On Wed, 12 Jun 2019, Harald Staub wrote: > On 12.06.19 17:40, Sage Weil wrote: > > On Wed, 12 Jun 2019, Harald Staub wrote: > > > Also opened an issue about the rocksdb problem: > > > https://tracker.ceph.com/issues/40300 > > > > Thanks! > > > > The 'rocksdb: Corruption: file is too short' the root of the problem > > here. Can you try starting the OSD with 'debug_bluestore=20' and > > 'debug_bluefs=20'? (And attach them to the ticket, or ceph-post-file and > > put the uuid in the ticket..) > > Now we have a log file of size 270 GB, so we tried to extract the interesting > part: > ceph-post-file: 78842f1f-1981-4a81-b3f4-3a3ca1dc6ae3 > Is that ok? Hmm, it looks like bluefs is crashing reading a very large .sst file (~13GB). Can you look back in teh logs a bit to see the *first* crash of this OSD? Presumably it's not not part of BlueStore::_mount ... Also, can you try ceph-bluestore-tool bluefs-export on this osd? I'm pretty sure it'll crash in the same spot, but just want to confirm it's a bluefs issue. Thanks! s _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |