Nutanix storage uses Storage Pool and Storage Container. The Storage Pool is the aggregated disks of all or some of the nodes.. You can create multiple Storage Pools depending on the business needs, but Nutanix recommends 1 Storage Pool. Within the Storage Pool are Storage Containers. With these containers there are different data reduction settings that can setup to get the optimal data reduction and performance that is needed.
Creating The Container
Once the cluster is setup with a Storage Pool created we are ready to create a Storage Container.
- Name the Container
- Select Storage Pool
- Choose which hosts to add.
That is all looks really simple until the advanced button is clicked. This is where the Geek Knobs be tweaked.
There are quite a few options to choose from, and each setting depends on the different use cases.
- Replication Factor – 2 copies of data in the cluster or 3. Depending on the use case.
- Reserved Capacity – How much guaranteed storage that is needed to be reserved for this container. All the Containers share storage with the Storage Pool so this is used to guarantee the capacity is always available.
- Advertised Capacity – How much storage the connected hosts will see. This can be use this to control actual usage on the Container side. To allow
- Compression – A setting of 0 will result in inline compression. This can be set to a higher number for desired performance.
- Deduplication – Cache deduplication can be used to optimize performance and use less storage. Capitcity deduplication will deduplicate all data globally across the cluster. Deduplication is only post-process, and if enabled after a Container is created then only new writes will be deduplicated.
- Erasure Coding – Requires at least 4 nodes. It is a more efficient than the simple replication factor. Instead of copies of data it uses parity to be able to rebuild anything. Enabling this setting will result in some performance impact.
As you can see there can be a lot of impact in performance depending on the settings that you choose. As always Architecture matters, and you will have to evaluate the needs that your workload has, and better understanding on how everything works results in a better performing system.