NVMe is not a new SAN technology but next-generation SAN protocol with options for both FC and IP networks. Today’s data centers are consolidating their high-performance solid-state drives (SSDs) on the fast, scalable, and power-efficient NVMe™ protocol. The challenge today is how to maximize the performance and investment in NVMe by spreading performance beyond a single server and across an entire data center.
NVMe is designed for a solid-state world, which means it supports more IOPS, better response times and reduces administration overhead of configuration, management and monitoring. Every customer with the SAN will be going through this conversion sooner than later.
What is NVMe/TCP? Why is it so special ?
NVMe/TCP combines performance benefits of NVMe-oF with the ubiquity of TCP. NVMe/TCP, like NVMe/FC, provides a path to achieving NVMe-oF but it runs over Ethernet and encapsulates NVMe commands and data inside a TCP datagram. it enables a larger number of queues and queue paths for data transport compared to iSCSCI resulting in significant increase in throughput and latency reduction.
NetApp allows you to get this next-generation SAN anywhere you need it.
- You can unify your network with IP everywhere - client connectivity, NFS/SMB for files, and NVMe/TCP for block
- Upgrade your use of iSCSI to NVMe
- Link to the cloud by replicating your on-premises NVMe/FC database footprint and accessing your data via NVMe/TCP. It's all NVMe to us.
Many vendors support specific implementations of NVMe over Fabrics to try and optimize the speed of NVMe (like RoCEv2), and claim that NVMe/TCP is slow. But the reality is, NVME/TCP is really fast when you build the processing and storage solution around that protocol to begin with, like we did.
The use of NVMe is transparent to database operations. Your database will be still on filesystems or ASM diskgroups as usual. The transition is seamless and even Oracle 12c R2 RAC clusters that were not written for NVMe in mind work perfectly on NVMe without the need for additional patches. It looks like LUN, manage like a LUN, behaves like a LUN but it is called as namespace. It is faster and under the covers the data transfer protocol is simpler and more efficient but that’s detail inside the Host operating system. your application need not know, and your management practices barely needs to change to embrace NVMe.
NVMe-TCP Benefits
- The ubiquitous nature of TCP. TCP is one of the most common network transports in use which is already implemented in most data centers across the world.
- Designed to work with existing network infrastructure. In Other words, there is no need to replace existing ethernet routers, switches, NICs which simplifies maintenance of the network infrastructure.
- Unlike RDMA-based implementations, TCP is fully routable and is well suited for larger deployments and longer distances while maintaining high performance and low latency.
- TCP is actively being maintained and enhanced by a large community.
- IT Admins are less distracted by the problems associated with legacy SAN configuration and management and it is 100% transparent to database operations
What's Next ?
If you are interested in high performance and massively scalable storage that will drop right into your existing data center network to support your mission-critical data storage and analytics needs, give us a shout! We’d love to talk with you about what we can do for you.
For more solutions, check the NetApp documentation or to set up a conversation with us by submitting a request here.