If you're using SATA/SAS SSDs I would aim for 150-200 PGs per OSD as shown by `ceph osd df`. If NVMe, 200-300 unless you're starved for RAM.
> On Apr 15, 2024, at 07:07, Mitsumasa KONDO <[email protected]> wrote: > > Hi Menguy-san, > > Thank you for your reply. Users who use large IO with tiny volumes are a > nuisance to cloud providers. > > I confirmed my ceph cluster with 40 SSDs. Each OSD on 1TB SSD has about 50 > placement groups in my cluster. Therefore, each PG has approximately 20GB > of space. > If we create a small 8GB volume, I had a feeling it wouldn't be distributed > well, but it will be distributed well. > > Regards, > -- > Mitsumasa KONDO > > 2024年4月15日(月) 15:29 Etienne Menguy <[email protected]>: > >> Hi, >> >> Volume size doesn't affect performance, cloud providers apply a limit to >> ensure they can deliver expected performances to all their customers. >> >> Étienne >> ------------------------------ >> *From:* Mitsumasa KONDO <[email protected]> >> *Sent:* Monday, 15 April 2024 06:06 >> *To:* [email protected] <[email protected]> >> *Subject:* [ceph-users] Performance of volume size, not a block size >> >> [Some people who received this message don't often get email from >> [email protected]. Learn why this is important at >> https://aka.ms/LearnAboutSenderIdentification ] >> >> Hi, >> >> In AWS EBS gp3, AWS says that small volume size cannot achieve best >> performance. I think it's a feature or tendency of general >> distributed storages including Ceph. Is that right in Ceph block storage? I >> read many docs on ceph community. I never heard of Ceph storage. >> >> >> https://can01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdocs.aws.amazon.com%2Febs%2Flatest%2Fuserguide%2Fgeneral-purpose.html&data=05%7C02%7Cetienne.menguy%40ubisoft.com%7C3076825a4d2a4897074208dc5d017852%7Ce01bd386fa514210a2a429e5ab6f7ab1%7C0%7C0%7C638487508098942744%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=wOQKqG41uccTbyNHDIps62ojcTFBZYlyxxp3TzccsJI%3D&reserved=0 >> <https://docs.aws.amazon.com/ebs/latest/userguide/general-purpose.html> >> >> Regard, >> -- >> Mitsumasa KONDO >> _______________________________________________ >> ceph-users mailing list -- [email protected] >> To unsubscribe send an email to [email protected] >> > _______________________________________________ > ceph-users mailing list -- [email protected] > To unsubscribe send an email to [email protected] _______________________________________________ ceph-users mailing list -- [email protected] To unsubscribe send an email to [email protected]
