Add more drives to the storage cluster anytime you need!
StorPool is extremely flexible and offers a higher flexibility than other storage systems. It has sophisticated storage cluster and volume management, allowing the creation of multiple volumes each with a different placement policy (meaning copies) on any subset of drives from the pool. E.g. you can have volumes on SATA drives, other volumes on SSDs or volumes on mixture of HDD and SSD drives (hybrid). You can live-migrate (tiering) data from one set of drives to another set. Also each volume can also be configured for data locality – on the compute node that needs it, i.e. keeping data close to where it is used.
Why is StorPool more flexible than other solutions:
- Anything in StorPool can be changed online – online expansion/shrink, online changes, automatic self-healing, auto-load balancing, in-service upgrades
- No cluster downtime on hardware changes – you can add/remove hardware without this bringing the service down – forget about hot-swappable disks. You can hot-swap whole servers (or even racks)
- StorPool provides unmatched levels of operational flexibility. It also scales-out seamlessly in capacity and performance.
- Different deployment options – StorPool can be used as a stand-alone storage (on dedicated storage nodes. It can be deployed in converged (Compute + Storage on the same servers) or hyper-converged fashion. Each server in a StorPool storage cluster can be only client, only server or both.
- Fully distributed system – StorPool does not have dedicated metadata servers, master-slave or other lock-up mechanisms – this makes it extremely flexible and robust, but also very fast due to the massive parallelism in processing data which combines IOPS and throughput of all servers in the storage cluster
Individual drives in a StorPool cluster can be added and taken away with no impact on the service/data availability, provided sufficient copies have been made. The StorPool cluster is a flat hierarchy of drives and new drives can be added or removed at any time. When new drives are added to a StorPool storage cluster the capacity of these drives is simply added to the pool.
StorPool automatically ensures that copies are placed in separate fault domains (typically separate servers), so there is no need to plan and configure RAIDs. StorPool volume management also offers a higher flexibility than most storage systems. StorPool allows for the creation of multiple volumes each with a different placement policy out of any subset of drives from the pool. E.g. you might want some volumes on SATA drives, while other volumes on SSDs. Each volume can also be configured for data locality, keeping data close to where it is used.