Deploying StorPool is Simple and Straight Forward

Hypervisor, minimal hardware, operating system, etc. – all you need to know

1) you provide 3 or more servers that match the system requirements, with base Linux installation, and SSH access
2) we install StorPool, do burn-in test and some performance tests/ fine tuning to make sure everything is working properly
3) we give the system back to you, together with user manuals and training and you can start testing or using it. We assist as necessary.

Operating StorPool on a day to day basis is also simple. A junior system administrator is usually capable of managing the system.

General requirements

  • x86-64 CPU
  • Local HDDs and SSDs (RAID controller is not needed. JBOD drives are recommended.)
  • GNU/Linux operating system
  • 10/25/40/56/100Gb Ethernet or RoCE network

Minimal hardware

  • 3 industry-standard x86 servers
  • 32+ GB RAM per node (4-8 GB used by StorPool)
  • Any x86-64 CPU with 2 threads or more
  • Any hard drive controller in JBOD mode
  • 3x SATA2 hard drives
  • Standard 10GE Ethernet LAN

Recommended hardware

  • 3+ industry-standard x86 servers
  • IPMI, iLO/LOM/DRAC desirable
  • Intel Nehalem generation (or newer) Xeon processor(s)
  • Dual 10/25/40GE network
  • Any hard drive controller in JBOD mode
  • 5+ hard drives per storage node*
  • 2+ SATA or NVMe SSDs per storage node

* Drives used in a single pool should be identical to preserve optimal performance. Drives should be spread evenly across servers. I.e. all servers should have SSDs and HDDs. For StorPool hybrid pools you need twice as much space on HDDs as on SSDs. E.g. for 10TB raw space on SSDs you need 20TB of raw space on HDDs.

Operating Systems

StorPool supports all Linux distributions through the StorPool driver/initiator. Any other operating system, such as Windows Server, UNIX, etc. are supported through highly-available, scale-out iSCSI.

File Systems

StorPool is compatible with ext4 and XFS file systems and with any system designed to work with a block device, e.g. databases and cluster file systems (like GFS2 or OCFS2).
StorPool can also be used with no file system, for example when using volumes to store VM images directly. StorPool is compatible with other technologies from the Linux storage stack, such as LVM, dm-cache/bcache and LIO.

We also support VMware VMFS and clustered VMFS and Windows file systems.

Hypervisor & Cloud management/orchestration

StorPool supports:

  • KVM (native client), VMware, Xen, XenServer (through iSCSI), Windows Hyper-V (through iSCSI, including Cluster Shared Volumes support)
  • LXC/containers/Docker/Kubernetes
  • OpenStack, CloudStack, Open Nebula (ONE), Proxmox, OnApp, Kubernetes
  • Any other technology compatible with the Linux storage stack.

Example configurations

Configuration for Converged / Hyper-converged
(storage+compute on the same servers)
Configuration for Storage only
(separate servers for storage)
2RU server with 16x 2.5" drive bays 1RU server with 10x 2.5" drive bays
Dual Socket P (LGA 3647), 16 DIMM slots Single socket AMD EPYC 7001/7002 8 DIMM slots
Intel Xeon Gold 6230 - 20 cores @ 2.8 GHz AMD EPYC gen2 Rome 7302P
384GB DDR4-2666 ECC RDIMM 128GB ECC DDR4-3200 RDIMM
Dual-port 10/25/40/100GE NIC Dual-port 10/25/40/100GE NIC

Detailed system requirements list

Download the detailed system requirements: