crush: apply chooseleaf_tries to firstn mode too

Parameterize the attempts for the _firstn choose method, and apply the
rule-specified tries count to firstn mode as well.  Note that we have
slightly different behavior here than with indep:

 If the firstn value is not specified for firstn, we pass through the
 normal attempt count.  This maintains compatibility with legacy behavior.
 Note that this is usually *not* actually N^2 work, though, because of the
 descend_once tunable.  However, descend_once is unfortunately *not* the
 same thing as 1 chooseleaf try because it is only checked on a reject but
 not on a collision.  Sigh.

 In contrast, for indep, if tries is not specified we default to 1
 recursive attempt, because that is simply more sane, and we have the
 option to do so.  The descend_once tunable has no effect for indep.

Reflects ceph.git commit 64aeded50d80942d66a5ec7b604ff2fcbf5d7b63.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>

2 files changed, 14 insertions, 5 deletions

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 2e50bab91655..07b8fd4f81fc 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -165,7 +165,10 @@ 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 */
+	/* attempt chooseleaf inner descent once for firstn mode; on
+	 * reject retry outer descent.  Note that this does *not*
+	 * apply to a collision: in that case we will retry as we used
+	 * to. */
 	__u32 chooseleaf_descend_once;
 };
 
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index e3ade074541c..c34320518c8b 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -299,6 +299,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       const __u32 *weight, int weight_max,
 			       int x, int numrep, int type,
 			       int *out, int outpos,
+			       unsigned int attempts,
+			       unsigned int recurse_attempts,
 			       int recurse_to_leaf,
 			       int descend_once, int *out2)
 {
@@ -385,6 +387,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 							 weight, weight_max,
 							 x, outpos+1, 0,
 							 out2, outpos,
+							 recurse_attempts, 0,
 							 0,
 							 map->chooseleaf_descend_once,
 							 NULL) <= outpos)
@@ -421,7 +424,7 @@ reject:
 						 flocal <= in->size + map->choose_local_fallback_tries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
-					else if (ftotal <= map->choose_total_tries)
+					else if (ftotal <= attempts)
 						/* then retry descent */
 						retry_descent = 1;
 					else
@@ -634,7 +637,8 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
-	int choose_leaf_tries = 1;
+	int choose_tries = map->choose_total_tries;
+	int choose_leaf_tries = 0;
 	const int descend_once = 0;
 
 	if ((__u32)ruleno >= map->max_rules) {
@@ -701,6 +705,8 @@ int crush_do_rule(const struct crush_map *map,
 						x, numrep,
 						curstep->arg2,
 						o+osize, j,
+						choose_tries,
+						choose_leaf_tries ? choose_leaf_tries : choose_tries,
 						recurse_to_leaf,
 						descend_once, c+osize);
 				} else {
@@ -711,8 +717,8 @@ int crush_do_rule(const struct crush_map *map,
 						x, numrep, numrep,
 						curstep->arg2,
 						o+osize, j,
-						map->choose_total_tries,
-						choose_leaf_tries,
+						choose_tries,
+						choose_leaf_tries ? choose_leaf_tries : 1,
 						recurse_to_leaf,
 						c+osize,
 						0);