Scaling out a Ceph cluster

When you are building a storage solution, scalability is one of the most important design aspects. Your storage solution should be scalable to accommodate your future data needs. Usually, a storage system starts with small to medium capacity and grows gradually over a period of time. Traditional storage systems are based on scale-up designs and are bound to a certain capacity. If you try to expand your storage system over a certain limit, you might need to compromise with performance and reliability. The scale-up design methodology for storage involves adding disk resources to the existing device, which becomes a bottleneck for performance, capacity, and manageability when it reaches a certain level.

On the other hand, scale-out designs focus on adding entire new node, including disk, CPU, and memory, to the existing cluster. In this type of design, you will not end up with limited storage; rather, you will get benefited by the performance and robustness. Have a look at the following architecture:

Scaling out a Ceph cluster

Ceph is a seamless scalable storage system based on the scale-out design, where you can add any off-the-shelf server node to a Ceph cluster and extend your storage system beyond the limits of a traditional system. Ceph allows on-the-fly addition of monitor and OSD nodes to an existing Ceph cluster. Now, let's see how to add nodes to a Ceph cluster.

..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
18.221.123.73