Community guidelines
Be specific and constructive. No vendor spam — promoting your own product belongs in a listing. Anyone can read; posting needs a free account.
we're planning new Ethernet storage and both our Pure Storage and NetApp reps are pushing NVMe over TCP. The network is already 100 GbE. Workload is mixed virtualization and databases, not a giant AI cluster. Is there a practical reason to choose it over mature iSCSI?
NVMe over TCP has a cleaner path for NVMe media and can reduce protocol overhead. Whether you notice depends on the array, host stack and workload. For ordinary VMs, latency elsewhere may dominate.
Don't discount operational maturity. Our monitoring, multipathing knowledge and recovery procedures are built around iSCSI. A small benchmark win didn't justify retraining and new edge cases. For a new high performance platform, I'd test both.
edit: that's where i'm leaning. The vendor demo is impressive, but our current pain is capacity and backup windows, not storage latency
Then fix the actual problem. Ask for an end to end test with your hosts and failure scenarios. Protocol decisions should survive a controller failover and a bad cable, not only a clean benchmark. New is interesting, but boring storage is underrated.