A few months ago, the folks at Webmetrics asked us if we’d like to work with them on some industry research (more on this below.)

Today, we’re publishing that research. It’s an extensive study of cloud performance, involving hundreds of tests from many locations across Amazon, Google, Salesforce, Rackspace, and Terremark. We built and deployed custom test agents on each cloud, and crunched hundreds of megabytes of log data. The report measures service response, network performance, CPU, and internal I/O.

Here’s a quick summary of the results; you can download the full study — complete with detailed conclusions, test methodology, and even agent code –for free from Webmetrics.

At Bitcurrent, we try to remain nonpartisan. We want to contribute to the industry’s growth and understanding. So we were thrilled at Webmetrics/Neustar’s approach here: they financed the research into cloud performance, and let us use their monitoring tool to collect the data from our agents. They were supportive, and enthusiastic, but exercised no editorial control whatsoever over the content of the report. This kind of altruistic, good-for-the-market contribution is, in our opinion, the best kind of marketing, and we commend them for adopting it.

On Tuesday, I had a chance to talk with government cloud users in DC about clouds. Rather than the usual “echo chamber” of clouds and IT, this was a more introductory session, and it gave me a chance to cover the broader trends in IT — the shift from a monopoly model to a free market, and the cultural changes it entails.

Here’s the slide deck, with speakers’ notes.

Over the coming weeks we will be transforming Bitcurrent from a blog into a site that represents more what we do – produce events, content and research.

The first step of this transition is that from now on, all Cloud Computing related blog entries will appear on our new cloud-centric blog.

We call it Rented Metal. Head on over and read about what’s happening at Cloud Connect.

In a few weeks, we’ll hold the inaugural Cloud Connect in Santa Clara, California. It’s actually the continuation of a series of events David Berlind launched around cloud computing, plus a spinoff of last year’s Enterprise Cloud Summit, plus a bunch of new content.

We’re pretty excited, because this is the first time Bitcurrent has helped build an event from scratch (unless you count Bitnorth, that is, but Cloud Connect is a beast of a different magnitude.) There are four days of content, built around three audiences: those who buy and finance cloud decisions; those who build cloud applications, and those who have to run the cloud platforms.

Getting here has been an interesting experience. Here’s what we did, plus an easter egg for reading all the way to the end. [Read more]

Recently, some journalism students from the American University in DC asked if they could interview me about cloud computing. As I wrote back to them, I realized that the discussion was different from what I usually talk about when it comes for clouds. These are journalism students, and they likely have a different view of “cloud computing” from the technobabble we technologists enjoy. It’s also about how schools will use on-demand applications. So I figured I’d re-post the thread here.

One of the biggest things I realized was that “clouds” can mean “elastic, on-demand compute platforms” or just “stuff that runs on the web” depending on who you’re talking to. And while these seem like two separate definitions, ultimately, they’re the same thing.

The Q&A, below the fold.

[Read more]

I’m in San Diego today with Lenny Rachitsky of Webmetrics, talking about possibilities for cloud research. We were discussing App Engine penetration, and fired off some searches to try and see how much attention the Google Platform-as-a-Service is getting. This is speculative at best, and fairly imprecise; but we did see some surprising things.

The trick here is that every Google App Engine site has a name that ends in appspot.com. You can call your new site whatever you want (mysite.com), but there’s a default name for it (mysite.appspot.com). And that makes it searchable.

First of all — how many are there? Well, according to Google’s own search, around 221,000. But what’s most interesting is that the top-ranked ones aren’t in North America. Many of them are Chinese, or Indian. Some of them are phishing sites (such as this one that is a pixel-for-pixel copy of Twitter — don’t log in.) Looks like the free trial and easy enrolment in the service make it appealing for certain markets.

Where’s the word “Appspot” being searched for? Once again, we turn to Google — this time their Insight for Search service — and see that China and Japan are where most of the discussion’s going on about “appspot”; for “appspot.com”, however, it looks like it’s North America.

It’s not clear that App Engine is getting the broad adoption of other cloud platforms, like Amazon. For one thing, it’s a Platform, not Infrastructure, model, which makes it less attractive for enterprises. There are concerns over portability, particularly for people who code to Google’s APIs for storage. But if these searches are anything to go by, it’s getting attention in some parts of the world.

I’m at IGT09 this week, put together by the energetic Avner Algom. Yesterday, I gave a presentation on the ROI of cloud computing (including some data that IDC and Peter Van Eijk were nice enough to let me use.) We started off with a panel on enterprise cloud use, with four panelists from very different backgrounds:

• Steve Rubinow, EVP and CIO of NYSE Euronext
• Yosi Shneck, CIO, Israeli Light Company
• Eyal Waldman, Co-founder & CEO, Mellanox
• Liam Lynch, Chief Security Strategist, eBay

Here are the slides, including panel questions.

Lots of good conclusions from the Hybrid Cloud panel at Interop; too many to see on one slide, so here they are.

• Hybrid isn’t one app in two places; it’s internal and external apps talking to one another
• Migrating for new apps is easy; for already deployed ones, it’s much harder
• In the new world, the developers are the admins and ops toolsets are changing
• The 2010 platform will be
  • Infrastructure-aware; parallel; split between dev and ops
  • Not really PaaS; but not IaaS either
  • Runs both in-house and externally
• Increased focus on making it easy for developers to transition to on-demand environments
• Portability becomes a bigger concern (in/out and between clouds)
• Where enterprises will initially embrace it:
  • Collaboration, messaging, things “just above” infrastructure
  • Areas that don’t add strategic value
  • Leverage utility model of what’s there now (apps with inherent burstability)
• Ideological battle in infrastructure
  • Bottoms-up focus on primitives (storage, queue, compute); we build things from easy-to-connect, RESTful functions
  • Top-down modelled approach, which we reduce down to the underlying patterns and can generate code from them (policies, etc.)
• Growth of 2 kinds of technologies
  • That make this easier for developers (Ruby on Rails) ➜ This will win
  • That help to migrate legacy systems into cloud-compatible containers
• Enterprises about 5-7 years behind consumer/public Internet (Web tech, Hadoop, enterprise mashups)
• Let us not forget: All big web businesses use a ton of Oracle
• Huge $ to be made solving enterprise migration: Discrete components or specific apps
• Standardization is 15% of the problem; standards bodies are still arguing taxonomies
• Internet standards are built on rough consensus and running code; whoever produces a useful product that is available to many people quickly will win

Interop’s in full swing in New York this week. Yesterday’s Enterprise Cloud Summit sold out, and the panelists and audience made it a joy to moderate — lots of good questions.

Let us know if you have questions or want to use the content somewhere.

Clouds are transforming IT; that’s not news. But regardless of your cloud computing agenda, clouds are already affecting your IT plans, because they give you a cudgel with which to bludgeon traditional software and infrastructure providers.

[Read more]