Hi In minimum_to_decode function of ErasureCodeLrc.c , I suspect non efficient implementation. More specifically, instead of reading the minimum, we read the maximum. The problem is in this case: // // Get all available chunks in that layer to recover the // missing one(s). // set_difference(i->chunks_as_set.begin(), i->chunks_as_set.end(), erasures_not_recovered.begin(), erasures_not_recovered.end(), inserter(layer_minimum, layer_minimum.end()));
Say this layer is encoded using Reed Solomon (Jerasure). Then we would require K chunks for reconstruction. Instead, the code reads all available chunks. Why is that? Thanks
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
