The Elevator Algorithm: Why SSTF Starvation Forced SCAN Scheduling
The Elevator Algorithm: Why SSTF Starvation Forced SCAN Scheduling In magnetic disk storage controllers and enterprise storage arrays, disk access latency is dominated by Seek Time : the mechanical physical movement of the actuator arm across concentric disk cylinders. Operating system disk schedulers reorder pending I/O requests to minimize total head movement. However, naive optimization…
The Elevator Algorithm, also known as SCAN, was developed to address the issue of disk access latency caused by Seek Time in magnetic disk storage controllers and enterprise storage arrays. Traditional disk scheduling algorithms, such as First-Come, First-Served (FCFS) and Shortest Seek Time First (SSTF), optimize for minimizing total head movement but introduce severe starvation issues.
FCFS can result in oscillating head movements, while SSTF can cause requests far from the current head position to starve. To eliminate starvation while preserving high throughput, the SCAN algorithm was adopted, mimicking an architectural elevator by sweeping continuously in one direction and servicing all pending requests along its path.
Upon reaching the end boundary, the actuator arm reverses direction and sweeps backward, ensuring every request is guaranteed service within a bounded maximum of two full disk sweeps.
Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.