13 521
правка
Изменения
м
→Micron setup example
They only got 350000 peak write iops with high parallelism with 100 % CPU load. It may seem a lot, but if you divide it by the number of NVMes — 350000/40 NVMe — it’s only 8750 iops per a NVMe. If we account for 2 replicas and WAL we get 8750*2*2 = 35000 iops per drive. So… Ceph only squeezed 35000 iops out of a NVMe '''that can deliver 260000 iops alone'''. That’s what Ceph overhead is.
Also there are no single-thread latency tests in that PDF. It Such tests could be very interesting.
== CAPACITORS! ==
