Performance

No Heavy Math

We do a lot of interoperability and performance testing, and this often involves schlepping a bunch of equipment to the partner or OEM site. Here in Silicon Valley, the facility may be just a few miles away so we drive, and that means packing up a bunch of moving cartons with servers, WAN emulators, and of course the two DMS systems. Today we were packing up after completing some tests and one of their QA guys who was helping commented on how light the DMS was, especially compared with all the servers that we needed to generate the +40Gbps flows.

“RAM,” I told him. “Our algorithm is really efficient.”

Huh? What does a little math formula have to do with the weight of our network deduplication switch?

Here’s the backstory...

Networking Field Day 3 – What A Rush!

As Ashwath mentioned in his blog a few days ago, we were scheduled to present to Tech Field Day delegates yesterday (March 29). The event was streamed live from our site, and snippets of the presentations will be made available on the same page within a few days.

In looking through the Twitter feed for #NFD3 yesterday, I saw some quotable and humorous quotes that I’m reproducing below:

@tbourke

Big difference between @infineta and other WOCs, no x86.

@ecbanks

Top 10 Blog Posts of 2011

2011 has been a memorable year here at Infineta. Here are a few things that come to the top of my mind:

WAN Optimization: Like Any Investment, Compounding Returns Matter

Two common ways of gauging DMS performance are the reduction rate, which looks at the data handled by the DMS, and throughput, which looks at the WAN link on which the data is carried.  There is a third way to measure DMS performance, however, and that is to look at the impact the DMS has on endpoint performance.  We call this the compound effect, and although it is perhaps the most telling measure of performance, it is often overlooked. The compound effect is simply the product of the reduction rate and the throughput increase.  

Let’s say after deploying the DMS you consistently observe reduction rates of 5x. Not bad! End of story, right?  No.

Sell Outcomes – Not Features

Before each customer deployment, our sales engineers work with the customer to fill out what we call a “Pre-site Survey,” where we collect information such as network diagrams, deployment and security concerns and any application-specific gotchas. Naturally, the most important metric we discuss with customers is their criteria for success, and we make sure that we “sell” the solution in terms of the outcomes that the customer is interested in.

In a recent customer discussion, the customer shared the following information:

Non-Commutative What?@#$%

Our product head Haseeb Budhani (@InfinetaProductGuy on Twitter) wrote an op-ed piece for Data Center Knowledge entitled “Data Center Traffic Highlights WAN Optimization.” Unlike a lot of the familiar vendor-submitted editorials that poorly mask biases, Haseeb does a great job of genuinely educating the marketplace without strings attached – kind of the way journalism is supposed to be done.
 

Accelerating Cross-Site Transfers For “Big Data” Applications

One of the best parts of my job is meeting some incredibly smart people who are pushing the envelope at all levels of networking. Seeing new technologies in use at Google and Yahoo! is one thing, but meeting enterprise IT guys who are experimenting and actively deploying the likes of Hadoop and Cassandra to fulfill their internal customers’ “big data” needs is truly inspiring. To top it off, if these IT guys are deploying their Hadoop clusters across multiple data centers and are building their WAN infrastructure to support multi-terabyte data transfers per day, that’s just magical!

Quick Note From The Field

I used to love watching “A” Team reruns when I was a kid. I always loved how the team would design some ingenious contraptions using “off the shelf” items and take down much larger opponents. My favorite part in every episode was when Hannibal Smith would light up a cigar towards the end and say: “I love it when a plan comes together.”

Our in-field trials are progressing extremely well, and we are successfully proving our performance claims in customer environments. The sales team is keeping us all extremely busy with customer meetings and the interest level is rising steadily.

If you have any specific queries for any of us here at Infineta, please feel free to drop me an email (haseeb at infineta dot com) and I’ll be happy to get your question(s) addressed.

I love it when a plan comes together. :-)

Deduplication and Compression – Different, But Complementary

Don MacVittie, a former editor for a major IT industry publication, currently manages technical marketing initiatives at F5 Networks. My colleagues and I are regular readers of Don’s informative, timely, and (quite frankly) enjoyable articles.

Don recently wrote a piece on F5’s DevCentral site, in which he compared deduplication and compression, two data reduction technologies used by WAN optimization solutions, and how they are complementary. I presented similar content to our field guys back in October of 2010, and as we typically do, we recorded the session and shared it for the world to see. The video is linked below:

Transport-Level Optimizations For Inter-Data Center WAN Traffic

Recently, I had the opportunity to pitch our inter-data center WAN acceleration solution to the crème-de-la-crème of the Internet networking community a few weeks ago. These are the guys who run the infrastructure for household names in e-commerce, social networking, SaaS, and mobile ad platforms. Many of these folks buy bulk bandwidth (in a few cases, in the 10s of lambdas) for their larger data centers and, for these specific cases, will not expect to benefit in any significant way fromour solution’s data reduction capabilities.

Pages

Subscribe to RSS - Performance
Content