Hi, Currently when something goes wrong with the backing Ceph cluster a RGW will block for ever because RADOS operationgs block indefinitely. Using 'rados_osd_op_timeout' and 'rados_mon_op_timeout' we can tune this behaviour by setting timeouts to 30 seconds. [0] By doing so we can give clients back a proper error instead of just hanging there. I'm just wondering, is there a danger here which I don't see? Possible corruption of multipart uploads not succeeding and corrupting that way for example? I can't think of a reason, but maybe somebody else has a clever insight on this. Wido [0]: https://github.com/ceph/ceph/blob/dc02b37a9704eb33c86108cf05768b85af05fe1b/src/common/config_opts.h#L1174 _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |