cluster/tier: readdirp to cold tier only

It is possible a file would get migrated in the middle
of a readdir operation. If there are four subvolumes A,B,C,D,
and if readdir reads them in order and reaches subvol B,
then, if a file is moved from D to A, it will not be included
in the readdir output.

This phenonema has pre-existed in DHT migration but is more
apparent in tiering.

When a file is moved off the hashed subvolume a T file is created.
For tiering, we will make the cold subvolume the hashed subvolume.
This will ensure the creation of a T file. Readdir will not skip T
files in the tier translator.

Making the cold subvolume the hashed subvolume ensures the T
files created on promotions or creates will be less likely to
fill the volume.

Creates still put the data on the hot subvolume.

This is a backport of 12530

> Change-Id: Ifde557d3d0e94a4570ca9f115adee3db2ee75407
> BUG:  1281598
> Signed-off-by: Dan Lambright <dlambrig@redhat.com>
> Reviewed-on: http://review.gluster.org/12530
> Tested-by: Gluster Build System <jenkins@build.gluster.com>
> Tested-by: NetBSD Build System <jenkins@build.gluster.org>
> Reviewed-by: N Balachandran <nbalacha@redhat.com>
> Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Signed-off-by: Dan Lambright <dlambrig@redhat.com>

Signed-off-by: Dan Lambright <dlambrig@redhat.com>

Conflicts:
	xlators/cluster/dht/src/tier.c

Change-Id: I5720a4cd04ae5088e5d7d23439b0f90d6bbc6265
BUG: 1283923
Reviewed-on: http://review.gluster.org/12722
Tested-by: NetBSD Build System <jenkins@build.gluster.org>
Reviewed-by: N Balachandran <nbalacha@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Dan Lambright <dlambrig@redhat.com>
Tested-by: Dan Lambright <dlambrig@redhat.com>

1 files changed, 6 insertions, 41 deletions

diff --git a/xlators/cluster/dht/src/tier.c b/xlators/cluster/dht/src/tier.c
index ce6ba4ce57d..476d3323087 100644
--- a/xlators/cluster/dht/src/tier.c
+++ b/xlators/cluster/dht/src/tier.c
@@ -16,6 +16,8 @@
 
 #include "dht-common.h"
 #include "tier.h"
+#include "tier-common.h"
+#include "syscall.h"
 
 /*Hard coded DB info*/
 static gfdb_db_type_t dht_tier_db_type = GFDB_SQLITE3;
@@ -445,7 +447,7 @@ tier_migrate_using_query_file (void *_args)
                                 goto abort;
                         }
 
-                        gf_msg_trace (this->name, 0,
+                        gf_msg_debug (this->name, 0,
                                 "Tier %d"
                                 " src_subvol %s file %s",
                                 query_cbk_args->is_promotion,
@@ -1557,53 +1559,16 @@ xlator_t *
 tier_search (xlator_t *this, dht_layout_t *layout, const char *name)
 {
         xlator_t                *subvol = NULL;
-        void                    *value;
-        int                      search_subvol = 0;
         dht_conf_t              *conf   = NULL;
-        gf_defrag_info_t        *defrag = NULL;
-        int                      layout_cold = 0;
-        int                      layout_hot = 1;
 
         GF_VALIDATE_OR_GOTO ("tier", this, out);
-        GF_VALIDATE_OR_GOTO (this->name, layout, out);
-        GF_VALIDATE_OR_GOTO (this->name, name, out);
         GF_VALIDATE_OR_GOTO (this->name, this->private, out);
 
         conf = this->private;
 
-        /* The first subvolume in the graph is always cold. */
-        /* Find the position of the cold subvolume in the layout. */
-        layout_cold = 0;
-        layout_hot = 1;
-        if (conf->subvolumes[0] != layout->list[0].xlator) {
-                layout_cold = 1;
-                layout_hot = 0;
-        }
-
-        search_subvol = layout_hot;
-
-        defrag = conf->defrag;
-        if (defrag && defrag->cmd == GF_DEFRAG_CMD_START_DETACH_TIER)
-                search_subvol = layout_cold;
-
-        /* "decommission_subvols_cnt" can only be non-zero on detach. */
-        /* This will change once brick add/remove is supported for */
-        /* tiered volumes. */
-        else if (conf->decommission_subvols_cnt) {
-                search_subvol = layout_cold;
-        }
-        else if (!dict_get_ptr (this->options, "rule", &value) &&
-                 !strcmp(layout->list[layout_cold].xlator->name, value)) {
-                search_subvol = layout_cold;
-        }
+        subvol = TIER_HASHED_SUBVOL;
 
-        if ((layout->list[search_subvol].err > 0) &&
-            (layout->list[search_subvol].err != ENOTCONN))
-                search_subvol = layout_cold;
-
-        subvol = layout->list[search_subvol].xlator;
  out:
-
         return subvol;
 }
 
@@ -1970,8 +1935,8 @@ struct xlator_fops fops = {
         .open        = dht_open,
         .statfs      = dht_statfs,
         .opendir     = dht_opendir,
-        .readdir     = dht_readdir,
-        .readdirp    = dht_readdirp,
+        .readdir     = tier_readdir,
+        .readdirp    = tier_readdirp,
         .fsyncdir    = dht_fsyncdir,
         .symlink     = dht_symlink,
         .unlink      = dht_unlink,