
+                        break;
+
+                }
+        }
+
+        return ret;
+}
+
+int
+dht_layout_index_from_conf (dht_layout_t *layout, xlator_t *xlator)
+{
+        int i = -1;
+        int j = 0;
+
+        for (j = 0; j < layout->cnt; j++) {
+                if (!strcmp (layout->list[j].xlator->name, xlator->name)) {
+                        i = j;
+                        break;
+                }
+        }
+
+        return i;
+}
+
+
+static int
+dht_selfheal_dir_xattr_for_nameless_lookup (call_frame_t *frame, loc_t *loc,
+                                            dht_layout_t  *layout)
+{
+        dht_local_t     *local = NULL;
+        int             missing_xattr = 0;
+        int             i = 0;
+        xlator_t        *this = NULL;
+        dht_conf_t      *conf = NULL;
+        dht_layout_t    *dummy = NULL;
+        int             j = 0;
+
+        local = frame->local;
+        this = frame->this;
+        conf = this->private;
+
+        for (i = 0; i < layout->cnt; i++) {
+                if (layout->list[i].err != -1 || !layout->list[i].stop) {
+                        /* err != -1 would mean xattr present on the directory
+                           or the directory is non existent.
+                           !layout->list[i].stop would mean layout absent
+                        */
+
+                        continue;
+                }
+                missing_xattr++;
+        }
+
+        /* Also account for subvolumes with no-layout. Used for zero'ing out
+           the layouts and for setting quota key's if present */
+
+        /* Send  where either the subvol is not part of layout,
+         * or it is part of the layout but error is non-zero but error
+         * is not equal to -1 or ENOENT.
+         */
+
+        for (i = 0; i < conf->subvolume_cnt; i++) {
+                if (dht_is_subvol_part_of_layout (layout, conf->subvolumes[i])
+                    == _gf_false) {
+                        missing_xattr++;
+                        continue;
+                }
+
+                j = dht_layout_index_from_conf (layout, conf->subvolumes[i]);
+
+                if ((j != -1) && (layout->list[j].err != -1) &&
+                   (layout->list[j].err != 0) &&
+                   (layout->list[j].err != ENOENT)) {
+                        missing_xattr++;
+                }
+
+        }
+
+
+        gf_log (this->name, GF_LOG_TRACE,
+                "%d subvolumes missing xattr for %s",
+                missing_xattr, loc->path);
+
+        if (missing_xattr == 0) {
+                dht_selfheal_dir_finish (frame, this, 0);
+                return 0;
+        }
+
+        local->call_cnt = missing_xattr;
+        for (i = 0; i < layout->cnt; i++) {
+                if (layout->list[i].err != -1 || !layout->list[i].stop)
+                        continue;
+
+                dht_selfheal_dir_xattr_persubvol (frame, loc, layout, i, NULL);
+
+                if (--missing_xattr == 0)
+                        break;
+        }
+
+        dummy = dht_layout_new (this, 1);
+        if (!dummy)
+                goto out;
+
+        for (i = 0; i < conf->subvolume_cnt && missing_xattr; i++) {
+              if (dht_is_subvol_part_of_layout (layout, conf->subvolumes[i])
+                  == _gf_false) {
+                        dht_selfheal_dir_xattr_persubvol (frame, loc, dummy, 0,
+                                                          conf->subvolumes[i]);
+                        missing_xattr--;
+                        continue;
+              }
+
+                j = dht_layout_index_from_conf (layout, conf->subvolumes[i]);
+
+                if ((j != -1) && (layout->list[j].err != -1) &&
+                    (layout->list[j].err != ENOENT) &&
+                    (layout->list[j].err != 0)) {
+                        dht_selfheal_dir_xattr_persubvol (frame, loc, dummy, 0,
+                                                          conf->subvolumes[i]);
+                        missing_xattr--;
+                }
+        }
+
+        dht_layout_unref (this, dummy);
+out:
+        return 0;
+
+}
+
 int
 dht_selfheal_dir_setattr_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
                               int op_ret, int op_errno, struct iatt *statpre,
@@ -1030,6 +1168,65 @@ sorry_no_fix:
         return 0;
 }
 
+int
+dht_selfheal_directory_for_nameless_lookup (call_frame_t *frame,
+                                            dht_selfheal_dir_cbk_t dir_cbk,
+                                            loc_t *loc, dht_layout_t *layout)
+{
+        dht_local_t     *local  = NULL;
+        uint32_t        down    = 0;
+        uint32_t        misc    = 0;
+        int             ret     = 0;
+        xlator_t        *this   = NULL;
+
+        local = frame->local;
+        this = frame->this;
+        dht_layout_anomalies (this, loc, layout,
+                              &local->selfheal.hole_cnt,
+                              &local->selfheal.overlaps_cnt,
+                              NULL, &local->selfheal.down,
+                              &local->selfheal.misc, NULL);
+
+        down     = local->selfheal.down;
+        misc     = local->selfheal.misc;
+
+        local->selfheal.dir_cbk = dir_cbk;
+        local->selfheal.layout = dht_layout_ref (this, layout);
+
+        if (down) {
+                gf_log (this->name, GF_LOG_WARNING,
+                        "%d subvolumes down -- not fixing", down);
+                ret = 0;
+                goto sorry_no_fix;
+        }
+
+        if (misc) {
+                gf_log (this->name, GF_LOG_WARNING,
+                        "%d subvolumes have unrecoverable errors", misc);
+                ret = 0;
+                goto sorry_no_fix;
+        }
+
+        dht_layout_sort_volname (layout);
+        ret = dht_selfheal_dir_getafix (frame, loc, layout);
+
+        if (ret == -1) {
+                gf_log (this->name, GF_LOG_WARNING,
+                        "not able to form layout for the directory");
+                goto sorry_no_fix;
+        }
+
+        dht_selfheal_dir_xattr_for_nameless_lookup (frame, &local->loc, layout);
+        return 0;
+
+sorry_no_fix:
+        /* TODO: need to put appropriate local->op_errno */
+        dht_selfheal_dir_finish (frame, this, ret);
+
+        return 0;
+
+
+}
 
 int
 dht_selfheal_restore (call_frame_t *frame, dht_selfheal_dir_cbk_t dir_cbk,