proper way to do defrag of a mountpoint

Usage: "glusterfs-defrag <MOUNTPOINT>"

there are new features added to distribute with this patch:

* bash# getfattr -n trusted.distribute.linkinfo <file>
  Gives output in the format "<hostname>:<directory>", if there is a
  linkfile present, where hostname is server, directory is backend
  directory where the actual linkfile is present.

* bash# getfattr -n trusted.glusterfs.pathinfo <path>
  Gives layout information if directory, and info about actual
  location of file in backend servers, in the form of
  'hostname:directory'. (TODO: should extend it to all xlators)

* bash# getfattr -n trusted.distribute.fix.layout <path>
  scales out the directory layout in distribute, so when new
  servers are added, layouts are fixed to include them.

* removed 'scale-n-defrag.sh' as its no more required.

* changed 'defrag.sh' to have a feature to specify target bricks,
  so defrag happens to only those nodes. moved the file to
  'glusterfs-defrag', which now gets installed to '${prefix}/bin'

* storage/posix:
  takes new option 'hostname' so it can resolve to same hostname
  given during 'gluster volume create'.
  with 'trusted.glusterfs.pathinfo' posix returns the value in
  'hostname:real_path' format.

Signed-off-by: Amar Tumballi <amar@gluster.com>
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>

BUG: 1073 ('gluster defrag <VOLNAME>' fails in mainline)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1073

5 files changed, 112 insertions, 97 deletions

diff --git a/extras/Makefile.am b/extras/Makefile.am
index c11137143..6ea4744c9 100644
--- a/extras/Makefile.am
+++ b/extras/Makefile.am
@@ -3,6 +3,8 @@ docdir = $(datadir)/doc/glusterfs/
 EditorModedir = $(docdir)/
 EditorMode_DATA = glusterfs-mode.el glusterfs.vim
 
+dist_bin_SCRIPTS = glusterfs-defrag
+
 SUBDIRS = init.d benchmarking volgen
 
 EXTRA_DIST = specgen.scm MacOSX/Portfile glusterfs-mode.el glusterfs.vim migrate-unify-to-distribute.sh backend-xattr-sanitize.sh backend-cleanup.sh defrag.sh scale-n-defrag.sh disk_usage_sync.sh
diff --git a/extras/defrag.sh b/extras/defrag.sh
deleted file mode 100644
index 465b09794..000000000
--- a/extras/defrag.sh
+++ /dev/null
@@ -1,60 +0,0 @@
-#!/bin/sh
-
-# This script gets called from 'scale-n-defrag.sh' script.
-# Don't run this stand alone.
-# 
-#
-
-set -e
-
-CP="cp"
-MV="mv"
-
-scan_dir()
-{
-    path=$1;
-    find "$path" -type f -perm +01000 -exec $0 '{}' \; 
-}
-
-rsync_filename()
-{
-    path=$1
-    dir=$(dirname "$path");
-    file=$(basename "$path");
-
-    echo "$dir/.$file.zr$$";
-}
-
-relocate_file()
-{
-    path=$1;
-    tmp_path=$(rsync_filename "$path");
-
-    pre_mtime=$(stat -c '%Y' "$path");
-    $CP -a "$path" "$tmp_path";
-    post_mtime=$(stat -c '%Y' "$path");
-
-    if [ $pre_mtime = $post_mtime ]; then
-	chmod -t "$tmp_path";
-	$MV "$tmp_path" "$path";
-	echo "file '$path' relocated" 
-    else
-	echo "file '$path' modified during defrag. skipping"
-	rm -f "$tmp_path";
-    fi
-}
-
-main()
-{
-    path="$1";
-
-    if [ -d "$path" ]; then
-	scan_dir "$path";
-    else
-	relocate_file "$@";
-    fi
-
-    usleep 500000 # 500ms
-}
-
-main "$1"
diff --git a/extras/glusterfs-defrag.in b/extras/glusterfs-defrag.in
new file mode 100644
index 000000000..982878bdb
--- /dev/null
+++ b/extras/glusterfs-defrag.in
@@ -0,0 +1,109 @@
+#!/bin/bash
+
+# Please leave 'added_bricks' as empty if you want 100% defrag.
+# If you want to move data to newly added bricks, properly give
+# brick info as "<hostname>:<export-dir>" form (which was given
+# in 'gluster volume create' command)
+# More than one brick can be given with space inbetween.
+
+#
+# (c) 2010 Gluster Inc <http://www.gluster.com/>
+#
+
+set -e;
+
+added_bricks="node1:/gfs/export1"
+
+CP="cp"
+MV="mv"
+
+scan_dir()
+{
+    path=$1;
+    # run defrag on files first #
+    find "$path" -maxdepth 1 -type f -perm +01000 -exec $0 '{}' \;
+
+    for subdir in $(find "$path" -maxdepth 1 -type d | sed 1d); do
+        $0 "$subdir";
+    done
+}
+
+fix_xattr()
+{
+    path=$1;
+    getfattr -n trusted.distribute.fix.layout "$path" 2>/dev/null;
+}
+
+rsync_filename()
+{
+    path=$1
+    dir=$(dirname "$path");
+    file=$(basename "$path");
+
+    echo "$dir/.$file.zr$$";
+}
+
+relocate_file()
+{
+    path=$1;
+    stat_info=$(stat -c '%a' "$path");
+    if [ $stat_info -lt 1000 ] ; then
+        return;
+    fi
+
+    flag=0;
+    linknode=$(getfattr --only-values -n trusted.distribute.linkinfo $path 2>/dev/null);
+    if [ -z $linknode ] ; then
+        return;
+    fi
+
+    for bricks in ${added_bricks}; do
+        current_brick=${linknode:0:${#bricks}};
+        if [ "${bricks}" == "${current_brick}" ]; then
+            flag=1;
+        fi
+    done
+
+    if [ $flag -ne 1 ]; then
+        return;
+    fi
+
+    tmp_path=$(rsync_filename "$path");
+
+    pre_mtime=$(stat -c '%Y' "$path");
+    $CP -a "$path" "$tmp_path";
+    post_mtime=$(stat -c '%Y' "$path");
+
+    if [ $pre_mtime = $post_mtime ]; then
+	chmod -t "$tmp_path";
+	$MV "$tmp_path" "$path";
+	echo "file '$path' relocated"
+    else
+	echo "file '$path' modified during defrag. skipping"
+	rm -f "$tmp_path";
+    fi
+}
+
+defrag_usage()
+{
+    echo "Usage: $0 <directory>"
+}
+
+main()
+{
+    path="$1";
+
+    if [ -z "$path" ]; then
+        defrag_usage;
+        return;
+    fi
+
+    if [ -d "$path" ]; then
+        fix_xattr "$path";
+	scan_dir "$path";
+    else
+	relocate_file "$@";
+    fi
+}
+
+main "$1"
diff --git a/extras/scale-n-defrag.sh b/extras/scale-n-defrag.sh
deleted file mode 100644
index 1031b3931..000000000
--- a/extras/scale-n-defrag.sh
+++ /dev/null
@@ -1,37 +0,0 @@
-#!/bin/sh
-
-# This script runs over the GlusterFS mountpoint (from just one client)
-# to handle the distribution of 'data', after the distribute translator's 
-# subvolumes count changes.
-#
-# (c) 2009 Gluster Inc, <http://www.gluster.com/>
-# 
-# 
-# Make sure the following variables are properly initialized
-
-MOUNTPOINT=/tmp/testdir
-directory_to_be_scaled="${MOUNTPOINT}/"
-
-logdir=$(dirname $0)
-cd $logdir
-LOGDIR=$(pwd)
-cd -
-
-# The below command is enough to make sure the new layout will be scaled across new 
-# nodes.
-find ${directory_to_be_scaled} -type d -exec setfattr -x "trusted.glusterfs.dht" {} \;
-
-# Now do a lookup on files so the scaling/re-hashing is done
-find ${directory_to_be_scaled}  > /dev/null
-
-
-# copy the defrag (to copy data across for new nodes (for linkfiles))
-# 
-
-
-cd ${directory_to_be_scaled};
-for dir in *; do
-        echo "Defragmenting directory ${directory_to_be_scaled}/$dir ($LOGDIR/defrag-store-$dir.log)"
-        $LOGDIR/defrag.sh $dir >> $LOGDIR/defrag-store-$dir.log 2>&1
-        echo Completed directory ${directory_to_be_scaled}/$dir
-done
diff --git a/extras/volgen/CreateVolfile.py b/extras/volgen/CreateVolfile.py
index ca5043a8d..378766cf7 100644
--- a/extras/volgen/CreateVolfile.py
+++ b/extras/volgen/CreateVolfile.py
@@ -270,6 +270,7 @@ class CreateVolfile:
             exp_fd.write ("#   option background-unlink yes # (default: no) boolean type\n")
 
             exp_fd.write ("    option directory %s\n" % export)
+            exp_fd.write ("    option hostname %s\n" % host)
             exp_fd.write ("end-volume\n\n")
 
             if self.nfs: