Following on from the log files article I decided to do some basic perf checks of ruby and python reading text files. The results were a little disapointing - performance was roughly the same, so my ruby log file reading optimisation was complete rot.
Further experimentation required.
ARGV.each do | param |
cc = 0
File.new(param, 'r').each_line do |line|
cc += line.size
end
puts "File has #{cc} characters"
end
Processing /Users/gcb/work/log-analysis/cc.rb ... created /Users/gcb/work/log-analysis/cc.rb.html
|
Realy simple script - and probably the most obvious - add up the length of all the lines in the file.
|
File has 1673435763 characters
real 0m56.035s
user 0m33.873s
sys 0m3.609s
|
ARGV.each do | param |
cc = 0
i = File.open(param, "r")
begin
line = i.readline()
until line.nil?
cc += line.size
line = i.readline()
end
rescue Exception => e
ensure
i.close
end
puts "File has #{cc} characters"
end
Processing /Users/gcb/work/log-analysis/cc1.rb ... created /Users/gcb/work/log-analysis/cc1.rb.html
|
Based on previoud observations this one uses the realine method from the IO library but did not affect the performance.
|
File has 1673435763 characters
real 0m55.569s
user 0m35.506s
sys 0m3.451s
|
import sys
cc = 0
source = open(sys.argv[1])
for line in source:
cc += len(line)
source.close()
print 'file has ', cc, ' characters'
Processing /Users/gcb/work/log-analysis/cc.py ... created /Users/gcb/work/log-analysis/cc.py.html
|
As a benchmark a simple python scrpt - again adding up all the line lengths in the file.
|
file has 1673435763 characters
real 0m53.462s
user 0m23.147s
sys 0m3.781s
|
#include <stdio.h>
int main(int argc, char** argv)
{
int count = 0;
FILE* f = fopen(argv[1], "r");
while (getc(f))
count++;
printf("File has %d characters\n", count);
}
Processing /Users/gcb/work/log-analysis/cc.cpp ... created /Users/gcb/work/log-analysis/cc.cpp.html
|
Baseline written in C++
|
File has 1673392372 characters
real 0m53.167s
user 0m31.473s
sys 0m3.094s
|
#include <stdio.h>
int main(int argc, char** argv)
{
int count = 0;
FILE* f = fopen(argv[1], "r");
char buffer[512];
int read = fread(buffer, 1, 512, f);
while (read > 0) {
count += read;
read = fread(buffer, 1, 512, f);
}
printf("File has %d characters\n", count);
}
Processing /Users/gcb/work/log-analysis/cc1.cpp ... created /Users/gcb/work/log-analysis/cc1.cpp.html
|
A (poor) buffered version of the baseline written in C++
|
File has 1673435763 characters
real 0m52.425s
user 0m1.526s
sys 0m4.473s
|
