Hi, Radosgw decided to reshard a bucket with 25 million objects from 256 to 512 shards. Resharding took about 1 hour, during this time all buckets on the cluster had a huge performance drop. "GET" requests for small objects (on other buckets) took multiple seconds. Are there any configuration options to reduce this impact? or limit resharding to a maximum of 256 shards? Micha Krause _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |