[ceph-users] Re: Balancer: Unable to find further optimization

2024-11-27 Thread Anthony D'Atri
In your situation the JJ Balancer might help. > > On 2024-11-27 17:53, Anthony D'Atri wrote: >>> Hi, >>> My Ceph cluster is out-of-balance. The amount of PG's per OSD ranges from >>> about 50 up to 100 PG's per OSD. This is far from balanced. >> Do you have multiple CRUSH roots or device classes

[ceph-users] Re: Balancer: Unable to find further optimization

2024-11-27 Thread sinan
So the balancer is working as expected; it is normal that it does or cannot further balance? Any other suggestions here? On 2024-11-27 18:05, Anthony D'Atri wrote: In your situation the JJ Balancer might help. On 2024-11-27 17:53, Anthony D'Atri wrote: Hi, My Ceph cluster is out-of-balance

[ceph-users] Re: Balancer: Unable to find further optimization

2024-11-27 Thread sinan
On 2024-11-27 17:53, Anthony D'Atri wrote: Hi, My Ceph cluster is out-of-balance. The amount of PG's per OSD ranges from about 50 up to 100 PG's per OSD. This is far from balanced. Do you have multiple CRUSH roots or device classes? Are all OSDs the same weight? Yes, I have 2 CRUSH roots

[ceph-users] Re: Balancer: Unable to find further optimization

2024-11-27 Thread Anthony D'Atri
> > Hi, > > My Ceph cluster is out-of-balance. The amount of PG's per OSD ranges from > about 50 up to 100 PG's per OSD. This is far from balanced. Do you have multiple CRUSH roots or device classes? Are all OSDs the same weight? > My disk sizes differs from 1.6T up to 2.4T. Ah. The numb