I have 15.3TB ssds but have 4x osds on those, so curious can go up higher or not with 4x 3.5TB logical volumes. Istvan Szabo Senior Infrastructure Engineer --------------------------------------------------- Agoda Services Co., Ltd. e: istvan.szabo@xxxxxxxxx<mailto:istvan.szabo@xxxxxxxxx> --------------------------------------------------- On 2021. Dec 15., at 7:29, Linh Vu <linh.vu@xxxxxxxxxxxxxxxxx> wrote: Email received from the internet. If in doubt, don't click any link nor open any attachment ! ________________________________ Pretty sure this rule of thumb was created during the days of 4TB and 6TB spinning disks. Newer spinning disks and SSD / NVMe are faster so they can have more PGs. Obviously a 16TB spinning disk isn't 4 times faster than a 4TB one, so it's not a linear increase, but I think going closer to 200 should be fine for the bigger disks. On Wed, Dec 15, 2021 at 5:21 PM Szabo, Istvan (Agoda) <Istvan.Szabo@xxxxxxxxx<mailto:Istvan.Szabo@xxxxxxxxx>> wrote: Hi, Just curious is this still the best practice? I just gave a try in my 144x osd cluster to have 150-160pg/osd and the speed went up I guess because I have a lot of small objects, but for me the stability still the most important so would be good to know the answer. Istvan Szabo Senior Infrastructure Engineer --------------------------------------------------- Agoda Services Co., Ltd. e: istvan.szabo@xxxxxxxxx<mailto:istvan.szabo@xxxxxxxxx><mailto:istvan.szabo@xxxxxxxxx<mailto:istvan.szabo@xxxxxxxxx>> --------------------------------------------------- _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx<mailto:ceph-users@xxxxxxx> To unsubscribe send an email to ceph-users-leave@xxxxxxx<mailto:ceph-users-leave@xxxxxxx> _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |