STORAGE: IP pools them together

E-mail has quickly become an essential tool in the business environment and
with it the demand for storage has grown rapidly. The amount of storage needed
to support e-mail applications has been affected by the myriad multimedia
attachments. The ease of forwarding e-mail with attachments, not only for
primary, but also for secondary and tertiary distributions, further accelerates
the storage needs of e-mail. And in many countries, like India, where e-mail is
recognized as a legal document, regulations are being put in place that require
the preservation of all e-mails-in a number of instances. This compliance
requirement will also drive the growth of storage for e-mail.

To date, the majority of e-mail storage is still directly attached to e-mail
servers. As e-mail storage capacity has increased, or remote offices have
opened, many businesses and organizations have simply installed additional
e-mail servers with local storage.

This has created a management nightmare. Multiple e-mail servers require
significant IT resources to: maintain efficient operations, backup all e-mail
data, and continue scaling the storage capacity. Each time a direct attached
storage is added to e-mail servers or when additional e-mail servers are added,
significant amount of IT effort is required to re-provision and re-balance the
e-mail system. In the process, e-mail service is interrupted. This is a major
challenge for today's budget-constrained IT organizations, which must maintain
the availability of e-mail services as a business critical function.

Networked storage offers a number of benefits in which the directly addressed
e-mail storage is challenged, such as, storage and server consolidation for
greater capacity and better server utilization. Unfortunately, a number of the
popular e-mail systems like Exchange and Notes, are optimized for block storage
and subsequently cannot effectively take advantage of file-based,
network-attached storage (NAS). At the same time, fiber channel-based storage
area network (FC-SAN) solutions are often too expensive to justify and too
complex to deploy.

IP-SAN to the Rescue

A new generation of SANs, which are based on the standard Internet Protocol
(IP) and Ethernet, are now available. With the recently adopted iSCSI protocol
standard, the IP-SAN offers a significantly more cost-effective alternative to
the FC-SAN to address the ever-increasing e-mail system storage needs.

Understanding IP-SAN

When the Internet and Engineering Task Force (IETF) ratified the iSCSI
standard, it paved the way for a new class of smarter, more intuitive, yet much
more affordable networked storage solutions that are the result of a fundamental
shift in the way network storage is designed-from making storage an extension
of the network, to designing networked storage to be a native part of the
network infrastructure. By leveraging established and broadly deployed industry
standards (such as Ethernet and IP, and the vast selection of IP-based services)
these new intelligent IP SANs enable the IT organizations to deliver
cost-effective, easily managed and scaled, and flexible networked storage as
part of their strategic IT infrastructure.

Initial applications of iSCSI-based storage solutions tended to act as a
bridges between IP and fiber channel networks. The resulting 'simplistic' IP
SANs, however, addressed only a small portion of today's needs, by merely
tying together the fiber channel SAN islands. They fell well short of leveraging
the maturity and power of existing IP networks and the lower connectivity costs
associated with Ethernet, to not only address the 'stranded' application
servers but also to enable the distributed, networked storage services.

Going parallel to the iSCSI development is the deployment of low-cost,
ATA-based storage arrays as a solution for nearline storage, enabling IT
administrators to regain control over the ever-increasing backup/restore window.
As a staging area for tape backup and archive, ATA-based nearline storage is a
natural networked resource for disk-to-disk backup of all of the application
servers' direct attached storage. Similar to fiber channel SANs, first being
adopted for LAN-free backup, iSCSI-enabled ATA disk arrays form one of the early
native applications of IP SANs.

Another important native application for IP SANs is server consolidation.
Many IT organizations are looking to consolidate their numerous legacy PC-class
servers within their data centers and among their enterprise workgroups, which
will enable them to reduce management and application software license costs.
The most notable applications are Web, e-mail, and CIFS/NFS file services (i.e.,
the NAS heads).

Since iSCSI is defined on top of TCP/IP, an application server host can
become iSCSI-enabled simply by installing iSCSI initiator software. The iSCSI
initiator software operates over the native TCP/IP stack and utilizes the
Ethernet network interfaces that are already installed. The application host
does not need to be shut down to install an iSCSI host bus adaptor (HBA).

Furthermore, since TCP/IP/Ethernet already provides the basic transport
interoperability, iSCSI interoperability is realized much faster than with fiber
channel. As native TCP/IP support within the various operating systems
(particularly Microsoft Windows) paved the way for the explosive growth of the
Internet, the availability of native support for iSCSI initiator software (also
within the various Microsoft Windows operating systems) is dramatically
accelerating the deployment of IP SANs.

With lower equipment acquisition costs and much quicker planning and
deployment compared with fiber channel SANs, IP SANs also offer lower TCO, which
includes calculations on both acquisition and maintenance costs. When the
additional cost of maintaining a separate fiber channel SAN is obviated, further
operational expense savings are realized.

IP-SANs: Now SANs Benefit the Masses

A significant part of the high costs associated with fiber channel SANs
result from the complexity required to design, deploy, manage, reconfigure, and
expand them. The high TCO applies to both the connectivity (i.e., the FC fabric)
and the storage subsystems. As such, the benefits that SANs promised (e.g.,
simplified shared storage provisioning and management), have remained beyond
reach for the vast majority of IT organizations.

IP SANs, however, will deliver the promised benefits of SANs to those
enterprises, and for those applications that simply cannot afford a fiber
channel solution. By exploiting broadly deployed IP network services and low
cost, standardized Ethernet connectivity native IP SANs directly address the
dominant components of storage costs; specifically: management, connectivity,
and access.

Native IP-SAN Construction Demystified

Native IP SANs start with the deconstruction of the conventional
peripheral-bus and loop interconnects-based RAID subsystem structure. By
replacing the conventional I/O within the storage subsystem with a gigabit
Ethernet network, a fully switched IP SAN architecture-from the application
hosts, through to the storage array controller, and IP-addressable disks-is
created.

De-coupling the storage array controller from the storage elements allows
both to become a part of the IP network. Keeping the storage array controller
and the storage elements separate, enables both to be scaled and/or repurposed
with the network-either independently or together-to meet the application
storage requirements. With a cluster of storage array controllers, a pool of
IP-addressable disks, and a flexible network interconnect, the resulting IP SAN
dynamically delivers fully virtualized storage arrays within the network
infrastructure.

In this three-tier IP SAN, the IP/Ethernet networks that connect the storage
array controllers to the application hosts and to the IP disks are logically
separate, but can be physically constructed as a single infrastructure that is
partitioned into virtual LANs (VLANs). DHCP is employed to manage the IP
addresses of the IP disks and the storage array controllers.

Any IP disk in the free storage pool can act as a spare for any of the
virtual storage devices/volumes in the IP SAN. The loosely coupled active-active
storage-array controllers are specialized IP servers executing policy-based
volume management and intelligent resource management. They form a cooperative
cluster that provides both fail-over and load balancing. As a result, the fault
tolerance, the high availability, and the centralized management of the system-traditionally
the domain of high-end fiber channel storage subsystems-are easily affordable
for the enterprise's mission-important functional or reference data.

Getting the Best out of IP SANs

A native IP SAN can be deployed to meet the expansion needs of existing
e-mail system transparently. As described above, e-mail servers can be
configured to attach to new storage volumes offered by the IP SAN and mailboxes
can ne migrated incrementally with minimal service disruptions. New e-mail
servers can be added as part of the e-mail server and storage consolidations
equally straight forwardly. As e-mail storage capacity needs further expansion,
IP disks can be added to the IP SAN and the virtualized storage volumes for the
e-mail expanded dynamically without further service interruption.

Beyond reigning in the e-mail storage challenges, the same IP SAN can also
provide networked storage to other applications within the business, including
voice mails. The broad availability of iSCSI boot capability will enable the
deployment of bladed application servers which will both remote boot-off the IP
SAN and enable access to the application data stored in the IP SAN. IP SANs will
manage the resources intelligently and adapt to failures as part of the IP
network. Remote replication of all of the data within and among IP SANs, as
managed by the intelligent IP SAN controllers, will simplify the deployment of
disaster recovery in a most cost-effective manner.

In essence, all of the benefits originally envisioned for a storage area
network, and much more, are much closer to reality in the form of IP SANs.
Native IP SANs are simply smarter solutions that ride the cost curve of
standardized commodity networking (IP and Ethernet) and disk technologies (ATA
and serial ATA), exploit mature Internet technologies and services, and leverage
the wealth of knowledge that has developed for distributed processing, to
deliver centrally managed, distributed storage and services. With intelligent,
native IP SANs these storage services will be easily deployed and quickly
provisioned to meet the critical business objectives of the enterprise, without
breaking the bank.

Peter Wang CTO and founder,
Intransa