3 Comments

Summary:

Hewlett Packard  today announced a new line of servers, a data center mapping program and some consulting and financing services aimed at companies that build out mega data centers. Potential purchasers of the new HP machines include those building cloud computing offerings and enterprise customers trying […]

proliantHewlett Packard  today announced a new line of servers, a data center mapping program and some consulting and financing services aimed at companies that build out mega data centers. Potential purchasers of the new HP machines include those building cloud computing offerings and enterprise customers trying to build their own clouds or high-performance computing clusters.

Problem is, HP is late to the mega data center party. SGI (formerly Rackable) has built special-purpose machines for years, and keeps introducing new options for the mega data center. IBM even launched its own, highly proprietary iDataPlex hardware for the same market last year. Two years ago Dell created a custom-order business aimed at serving this market while HP focused on better blades for enterprises and building custom setups for clients. HP is now combining some of the features its rivals’ cloud computing servers already offer, such as stripping out redundant power, sharing fans and making things easily interchangeable, as part of its new HP ProLiant SL server family. The resulting servers use 28 percent less power than standard rack-mounted servers, according to HP.

Creating some type of product portfolio for this market, however delayed, makes sense, and Christine Martino, VP and general manager of HP’s Scalable Computing & Infrastructure group says the company thinks it can compete with the existing offerings in the space quite well. She also stressed that both the data center mapping software (The HP Datacenter Environmental Edge), which helps cut costs by finding inefficiencies in the data center, and the consulting would be of use for enterprise customers that have the experience building out large-scale data centers that companies such as Google, or Amazon have.

  1. Hi Stacey,

    I’d argue with your “late to the party” description here. HP’s had their POD (shipping container) option for a while and have been doing a lot of large-scale deployments with their existing gear. (I forget the exact percentage but there are an impressive number of BladeSystems in the TOP500 list.) If I had to criticize HP for anything in this space, it would be ceding some of the thought leadership to others–such as Sun. But, as a practical matter, they’ve been on the ground selling lots of systems for large-scale installations. Frankly, in this space it’s more important to have the right supply chains and channels than it is to have a specific design that is marketed and sold for a specific purpose.

    Share
  2. Steve Cumings, HP Wednesday, June 10, 2009

    Hi Stacey:

    Actually, HP works with most of the Web giants you’d expect, and we’ve been building and selling custom hardware and solutions to these customers – thousands of nodes at a time — for years.

    Back in May of 2008, we made public our Scalable Computing & Infrastructure group (SCI), which had already been working with scale-out customers for a couple of years, and had privately delivered multiple innovative compute and storage platforms to support them.

    Also in May ’08 we introduced our 2-in1 blade server, the BL2x220c, created to meet the unique needs of these large scale data center customers. In fact, that double-density blade was built to meet the needs of a very well-known global online content provider to meet their specific scale-out requirements. And as Gordon Haff mentioned, HP blades power more of the world’s biggest super computing centers (42%) than any other single vendor or platform.

    And earlier that same month in May 08, HP introduced the Extreme Data Storage system, designed to meet the unique storage needs of companies like our own online photo-sharing service, Snapfish.

    And now, as you noted (thanks!), HP is delivering the ProLiant SL family, a new product line to join the existing public and private portfolios for scale-out. Different than most of our competitors, it’s based on industry-standards, so our customers don’t have to change their datacenter design and practices simply to deploy IT. And it delivers compelling advantages in terms of energy, weight, and cost savings for customers.

    Competition in this area is great –particularly for the customer. But make no mistake, as the world’s largest IT company, our competitors have to run pretty hard to catch up with the combination of our broad scale-out IT portfolio, unmatched knowledge and solutions for the datacenter, and the global supply chain required to build -and deliver –10 thousand servers at a pop.

    Share
  3. [...] Commodity hardware gets a boost here, which doesn’t bode well for Cisco’s (c csco) new blade servers or IBM’s efforts to create specialized hardware for different workloads in the cloud. The paper also discusses the challenges of building software that can run across a heterogeneous hardware layer, as well as programming for redundancy and resiliency. Given how much publicity Google’s various failures and traffic slowdowns have received, the chart below illustrating the causes behind such glitches is notable. [...]

    Share

Comments have been disabled for this post