Ok, I am make another experiment. I am buy new HDD and format it with btrfs file system. Also I increased size of grep data and make bash script wich automate testing:
#!/bin/bash #For testing on windows machine #grep_path='/cygdrive/e/Sources/inside' #For testing on new HDD #grep_path='/run/media/mikhail/eaa531cd-25f4-4e00-b31f-22665faa9768/sources/inside' #For testing in real life grep_path='/home/mikhail/sources/inside' command="grep -rn 'float:left;display: block;height: 24px;line-height: 1.2em;position: relative;text-align: center;white-space: nowrap;width: 80px;' '$grep_path'" log_file='res.log' exec 3>&1 1>>${log_file} 2>&1 while [ 1 = 1 ] do (( count++ )) echo "PASS: $count" at `date +"%T"` | tee /dev/fd/3 echo $command | tee /dev/fd/3 eval "{ time $command > /dev/null; } |& tee /dev/fd/3" done And get very interesting results: Linux btrfs with NEW HDD: 6.441s (result as in syntetic tests) Linux btrfs with real data HDD (used 94%): 16m52.036s Very bad why??? Data are same with first variant. Windows ntfs NEW HDD: 1m27.643s I am really disappointed why in real life (home folder) have so bad results It's possible HDD which is used 94% optimise speed as on empty hard drive? Both hard disk are same. This is ST4000NM0033-9ZM170. -- Best Regards, Mike Gavrilov.