IBM SAN Volume Controller

From Wikipedia, the free encyclopedia

The IBM San Volume Controller (SVC) is a block storage virtualization appliance. SVC implements an indirection or "virtualization" layer in a Fibre Channel Storage Area Network (SAN).

[edit] Architecture

SVC is deployed as a cluster of nodes. Each node is a 1U high rack mounted appliance based on an IBM x86 based IBM System x server (SVC Machine type 2145). Each node has four fibre channel ports and is protected by a Uninterruptible power supply. The nodes are clustered together so that surviving nodes can take over if a node fails. The nodes run a customized IBM Linux kernel (code name "Little Blue") that runs a specialized Virtualization Storage Software environment.

SVC uses an in-band architecture which means that data flowing between a host and a storage controller flows into an SVC node and then back out onto the SAN. SVC presents an interface to a server which looks like a storage controller and an interface to a storage controller that looks like a server.

SVC also holds the current Storage Performance Council (SPC) record for SPC-1 performance benchmarks, returning 155K iops (release 3.1.0) with 2006 release (4.1.0) returning over 175K iops. There is no faster storage subsystem commercially available. (SPC-2 benchmarks expected soon)

[edit] Features

As of release 4.1, the major features of SVC are:

Virtual LUN to Physical LUN indirection or mapping: Servers access SVC as if it were a storage controller. The SCSI LUNs they see represent virtual disks which are allocated in SVC from a pool of storage made up from one or more managed disks (mdisks). A managed disk is simply a storage LUN provided by one of the storage controllers that SVC is virtualising.
Data migration: SVC can move data from mdisk to mdisk, whilst maintaining IO access to the data.
Importing existing LUNs via a feature called Image Mode: LUNs can also be backed out of virtualized mode
Host LUN Mapping: This allows the set of vdisk that each host sees and the SCSI lun number at which each vdisk is presented.
Synchronous remote copy Metro Mirror: This allows a remote Disaster recovery site at a distance of up to about 200km
Asynchronous remote copy Global Mirror: This allows a remote Disaster recovery site at a distance of thousands of kilometres.
Write-back Cache: Writes from hosts are completed once they have been committed into the SVC cache but prior to be destaged to the underlying storage controllers. Data is protected by being replicated to the other node in the IO group.
Point in time copy - IBM calls this FlashCopy: This is used to create an online backup, for application testing or backup to tape.