4 files changed, 23 insertions, 5 deletions

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 6b7c6acbb3bf..2160aab482f6 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -14,7 +14,9 @@
 #define CEPH_FEATURE_DIRLAYOUTHASH  (1<<7)
 /* bits 8-17 defined by user-space; not supported yet here */
 #define CEPH_FEATURE_CRUSH_TUNABLES (1<<18)
-/* bits 19-25 defined by user-space; not supported yet here */
+/* bits 19-24 defined by user-space; not supported yet here */
+#define CEPH_FEATURE_CRUSH_TUNABLES2 (1<<25)
+/* bit 26 defined by user-space; not supported yet here */
 #define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27)
 
 /*
@@ -22,7 +24,8 @@
  */
 #define CEPH_FEATURES_SUPPORTED_DEFAULT  \
         (CEPH_FEATURE_NOSRCADDR |        \
-         CEPH_FEATURE_CRUSH_TUNABLES |   \
+         CEPH_FEATURE_CRUSH_TUNABLES |    \
+         CEPH_FEATURE_CRUSH_TUNABLES2 |   \
          CEPH_FEATURE_REPLY_CREATE_INODE)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 25baa287cff7..6a1101f24cfb 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -162,6 +162,8 @@ struct crush_map {
         __u32 choose_local_fallback_tries;
         /* choose attempts before giving up */ 
         __u32 choose_total_tries;
+        /* attempt chooseleaf inner descent once; on failure retry outer descent */
+        __u32 chooseleaf_descend_once;
 };
 
 
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 35fce755ce10..96c8a58937db 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -287,6 +287,7 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in
  * @outpos: our position in that vector
  * @firstn: true if choosing "first n" items, false if choosing "indep"
  * @recurse_to_leaf: true if we want one device under each item of given type
+ * @descend_once: true if we should only try one descent before giving up
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
  */
 static int crush_choose(const struct crush_map *map,
@@ -295,7 +296,7 @@ static int crush_choose(const struct crush_map *map,
                         int x, int numrep, int type,
                         int *out, int outpos,
                         int firstn, int recurse_to_leaf,
-                        int *out2)
+                        int descend_once, int *out2)
 {
         int rep;
         unsigned int ftotal, flocal;
@@ -399,6 +400,7 @@ static int crush_choose(const struct crush_map *map,
                                                          x, outpos+1, 0,
                                                          out2, outpos,
                                                          firstn, 0,
+                                                         map->chooseleaf_descend_once,
                                                          NULL) <= outpos)
                                                         /* didn't get leaf */
                                                         reject = 1;
@@ -422,7 +424,10 @@ reject:
                                         ftotal++;
                                         flocal++;
 
-                                        if (collide && flocal <= map->choose_local_tries)
+                                        if (reject && descend_once)
+                                                /* let outer call try again */
+                                                skip_rep = 1;
+                                        else if (collide && flocal <= map->choose_local_tries)
                                                 /* retry locally a few times */
                                                 retry_bucket = 1;
                                         else if (map->choose_local_fallback_tries > 0 &&
@@ -485,6 +490,7 @@ int crush_do_rule(const struct crush_map *map,
         int i, j;
         int numrep;
         int firstn;
+        const int descend_once = 0;
 
         if ((__u32)ruleno >= map->max_rules) {
                 dprintk(" bad ruleno %d\n", ruleno);
@@ -544,7 +550,8 @@ int crush_do_rule(const struct crush_map *map,
                                                       curstep->arg2,
                                                       o+osize, j,
                                                       firstn,
-                                                      recurse_to_leaf, c+osize);
+                                                      recurse_to_leaf,
+                                                      descend_once, c+osize);
                         }
 
                         if (recurse_to_leaf)
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index de73214b5d26..ca05871635bc 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -170,6 +170,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
         c->choose_local_tries = 2;
         c->choose_local_fallback_tries = 5;
         c->choose_total_tries = 19;
+        c->chooseleaf_descend_once = 0;
 
         ceph_decode_need(p, end, 4*sizeof(u32), bad);
         magic = ceph_decode_32(p);
@@ -336,6 +337,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
         dout("crush decode tunable choose_total_tries = %d",
              c->choose_total_tries);
 
+        ceph_decode_need(p, end, sizeof(u32), done);
+        c->chooseleaf_descend_once = ceph_decode_32(p);
+        dout("crush decode tunable chooseleaf_descend_once = %d",
+             c->chooseleaf_descend_once);
+
 done:
         dout("crush_decode success\n");
         return c;