Take the 2-minute tour ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.

This is completely hypothetical, and just something I've been curious about. I remember Grace Hopper on Letterman talking about correlating lengths of wire to nano seconds (a certain length of wire was the equivalent of the distance light travels in one nanosecond), and wondered if that could apply to internal components inside a host.

Imagine if I have two hard drives, A and B, where they both exactly the same, only difference is length of cable connecting the two (A has a 20 cm cable, B has a 30 cm one) to the motherboard. Would A have any difference in performance, would it be just slight faster, or is the difference so insignificant that the processor wouldn't be fast enough to notice it?

share|improve this question

closed as primarily opinion-based by CharlieRB, Xavierjazz, digitxp, Ƭᴇcʜιᴇ007, random Jul 29 at 5:14

Many good questions generate some degree of opinion based on expert experience, but answers to this question will tend to be almost entirely based on opinions, rather than facts, references, or specific expertise.If this question can be reworded to fit the rules in the help center, please edit the question.

    
I don't know about IDE/SATA, but length of a data bus can be very important. In the SPI bus, the clock for the data always comes from the master. When clocking data out of the slave at a very high rate, it's possible for the data to arrive at the master's end that is no longer coincident with the clock, causing bad data to be received. This is completely due to the length of wire. –  Steve Jul 23 at 19:23

2 Answers 2

up vote 2 down vote accepted

There would be a difference but that difference is so insignificant that it would not be noticeable to the user or even to a hard drive performance testing program.

The reason there would be a difference is because the information sent back and forth from the hard drive needs to travel an additional 10cm there and 10cm back. Even if that additional time only takes .1ns, that's still an additional .2ns the computer is waiting for the information.

The reason it is too insignificant is because there are many other things that would affect the performance of the drive (fragmentation, background processes, Northbridge/CPU usage) a lot more than waiting a tiny bit longer for information it requested.

share|improve this answer

A length difference of 10cm doesn't matter much, only theoretically. The mechanics of a harddisk affects more.

For some insight:
You will not find cheap USB cables longer than 5 meters.
The longer ones has attached electronics, which is required for reliable operation.

This is due to physical facts, causing the length of the cable degenerate the signal passing through it. Generally: The lover voltages used, the faster the data sent on it and the more complex the cable is, the lesser the distance that it is practical/possible to use it.

Some facts behind it: http://en.wikipedia.org/wiki/Transmission_line
And a warning; there is a lot of maths in it. ;-)

share|improve this answer
    
Oh by the way, the wikipedia page is about radio frequency signals; note that digital signals come close to this as you begin to send at mega and giga-bit rates - and need to transfer a seventh order higher frequency to keep signal integrity. –  Hannu Jul 23 at 20:20

Not the answer you're looking for? Browse other questions tagged or ask your own question.