Tukukkk

I am trying to see how I can speed up the below script that reports disk_usage. The timed find command towards the end is the problematic line that I am trying to speed up. This script is run on directories that have over 6-7TB of data and it takes 16-18hrs. However I want it to run in under 8hrs. Can someone please suggest alternate ways to modify this script?

# -disk_check.csh takes dir name as a mandatory argument and an options <num> or -verbose as a second argument.

#  Ex1: disk_check <dir_name> - Reports out the disk usage per user and the total disk consumption

#  Ex2: disk_check <dir_name> -verbose -Along with the above, it also lists all files by size in the given directory

#  Ex3: disk_check <dir_name> -<num> -Similar to Ex2, But here it reports out the top <num> files by size in the given directory





if ($#argv == 0) then

    echo " Error : Dir path missing"

    echo " Syntax : disk_check <dir-name> <verbose>"

    echo "          verbose gives a list of all files per individual sorted by size" 

    exit 0 

endif



set cwd = $argv[1]

if ($cwd =~ "-help") then

    echo " Error : Dir path missing"

    echo " Syntax : disk_check <dir-name> <-verbose>"

    echo "          -verbose gives a list of all files per individual sorted by size" 

    exit 0

endif



if ($#argv > 1) then

    set opt = $argv[2]

#echo "opt : $opt"

endif



if ( -d $cwd ) then



set ava = `df -h $cwd | tail -1 | awk '{print $1'}`

set tot = `df -h $cwd | tail -1 | awk '{print $2'}`

set ad = `df -h $cwd | tail -1 | awk '{print $3'}`

set pcu = `df -h $cwd | tail -1 | awk '{print $4'}`



echo ""

echo "Summary for dir ${cwd}: $tot Used (${pcu})"

echo "-----------------------------------------------------------------------------"

echo " Total Volume $ava"

echo " Available on disk $ad "

echo " Percentage used $pcu"

echo ""

echo "Summary by User:"

printf "%sUser%15sSize%10sCountn" ""

echo "---------------------------------------------"



# This is the command that takes a long time:

time find $cwd -type f -printf "%u %sn" | awk '{user[$1]+=$2;count[$1]++}; END{ for( i in user) printf "%s%-13s%5s%-0.2f%s%5s%7sn","", i, "", user[i]/1024**3,"GB", "", count[i]}'| sort -nk2 -r





if ($#argv > 1) then

    if ($opt =~ "-verbose") then

        echo "nDetail, Sorted by size"

        printf " User%15sFile%15sSizen" ""

        echo "---------------------------------------------------"

        find $cwd -type f -not -path '*/.*'  -printf "%-13u | %-50p | %-10s n" | sort -nk5 -r 

endif