Re: [ceph-users] Erasure coded pools and ceph failure domain setup

evenly spread by default? If not, how might we go about configuring them? Cheers, Ravi --- Ravi Patel, PhD Machine Learning Systems Lead Email: r...@kheironmed.com On Thu, 28 Feb 2019 at 14:26, Ravi Patel wrote: > Hello, > > My question is how crush distributes chunks through

[ceph-users] Investigating Config Error, 300x reduction in IOPs performance on RGW layer

be looking at to debug the RGW layer. Where do we need to look? --- Ravi Patel, PhD Machine Learning Systems Lead Email: r...@kheironmed.com -- *Kheiron Medical Technologies* kheironmed.com <http://kheironmed.com/> | supporting radiologists with deep learning Kheiron M

Re: [ceph-users] Investigating Config Error, 300x reduction in IOPs performance on RGW layer

be. --- Ravi Patel, PhD Machine Learning Systems Lead Email: r...@kheironmed.com On Jul 18, 2019, 2:43 AM +0100, Robert LeBlanc , wrote: > I'm pretty new to RGW, but I'm needing to get max performance as well. Have > you tried moving your RGW metadata pools to nvme? Carve out a bit o

Re: [ceph-users] Investigating Config Error, 300x reduction in IOPs performance on RGW layer

in terms of IOP/s It would be good to understand what metrics we should look at in ceph to debug the issue, what to try next from a tuning perspective, and any other benchmarks that the community could suggest to help us figure this out. Cheers, Ravi --- Ravi Patel, PhD Machine Learning Systems