I’m pleased to be heading back to Interop this spring with two sessions on enterprise storage. Although significantly changed from the old “Networld + Interop” days, the event is enjoyable and technical, with many interesting sessions and speakers. And the New York show at least had plenty of end user attendees!

Interop Las Vegas is April 25-29, 2010, and registration appears to still be open. Let me know if you’ll be there!

My two sessions:

State of the Art Thin Provisioning

Wednesday, April 28 10:15 AM–11:15 AM

The concept of thin provisioning is not new, but the state of the art has advanced, adding awareness between the operating system and storage device for enhanced efficiency. This session introduces the value proposition and concept of thin provisioning, covers the technology of the major thin storage vendors (3PAR, BlueArc, Compellent, Dell, EMC, HDS, HP, IBM, NetApp, Pillar) and operating system integration layers (Symantec, VMware, and T10), and presents novel approaches from Data Robotics, Apple, and cloud storage systems. We will present the pros and cons of these various approaches in the context of enterprise storage management.

The Right Approach to Cloud Storage

Wednesday, April 28 11:30 AM–12:30 PM

Enterprises are now leveraging cloud storage services at a rapid pace and are looking for qualified answers on how using a cloud platform can increase efficiency and ROI simultaneously. The old model of purchasing expensive storage systems or using large amounts of tape are prehistoric, adapting a new approach to storage is necessary in today’s tough economic climate as budgets continue to be slashed and performance upkeep is critical. This session will enable users to learn about the benefits and economies of scale as it relates to developing/implementing a cloud storage solution, a focus will be placed on performance, cost-effectiveness, user experience, and customer service/satisfaction.

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Thin Provisioning and Cloud Storage: My Interop 2010 Topics
This post was categorized as Enterprise storage, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

HP recently commissioned Tolly Group to benchmark their BladeSystem c7000 against the Cisco UCS 5100. The short report focuses on two results, and reads like so many competitive benchmarks in the IT industry: Tolly focuses on metrics that highlight the strength of HP’s solution and the weaknesses of Cisco’s. I do not dispute the accuracy of these results, and HP and Tolly are doing exactly what tech companies do. But what’s the real value of pinpoint maximum-performance benchmarks like this?

0-100-0

Automotive media like Car and Driver and Top Gear frequently test the maximum performance of cars, racing to 100 mph or beyond, sliding around a skidpad, and slamming on the brakes. These tests can be enlightening when it comes to high-performance cars, and the punishing 0-100-0 test is especially impressive. But what’s the point of hammering an economy car or pickup truck like this? Maximal acceleration and cornering are entirely irrelevant to buyers of commuter cars and work vehicles.

Even though a given test can be conducted, it may not be enlightening. The Tolly report demonstrates two key findings:

1. Although 4-blade configurations perform the same under maximum stress, Cisco UCS performance declines with 6 blades while HP’s remains steady.
2. When using a shared blade uplink, Cisco UCS performance fell by half.

These are not startling results. Cisco blades sometimes need to share one I/O channel, and this can’t match the performance of an HP blade with dedicated I/O. Would it shock you to learn that a one-gallon bucket requires twice as many trips to the well as one that holds two gallons? Does it shock anyone to learn that a V6-powered Toyota RAV4 accelerates quicker than a four cylinder Honda CR-V? HP’s c7000 is bigger than Cisco’s UCS and offers more I/O channels, so HP beats Cisco whenever larger configurations with more I/O are tested.

Innocent Benchmarks

Greta examines the marks on an 18th century cooper's bench

I’ll leave the deeper commentary on blade performance to experts like Kevin Houston and Martin Macleod, but these maximum-utilization benchmarks are only half the story. I’m much more interested in how the different approaches to I/O impact everyday (20%-40% load) performance and how oversubscription impacts performance as more blades are installed and workloads are moved around. In automotive terms, I’d like to know how well a car handles in the snow or how economical it is with three or four passengers. These real-world scenarios are much more telling than a test of a few blades under 100% load!

Clearly, HP wanted to call attention to specific shortcomings of a competitor’s product, and it was wise to do so with objective numbers instead of mudslinging and name-calling. I hope that future tests and releases include real-world workloads and logical configurations, not the extreme situation used in this report. The same lesson applies to all tech companies: Simple, objective tests of maximum performance are welcome, but customers need many more metrics!

Note: Along with 9 other independent bloggers, I attended HP’s Blades Tech Day in Houston on February 25 and 26. Most of my travel and living expenses were paid for by HP, and the company provided a small gift bag (pictured here).

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Innocence, Fairness, and Technology Benchmarks
This post was categorized as Enterprise storage, Gestalt IT, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

My presence at Storage Expo NL may have been cursed, but my presentation went off without a hitch thanks to the creativity and flexibility of the VNU staff and Expo volunteers like Ilja Coolen. In my session, I talked about the shortcomings of traditional tiered storage as a way to advance the Noble Goals of Storage Management and proposed a solution: Although merely using different disk types will never deliver the goods, adding flash and cloud to an integrated, automated solution will be truly revolutionary. I look forward to the day when all of today’s buzz-worthy technologies (flash, cloud, thin provisioning, automated tiering, post-RAID) are mixed together to form a really revolutionary storage system.

I went ahead and recorded the entire presentation and posted it on Vimeo for anyone to see. But I just realized I never posted it here to my blog. So without further ado, I give you “Extreme Tiered Storage: Flash, Disk, and Cloud!”

Stephen Foskett on Extreme Tiered Storage from Stephen Foskett on Vimeo.

By the way, in case you were wondering, I used BoinxTV to create this video.

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Extreme Tiered Storage: Flash, Disk, and Cloud
This post was categorized as Enterprise storage, Gestalt IT, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

CommVault is bringing a new dish to dinner: Cloud storage!

If your family was like mine, Thanksgiving was a two-tiered affair: The adults sat at the fancy dining room table while the kids had to sit in the kitchen, some even using a card table and folding chairs. You knew you were grown up when you moved up to the adult table. I guess this American coming-of-age ritual is pretty common with other rituals, too. There’s no formal ceremony, but everyone knows when little Johnny becomes just-plain John.

We see similar things happen in IT. New technologies and ideas are often given a pat on the head, a pinch on the cheek, but then sent to the kids table in the kitchen. Only mature technologies are taken seriously and granted equal status when enterprise architectures are defined!

One sure-fire way of determining when a technology is ready for prime time is when it is integrated with a major enterprise product. Sure, lots of products will support this or that, but thoroughly integrating a new technology requires serious effort. Not just any technology gets this kind of focus!

That’s why I’m pleased to see today’s announcement that CommVault has completely integrated API-driven public cloud storage with Simpana, their impressive data protection and archiving suite. It reminds me of that point when the backup products of yore finally adopted disk-based technology. Now there are three equal backup targets: Tape, disk, and cloud.

CommVault calls their new integrated cloud storage "Farline" - as opposed to "Nearline", get it?

CommVault’s reputation in the storage industry is like BMW’s in cars: They’re an engineering-driven company and focus on offering the best technology. There’s no way CommVault would cut corners when it came to a fundamental technology. So they applied considerable engineering resources and delivered a really advanced product.

I’ve previously noted that cloud storage is not backup, but that the combination of cloud storage with a solid backup platform makes a killer data protection value proposition. This is exactly what CommVault is delivering. Plus, Simpana’s integrated encryption and data deduplication technology work to reduce cloud-related angst. And CommVault will be supporting just about every public cloud provider, beginning with Amazon S3, Microsoft Azure, and Nirvanix (where I spend my days), and I hear Iron Mountain and EMC Atmos are on the way, too.

Read more over at Network World, DGIC, or check out my Nirvanix blog about CommVault’s cloud integration.

Note: Yeah, that’s a Tofurkey-brand vegetarian turkey in the photo above. Yum!

© sfoskett for Stephen Foskett, Pack Rat, 2010. | CommVault Gives Cloud Storage A Seat At The Adult Table
This post was categorized as Enterprise storage, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

Western Digital is first to market with "Advanced Format" 4K-sector drives, but when will vendors support them?

A few weeks ago, I wrote about the new generation of hard disk drives that use 4K sectors rather than the historic 512 byte size. As I noted in that piece, although PC and Mac users with recent OS versions had nothing to fear from these, embedded devices like the TiVo and Drobo I use and love might not be compatible. I tried reaching out to these vendors, but only one has actually responded.

Drobo Compatibility Is Coming

You can discover all sorts of things in firmware release notes if you look hard enough. The latest firmware for the Data Robotics DroboElite and Drobo S (versions 1.0.1 and 2.0.1, respectively) now include 4K drive support. The former was released at the end of December, though I didn’t get around to blogging about it then. So users of the third-generation Drobo products are set as far as 4K “Advanced Format” drives go.

I sat down with Drobo’s new CEO, Tom Buiocchi, at the Business Development Event in Palo Alto today and asked about this issue. The company assures me that the still-current second-generation devices, the Drobo and Drobo Pro, will also get 4K disk drive support in their next firmware update. They recommend updating the firmware of any Drobo device before installing a 4K drive, since the drive will have to be reformatted and rebuilt otherwise. I appreciate their responsiveness.

Update: Drobo Pro (firmware 1.1.5) and the base Drobo (firmware 1.3.6) got 4k drive support in early February!

If Not Now, When?

Since these new drives remain scarce, I agree that this support alone is not cause for a firmware rev. But the fact that online retailers are shipping them with little notice or warning about incompatibility does raise flags. Here’s hoping everyone supports them before they become common!

I remain concerned that no other maker of embedded hard disk-based devices has responded. This is not a priority for those that don’t support end users swapping out hard disk drives, but there are many devices that remain questionable. I’d love to hear from Netgear, Iomega, Linksys, Synology and others regarding their level of support.

Update: Synology released updated firmware to support the Western Digital EARS 4K Advanced Format family of drives at the exact moment I posted this!

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Drobo Adding 4K Drive Support – What About Everyone Else?
This post was categorized as Apple, Enterprise storage, Terabyte home. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

Concluding my series on vendor blogs, I’d like to share my own experiences. This will be much more personal than the other three articles, but will hopefully still be helpful.

Everyone is a vendor - what are you selling?

We’re All Selling Something

I’ve always been a vendor blogger, and so have you. It took me a long time to come to terms with this, but nearly everybody is a vendor of one sort or another: Regardless of whether you deliver results to your employer, sell your own services, or push a product, we’re all selling something.

I’ve been delivering enterprise IT consulting for a living for almost 15 years now. It’s easy to pretend that human services like consulting are somehow more pure than the “box pushers”, but this is simply not the case. Even internal end-user employees are trying to keep themselves employed, and the most effective way to do this is to promote their company and themselves.

It’s not a black and white scale. If we are all selling ourselves and our employers,then we are all vendors to greater or lesser extents. We all have our axes to grind, our prejudices to expose, and only our experience to draw on. So no one is perfectly credible and no one is perfectly tainted.

I’ve long labored to maintain my credibility and independence, even as I have moved from an IT outsourcer (Sprint Paranet) to a storage service provider (StorageNetworks) to strategic consulting companies (GlassHouse Technologies and Contoural) to a cloud storage provider (Nirvanix). I’ve always remained separate from any product focus, but I’ve always been part of the sales and delivery process for consulting services.

Get Out Of Jail Free?

The fact that it’s all shades of gray does not mean, however, that we are free to twist the facts with impunity or that we should object when others pass judgement on our motivations. Quite the opposite: If we are all vendors, we all had better be careful what our actions say about us!

This is the most important lesson I have learned about blogging: Credibility is our currency, and no one has yet offered me enough reward to sacrifice mine. Can I be bought? Well, in the words of Jayne Cobb, “that’ll be an interesting day!”

Because I recognize the importance of credibility, I try to keep a level head and maintain a respectable persona. This means avoiding personality-driven battles and engaging in accptable business practices I would be proud for the world to know. This isn’t always easy: As your personal profile rises, there will be outside pressure (or inside temptation) to leverage it. Our shared challenge is to keep level heads.

The Messenger Matters

One inescapable fact remains: Employees of companies known for FUD are held to a higher standard of scrutiny. No matter how personally responsible and credible you are, if you work for a marketing-driven product vendor, you will be under the microscope.

Comments that would be considered innocuous or even respectably aloof from an “independent” might seem like mud slinging from a vendor employee. Imagine reading blog posts or tweets from an end user criticizing the products of Microsoft and IBM. If the exact same statements were made by employees of EMC or HP, wouldn’t they be seen in a different light? The message is the same, but the messenger matters.

I have personally experienced the doors that close when moving from a consulting company to a managed service provider. Certain publications and event organizers have strict rules denying “vendors” the right to participate; others have no such restrictions. I was sad to say goodbye to TechTarget after 5 years, but I respect their rules. Happily, as their door closed, others opened and I was able to write and present more last year than any year previous!

My Approach

My new role at Nirvanix explicitly allowed me to continue my personal social media presence, including organizing Gestalt IT and Tech Field Day. Management saw that my reputation was a benefit to the company and trusted I would remain objective and keep my work and non-work roles separated.

I’ve endeavored to do just that, launching a new blog, Enterprise Storage Strategies, specifically for cloud storage strategy and restricted crossover between the two domains. In the interest of objectivity, I’ve also “recused” myself from discussions of cloud storage on the Gestalt IT web site and at Tech Field Day.

I don’t want to say that this is the correct approach for everyone, but it’s worked well for me. What do you think? How can vendor bloggers remain credible in the increasingly social world?

Hot dog cart image by rollingrck

© sfoskett for Stephen Foskett, Pack Rat, 2010. | What I’ve Learned From Vendor Blogging
This post was categorized as Enterprise storage, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

As previously-independent bloggers are being hired in droves by the major IT infrastructure hardware and software vendors, attention is turning to their independence and credibility. But this extends far beyond blogs: Today’s social media influencers are everywhere!

Biased content isn't just found on blogs - it's much more likely to be found in other areas like Twitter and discussion forums. When does discussion become Astroturf?

Discussions Are On The Move

The new Internet isn’t just about blogs. In fact, the majority of social media discussion and linkage probably happens on Twitter, LinkedIn, discussion forums, and other sites. But non-blog content raises even thornier bias issues than blogs:

1. Discussions are less formal than blog posts, so off-the-cuff comments are common. The rapid turnaround of Twitter comments encourages “post-before-you-think” thinking, and knee-jerk comments can be damning. Even if one did not intend to but another vendor down, it’s easy to say something inappropriate.
2. The length of a comment is limited, so subtle nuances get lost. I’ve often had trouble saying what I want in 140 characters, and even blog and forum comment conventions restrict verbosity. Again, sometimes your meaty tweet will really cut a competitor to the bone.
3. Biographical information is limited. Twitter profiles include just a few words and a single URL, restricting the disclosure of relevant information. Many profiles don’t include the name of an employer or disclosure of other vendor ties. Forum profiles and signatures are similarly restricted.
4. The Internet scatters content. Even if one is careful to disclose one’s business relationships on a blog, Twitter profile, or LinkedIn page, interactions go far beyond these.

Conferences are even worse. Many attendees switch badges or intentionally list a different company just to get in the door, obscuring their identity. And no one knows who the guy in row 12 is or why he is asking such pointed questions of the panel. The same thing happens with webinars and Internet polls.

All these limits obscure the good folks out there and conspire to allow the bad ones to act with impunity. This makes everyone suspect. Actively comment on a number of industry blogs and you could be accused of astroturfing! Whether it’s fair or not, employees of hardware and software vendors are being held to a higher standard than so-called independents.

Personal Defensive SEO

I’m going to assume you’re a good egg and want everyone to know where you’re coming from when you interact on the Internet. Many businesses actively engage in search engine optimization (SEO) to help them rise to the top of Internet search results. Individuals need to start doing some SEO, too, but the reason is different: Make yourself easy to find and disclose your connections and you won’t look like a bad egg.

1. Get a LinkedIn profile, keep it up to date, and set your name and company information to public. Go to Settings -> Public Profile, and turn on Basics, Summary, Current Positions, and Websites at a minimum. And make sure Websites includes your current employer and blog(s).
2. Create a Google profile with links to your LinkedIn profile, blog, Twitter, and other profiles. This helps Google and other search engines disambiguate you from the rest of the crowd. FriendFeed is another great place to set up a profile. I only use Facebook for personal/private connections, so I don’t bother with corporate links there.
3. Make sure your blog includes links to your Twitter and LinkedIn profiles, too. And pepper your blog with your own full name so it shows up in Google searches.
4. Include your employer’s name in your Twitter “one line bio” and use your blog as your Twitter profile URL.
5. Set up Disqus, Intense Debate, WordPress, and Typepad profiles and use them whenever possible.

All this effort won’t directly help you, though it might save a few minutes when you try to comment on a blog. But they will make you easier to find, and reduce the likelihood that someone will accuse you of not disclosing your corporate affiliations.

Astroturf car, public domain image by Ingolfson

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Vendor Non-Blogs
This post was categorized as Enterprise storage, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

As companies discover blogging and social media, a spectrum of vendor-oriented blogging emerges: Some are more or less open about where they work, some focus on common technology, and others work in marketing. Companies must strive for openness in social media, and bloggers are wise to keep these considerations in mind as they move to new companies!

Not all bloggers are equally vendor-focused - it's a spectrum

The Vendor Blogging Spectrum

Although most folks know they should take official company comments with a grain of salt, social media muddies the waters. Consider a spectrum of vendor blogs, ranked here from most- to least-forthright:

1. It’s easy to tell that a blog hosted at “companyxyz.com” is at least a semi-official statement from that company. For examples, see NetApp or HP’s lists of blogs. At the very least, the content of corporate-domain blogs will focus on the positives of the company. This is my preferred venue for business-related blog posts.
2. There are also independent-seeming official blogs from many companies. Sussing out the corporate can be fairly easy (as in OnlineStorageOptimization) or somewhat more difficult (see CloudStorageStrategy) but a reasonably persistent person can see that these are corporate communications vehicles. Also, see Quest Software’s SQLServerPedia for an excellent example of a community service site!
3. Companies like EMC encourage employees to create independent blogs outside the corporate domain, but most blogs include an “About” page listing their corporate affiliation. Again, one expects the corporate glow to radiate from these blogs and they rarely include anything but corporate-oriented content. It you’re blogging about your company on your personal blog, you must make sure it’s obvious where you work!
4. Next are the personal blogs of employees, which may or may not include business content. Many expect that these will disclose employment affiliation but some do not. I have often had to turn to Google or LinkedIn to discover who is and is not an employee of one company or another. This is fine as long as business content isn’t included, but disclosure is a must when there is crossover.
5. There are also paid placement blogs that serve as PR vehicles outside the corporate domain. Above-board examples like DCIG do an excellent job of providing solid content along with sponsor-oriented paragraphs, but it can be much harder to discover the paid connections in others. Some analysts even speak and write on behalf of their clients with no disclosure whatsoever!

And these are only direct connections. Is a reseller any more independent than a vendor? How about a consultant who gets paid to install and configure the product? Or an analyst who gets paid for strategic advice? Or a reporter taken on a junket? Perhaps the FTC disclosure rules weren’t so crazy after all…

Does Industry Matter?

Surprisingly, the tolerance of readers to vendor bloggers varies greatly by industry. What would be acceptable in one segment would be odious in another.

Base IT infrastructure components (storage, servers, switches) are an incredibly competitive market, so competition from bloggers tends to be equally fierce. The same is true of emerging technologies like cloud computing. Head-to-head competition is going to attract both overt blog battles and covert mindshare wars, so these industries tend to be much more concerned about who is and who is not “a vendor”. Marc Farley’s move from Dell/EqualLogic to 3PAR, for example, was the topic of heated debate due in part to the intense competition between these vendors. Tony Asaro’s blogging and career moves have caused similar debate for much the same reason.

In contrast, virtualization platforms, database software, applications, and development environments are more about making effective use of a singular product. Without the foundation of competition, much less attention is paid to where a blogger works. This is why the hiring of many top VMware bloggers by VMware and EMC hasn’t caused much concern. Who cares if you work for VMware when the relative merits of the platform is not a subject of debate? Folks like Scott Lowe, Ed Saipetch, and Rick Scherer are known for their quality technical contributions, so it’s unlikely that their moves into “the mothership” will change anything. But I know they’ll be watched much more closely from now on…

Case in point: See the recent “best blogs” polls at vSphere-Land and Storage Monkeys: The VMware blogger list includes (by my count) 11 vendor bloggers out of 25. In contrast, the Storage Monkeys site chose to have two separate lists, one for vendors and another for independents. It is interesting that the VMware community thinks nothing of combining “vendors” and “independents”, while the storage community wouldn’t have it.

Another cause of “vendor blogger” FUD is the orientation of the bloggers. Folks who are focused on message tend to be more criticized than those focused on technology. This is not always the case, however. If one became widely known as a proponent of a specific product or technological approach (say, NAS for VMware storage), it would be very difficult for them to make a move to a vendor with an entirely different approach (like a Fibre Channel or iSCSI player).

Expose Yourself!

There are ways to mitigate the impact of a vendor job move, of course. We’ll be talking about these in detail later in this series, but one easy way is to make sure there is a clear distinction between the person and the company. Here are some specific suggestions for your blog:

1. Create an “About Me” page, obviously linked from every page on your blog, that lists your full name and employer. I shouldn’t have to google you to discover who you are.
2. Create a separate work blog. Clearly spell out which “hat” you are wearing on each of these blogs, and keep from mixing work and personal content.
3. Don’t get into personal battles over work-related topics. Remain calm and professional and don’t make enemies. You never know when you’ll be playing for a different team!
4. Move work content up the stack. The closer you get to the top of the vendor blog spectrum, the less problems you’ll have. Some companies won’t allow a “company.com” blog, but maybe they would allow the creation of a special company-wide blogging site.

Your goal is to be open and honest about who you work for. Above all, remember: Your credibility is the currency of the new social economy!

Prism image: GFDL by Peo

© sfoskett for Stephen Foskett, Pack Rat, 2010. | The Spectrum of Vendor Blogs
This post was categorized as Enterprise storage, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

Something big is happening in the IT infrastructure blogging world: Previously-independent bloggers are being hired in droves by the major hardware and software vendors, particularly EMC and VMware. What does this mean for the community? This series of articles investigates the impact that this transition will have on the IT infrastructure community.

Are you a vendor blogger or an independent? Can you straddle the line and be both?

Why Do Vendor Bloggers Matter?

I suppose it’s best to get some definitions out of the way at the outset. Blogging and social media is a diverse and ill-defined region of the Internet, a world which itself in its infancy. What I write here is focused on my particular corner of the online world: Enterprise IT infrastructure, and enterprise storage in particular. I am sure that other areas, both inside and outside of IT infrastructure, have different norms and values.

In fact, this particular focus on who is a vendor and who is not will seem peculiar to many. Some areas are dominated by insiders blogging for their employer, other companies are entirely absent from the blogging sphere (Exhibit A: Apple), and still others don’t make much of a fuss over who someone works for. Yet concern about payola and bias runs deep even in the most liberal circles.

Can You Trust It?

It boils down to a simple question: How much can you trust what you read? Blogging and other social media activities (Twitter, conferences, forums, etc) have come to dominate discourse and drive search engine ranking. An outspoken social media maven can drive mind-space and thought leadership using these tools. Yet the democratic Internet is open to any and all.

This kind of influence can be very subtle. A connected employee can be expected to be part of the larger conversation about a product, service, or technology. Once also expects them to influence this discussion, and this will always be biased based on their experience and background within the company. Where outside critics see a profit-motivated monolith, an employee sees an all-too-human company trying its best to succeed. And since that success feeds their children, it’s hard to expect them to be too critical.

Certainly some content is inherently trustworthy, especially in technical areas like IT. I love Chad Sakac’s posts on EMC/VMware integration, for example. I also look forward to reading what the VMware and Microsoft employee bloggers write, since they’re so detailed and factual. And finding this kind of content of a personal blog, even without disclosure, wouldn’t raise my hackles. But even the most technical blogs sometimes get into “mine is better than yours” arguments between vendors.

The world of strategy and opinion is much less black and white. Consider just about anything on Chuck Hollis’ blog. He writes at EMC.com and his content is always on point for that company. But many others (from many companies) write similarly corporate-focused pieces with much less disclosure. This is an old PR trick, and the Internet makes it easier than ever both to get published and to disguise affiliation.

But even with the best of intentions, we are all biased in one way or another. Our experience, our employer, our friends, and indeed the entire world we live in influence our experience. It is not a simple thing to be independent of this, and we should expect everyone to be impacted to one extent or another. The trick is to detect overt bias and manipulation.

Throwing Stones

I’m not trying to throw stones here. In fact, I write a vendor blog myself for my employer, Nirvanix. I am very used to wearing multiple hats, and I pride myself on my ability to step into and out of the corporate shadow. But it’s a very difficult game to play, and I’ve failed on occasion.

Rather, I’m hoping that this series of articles will spark some discussion on the whole concept of vendor blogs. I’ll be posting about the spectrum of options that corporate bloggers have, non-blogging soapboxes they use, and best practices to keep everything straight.

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Vendor Bloggers 1: Why Does It Matter?
This post was categorized as Enterprise storage, Personal, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.

Using system memory for storage is something of a lost art these days. Although system RAM capacity has become plentiful, cheap and quick disk storage is just as common. But many of today’s I/O intensive tasks can still benefit from the untouchable quickness provided by a ramdisk. Happily, most operating systems are still capable of creating and using ramdisks. This article discusses the creation, use, and performance of ramdisks in Mac OS X.

On The Extinction Of Ramdisks

System RAM is not typically used for storage anymore

Ramdisks were a cheat to make slow system I/O tolerable, but it was never an easy decision. These days, computers are fast enough that ramdisks are rare. Every part of the computer has gotten quicker and cheaper over the last two decades, including hard disk drives, RAM, and CPUs. A typical laptop like my MacBook Pro might have 4 GB of system RAM, 320 GB of hard disk capacity, and dual 2 GHz CPUs.Those specs would have seemed inconceivable just a few years ago: I still have a Dell laptop with a 20 MHz CPU and two expensive upgrades: 1 MB of RAM and a 20 MB hard drive!

Far more impressive, though, are the numerous performance optimizations that have appeared. I/O channels are quicker than ever, and caches have appeared at most performance bottlenecks. It’s hard to believe, but computers used to rely much more on raw storage. Many hobbyists recall waiting for data to load from cassette tape drives, or that one key performance advance in Intel’s 80486 chip was its on-chip cache. Today’s CPUs have three levels of cache, and operating systems have gotten much better at caching data internally as well.

Hard disk drives have sprouted their own caches, too, making I/O seem quicker than it is. My 1997 Toshiba laptop used an un-cached 4200 rpm hard disk, but even laptop drives today sport 16 MB or more and spin at 5400 rpm or faster. Although RAM was scarce back in the day, the performance gained from a ramdisk was worth the effort. Faster I/O and strategic caching has largely eliminated this need. Increasing operating system intelligence also plays a major part – witness the failure of hybrid hard drives.

The Modern Use Case

A long-standing argument in the field of computer system performance revolves around whether to manually reserve resources and place data or to let the system dynamically manage resources on its own. Computers do a decent job if allowed to, often adapting quicker and more efficiently to changing demands. But some jobs are harder to automate, and buffers and caches don’t always catch the right data.

Purely temporary data can be written to a ramdisk as a high performance scratch space. There is no need to store this on disk at all, and merely placing it there is likely to “pollute” the buffers, pushing out real useful data.

A ramdisk can also increase security somewhat by never allowing certain data to be written to disk. Ramdisks are sure to be flushed on the next reboot, but data on disk can linger and be discovered later.

One could even argue that today’s high-performance solid state disk is simply an evolution of the old ramdisk concept. NAND flash and RAM both offer the high random performance of the ramdisks of yore, and many analysts expect them to displace high-performance hard disk drives in the coming years. So perhaps ramdisks are not extinct after all!

Ultra-performance storage systems like this Violin array use RAM for storage

Using Ramdisks In Mac OS X

Mac OS X has the ability natively to create and use ramdisks. Here’s the simple procedure:

1. Create the ramdisk with hdiutil – This terminal command will create a 1 GB ram disk and report the name used. The number following the “ram://” statement is a number of 512 KB disk blocks – multiply the desired ram size in MB by 2048 (that’s 1024 times 2) to derive other sizes.
   hdiutil attach -nomount ram://2097152
2. Format the ramdisk with diskutil – The next command will format the newly-created ramdisk using the diskutil tool. We will use /dev/disk3, but you should specify whatever disk device hdiutil reported from step 1. You can also specify a different filesystem or disk name.
   diskutil eraseVolume "HFS+" "ramdisk" /dev/disk3
3. Your ramdisk will now appear – OS X will now mount the newly-created ramdisk and it will appear on your desktop. Note that the contents will be destroyed if it is unmounted or if the operating system is rebooted!
4. Delete your ramdisk – It’s worth saying once again: The ramdisk will disappear and all data will be deleted when you eject it or power off your computer. Be sure to back up any important data from it, then eject it with the following command:
   hdiutil eject /Volumes/ramdisk

Script It!

My backup script called for the creation of a tar file, compression, encryption, and rsync copying. I decided that I could perform the first three functions on the ramdisk to increase performance and reduce the chance that an unencrypted version would remain on the disk if the script failed.

A simple command line combination of the above creates the necessary ramdisk:

diskutil eraseVolume "HFS+" "ramdisk" `hdiutil attach -nomount ram://2097152`

This failed once I put it in a shell script, however. The issue was the finicky nature of diskutil – hdiutil’s output included a number of whitespace characters, and diskutil failed in the script whenever it encountered this. So I used the cut command to grab just the first field of the output, like so:

diskutil eraseVolume "HFS+" "ramdisk" `hdiutil attach -nomount ram://2097152 | cut -d " " -f 1`

This solved my problem, and I was able to tar and compress to /Volumes/ramdisk in my script. I added the hdiutil eject command to the script right after the encryption step to wipe out the unencrypted data. Although this isn’t foolproof security by any means, it’s better than nothing.

© sfoskett for Stephen Foskett, Pack Rat, 2010. | Ramdisks: Back From the Brink of Extinction
This post was categorized as Apple, Computer history, Enterprise storage, Virtual Storage. Each of my categories has its own feed if you'd like to filter out or focus on posts like this.