Hi, The goal is to have the data pool 2048pg (currently 128) and the current 1osd/disk change to 4osd/ssd. Data pool is on 4:2 ec (1.5B objects in it) I have 7 servers with 6x 15.3TB ssd. The plan: - set norecover, norebalance, nobackfill - purge all osd on 1 host - recreate with 4osd/disk - unset norecover, norebalance, nobackfill - wait to finish Continue this on all host After what would better? Create a new data pool with 2048pg in it and copy from old pool to the new one or increase the pg and let it finish in the original one? Finally set balancer module on with max deviation 1. Any idea or suggestion? Istvan Szabo Senior Infrastructure Engineer --------------------------------------------------- Agoda Services Co., Ltd. e: istvan.szabo@xxxxxxxxx<mailto:istvan.szabo@xxxxxxxxx> --------------------------------------------------- _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |