I have a simple program to measure floating point multiplication (and random generation, compiles g++ -O0). When running on host (Ubuntu 16.04) it gives ~ 1.6s per 10000000 multiplications, when running in container from image 'ubuntu' (without recompilation) it gives ~3.6s. Can someone explain why it slower in ~2.5 times?

p.s. I got multiple runs of program to get rid of outliers. I do not need to optimize it, just detailed explanation of what is happen there.

test.cpp

#include <cstdio> #include <math.h> #include <chrono> using namespace std; using namespace std::chrono; // timer cribbed from // https://gist.github.com/gongzhitaao/7062087 class Timer { public: Timer() : beg_(clock_::now()) {} void reset() { beg_ = clock_::now(); } double elapsed() const { return duration_cast<second_>(clock_::now() - beg_).count(); } private: typedef high_resolution_clock clock_; typedef duration<double, ratio<1>> second_; time_point<clock_> beg_; }; #define randf() ((double)rand()) / ((double)(RAND_MAX)) double warmup(Timer tmr) { tmr.reset(); for (int i = 0; i < 100000000; i++) { double r1 = randf(); double r2 = randf(); } double elapsed = tmr.elapsed(); return elapsed; } double test(Timer tmr) { double total = 0.0; tmr.reset(); for (int i = 0; i < 100000000; i++) { double r1 = randf(); double r2 = randf(); total += r1*r2; } double elapsed = tmr.elapsed(); return elapsed; } double avg(double* arr) { double res = 0.0; for (int i = 0; i < 10; i++) { res += *(arr + i); } return res / 10; } int main() { double total; int total2; Timer tmr; double warmup_runs[10]; for (int i = 0; i < 10; i++) { warmup_runs[i] = warmup(tmr); printf("warm - %f\n", warmup_runs[i]); } double avg_warmup = avg(warmup_runs); printf("avg warm - %f\n", avg_warmup); const int runs = 10; double result[runs]; for (int i = 0; i < runs; i++) { result[i] = test(tmr); printf("real - %f\n", result[i]); } double avg_result = avg(result); printf("avg real - %f\n", avg_result); printf("d - %f\n", avg_result - avg_warmup); } 

Dockerfile

FROM ubuntu WORKDIR /arythmetics COPY a.out . 

compile g++ -O0 test.cpp

to run inside container I use after build:

docker run -it <container> .bin/bash

.\a.out

UPDATE: after compiling with -static flag, program run time is same in both environments there is another question, why it is practically same? is'n there should be some containerization overhead?