Fiddling with the crush weights sorted this out and I was able to remove the OSD from the cluster. I set all the big weights down to 1 ceph osd crush reweight osd.7 1.0 etc. Tx for all the help On Tue, Nov 23, 2021 at 9:35 AM Stefan Kooman <stefan@xxxxxx> wrote: > On 11/23/21 08:21, David Tinker wrote: > > Yes it recovered when I put the OSD back in. The issue is that it fails > > to sort itself out when I remove that OSD even though I have loads of > > space and 8 other OSDs in 4 different zones to choose from. The weights > > are very different (some 3.2 others 0.36) and that post I found > > suggested that this might cause trouble for the crush algorithm. So I > > was thinking about making them more even before removing the OSD. > > Sure, that sounds like a good plan. If the balancer is not able to > optimize at this point, the improved balancer bij Jonas Jelten might do > the trick here [1], also see ML thread [2]. > > Do you have many different pools? > > What Weiwen Hu said in reply to this threads sounds very plausible. You > might dump your crush map, remove OSD.7, and check if the mappings can > still be made. > > Gr. Stefan > > [1]: https://github.com/TheJJ/ceph-balancer > [2]: > > https://lists.ceph.io/hyperkitty/list/ceph-users@xxxxxxx/thread/QXTFTYRD43XB3JRDSTMH657ISSMZ6QTU/ > _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |