Fix bug with routing to an acting set like [None,Y,X,X]p(X)
for a 3+1 optimzed pool where osd X is representing more
than one shard. For an optimized EC pool we want it to
choose shard 3 because shard 2 is a non-primary. If we
just search the acting set for the first OSD that matches
X this will pick shard 2, so we have to convert the order
to primary's first, then find the matching OSD and then
convert this back to the normal ordering to get shard 3.
Signed-off-by: Bill Scales <bill_scales@uk.ibm.com>
(cherry picked from commit
3310f97859109090706b84824cac2f8a6cfe6928)
t->pg_num_pending = pg_num_pending;
spg_t spgid(actual_pgid);
if (pi->is_erasure()) {
+ // Optimized EC pools need to be careful when calculating the shard
+ // because an OSD may have multiple shards and the primary shard
+ // might not be the first one in the acting set. The lookup
+ // therefoere has to be done in primaryfirst order.
+ std::vector<int> pg_temp = t->acting;
+ if (osdmap->has_pgtemp(actual_pgid)) {
+ pg_temp = osdmap->pgtemp_primaryfirst(*pi, t->acting);
+ }
for (uint8_t i = 0; i < t->acting.size(); ++i) {
- if (t->acting[i] == acting_primary) {
+ if (pg_temp[i] == acting_primary) {
spgid.reset_shard(osdmap->pgtemp_undo_primaryfirst(*pi, actual_pgid, shard_id_t(i)));
break;
}