IBM Flex System Storage Expansion Node

The IBM® Flex System™ Storage Expansion Node is a locally attached storage node that is dedicated and directly attached to a single half-wide compute node. The Storage Expansion Node provides storage capacity for Network Attach Storage (NAS) workloads, providing flexible storage to match capacity, performance, and reliability needs.

The Storage Expansion Node adds 12 drive bays to the attached compute node and all bays in the expansion node are hot-swap. The drive bays slide out on an internal rail system; provided that a suitable RAID level is employed, a failed drive can be removed while the system is still running. With storage capacity of up to 12 TB, the Storage Expansion Node is ideal for applications that can use large amounts of additional local storage.

Ideal workloads include distributed database, transactional database, NAS infrastructure, video surveillance and streaming solutions.

Features

The System Expansion Node has the following features:

* Connects directly to supported compute nodes via a PCIe 3.0 interface to the compute node's interposer connector (also known as the ETE connector)
* Support for 12 hot-swap 2.5-inch drives, accessible via a sliding tray
* Support for 6 Gbps SAS and SATA drives, both HDDs and SSDs
* Based on an LSI SAS2208 6 Gbps RAID on Chip (ROC) controller
* Supports RAID 0, 1, 5, 10, and 50 as standard. JBOD also supported. Optional RAID 6 and 60 with a Features on Demand upgrade.
* Optional 512 MB or 1 GB cache with cache-to-flash super capacitor off-load
* Includes an expansion shelf to physically support the Storage Expansion Node and its compute node attached together
* Internal and external light path diagnostics
* Optional Feature on Demand upgrades for RAID 6, 60 support and SSD performance and caching enablers
* Optional support for SSD performance acceleration and SSD caching with Features on Demand upgrades
* Support for up to 64 virtual drives, up to 128 drive groups, up to 16 virtual drives per one drive group, and up to 32 physical drives per one drive group
* Support for logical unit number (LUN) sizes up to 64 TB
* Configurable stripe size up to 1 MB
* Compliant with Disk Data Format (DDF) configuration on disk (COD)
* S.M.A.R.T. support
* Managed through the IMMv2 management processor on the compute node and with the MegaRAID Storage Manager management software