Re: OSDs too slow to start

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 





On 13/06/18 01:03, Konstantin Shalygin wrote:
Each node now has 1 SSD with the OS and the BlockDBs and 3 HDDs with
bluestore data.


Very. Very bad idea. When your ssd/nvme dead you lost your linux box.

I have 3 boxes. And I'm installing a new one. Any box can be lost without data problem. If any SSD is lost I will just reinstall the whole box, still have data duplicates and in about 40 hours the triplicates will be ready.

I understand the HIERARCHICAL crush map works this way. If I have 3 copies and 3 hosts, any host can be lost without problem (I now reboot any host for maintenance and nobody notices it)
Please correct me if I'm wrong.


_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com



[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Ceph Dev]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux