Ah... yes...

but what happens when the house plumber does not understand the materials and tools he is using? 3 months later... poooooofffff... water all over the place.

sizzle, spark, kawoff.... the whole house is in flame from the electrical short circuits caused by all the water on the electric wiring done by the unqualified electricians.

The nasty truth is that you will never design the underlying stuff well without having a decent knowledge of how it is used, and you can never use things well without having a decent understanding of how things works (with some limitations of course, I don't expect you to know assembly code of the windows bootstrap to be able to use Word well).

Unless you are making some extremely teoretical scenario, in which case the I/O is not really random anymore, you will still statistically hit some data in cache and you will hit more the more cache you have vs. data. For instance, if your cache i larger than the data, then random I/O will be 100% cacheable... Also, while the read might have low cache hit rates (which is more correct than saying it is not cachable), a NVram cache can still give you great benefits on writes as it might open for better write scheduling. That is, you can delay the flush to disk and coordinate that better with head movements which can significantly speed up things.

How long until we see a mass movement of hosting facilities to other states and countries? This is really scary. I don't mind the fact that hosting facilities are now liable a lot more than before, but the court just _forced_ hosting providers to become judges of who is in breach or not of copyright. No sane hosting provider will ever protect its customer from for instance the laywers of MS. Practically any content you have can, one way or the other, be twisted into a copyright infringement by a clever lawyer. You can be shut down at any time without any chance to protect yourself. Yikes!

Having low cost chinese programmers do this is probably the only way they can stay within budget....

Can you imagine all the cool new possibilities for iphone games if they make this available from applications? Dive down to 100 meters to save Nemo Cooking game where you need to show that you put the owen at 200C for 25 minutes Car wrecking game where you get extra crash bonus if your phone hits certain Gs. Possibilities are endless!

who on earth wants to break into your house anyway? Now... some hacked keyboards at NSA, whitehouse or pentagon which can snoop interesting stuff without any traceable changes to OS or the HW except some codelines in the firmware, then we are talking. Serviceman comes in one day, replace keyboard with a hacked unit. Finds an excuse to come back a bit later to pick it up again including data.

Only if the complete source for what you are selling is available to everybody (and you state that it already is).

If all that is good, I think the response should really be that if you need to recover your cost, then you should of course be able to do that. However if anyone wants wants to make binaries available for free, then they can always compile the source themselves and make a free app available on app store or offer it through on of the installers available on jailbroken phones.

Much more annoying is the fact that you will start flashing once the infection finds the answer!

Nothing new here.

Anyone seriously into benchmarking or high performance applications would know that raid controllers has been a bigger bottleneck than the harddrives for ages already.

It's just the last 2-3 years or so that you have gotten raid controllers fast enough to properly deal with the performance of the 6 tp 8 15k rpm drives that a normal 2U server can hold, and still today, many of the server raid cards out there still cannot do this.

Raid card performance has easily been the biggest differentiator on server performance for anyone that needed a reasonable amount of I/O capacity on their servers. Most servers have been reasonably equal in terms of memory and network performance. After all, they are all built around a very limited number of CPU and chipset architectures and there is only so much that can different there and it is a long time since gigabit network HW for server did not manage to fill a gigabit link.

Raid cards on the other side has major differences in architecture, software and processors. Proper HW raids are basically small computers on a card. They got their own CPU, memory and OS. This isolate them from the host they are plugged into and protect the data even if the host crash (the raid card will normally not crash and has all data in the battery backed up cache, which means a great deal for critical data and massively reduces the chances that you need to do consistency checks/validation and rebuilds after a crash on the host server which is equally important for a server).

Unfortunately as a result of all that extra complexity, you also get the potential for large performance variations between different raid cards.

When that is said, a good quality raid card now definately help on performance in most scenarios and easily outperforms software raids for most server usage that includes a reasonable amount of writing as long as you got that battery backup on your cache so you can safely enable write back caching.

Just do your homework and make sure you get a good card when you shop. The better cards can easily be 2-3x faster than the worst.

And what exactly is the temperature of a space rabbit anyway?

Problem is... there arent really that many ships out there with proper equipment for this type of work (multi beam echo sounders and and sonarts for quality mapping of the ocean floor) and if someone went out there to rent 100 ships for 2 years, there would be a significant shortage of surveying vessels for everybody.

Prices would head towards infinity and beyond faster than the US gov could print money to pay with.

On the positive side, you would need a lot of additional people. You would need quality positioning data for places which do not have it today (basically, differential GPS reference stations) and you would need satcom to collect the data in real time so the ships did not need to stop surveying to offload data and did not get too far away from the survey area before the data had been through proper quality control.

That is, you also need staff to work around the clock processing the massive amounts of data you would get.

You will also need equipment specialized for shallow waters where ships normally cannot go without high risk (corals reefs for instance). Probably smaller boats that can be operated from a larger mother ship or helicopters.

The article simplifies this a lot. The real cost of mapping the entire ocean floor without gaps would most certainly be much higher than 2 billion usd.

Not to mention that many countries would never let a foreign power go into their territorial waters and do detailed charting of the seafloor. Both for military reasons and because things like exact positions of wrecks are often classified because they do not want crazy divers all over the place looting.

On the other side... I am willing to bet that both US Navy and Russian Navy are sitting on a bunch of highly classified charts of significant chunks of the ocean floor for use on their subs.