Condusiv Technologies Blog

Condusiv Technologies Blog

Blogging @Condusiv

The Condusiv blog shares insight into the issues surrounding system and application performance—and how I/O optimization software is breaking new ground in solving those issues.

Is Fragmentation Robbing SAN Performance?

by Brian Morin 16. March 2015 09:39

This month Condusiv® announced the most significant development in the Diskeeper® product line to date – expanding our patented fragmentation prevention capabilities beyond server local storage or direct-attached storage (DAS) to now include Storage Area Networks, making it the industry's first real-time fragmentation solution for SAN storage.

Typically, as soon as we mention "fragmentation" and "SAN" in the same sentence, an 800 pound gorilla walks into the room and we’re met with some resistance as there is an assumption that RAID controllers and technologies within the SAN mitigate the problem of fragmentation at the physical layer.

As much as SAN technologies do a good job of managing blocks at the physical layer, the real problem why SAN performance degrades over time has nothing to do with the physical disk layer but rather fragmentation that is inherent to the Windows file system at the logical disk software layer.

In a SAN environment, the physical layer is abstracted from the Windows OS, so Windows doesn't even see the physical layer at all – that’s the SAN's job. Windows references the logical disk layer at the file system level.

Fragmentation is inherent to the fabric of Windows. When Windows writes a file, it is not aware of the size of the file or file extension, so it will break that file apart into multiple pieces with each piece allocated to its own address at the logical disk layer. Therefore, the logical disk becomes fragmented BEFORE the SAN even receives the data.

How does a fragmented logical disk create performance problems? Unnecessary IOPS (input/output operations per sec). If Windows sees a file existing as 20 separate pieces at the logical disk level, it will execute 20 separate I/O commands to process the whole file. That’s a lot of unnecessary I/O overhead to the server and, particularly, a lot of unnecessary IOPS to the underlying SAN for every write and subsequent read.

Diskeeper 15 Server prevents fragmentation from occurring in the first place at the file system layer. That means Windows will write files in a more contiguous or sequential fashion to the logical disk. Instead of breaking a file into 20 pieces that needs 20 separate I/O operations for every write and subsequent read, it will write that file in a more contiguous fashion so only minimal I/O is required.

Perhaps the best way to illustrate this is with a traffic analogy. Bottlenecks occur where freeways intersect. You could say the problem is not enough lanes (throughput) or the cars are too slow (IOPS), but we’re saying the easiest problem to solve is the fact of only one person per car!

By eliminating the Windows I/O "tax" at the source, organizations achieve greater I/O density, improved throughput, and less I/O required for any given workload – by simply filling the “car” with more people. Fragmentation prevention at the top of the technology stack ultimately means systems can process more data in less time.

When openBench Labs tested Diskeeper Server, they found throughput increased 1.3X. That is, from 75.1 MB/sec to 100 MB/sec. A manufacturing company saw their I/O density increase from 24KB to 45KB. This eliminated 400,000 I/Os per server per day, and the IT Director said it "eliminated any lag during peak operation."

Many administrators are led to believe they need to buy more IOPS to improve storage performance when in fact, the Windows I/O tax has made them more IOP dependent than they need to be because much of their workload is fractured I/O. By writing files in a more sequential fashion, the number of I/Os required to process a GB of data drops significantly so more data can be processed in less time.

Keep in mind, this is not just true for SANs with HDDs but SSDs as well. In a SAN environment, the Windows OS isn’t aware of the physical layer or storage media being used. The I/O overhead from splitting files apart at the logical disk means just as many unnecessary IOPS to SSD as HDD. SSD is only processing that inefficient I/O more quickly than a hard disk drive.

Diskeeper 15 Server is not a "defrag" utility. It doesn’t compete with the SAN for management of the physical layer by instructing the RAID controllers on the how to manage the data. Diskeeper’s patented proactive approach is the perfect complement to a SAN by ensuring only productive I/O is processed from server to storage to keep physical servers and SAN storage running like new.

With organizations spending tens of thousands of dollars on server and storage hardware and even hundreds of thousands of dollars on large SSD deployments, why give 25% or more performance over to fragmentation when it can be prevented altogether for a mere $400 per physical server at our lowest volume tier?

Try Diskeeper 15 Server for 30 Days ->

The Real Meaning of Disruption

by Jerry Baldwin 25. March 2014 07:26

Disruption is a popular word these days. Is it the replacement for innovation, which we’ve overused into pointlessness over the past ten years? Maybe, but disruption means more: it carries the weight of shaking up the status quo—of not only creating something new—but creating something that shifts models and opens our eyes to possibility.

We talk about disruption like it’s a new thing, cooked-up by a team of marketers in a conference room somewhere. But its roots lie in a theory introduced by an Austrian economist in 1942. Joseph Schumpeter captured the world’s attention in only six pages, where he clarified the free market’s muddled way of delivering progress. He called this theory Creative Destruction.

I don’t have a PhD in economics so I’ll dodge the minutiae, but the overall meaning of the theory is what resonates—as it should to anyone engaged in business today. “Creative destruction is the same process of industrial mutation that revolutionizes the economic structure from within, incessantly destroying the old one and incessantly creating a new one.”

Simply put, to continually move forward we must be willing to embrace the destruction of what came before.

Economists often use the Montgomery Ward example. MW started as a mail-order company in the nineteenth century. With no cars or trucks in those days, and most Americans living in small rural pockets, it was too costly to ship products to widely-dispersed local stores. That model would result in a high cost to the consumer, making goods too expensive for the average buyer. So instead MW turned its enormous Chicago warehouse (complete with a railroad running through it) into its hub, and used the already well-established US mail to deliver products directly to customers at a low cost.

And a successful model it was. With a high-volume of sales, MW could charge lower prices. By the 1890s Montgomery Ward was the world’s largest retailer. But all that came to an end. Why? Because over time Americans were moving to urban centers and could afford a higher standard of living.

Robert Wood was an MW exec, and may well be the first adopter of Big Data on record. He analyzed data, studied the census, and saw the shift in American lifestyle. He presented his findings to leadership, suggesting that selling goods through a chain of urban department stores would replace the mail-order model as the most profitable path for retail.

So MW did what any unmovable enterprise would do. They fired him.

Meanwhile James Cash Penney recognized the same trends as Robert Wood, and it wasn’t long before J.C. Penney stores put a serious dent in MW’s profits. The mail-order giant was late to the party and couldn’t change direction fast enough. And Robert Wood? He went to work for Sears, who also took a big bite out of MW’s market share.

Remind you of anything? Netflix and Blockbuster. Blockbuster was the established enterprise, staring streaming revenue in the face, yet unable to let go of profits from the rental market. Netflix is the newcomer—the creative destructor—free from the ball and chain of a dying business model, free to focus 100% on new streaming revenue. And we all know the end of that story.

We also know that business is anything but stagnant, there are waves and cycles, and the same is true of companies. It’s very difficult (impossible?) for an established enterprise to turn around, to be truly disruptive, and to compete with newcomers. But if you’re an organization that can stomach the destruction of what came before to create new growth and opportunity, you might stand a chance.

Condusiv is unique. We’re a software company with a 30-year history as an established player in file system management and caching technologies. But in the spirit of disruption—of creative destruction—we’ve shifted all our focus and resources to V-locity, our flagship product that in itself signifies disruption in how organizations run their data centers. A 100% software approach to solving today’s application performance issues at the root on the VM or OS layer, without requiring any additional hardware.

When you embrace creative destruction you must ceaselessly devalue existing wealth in order to clear the ground for the creation of new wealth.

It’s true, our discussions may be very different from those had in other conference rooms. But that’s what disruption should be about—that’s how Condusiv can deliver performance in a software solution at 1/10th the cost of the hardware alternative. While others go for margin erosion—trying to win business by saving customers 20 cents on every dollar spent, we help customers save 90 cents on every dollar.

As a channel partner, we allow you to fulfill your mission to your customers with added value, while also protecting your bottom line with a generous software margin that grows your profit over razor thin commodity hardware margins. You win. Your customer wins. A new market is emerging where hardware becomes the 2nd option for improved application performance.

Welcome to our conference room.

Mad Men, Awesome Chairs, and a Pretty Big IT Problem

by Robin Izsak 13. March 2014 07:57

Next month Mad Men returns to AMC for its final season. I'll miss it. The show had some great character development, terrific dialogue, and cool cars. But the set design! Oh the set design. I'm a fan of mid-century modern—the sharp angles, clean lines, and wood tones mixed with bold, primary colors. Don Draper's New York apartment and the Sterling Cooper offices are the pinnacle of perfectly curated spaces, designed for maximum form and function. 

Which brings me to Creative Office Pavilion, a large Boston-based firm of workplace consultants, and the primary US dealer of Herman Miller furniture—the undisputed kings of mid-century modern.

I mention all this as an excuse for my daydreaming. During my call with Robert Del Vecchio, Creative Office Pavilion's IT Infrastructure Manager, I was imagining conference rooms filled with Eames chairs of every color, wall clocks reminiscent of Sputnik, and enormously awesome lamps casting warm, non-fluorescent light. But Robert had more important issues to discuss, and discuss we did.

Robert's team supports a large base of business users: designers, mobile CRM users, support staff, accounting, and customer service. But he's also responsible for tons of data and heavy workload generated by an order entry system, CRM application, Lotus Notes, SQL Server, and hundreds of employees constantly accessing architect drawings, massive PowerPoint presentations, and database files. That's a lot of Eames chairs, going to a lot of workplaces, including Harvard University's Innovation Lab and Boston's Spaulding Hospital.

Sluggishness and poor performance had become a constant problem for his users, and Robert's team felt the full force of it—spending more and more time troubleshooting and doing storage health checks. So Robert did what any of us would do when faced with mounting pressure and scrutiny.

He Googled. And stumbled across a software solution that seemed to be the answer to his application performance problems, without requiring any new hardware.


What happened next is more exciting than Don Draper after one too many old-fashioneds.

Read the Creative Office Pavilion case study to learn more.

 

V-locity version 5 – The Director’s Cut

by Brian Morin 5. March 2014 07:08

As you know, we just released V-locity version 5. Here’s the director’s cut.

We committed a slew of engineers to several months of development to build an enterprise-class management console for V-locity. In a world where a couple developers with a few pizzas can create a robust app from scratch in 6 weeks, that represents a lot of apps!

Our previous management console didn’t scale beyond 500 nodes and didn’t play well with modern environments that span geographic locations with a hybrid of virtual and physical servers while provisioning some workloads to the cloud.

That meant a console needed to be built that has the ability to auto-detect the most complex environments and batch deploy V-locity in seconds. A management console that is aware of the new world order of hybrid environments – virtual, physical, cloud – and deploy and manage to all from a single point.

Customers asked for flexible pricing models whether it be volume perpetual licenses or site licenses or even subscription, and so we listened. They asked for I/O performance management that delivers insight into the anatomy of I/O behavior on all their workloads from virtual server (or physical server) to storage to help take the guesswork out of performance troubleshooting. Customers wanted to be able to set up alerts based on workload thresholds. They asked for a console that could validate V-locity before/after performance across workloads and have ongoing performance validation for continued ROI transparency.

So we built it. The whole enchilada.

Typically, when the baton is handed to marketing, the first two questions are almost always the same – “What do we call it?” and “What do we charge for it?”

When you commit engineering resource the size of a small island, the very first temptation is to productize, to monetize, to ROI-ize what you put in because there is a cost to building products.

Then again, this wasn’t really a stand-alone product, but rather a big enhancement to an existing product.

A lot of companies charge for that enhancement. Many of you have purchased hardware or software products, only to find a separate line item and SKU for the management software itself to manage the product you purchased – the never ending high tech rabbit hole of monetization where you buy cars but batteries and steering and tires are not included.

As my daughter tells me, “Dad, everyone does it.” So, in our initial brainstorming session, we kicked around the idea of doing it too. But when it came down to it, we agreed it’s not in the core tenet of our business model to disrupt.

V-locity provides performance at 1/10th the cost of the hardware alternative. That’s disruption. And in that spirit of disruption, we decided against productizing and charging for the management console.

It’s bundled with V-locity and available for free to every V-locity customer under maintenance. No extra charge required. No extra hardware required.

Announcing V-locity version 5

by Robert Woolery 28. February 2014 03:10

 It is not a daily increase, but a daily decrease. Hack away at the inessentials.” - Bruce Lee

Removing the nonessential is a key element of simplicity and efficiency, yet it is deceptively difficult to accomplish. We need reminding. And then more reminding.

When I get too caught-up in what’s on my desk, in Outlook, on the calendar, I get on the phone with one of our V-locity customers and I remember what we’re doing here. Why I pull into the Condusiv parking lot every day. We hack away at the inessentials, and in doing so, we enable our customers to work better, faster, more efficiently, without buying more hardware to achieve it.

We’re very pleased to announce V-locity version 5. In this release, V-locity is now bundled with the V-locity Management Console, giving IT organizations the visibility, command, and control to optimize applications and maximize users’ efficiency—proactively managing I/O and its impact on performance across the entire environment.

Enterprise-class and cloud-ready, the V-locity Management Console enables seamless deployment and centralized management of V-locity on-premises in a virtual or physical environment, or in the cloud. With central control of assets, configuration, and performance management, admins can deploy V-locity to thousands of VMs and physical servers in just five clicks, manage a large number of licenses, and support various pricing models.

The highlights:

  • Central command and control with web-based management from a single pane of glass across geographic locations
  • Fast, non-disruptive deployment to even the most complex multi-site and hybrid environments
  • Auto-detection of virtual and physical server environments for easy asset and license management
  • Flexible pricing options from site licenses, subscription, or perpetual volume licenses
  • Single solution for virtual and physical servers
  • V-locity alert management with email notifications based on customized I/O performance profiles for any application
  • Ongoing performance validation of V-locity for ROI reporting capabilities


No more needle-in-the-haystack approach to troubleshooting. No more contending with a disjointed view of the environment. No more lack of understanding what’s happening from server to network to storage.

Maybe you’ve virtualized, maybe you’ve gone cloud, maybe you’re using VDI to ease management of so many endpoints… whatever the case—in any of these scenarios—the marketing message is always simplification.

And while simplification might be partly real, each of these strategies comes with an inherent problem: I/O. More and more I/O, which leads to serious performance degradation, more hardware to throw at the problem, increasingly formidable data centers, and more hours spent troubleshooting and stressing out. The root of the problem is I/O.

And V-locity is software that dramatically reduces I/O—literally overnight. And now it comes with the V-locity Management Console to make managing complex environments more efficient than ever.

So today I channel Bruce Lee and his thoughts on simplicity, on hacking away at the inessentials. That’s what we’re doing at Condusiv. That’s the vision of V-locity version 5. Enabling organizations to perform faster, better, simpler, happier.

Learn more about the V-locity version 5 release »

Month List

Calendar

<<  November 2017  >>
MoTuWeThFrSaSu
303112345
6789101112
13141516171819
20212223242526
27282930123
45678910

View posts in large calendar