hi, In current record_write_error logic, we do not shard the last_complete during peers. This cause that osd could not trim pg log, and store tens of thousands of pg log in memory This occurs when we remove a very large empty image and there are not successful write. -- Regards, Xinze Chi -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
