Wall time is the "real-world" metric of performance. It tells you how long a process takes in the eyes of a human observer. While CPU time tells you how hard the computer worked, wall time tells you how long you had to wait—making it perhaps the most critical metric for efficiency and productivity in the digital age.
In cloud computing, data traveling between servers adds significant wall time. Measuring Wall Time in Programming wall time
In software development and high-performance computing (HPC), wall time is the ultimate measure of Wall time is the "real-world" metric of performance
For reproducible benchmarks, use CPU time. For user-facing performance, measure wall time under realistic load. In cloud computing, data traveling between servers adds
If you run a task on 10 different processor cores simultaneously, the "CPU time" is the sum of work done by all 10 cores. However, because they worked at the same time, the "Wall time" might only be one-tenth of that total. This is the primary goal of multi-threading: keeping CPU time high (utilizing all resources) while driving wall time as low as possible.
Think of it literally: if you started a program and looked at a physical clock on your office wall, then looked again when the program finished, the difference between those two times is the wall time. It measures the total elapsed "human" time, including every second spent waiting for data, performing calculations, or even idling while other programs run. Wall Time vs. CPU Time: The Great Distinction