System overview

Each FlashSystem 5000 system is a virtualizing RAID storage system. Several different system models are available.

IBM Spectrum Virtualize software

IBM® FlashSystem 5000 systems are built with IBM Spectrum Virtualize software, which is part of the IBM Spectrum Storage™ family.

IBM Spectrum Virtualize is a key member of the IBM Spectrum Storage portfolio. It is a highly flexible storage solution that enables rapid deployment of block storage services for new and traditional workloads, on-premises, off-premises and in a combination of both. Designed to help enable cloud environments, it is based on the proven technology. For more information about the IBM Spectrum Storage portfolio, see the following website.
http://www.ibm.com/systems/storage/spectrum
The software provides these functions for the host systems that attach to the system:
  • Creates a single pool of storage
  • Provides logical unit virtualization
  • Manages logical volumes

System hardware

Each FlashSystem 5000 storage system consists of a set of drive enclosures. The control enclosure contains disk drives and two node canisters. Expansion enclosures contain disk drives and two expansion canisters.

Table 1 shows the front view of the large form factor (LFF) and small form factor (SFF) FlashSystem 5000 systems. The LFF systems can support up to 12 3-inch disk drives. The SFF systems can support up to 24 2-inch disk drives.

Table 1. Front view of the control enclosures
Large form factor model Small form factor model
Front view of the LFF model (12 drives)
Front view of the SFF model (24 drives)

The following table summarizes the features and machine type and model (MTM) of the FlashSystem 5000 control enclosures.

Table 2. Control enclosure models
System model MTM Specific Features Common Features
IBM FlashSystem 5010 2072-2H2 or 2072-2H4
  • Minimum of 8 GB of memory per node canister.
  • Memory expansion to 16 GB or 32 GB per I/O group.
  • Two node canisters, each with a 2-core, 4-thread 2.2 GHz processor.
  • Two 1 Gbps Ethernet ports per canister that also support 100 Mbps. The second Ethernet port (port 2) is also the technician port, which is used for system setup.
  • One 12 Gbps SAS port, per node canister, to attach to expansion enclosures.
IBM FlashSystem 5015 2072-2N2 or 2072-2N4
  • Minimum of 16 GB of memory per node canister.
  • Node canister memory can be expanded to 32 GB per I/O group.
  • Support for distributed RAID 1.
IBM FlashSystem 5030 2072-2H2 or 2072-2H4
  • Two node canisters, each with a 6-core, 12-thread 1.9 GHz processor.
  • Minimum of 16 GB of memory per node canister.
  • Node canister memory can be expanded to 32 GB, with a maximum memory of 64 GB per I/O group.
  • One dedicated 1 Gbps Ethernet technician port per node canister, which is used for system setup and node service interface.
  • Two 10 Gbps Ethernet ports per canister that also support 1 Gbps, which are used for iSCSI and system management.
  • Two 12 Gbps SAS port per canister for expansion enclosure attachment.
IBM FlashSystem 5035 2072-3N2 or 2072-3N4
  • Two node canisters, each with a 6-core, 12-thread 2.2 GHz processor.
  • Support for distributed RAID 1.
The system also provides the following functions:
  • Large scalable cache
  • Copy Services:
    • IBM FlashCopy® (point-in-time copy) function, including thin-provisioned FlashCopy to make multiple targets affordable
    • IBM HyperSwap® (active-active copy) function (for FlashSystem 5030 or FlashSystem 5035 systems only)
    • Metro Mirror (synchronous copy)
    • Global Mirror (asynchronous copy)
    • Data migration
  • Space management:
    • IBM Easy Tier® function to migrate the most frequently used data to higher-performance storage
    • Metering of service quality when combined with IBM Spectrum® Connect. For information, refer to the IBM Spectrum Connect documentation.
    • Thin-provisioned logical volumes
    • Compressed volumes to consolidate storage using data reduction pools
    • Data Reduction pools with deduplication
In addition, FlashSystem 5000 systems support the expansion enclosures that are listed in Table 3.
Table 3. Supported expansion enclosures
Enclosure (MTM) Description Enclosure height
2072-12G / 2072-F12 12-slot expansion enclosure (2U) for 3.5-inch drives 2U
2072-24G / 2072-F24 24-slot expansion enclosure (2U) for 2.5-inch drives 2U
2072-92G / 2072-F92 92-slot expansion enclosure (5U) for 2.5-inch or 3.5-inch drives 5U

Figure 1 shows an example of a FlashSystem 5000 system as a traditional RAID storage system. The internal drives are configured into arrays. Volumes are created from those arrays.

Figure 1. Example of the system as a RAID storage system
This figure shows an overview of a RAID storage system.

The two node canisters are known as an I/O group. The node canisters are responsible for serving I/O on the volumes. Because a volume is served by both node canisters, no availability is lost if one node canister fails or is taken offline. The Asymmetric Logical Unit Access (ALUA) features of SCSI are used to disable the I/O for a node before it is taken offline or when a volume cannot be accessed through that node.

System topology

The system topology can be set up in several different ways.
  • Standard topology, where all node canisters in the system are at the same site.
    Figure 2. Example of a standard system topology
    This figure shows an example of a standard system topology
  • HyperSwap topology, where the system consists of at least two I/O groups. Each I/O group is at a different site. Both nodes of an I/O group are at the same site. A volume can be active on two I/O groups so that it can immediately be accessed by the other site when a site is not available. The HyperSwap topology is supported on systems.
    Figure 3. Example of a HyperSwap system topology
    This figure shows an example of a HyperSwap system topology

Volumes types

You can create the following types of volumes on the system.
  • Basic volumes, where a single copy of the volume is cached in one I/O group. Basic volumes can be established in any system topology; however, Figure 4 shows a standard system topology.
    Figure 4. Example of a basic volume
    This figure shows an example of a basic volume in a standard system configuration.
  • Mirrored volumes, where copies of the volume can either be in the same storage pool or in different storage pools. The volume is cached in a single I/O group, as Figure 5 shows. Typically, mirrored volumes are established in a standard system topology.
    Figure 5. Example of mirrored volumes
    This figure shows an example of a mirrored volume in a standard system configuration.
  • HyperSwap volumes, where copies of a single volume are in different storage pools that are on different sites. As Figure 6 shows, the volume is cached in two I/O groups that are on different sites. These volumes can be created only on FlashSystem 5030 or FlashSystem 5035 systems when the system topology is HyperSwap.
    Figure 6. Example of HyperSwap volumes
    This figure shows an example of HyperSwap volumes in a HyperSwap system configuration.

System management

Each control enclosure contains two node canisters. Together, the system nodes canisters operate as a single system. System management and error reporting are provided through an Ethernet interface to one of the nodes in the system, which is called the configuration node. The configuration node runs a web server and provides a command-line interface (CLI). The configuration node is a role that either node can take. If the current configuration node fails, the other node becomes the configuration node. Each node also provides a command-line interface and web interface for servicing hardware.

Fabric types

I/O operations between hosts and system nodes and between the system nodes and RAID storage systems use the SCSI standard. The system nodes communicate with each other by using private SCSI commands.

Table 4 shows the fabric types that can be used for communicating between hosts, nodes, and RAID storage systems. All installed fabric types can be used at the same time.
Table 4. System communications types
Communications type Host to system node System node to storage system
Fibre Channel SAN Yes, using an optional 4-port 16 Gbps Fibre Channel host interface adapter. Yes, using an optional Fibre Channel host interface adapter
iSCSI (10 Gbps Ethernet) Yes
  • FlashSystem 5010 or FlashSystem 5015 systems must have an optional 4-port 10 Gbps Ethernet host interface adapter installed.
  • FlashSystem 5030 or FlashSystem 5035 systems have two onboard 10 Gbps Ethernet ports that can be used for host attachment.

    The optional 4-port 10 Gbps Ethernet host interface adapter can also be installed.

Yes, using Ethernet adapters.
iSCSI (25 Gbps Ethernet) Yes, using an optional 2-port 25 Gbps host interface adapter Yes, using Ethernet adapters.
Serial-attached SCSI (SAS) Yes, using an optional 4-port 12 Gbps SAS host interface adapter. The system supports a one-time migration of external storage data to the system. In the management GUI, select Pools > Storage Migration > New Migration to start the storage migration wizard.