Hi,
Am 05.05.21 um 11:44 schrieb Andres Rojas Guerrero:
I have in the cluster 768 OSD, it is enough that 32 (~
4%) of them (in
the same node) fall and the information becomes inaccessible. Is it
possible to improve this behavior?
You need to spread your failure zone in the crush map. It looks like the
OSD is the failure zone, and not the host. If it woould be the host the
failure of any number of OSDs in a single host would not bring PGs down.
For the default redundancy rule and pool size 3 you need three separate
hosts.
Regards
--
Robert Sander
Heinlein Consulting GmbH
Schwedter Str. 8/9b, 10119 Berlin
http://www.heinlein-support.de
Tel: 030 / 405051-43
Fax: 030 / 405051-19
Zwangsangaben lt. §35a GmbHG:
HRB 93818 B / Amtsgericht Berlin-Charlottenburg,
Geschäftsführer: Peer Heinlein -- Sitz: Berlin