Some locations are farther than others, and this makes shipping gear pretty expensive. We’ve been asked for a software only version of our stack from the 2 remaining continents we don’t have installs on (ok, 2 of 3 … not to much business in Antarctica right now).
I won’t get into the positives/negatives of this business model. Shipping bits lowers costs as compared to shipping atoms. But atoms are tangible, and require a cost to reproduce patterns that bits don’t impose.
This said, a great concern for us is the myriad of poorly designed very low end storage we see people designing and building, and pretending it is high performance. We get lots of inquiries from people who have built once, discovered its not fast, and then realize that mebbe there is an art/science to this.
There is. It ain’t easy to get good performance, and its real easy to get poor performance. Which is what most people get.
A good software stack won’t turn a crappy machine into a good machine. It won’t turn a poor design into a fire breathing dragon of a system. It may make some of the more painful aspects easier to deal with, but if its gonna suck because it was poorly designed, then, yes, its gonna suck regardless of the stack on it.
Inevitably, when people build these things, if they really don’t know how to architect for performance, then chances are they won’t. They’ll architect for … something … unrelated to performance.
We’ve watched partners (well, a specific former partner in this case), massacre a well designed storage system, by changing its configuration to one they were comforatble with. They called us up and asked why our JackRabbit performance was so terrible. It wasn’t terrible, they just didn’t have the slightest clue as to how to build storage. And this was a supposedly knowledgeable company, doing something terrible with the unit, because they thought they knew what they were doing. And yes, we had to fix it for them
Its possible the hobbyist types could do a better job than this company. More power to them. I don’t think we want to supply that market at this time.
We may eventually figure out a way to service this market. I need to figure out if it is a market, how large it is, and whether or not servicing it makes economic sense.
Until then, we’ll keep building, selling, and supporting some of the fastest storage you can get anywhere. The performance comes in part from the hardware. Crappy hardware begets crappy performance.