Home | Featured | Enterprise Computing: HP Blades Day – Lab Session – Part IV

Enterprise Computing: HP Blades Day – Lab Session – Part IV

0 Flares Twitter 0 Facebook 0 Google+ 0 StumbleUpon 0 Buffer 0 LinkedIn 0 Filament.io 0 Flares ×

This is part of a series of posts with video recorded at the HP Blades Day in Houston, February 2010. Previous posts:

In this final post from the Lab Session, James Singer discusses more about airflow and the chassis design.  The video doesn’t always follow the subject (due to my quality videoing techniques; in fact I was trying to pay attention), however the soundtrack is accurate.

[vimeo]http://www.vimeo.com/11986209[/vimeo]

About Chris M Evans

Chris M Evans has worked in the technology industry since 1987, starting as a systems programmer on the IBM mainframe platform, while retaining an interest in storage. After working abroad, he co-founded an Internet-based music distribution company during the .com era, returning to consultancy in the new millennium. In 2009 Chris co-founded Langton Blue Ltd (www.langtonblue.com), a boutique consultancy firm focused on delivering business benefit through efficient technology deployments. Chris writes a popular blog at http://blog.architecting.it, attends many conferences and invitation-only events and can be found providing regular industry contributions through Twitter (@chrismevans) and other social media outlets.
  • Pingback: Tweets that mention The Storage Architect » Blog Archive » Enterprise Computing: HP Blades Day – Lab Session – Part IV -- Topsy.com()

  • Vince

    Nimble’s analytics platform is called “Infosight” not “Insight”

    • http://architecting.it Chris M Evans

      Argh, corrected, thanks Vince, stupid autocorrect!

  • http://www.StorageFreak.com/ David S. – StorageFreak

    Autocorrect at fault again– “…we continue to product exabytes of new data…”

    • http://architecting.it Chris M Evans

      D’oh, fixed, thanks!

  • J-Scott

    HPE should have went all in a year ago with NetApp, it was half the price. HPE has never had a decent filer and all other technologies comes with NetApp with SF, StorageGrid for Object (Bycast), AltaStore, Cheap and deep E-Series, OCI and a nice size customer list that comes with a channel that they so desperately need. Then they start the process of flipping FlexPods.

    They could not have outright purchased NetApp but a merger would have been well worth the cost to compete with Dell-EMC, leave Cisco to pickup Pure Storage.

  • https://storpool.com/ Boyan, StorPool

    Well summed-up, Chris. It seems it’s finally clear to everyone that specialized storage boxes will fade to a large extent. Still one can expect a couple of “traditional” acquisitions, before legacy vendors get into shopping spree around SDS.

    • http://architecting.it Chris M Evans

      So Boyan, what happens when we move towards SDS (once the array vendors have become mainframe-style niche)? Will the margins be there? Nimble I think was 59%. Pure is a similar number. So (a) is it relevant to expect a high margin (b) is a high margin needed to develop new features?

      • https://storpool.com/ Boyan, StorPool

        Hey Chris, I got so much travel this month that I get to this just now. To your questions, both (a) & (b) – it is a question of a business model. On the one hand you can expect a higher margin, as SW is generally a higher margin business than HW. Still it comes down to go-to-market and pricing policy. For example we price so that customers using our SW will have a total solution cost which is the best on the market. It “eats” some of our profit margins as we invest and work hard to add more features, but also allows us to deliver more value and thus build a strong brand, which is good in the long term. Oh, and we have a long terms strategy of building the best product in a particular segment, so we do not “tune” margins to leverage short- or mid-term “opportunities”.

  • meh130

    “In 1999, the ASIC was a game changer, however some 18 years later, processor speeds are much higher and one does wonder how much of the ASIC functionality is still required and how much can be done with modern processors.”

    This is a spot-on observation. The same holds true for XOR ASICs, which have left most storage systems today in favor of software running on x86 processors. XOR ASICs were primarily designed for RAID-5, and when RAID-6 was developed, arrays relying on XOR ASICs encountered a significant performance penalty. In addition, those arrays had to wait for a new ASIC, rather than just new code.

    Most of the older ASIC based systems had paltry CPUs, which did little work. So it was not possible to offload computational intensive actions to the CPU.

0 Flares Twitter 0 Facebook 0 Google+ 0 StumbleUpon 0 Buffer 0 LinkedIn 0 Filament.io 0 Flares ×