From 0b3827f3e5ab7cd715da89c50d8fffb79b4191c7 Mon Sep 17 00:00:00 2001
From: Hayden Bilbo <haydenbilbo@gmail.com>
Date: Mon, 14 Oct 2024 23:01:24 -0500
Subject: [PATCH] Added script to rebalance hardlinked files. This one requires
 both directories as inputs. Modified original zfs-inplace-rebalance.sh script
 to only process non hard-linked files.

---
 notes.txt                   |  41 ++++++++++++
 testing-hardlinks.sh        | 127 ++++++++++++++++++++++++++++++++++++
 zfs-hardlink-rebalancing.sh | 104 ++++++++++++++---------------
 zfs-inplace-rebalancing.sh  |  75 ++++++++-------------
 4 files changed, 243 insertions(+), 104 deletions(-)
 create mode 100644 notes.txt
 create mode 100755 testing-hardlinks.sh

diff --git a/notes.txt b/notes.txt
new file mode 100644
index 0000000..fc427b7
--- /dev/null
+++ b/notes.txt
@@ -0,0 +1,41 @@
+ZFS Rebalancing Script
+
+Modifications to original reblancing script
+1. Take two directory inputs to script call which contain the two locations of hardlinks. e.g. /data/media/movies and /data/torrents/movies
+	- These MUST be in the order /data/torrents/movies, then /data/media/movies
+2. Loop through each subdirectory, if input is a file then store it with the torrent full path name as "sourcefile"
+3. Function to check if the source file is a hardlink
+
+# Function to check if a file is a hard link
+is_hardlink() {
+    local file="$1"
+    local link_count=$(stat -c '%h' "$file")
+
+    # If the link count is greater than 1, it is a hard link
+    if [ "$link_count" -gt 1 ]; then
+        return 0  # True
+    else
+        return 1  # False
+    fi
+}
+
+4. Continue on if so
+
+# Main script
+sourcefile="torrent file path"
+
+if is_hardlink "$sourcefile"; then
+    # Proceed with further actions here
+fi
+
+3. Get inode value of torrent file
+   `inode_val=$(ls -i $sourcefile | awk '{print $1}')`
+4. Find files in media directory that match this inode
+   `filepath=$(find /data/media/movies/ -inum $test)`
+6. Remove the media hardlink
+   `rm "$filepath"`
+7. Run rebalance process on torrent hardlink
+8. Recreate the media hardlink
+   `ln "$sourcefile" "$filepath" 
+9. Proceed to next file
+10. ONLY PERFORM THIS PROCESS ON THE FIRST (e.g. /data/media/movies) DIRECTORY
diff --git a/testing-hardlinks.sh b/testing-hardlinks.sh
new file mode 100755
index 0000000..d60ec75
--- /dev/null
+++ b/testing-hardlinks.sh
@@ -0,0 +1,127 @@
+#!/usr/bin/env bash
+
+# exit script on error
+set -e
+# exit on undeclared variable
+set -u
+
+# file used to track processed files
+rebalance_db_file_name="rebalance_db.txt"
+
+# index used for progress
+current_index=0
+
+## Color Constants
+
+# Reset
+Color_Off='\033[0m'       # Text Reset
+
+# Regular Colors
+Red='\033[0;31m'          # Red
+Green='\033[0;32m'        # Green
+Yellow='\033[0;33m'       # Yellow
+Cyan='\033[0;36m'         # Cyan
+
+## Functions
+
+# print a help message
+function print_usage() {
+  echo "Usage: zfs-inplace-rebalancing --checksum true --passes 1 /data/source /data/dest"
+}
+
+# print a given text entirely in a given color
+function color_echo () {
+    color=$1
+    text=$2
+    echo -e "${color}${text}${Color_Off}"
+}
+
+
+function get_rebalance_count () {
+    file_path=$1
+
+    line_nr=$(grep -xF -n "${file_path}" "./${rebalance_db_file_name}" | head -n 1 | cut -d: -f1)
+    if [ -z "${line_nr}" ]; then
+        echo "0"
+        return
+    else
+        rebalance_count_line_nr="$((line_nr + 1))"
+        rebalance_count=$(awk "NR == ${rebalance_count_line_nr}" "./${rebalance_db_file_name}")
+        echo "${rebalance_count}"
+        return
+    fi
+}
+
+# rebalance a specific file
+function rebalance () {
+    file_path=$1
+    hardlink_dir=$2
+    hardlink_count=$(stat -c "%h" "${file_path}")
+    
+    echo "File path: $file_path"
+
+    # Find other hardlinked file and remove it
+    inode_val=$(ls -i "$file_path" | awk '{print $1}')
+    hardlink_path=$(find "$hardlink_dir" -inum $inode_val)
+
+    echo "inode Value: $inode_val"
+    echo "Hardlinked File: $hardlink_path"
+}
+
+checksum_flag='true'
+passes_flag='1'
+
+if [[ "$#" -ne 2 ]]; then
+    print_usage
+    exit 0
+fi
+
+while true ; do
+    case "$1" in
+        -h | --help )
+            print_usage
+            exit 0
+        ;;
+        -c | --checksum )
+            if [[ "$2" == 1 || "$2" =~ (on|true|yes) ]]; then
+                checksum_flag="true"
+            else
+                checksum_flag="false"
+            fi
+            shift 2
+        ;;
+        -p | --passes )
+            passes_flag=$2
+            shift 2
+        ;;
+        *)
+            break
+        ;;
+    esac 
+done;
+
+source_path=$1
+dest_path=$2
+
+color_echo "$Cyan" "Start rebalancing $(date):"
+color_echo "$Cyan" "  Rebalance Path: ${source_path}"
+color_echo "$Cyan" "  Hardlink Path: ${dest_path}"
+color_echo "$Cyan" "  Rebalancing Passes: ${passes_flag}"
+color_echo "$Cyan" "  Use Checksum: ${checksum_flag}"
+
+# count number of hardlinked files
+file_count=$(find "${source_path}" -type f -links 2 | wc -l)
+
+color_echo "$Cyan" "  File count: ${file_count}"
+
+# create db file
+if [ "${passes_flag}" -ge 1 ]; then
+    touch "./${rebalance_db_file_name}"
+fi
+
+# recursively scan through files and execute "rebalance" procedure if the file is a hardlink
+find "$source_path" -type f -links 2 -print0 | while IFS= read -r -d '' file; do rebalance "$file" "$dest_path"; done
+
+echo ""
+echo ""
+color_echo "$Green" "Done!"
diff --git a/zfs-hardlink-rebalancing.sh b/zfs-hardlink-rebalancing.sh
index b9fe6ce..d7564be 100755
--- a/zfs-hardlink-rebalancing.sh
+++ b/zfs-hardlink-rebalancing.sh
@@ -26,7 +26,7 @@ Cyan='\033[0;36m'         # Cyan
 
 # print a help message
 function print_usage() {
-  echo "Usage: zfs-inplace-rebalancing --checksum true --skip-hardlinks false --passes 1 /my/pool"
+  echo "Usage: zfs-inplace-rebalancing --checksum true --passes 1 /data/source /data/dest"
 }
 
 # print a given text entirely in a given color
@@ -55,37 +55,36 @@ function get_rebalance_count () {
 # rebalance a specific file
 function rebalance () {
     file_path=$1
+    hardlink_dir=$2
 
-    # check if file has >=2 links in the case of --skip-hardlinks
-    # this shouldn't be needed in the typical case of `find` only finding files with links == 1
+    # check if file has exactly 2 links
+    # this shouldn't be needed in the typical case of `find` only finding files with links == 2
     # but this can run for a long time, so it's good to double check if something changed
-    if [[ "${skip_hardlinks_flag,,}" == "true"* ]]; then
-	if [[ "${OSTYPE,,}" == "linux-gnu"* ]]; then
-	    # Linux
-	    #
-	    #  -c  --format=FORMAT
-	    #      use the specified FORMAT instead of the default; output a
-	    #      newline after each use of FORMAT
-	    #  %h     number of hard links
-
-	    hardlink_count=$(stat -c "%h" "${file_path}")
-	elif [[ "${OSTYPE,,}" == "darwin"* ]] || [[ "${OSTYPE,,}" == "freebsd"* ]]; then
-	    # Mac OS
-	    # FreeBSD
-	    #  -f format
-	    #  Display information using the specified format
-	    #   l       Number of hard links to file (st_nlink)
-
-	    hardlink_count=$(stat -f %l "${file_path}")
-	else
-		echo "Unsupported OS type: $OSTYPE"
-		exit 1
-	fi
-
-	if [ "${hardlink_count}" -ge 2 ]; then
-            echo "Skipping hard-linked file: ${file_path}"
-            return
-        fi
+    if [[ "${OSTYPE,,}" == "linux-gnu"* ]]; then
+        # Linux
+        #
+        #  -c  --format=FORMAT
+        #      use the specified FORMAT instead of the default; output a
+        #      newline after each use of FORMAT
+        #  %h     number of hard links
+    
+        hardlink_count=$(stat -c "%h" "${file_path}")
+    elif [[ "${OSTYPE,,}" == "darwin"* ]] || [[ "${OSTYPE,,}" == "freebsd"* ]]; then
+        # Mac OS
+        # FreeBSD
+        #  -f format
+        #  Display information using the specified format
+        #   l       Number of hard links to file (st_nlink)
+    
+        hardlink_count=$(stat -f %l "${file_path}")
+    else
+    	echo "Unsupported OS type: $OSTYPE"
+    	exit 1
+    fi
+    
+    if [ "${hardlink_count}" -ne 2 ]; then
+        echo "Skipping non hard-linked file: ${file_path}"
+        return
     fi
 
     current_index="$((current_index + 1))"
@@ -108,6 +107,13 @@ function rebalance () {
     tmp_extension=".balance"
     tmp_file_path="${file_path}${tmp_extension}"
 
+    # Find other hardlinked file and remove it
+    inode_val=$(ls -i "${file_path}" | awk '{print $1}')
+    hardlink_path=$(find "${hardlink_dir}" -inum ${inode_val})
+    echo "Removing hardlink '${hardlink_path}'..."
+    rm "${hardlink_path}"
+
+    # Continue with rebalance
     echo "Copying '${file_path}' to '${tmp_file_path}'..."
     if [[ "${OSTYPE,,}" == "linux-gnu"* ]]; then
         # Linux
@@ -190,6 +196,9 @@ function rebalance () {
     echo "Renaming temporary copy to original '${file_path}'..."
     mv "${tmp_file_path}" "${file_path}"
 
+    echo "Recreating deleted hardlink '${hardlink_path}'..."
+    ln "$file_path" "$hardlink_path"
+
     if [ "${passes_flag}" -ge 1 ]; then
         # update rebalance "database"
         line_nr=$(grep -xF -n "${file_path}" "./${rebalance_db_file_name}" | head -n 1 | cut -d: -f1)
@@ -206,10 +215,9 @@ function rebalance () {
 }
 
 checksum_flag='true'
-skip_hardlinks_flag='false'
 passes_flag='1'
 
-if [[ "$#" -eq 0 ]]; then
+if [[ "$#" -ne 2 ]]; then
     print_usage
     exit 0
 fi
@@ -228,14 +236,6 @@ while true ; do
             fi
             shift 2
         ;;
-        --skip-hardlinks )
-            if [[ "$2" == 1 || "$2" =~ (on|true|yes) ]]; then
-                skip_hardlinks_flag="true"
-            else
-                skip_hardlinks_flag="false"
-            fi
-            shift 2
-        ;;
         -p | --passes )
             passes_flag=$2
             shift 2
@@ -246,20 +246,17 @@ while true ; do
     esac 
 done;
 
-root_path=$1
+source_path=$1
+dest_path=$2
 
 color_echo "$Cyan" "Start rebalancing $(date):"
-color_echo "$Cyan" "  Path: ${root_path}"
+color_echo "$Cyan" "  Rebalance Path: ${source_path}"
+color_echo "$Cyan" "  Hardlink Path: ${dest_path}"
 color_echo "$Cyan" "  Rebalancing Passes: ${passes_flag}"
 color_echo "$Cyan" "  Use Checksum: ${checksum_flag}"
-color_echo "$Cyan" "  Skip Hardlinks: ${skip_hardlinks_flag}"
 
-# count files
-if [[ "${skip_hardlinks_flag,,}" == "true"* ]]; then
-    file_count=$(find "${root_path}" -type f -links 1 | wc -l)
-else
-    file_count=$(find "${root_path}" -type f | wc -l)
-fi
+# count number of hardlinked files
+file_count=$(find "${source_path}" -type f -links 2 | wc -l)
 
 color_echo "$Cyan" "  File count: ${file_count}"
 
@@ -268,13 +265,8 @@ if [ "${passes_flag}" -ge 1 ]; then
     touch "./${rebalance_db_file_name}"
 fi
 
-# recursively scan through files and execute "rebalance" procedure
-# in the case of --skip-hardlinks, only find files with links == 1
-if [[ "${skip_hardlinks_flag,,}" == "true"* ]]; then
-    find "$root_path" -type f -links 1 -print0 | while IFS= read -r -d '' file; do rebalance "$file"; done
-else
-    find "$root_path" -type f -print0 | while IFS= read -r -d '' file; do rebalance "$file"; done
-fi
+# recursively scan through files and execute "rebalance" procedure if the file is a hardlink
+find "${source_path}" -type f -links 2 -print0 | while IFS= read -r -d '' file; do rebalance "${file}" "${dest_path}"; done
 
 echo ""
 echo ""
diff --git a/zfs-inplace-rebalancing.sh b/zfs-inplace-rebalancing.sh
index b9fe6ce..c29d246 100755
--- a/zfs-inplace-rebalancing.sh
+++ b/zfs-inplace-rebalancing.sh
@@ -26,7 +26,7 @@ Cyan='\033[0;36m'         # Cyan
 
 # print a help message
 function print_usage() {
-  echo "Usage: zfs-inplace-rebalancing --checksum true --skip-hardlinks false --passes 1 /my/pool"
+  echo "Usage: zfs-inplace-rebalancing --checksum true --passes 1 /my/pool"
 }
 
 # print a given text entirely in a given color
@@ -56,36 +56,34 @@ function get_rebalance_count () {
 function rebalance () {
     file_path=$1
 
-    # check if file has >=2 links in the case of --skip-hardlinks
+    # check if file has >=2 links
     # this shouldn't be needed in the typical case of `find` only finding files with links == 1
     # but this can run for a long time, so it's good to double check if something changed
-    if [[ "${skip_hardlinks_flag,,}" == "true"* ]]; then
-	if [[ "${OSTYPE,,}" == "linux-gnu"* ]]; then
-	    # Linux
-	    #
-	    #  -c  --format=FORMAT
-	    #      use the specified FORMAT instead of the default; output a
-	    #      newline after each use of FORMAT
-	    #  %h     number of hard links
+    if [[ "${OSTYPE,,}" == "linux-gnu"* ]]; then
+        # Linux
+        #
+        #  -c  --format=FORMAT
+        #      use the specified FORMAT instead of the default; output a
+        #      newline after each use of FORMAT
+        #  %h     number of hard links
 
-	    hardlink_count=$(stat -c "%h" "${file_path}")
-	elif [[ "${OSTYPE,,}" == "darwin"* ]] || [[ "${OSTYPE,,}" == "freebsd"* ]]; then
-	    # Mac OS
-	    # FreeBSD
-	    #  -f format
-	    #  Display information using the specified format
-	    #   l       Number of hard links to file (st_nlink)
+        hardlink_count=$(stat -c "%h" "${file_path}")
+    elif [[ "${OSTYPE,,}" == "darwin"* ]] || [[ "${OSTYPE,,}" == "freebsd"* ]]; then
+        # Mac OS
+        # FreeBSD
+        #  -f format
+        #  Display information using the specified format
+        #   l       Number of hard links to file (st_nlink)
 
-	    hardlink_count=$(stat -f %l "${file_path}")
-	else
-		echo "Unsupported OS type: $OSTYPE"
-		exit 1
-	fi
+        hardlink_count=$(stat -f %l "${file_path}")
+    else
+    	echo "Unsupported OS type: $OSTYPE"
+    	exit 1
+    fi
 
-	if [ "${hardlink_count}" -ge 2 ]; then
-            echo "Skipping hard-linked file: ${file_path}"
-            return
-        fi
+    if [ "${hardlink_count}" -ge 2 ]; then
+        echo "Skipping hard-linked file: ${file_path}"
+        return
     fi
 
     current_index="$((current_index + 1))"
@@ -206,7 +204,6 @@ function rebalance () {
 }
 
 checksum_flag='true'
-skip_hardlinks_flag='false'
 passes_flag='1'
 
 if [[ "$#" -eq 0 ]]; then
@@ -228,14 +225,6 @@ while true ; do
             fi
             shift 2
         ;;
-        --skip-hardlinks )
-            if [[ "$2" == 1 || "$2" =~ (on|true|yes) ]]; then
-                skip_hardlinks_flag="true"
-            else
-                skip_hardlinks_flag="false"
-            fi
-            shift 2
-        ;;
         -p | --passes )
             passes_flag=$2
             shift 2
@@ -252,14 +241,9 @@ color_echo "$Cyan" "Start rebalancing $(date):"
 color_echo "$Cyan" "  Path: ${root_path}"
 color_echo "$Cyan" "  Rebalancing Passes: ${passes_flag}"
 color_echo "$Cyan" "  Use Checksum: ${checksum_flag}"
-color_echo "$Cyan" "  Skip Hardlinks: ${skip_hardlinks_flag}"
 
 # count files
-if [[ "${skip_hardlinks_flag,,}" == "true"* ]]; then
-    file_count=$(find "${root_path}" -type f -links 1 | wc -l)
-else
-    file_count=$(find "${root_path}" -type f | wc -l)
-fi
+file_count=$(find "${root_path}" -type f -links 1 | wc -l)
 
 color_echo "$Cyan" "  File count: ${file_count}"
 
@@ -268,13 +252,8 @@ if [ "${passes_flag}" -ge 1 ]; then
     touch "./${rebalance_db_file_name}"
 fi
 
-# recursively scan through files and execute "rebalance" procedure
-# in the case of --skip-hardlinks, only find files with links == 1
-if [[ "${skip_hardlinks_flag,,}" == "true"* ]]; then
-    find "$root_path" -type f -links 1 -print0 | while IFS= read -r -d '' file; do rebalance "$file"; done
-else
-    find "$root_path" -type f -print0 | while IFS= read -r -d '' file; do rebalance "$file"; done
-fi
+# recursively scan through files and execute "rebalance" procedure on files with links == 1
+find "$root_path" -type f -links 1 -print0 | while IFS= read -r -d '' file; do rebalance "$file"; done
 
 echo ""
 echo ""