DEV Community πŸ‘©β€πŸ’»πŸ‘¨β€πŸ’»

DEV Community πŸ‘©β€πŸ’»πŸ‘¨β€πŸ’» is a community of 968,873 amazing developers

We're a place where coders share, stay up-to-date and grow their careers.

Create account Log in
murugan
murugan

Posted on • Originally published at dev.to

# Golang Profiling

Golang Profiling

Profiling is a form of analyzing the program for optimizable code or functions. In software engineering, it is an essential task since optimization is a key factor when developing an application.
Avoiding memory leaks and optimizing for better performance is almost always a target for enterprise-level software.

Profiling is an important task that cannot be avoided for larger applications. Profiling helps us understand CPU and memory intensive code and helps us write better code for optimization

To create any profile first we need to have a test file. Here we are going to use the Fibonacci function to see profiles of it

// main.go
package main

func Fib2(n int) uint64 {
    if n == 0 {
        return 0
    } else if n == 1 {
        return 1
    } else {
        return Fib2(n-1) + Fib2(n-2)
    }
}

func main() {
    // fmt.Println(Fib2(30)) // 832040
}
Enter fullscreen mode Exit fullscreen mode

Now, the test file is:

// main_test.go
package main

import "testing"

func TestGetVal(t *testing.T) {
    for i := 0; i < 1000; i++ {             // running it a 1000 times
        if Fib2(30) != 832040 {
            t.Error("Incorrect!")
        }
    }
}
Enter fullscreen mode Exit fullscreen mode

Now when we run the go test we got the below output

output:

go test
Pass
Ok
Enter fullscreen mode Exit fullscreen mode

It took almost 7.25s to complete. Now let’s create a CPU profile. We will use this command shown below to generate a profile file.

go test -cpuprofile cpu.prof -bench . 
Enter fullscreen mode Exit fullscreen mode

which will return the below output

PS C:\work\latest\go-tutorial\profile> go test -cpuprofile cpu.prof -bench .
PASS
ok      profile 8.052s
Enter fullscreen mode Exit fullscreen mode

Now, we will view it using the pprof tool. The command will be:

go tool pprof cpu.prof
Enter fullscreen mode Exit fullscreen mode

When we run the above commands we got the below output

PS C:\work\latest\go-tutorial\profile> go tool pprof cpu.prof
Type: cpu
Time: Feb 22, 2022 at 10:53am (IST)
Duration: 7.64s, Total samples = 4.86s (63.60%)
Entering interactive mode (type "help" for commands, "o" for options")
Enter fullscreen mode Exit fullscreen mode

Typing help will show all commands available. We will run the following command

top5 -cum
Enter fullscreen mode Exit fullscreen mode

The topN function shown top N entries and the -cum flag shows the cumulative time taken

(pprof) top5 -cum
Showing nodes accounting for 4700ms, 96.71% of 4860ms total
Dropped 33 nodes (cum <= 24.30ms)
Showing top 5 nodes out of 15
      flat  flat%   sum%        cum   cum%
    4700ms 96.71% 96.71%     4700ms 96.71%  profile.Fib2
         0     0% 96.71%     4700ms 96.71%  profile.TestGetVal
         0     0% 96.71%     4700ms 96.71%  testing.tRunner
         0     0% 96.71%       90ms  1.85%  runtime.mcall
         0     0% 96.71%       90ms  1.85%  runtime.park_m
Enter fullscreen mode Exit fullscreen mode

based on the above results we will optimize our code.

To create a memory profile we simply use this command:

go test -memprofile mem.prof -bench . 
Enter fullscreen mode Exit fullscreen mode

which will return the below output

PS C:\work\latest\go-tutorial\profile> go test -memprofile mem.prof -bench .
PASS
ok      profile 0.644s
Enter fullscreen mode Exit fullscreen mode

We can generate both profiles (main, test) using the following command

go test -cpuprofile cpu.prof -memprofile mem.prof -bench . 
Enter fullscreen mode Exit fullscreen mode

which will return the below output

PS C:\work\latest\go-tutorial\profile> go test -cpuprofile cpu.prof -memprofile mem.prof -bench .
PASS
ok      profile 0.655s 
Enter fullscreen mode Exit fullscreen mode

Top comments (0)

🌚 Browsing with dark mode makes you a better developer by a factor of exactly 40.

It's a scientific fact.