No, we sticked at the moment with octopus. Istvan Szabo Senior Infrastructure Engineer --------------------------------------------------- Agoda Services Co., Ltd. e: istvan.szabo@xxxxxxxxx --------------------------------------------------- -----Original Message----- From: Stefan Kooman <stefan@xxxxxx> Sent: Wednesday, December 1, 2021 6:05 PM To: Frank Schilder <frans@xxxxxx>; Szabo, Istvan (Agoda) <Istvan.Szabo@xxxxxxxxx>; ceph-users <ceph-users@xxxxxxx> Subject: Re: Re: ceph-osd iodepth for high-performance SSD OSDs Email received from the internet. If in doubt, don't click any link nor open any attachment ! ________________________________ On 12/1/21 11:19, Frank Schilder wrote: > Hi Szabo, > > no, I didn't. I deployed 4 OSDs per drive and get maybe 25-50% of their performance out. The kv_sync thread is the bottleneck. Are you running Pacific? Have you tried RocksDB sharding [1]? I haven't tried this myself yet, but I'm planning on testing Ceph with SPDK [2]. Gr. Stefan [1]: https://docs.ceph.com/en/latest/rados/configuration/bluestore-config-ref/#rocksdb-sharding [2]: https://docs.ceph.com/en/latest/rados/configuration/bluestore-config-ref/#spdk-usage _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |