Hi, Has anybody ever tried or does know how safe it is to set 'rados_osd_op_timeout' in a RGW-only situation? Right now, if one PG becomes inactive or OSDs are super slow the RGW will start to block at some point since the RADOS operations will never time out. Using rados_osd_op_timeout you can say that after X seconds the operation needs to be aborted from the client's side. How safe or dangerous would it be to set this on RGW? This way you would still serve data from PGs which are available instead of having your complete RGW go down due to one PG blocking. Wido _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com