HDS Hungry for High End With New Platform

Enterprise Storage Forum content and product recommendations are editorially independent. We may make money when you click on links to our partners. Learn More.

NEW YORK — Angling to cast aside doubt about its position in the market for
large storage systems, Hitachi Data Systems (HDS) launched an ambitious new
platform with the most advanced virtualization software in the space to
date, as well as logical partitioning features and new data replication

The HDS TagmaStore Universal Storage Platform can house and manage an
unprecedented 32 petabytes of internal and external data and separate that
data into 32 logical partitions, much like a classic mainframe can separate
operating systems.

Storage is managed by three core software components, said HDS CTO Hu
Yoshida during a technical briefing here Tuesday.

Hitachi Universal Volume Manager, the first large-scale virtualization layer
of its kind, helps storage to be aggregated into one common pool and managed
by a single set of policy-based software tools, making it easier for IT
administrators to manage massive amounts of data in their enterprises.

Hitachi Virtual Partition Manager Software, a mainframe-inspired logical
partitioning technology that has been applied to storage, allocates physical
storage resources, including ports, cache and disks, into as many as 32
Private Virtual Storage Machines.

All the while, Yoshida said, the Virtual Storage Machine appears as if it
were its own storage system, providing decentralized management of allocated

Replication software is key at a time when concerns about keeping the
continuity of businesses as close to always-on as possible has become
paramount. This can be challenging when remote offices of global
businesses are located so far apart.

Claus Mikkelsen, chief scientist of HDS said during the
briefing that the new Hitachi Universal Replicator asynchronous remote features
heterogeneous replication, disk-based journaling, protection against link
failure, “pull”
copying and multi-data center support.

Replicator does so over any distance without the need for redundant servers
or replication appliances, building on the company’s TrueCopy replication

By early 2005, TagmaStore will have the ability to manage storage servers
from its competitors IBM and EMC, making it attractive for customers who
have disparate storage infrastructure to corral and handle data.

The timing of the release is crucial for HDS, which is looking
to win more market share from traditional high-end system leaders EMC and
IBM. In the latest Gartner estimates, HDS had a 6.9 percent share of the
external disk storage systems market, with EMC leading at 23.1 percent and
IBM at 13.2 percent.

Many experts agree that HDS must have a big answer to existing and forthcoming products from EMC and
IBM in order to gain double-digit market share. Currently, the company is up against EMC and its Symmetrix DMX
and Storage Router, and IBM, which is expected to
unveil a number of new products, including a revision to its Shark
Enterprise Storage Server (ESS), in the coming months.

TagmaStore is the answer. Now it’s up to the customers. In support of HDS, HP will
resell it as its StorageWorks 12000 disk array and Sun Microsystems will resell it as
its StoreEdge 9900 disk array.

Available now in three models, TagmaStore employs Hitachi Universal Star Network — the company’s crossbar
switch architecture — as its engine, making it
possible for the platform to perform two million input/output operations per
second, which is significantly greater than the calculations of EMC’s
Symmetrix DMX or IBM’s ESS.

The entry-level USP100 has maximum internal raw capacity of 77 terabytes
with up to 256 146 gigabyte or 300GB disk drives and 17GB per second of
cached bandwidth.

This performance is equivalent to the Hitachi Lightning 9980V system, which
HDS will not phase out. Instead, the company said TagmaStore will co-exist
with the Lightning 9900 V Series, allowing “customers the freedom to
choose the appropriate system to meet their business needs.”

The “enhanced” USP600 will feature maximum internal raw capacity of 154TB
with up to 512 146GB or 300GB disk drives, 34GB per second of cached
bandwidth, and up to 128 Fibre Channel interfaces.

Rounding out the trinity of new machines, the USP1100 boasts internal raw
capacity to 332TB with up to 1,152 146GB or 300GB disk drives and 68GB per
second of cached bandwidth. It also handles as many as 192 Fibre Channel

All of the new systems will support Fibre Channel ,

Clint Boulton
Clint Boulton
Clint Boulton is an Enterprise Storage Forum contributor and a senior writer for CIO.com covering IT leadership, the CIO role, and digital transformation.

Get the Free Newsletter!

Subscribe to Cloud Insider for top news, trends, and analysis.

Latest Articles

15 Software Defined Storage Best Practices

Software Defined Storage (SDS) enables the use of commodity storage hardware. Learn 15 best practices for SDS implementation.

What is Fibre Channel over Ethernet (FCoE)?

Fibre Channel Over Ethernet (FCoE) is the encapsulation and transmission of Fibre Channel (FC) frames over enhanced Ethernet networks, combining the advantages of Ethernet...

9 Types of Computer Memory Defined (With Use Cases)

Computer memory is a term for all of the types of data storage technology that a computer may use. Learn more about the X types of computer memory.