crush: be more tolerant of nonsensical crush maps
If we get a map that doesn't make sense, error out or ignore the badness
instead of BUGging out. This reflects the ceph.git commits
9895f0bff7dc68e9b49b572613d242315fb11b6c and
8ded26472058d5205803f244c2f33cb6cb10de79.
Reviewed-by: Alex Elder <elder@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com>
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 583f644..00baad5 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -152,8 +152,8 @@
return bucket->h.items[i];
}
- BUG_ON(1);
- return 0;
+ dprintk("bad list sums for bucket %d\n", bucket->h.id);
+ return bucket->h.items[0];
}
@@ -239,6 +239,7 @@
static int crush_bucket_choose(struct crush_bucket *in, int x, int r)
{
dprintk(" crush_bucket_choose %d x=%d r=%d\n", in->id, x, r);
+ BUG_ON(in->size == 0);
switch (in->alg) {
case CRUSH_BUCKET_UNIFORM:
return bucket_uniform_choose((struct crush_bucket_uniform *)in,
@@ -253,7 +254,7 @@
return bucket_straw_choose((struct crush_bucket_straw *)in,
x, r);
default:
- BUG_ON(1);
+ dprintk("unknown bucket %d alg %d\n", in->id, in->alg);
return in->items[0];
}
}
@@ -354,7 +355,11 @@
item = bucket_perm_choose(in, x, r);
else
item = crush_bucket_choose(in, x, r);
- BUG_ON(item >= map->max_devices);
+ if (item >= map->max_devices) {
+ dprintk(" bad item %d\n", item);
+ skip_rep = 1;
+ break;
+ }
/* desired type? */
if (item < 0)
@@ -365,8 +370,12 @@
/* keep going? */
if (itemtype != type) {
- BUG_ON(item >= 0 ||
- (-1-item) >= map->max_buckets);
+ if (item >= 0 ||
+ (-1-item) >= map->max_buckets) {
+ dprintk(" bad item type %d\n", type);
+ skip_rep = 1;
+ break;
+ }
in = map->buckets[-1-item];
retry_bucket = 1;
continue;
@@ -478,7 +487,10 @@
int numrep;
int firstn;
- BUG_ON(ruleno >= map->max_rules);
+ if ((__u32)ruleno >= map->max_rules) {
+ dprintk(" bad ruleno %d\n", ruleno);
+ return 0;
+ }
rule = map->rules[ruleno];
result_len = 0;
@@ -528,7 +540,8 @@
firstn = 1;
case CRUSH_RULE_CHOOSE_LEAF_INDEP:
case CRUSH_RULE_CHOOSE_INDEP:
- BUG_ON(wsize == 0);
+ if (wsize == 0)
+ break;
recurse_to_leaf =
rule->steps[step].op ==
@@ -597,7 +610,9 @@
break;
default:
- BUG_ON(1);
+ dprintk(" unknown op %d at step %d\n",
+ curstep->op, step);
+ break;
}
}
return result_len;