Hu Yoshida

VMworld – Exciting New and Expanded Capabilities from Hitachi and VMware

Blog Post created by Hu Yoshida Employee on Nov 11, 2014

Aug 22, 2014


VMworld 2014 at Moscone Center in San Francisco, August 24 to 28, has many new products and capabilities to help our customers achieve greater efficiency and availability with infrastructure virtualization.  Some solutions that HDS will highlight in our booth include the following:


Business Defined IT With UCP and vCOps

VMware users can align IT with business processes through their VMware vCenter Operations Manager (vCOps), coupled with Hitachi Unified Compute Platform (UCP) for VMware vSphere and its Unified Compute Platform Director software.  This converged-infrastructure management platform centralizes and automates the management of all of the hardware elements in VMware vSphere through a single pane of glass. It provides deep insights into the health, risk, and efficiency of each of the converged elements within vCenter Operations Manager (vCOps) and integrates the management of physical and virtual layers to significantly reduce mean time to resolution and operational costs – across a single or multiple data centers. While other converged solutions provide support for vCOps and have similar functionality, the Hitachi approach to integration is different. The Hitachi approach is a “native” one where we plug into vCenter and naturally extend to vCOps from inside VMware. This “native” approach from Hitachi also enables us to work with vCAC (vCloud Automation Center) for overall cloud management without the need for a plugin like other vendors do. This “native” approach, working from within vCenter, makes Business Defined IT much simpler to implement.

Hitachi VSP G1000 GAD Active/Active Availability with VMware Stretch Cluster

Our global active device (GAD) capability that we announced with our new VSP G1000 virtualization storage array will be demoed with a VMware Stretch Cluster. GAD is now generally available after extensive testing in the field with high availability block and file accounts. GAD provides active/active clustering across VSP G1000 storage arrays, which greatly simplifies and automates high availability to ensure continuous operations across stretch clusters.  Applications can continue to run despite a server or storage array failure. This avoids the complexity and limitations of appliances that are inserted in front of storage systems to perform similar functions.

VVOL with VASA Provider

The extended buzz around this year’s VMworld will be around VVOL virtual volumes, which many vendors have in beta test. VVOL promises to be the next big thing in the storage ecosystem due to its ability to immensely simplify storage management and drive up IT efficiency by leveraging the unique capabilities of different storage systems, whether they support block or file protocols. VVOL provides VM-level granularity to IT administrators by providing an abstraction layer in the form of a storage API between control plane and storage systems. It also provides increased scalability and unprecedented automation in policy-based storage management. Using vSphere APIs for Storage Awareness (VASA), Hitachi is creating providers for its storage and converged solution products to present their unique capabilities to vCenter for consumption. VVOLs can also use these storage providers to set policies and push information down to the external storage to make the storage VM-aware and able to negotiate with individual VMs; rather than the traditional way of dealing with a set of VMs in a LUN or file share. VVOLs minimize the NAS-vs-SAN debate due to its VM-centric management perspective.

SAP on UCP with VMware

More than half of our UCP Director wins have been with SAP Apps on the VMware platform. The driver for adoption is modernization. Customers want more flexibility and features while retaining reliability and performance. By putting SAP on VMware, the App takes on the properties of a VM. It is portable, can be vMotioned, snapshot, replicated, copied, and moved to higher or lower tiers. By placing VMware on Hitachi, the VM takes on the benefits of UCP. It is highly reliable, can be hardware offloaded in several areas for performance, can be non-disruptively upgraded or replicated, globally active, and increased in power with SMP. Another popular feature of our UCP Director is the integrated support for vCOps, which moves up the stack to SAP with application adapters. A customer can see real-time SAP statistics all the way through to the hardware.

Hitachi NAS Platform with High Performance Flash for VMware

The number of virtual machines per server is increasing, which is causing a greater demand for random IOPs. Random IOPs negate the advantages of cache controllers, as we are seeing an increasing demand for flash drives. Block based flash arrays have higher performance than file based flash arrays, due to lower overheads in the controllers, but require more configuration complexity in terms of port assignments, LUN configurations, and load balancing.  However, Hitachi Data System’s unique HNAS and HUS systems incorporate a hybrid NAS architecture that includes a multiprocessor compute plane for management and Field Programmable Gate Arrays (FPGA) for hardware-accelerated data movement. This combination provides the highest performance SPECsfs NFS operations per second results in the industry with the least number of nodes, cache capacity and storage drives.  The Hitachi Virtual Storage Platform G1000, with an 8-node file cluster has a SPECsfs2008  nfs.v3 Ops/sec of 1,222,089 with an overall response time of .75 msec; using 128 x 1.6 TB Hitachi Accelerated Flash modules. This would beat most other block based flash arrays in throughput while providing all the management benefits of file virtualization.  In addition to raw performance, Hitachi NAS platforms provide an object-based file system, which can accelerate the process of taking snapshots, file clones, and remote replication. The object-based file system enables HNAS to create only pointers to the original VM image and physically store unique user-added data to clones; thus saving duplication time and capacity. For example,  the cloning of a 1 TB VM takes about 4 seconds. HNAS can support over 100 million clones per file system.

While you have a choice of block or file storage with vSphere, VMware Horizon Mirage applications require high performance file storage. Horizon Mirage can be used to backup desktops deployed throughout the enterprise and is most useful for migrating remote desktops from Microsoft Windows XP to Windows 7. If the storage does not have sufficient IOPS, Horizon Mirage will throttle its operations, increasing the amount of time it takes to perform each operation. This is a perfect application for a high performance file storage system like HNAS and HUS.

Introducing UCP 4000E for the VMware Midrange Market

At VMworld Hitachi will introduce the UCP 4000E for VMware vSphere with UCP Director for the midrange market. The UCP 4000E for VMware vSphere comes with the UCP Director, a cloud infrastructure management system for monitoring, provisioning, protecting and remediating virtual and physical infrastructure. It is designed with Hitachi enterprise-class CB500 blade servers (from 2 to 16 servers) and a choice of either HUS-130 or HUS-VM storage (existing VSP storage can be bolted onto the 4000E). The system also includes Cisco Nexus 5548 converged networking and a management server. The UCP 4000E is designed to be deployed in five days or less and sold by Hitachi TrueNorth channel partners.

Visit our booth # 905, meet our developers and executives, and see what we have to offer for your VMware environment.