Re: [ceph-users] New Ceph cluster design

2018-03-09 Thread Tristan Le Toullec
Hi,     same REX, we had troubles with OutOfMemory Kill Process on OSD process with ten 8 To disks. After an upgrade to 128 Go these troubles disapears. Recommendations on memory aren't overestimated. Regards, Tristan On 09/03/2018 11:31, Eino Tuominen wrote: On 09/03/2018 12.16, Ján

Re: [ceph-users] how to troubleshoot "heartbeat_check: no reply" in OSD log

2017-12-14 Thread Tristan Le Toullec
Hi Jared,     did you have find a solution to your problem ? It appear that I have the same osd problem, and tcpdump captures won't show any solution. All OSD nodes produced logs like 2017-12-14 11:25:11.756552 7f0cc5905700 -1 osd.49 29546 heartbeat_check: no reply from 172.16.5.155:6817