From 7a9a66cc5fb7f06118fab1fc2ae1c43cfbb1178f Mon Sep 17 00:00:00 2001
From: Kotresh HR <khiremat@redhat.com>
Date: Thu, 29 Jan 2015 15:53:19 +0530
Subject: tools: Finds missing files in gluster volume given backend brickpath

The tool finds the missing files in a geo-replication slave volume.
The tool crawls backend .glusterfs of the brickpath, which is passed
as a parameter and stats each entry on slave volume mount to check
the presence of file. The mount used is aux-gfid-mount, hence no path
conversion is required and is fast. The tool needs to be run on every
node in cluster for each brickpath of geo-rep master volume to find
missing files on slave volume. The tool is generic enough and can be
used in non geo-replication context as well.

Most of the crawler code is leverged from Avati's xfind and is modified
to crawl only .glusterfs (https://github.com/avati/xsync)

Thanks Aravinda for scripts to convert gfid to path.

Change-Id: I84deaaaf638f7c571ff1319b67a3440fe27da810
BUG: 1187140
Signed-off-by: Aravinda VK <avishwan@redhat.com>
Signed-off-by: Kotresh HR <khiremat@redhat.com>
Reviewed-on: http://review.gluster.org/9503
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
---
 tools/gfind_missing_files/gfind_missing_files.sh | 119 +++++++++++++++++++++++
 1 file changed, 119 insertions(+)
 create mode 100644 tools/gfind_missing_files/gfind_missing_files.sh

(limited to 'tools/gfind_missing_files/gfind_missing_files.sh')

diff --git a/tools/gfind_missing_files/gfind_missing_files.sh b/tools/gfind_missing_files/gfind_missing_files.sh
new file mode 100644
index 00000000000..07d6befc958
--- /dev/null
+++ b/tools/gfind_missing_files/gfind_missing_files.sh
@@ -0,0 +1,119 @@
+#!/bin/sh
+
+##  Copyright (c) 2015 Red Hat, Inc. <http://www.redhat.com/>
+##  This file is part of GlusterFS.
+##
+##  This file is licensed to you under your choice of the GNU Lesser
+##  General Public License, version 3 or any later version (LGPLv3 or
+##  later), or the GNU General Public License, version 2 (GPLv2), in all
+##  cases as published by the Free Software Foundation.
+
+BRICKPATH=    #Brick path of gluster volume
+SLAVEHOST=    #Slave hostname
+SLAVEVOL=     #Slave volume
+SLAVEMNT=     #Slave gluster volume mount point
+WORKERS=4     #Default number of worker threads
+
+function out()
+{
+    echo "$@";
+}
+
+function fatal()
+{
+    out FATAL "$@";
+    exit 1
+}
+
+function ping_host ()
+{
+    ### Use bash internal socket support
+    {
+        exec 400<>/dev/tcp/$1/$2
+        if [ $? -ne '0' ]; then
+            return 1;
+        else
+            exec 400>&-
+            return 0;
+        fi
+    } 1>&2 2>/dev/null
+}
+
+function mount_slave()
+{
+    local i; # inode number
+    SSH_PORT=22
+
+    SLAVEMNT=`mktemp -d`
+    [ "x$SLAVEMNT" = "x" ] && fatal "Could not mktemp directory";
+    [ -d "$SLAVEMNT" ] || fatal "$SLAVEMNT not a directory";
+
+    ping_host ${SLAVEHOST} $SSH_PORT
+    if [ $? -ne 0 ]; then
+        echo "$SLAVEHOST not reachable.";
+        exit 1;
+    fi;
+
+    glusterfs --volfile-id=$SLAVEVOL --aux-gfid-mount --volfile-server=$SLAVEHOST $SLAVEMNT;
+    i=$(stat -c '%i' $SLAVEMNT);
+    [ "x$i" = "x1" ] || fatal "Could not mount volume $2 on $SLAVEMNT Please check host and volume exists";
+}
+
+function parse_cli()
+{
+    if [[ $# -ne 4 ]]; then
+        echo "Usage: gfind_missing_files <brick-path> <slave-host> <slave-vol> <OUTFILE>"
+        exit 1
+    else
+        BRICKPATH=$1;
+        SLAVEHOST=$2;
+        SLAVEVOL=$3;
+        OUTFILE=$4;
+
+        mount_slave;
+        echo "Slave volume is mounted at ${SLAVEMNT}"
+        echo
+    fi
+}
+
+function main()
+{
+    parse_cli "$@";
+
+    echo "Calling crawler...";
+    path=$(readlink -e $0)
+    $(dirname $path)/gcrawler ${BRICKPATH} ${SLAVEMNT} ${WORKERS} > ${OUTFILE}
+
+    #Clean up the mount
+    umount $SLAVEMNT;
+    rmdir $SLAVEMNT;
+
+    echo "Crawl Complete."
+    num_files_missing=$(wc -l ${OUTFILE} | awk '{print $1}')
+    if [ $num_files_missing -eq 0 ]
+    then
+        echo "Total Missing File Count : 0"
+        exit 0;
+    fi
+
+    echo "gfids of skipped files are available in the file ${OUTFILE}"
+    echo
+    echo "Starting gfid to path conversion"
+
+    #Call python script to convert gfids to full pathname
+    INFILE=$(readlink -e ${OUTFILE})
+    python $(dirname $path)/gfid_to_path.py ${BRICKPATH} ${INFILE} 1> ${OUTFILE}_pathnames 2> ${OUTFILE}_gfids
+    echo "Path names of skipped files are available in the file ${OUTFILE}_pathnames"
+
+    gfid_to_path_failures=$(wc -l ${OUTFILE}_gfids | awk '{print $1}')
+    if [ $gfid_to_path_failures -gt 0 ]
+    then
+       echo "WARNING: Unable to convert some GFIDs to Paths, GFIDs logged to ${OUTFILE}_gfids"
+       echo "Use $(dirname $path)/gfid_to_path.sh <brick-path> ${OUTFILE}_gfids to convert those GFIDs to Path"
+    fi
+
+    #Output
+    echo "Total Missing File Count : $(wc -l ${OUTFILE} | awk '{print $1}')"
+}
+
+main "$@";
-- 
cgit