For a magnetic disk with concentric circular tracks, the seek latency is not linearly proportional to the seek distance due to
non-uniform distribution of requests
arm starting and stopping inertia
higher capacity of tracks on the periphery of the platter
use of unfair arm scheduling policies
Correct option is (B).
The positioning time, or random-access time, consists of two parts: the time necessary to move the disk arm to the desired cylinder, called the seek time, and the time necessary for the desired sector to rotate to the disk head, called the rotational latency.
the seek latency is not linearly proportional to the seek distance due to arm starting and stopping inertia.
According to wiki: http://en.wikipedia.org/wiki/Hard_disk_drive_performance_characteristics#Seek_time
answer should be (B).
Why not use of unfair arm scheduling policies
What if SCAN or LOOK algorithms are used?
The answer cannot be B, latency used by itself is used to refer to rotational latency and not seek time. Even then I find no other option to be suitable.
Note that we are asked “why seek latency is not linearly proportional to the seek distance”, that is why “duration required to travel a distance is not linearly proportional to the distance”. This definitely has to do with either the road surface or road shape. The surface here is uniform magnetic, but road shape does change. Here we don’t take turns, but put break and go on reverse gear, again put break and drive straight. Stopping a moving car takes time, it doesn’t stop instantly. Similarly accelerating stopped car to full speed takes time.
Why not option A: We have not been asked anything related to going to different cities located far from each other.
Why not option B: Tracks might be related with rotational latency / timings but has nothing to do with seek time.
Why not option C: Question is simple. Its just asking why going from one position to another takes different time each time. Policy come in to play when we are asked to read different sectors to decide which sectors to read first (if I am correctly interpreting what is meant by policy).
Feedback for next edition (if ever there's...