ctdb 1.11+git20111102-2 / usr / bin / ctdb_diagnostics

#!/bin/sh
# a script to test the basic setup of a CTDB/Samba install 
# tridge@samba.org September 2007
# martin@meltin.net August 2010

usage ()
{
    cat >&2 <<EOF
Usage: ctdb_diagnostics [OPTION] ...
  options:
    -n <nodes>  Comma separated list of nodes to operate on
    -c          Ignore comment lines (starting with '#') in file comparisons
    -w          Ignore whitespace in file comparisons
    --no-ads    Do not use commands that assume an Active Directory Server
EOF
    exit 1

}

nodes=$(ctdb listnodes -Y | cut -d: -f2)
bad_nodes=""
diff_opts=
no_ads=false

parse_options ()
{
    temp=$(getopt -n "ctdb_diagnostics" -o "n:cwh" -l no-ads,help -- "$@")

    [ $? != 0 ] && usage

    eval set -- "$temp"

    while true ; do
	case "$1" in
	    -n) nodes=$(echo "$2" | sed -e 's@,@ @g') ; shift 2 ;;
	    -c) diff_opts="${diff_opts} -I ^#.*" ; shift ;;
	    -w) diff_opts="${diff_opts} -w" ; shift ;;
	    --no-ads) no_ads=true ; shift ;;
	    --) shift ; break ;;
	    -h|--help|*) usage ;;
	esac
    done

    [ $# -ne 0 ] && usage
}

parse_options "$@"

# Use 5s ssh timeout if EXTRA_SSH_OPTS doesn't set a timeout.
case "$EXTRA_SSH_OPTS" in
    *ConnectTimeout=*) : ;;
    *)
	export EXTRA_SSH_OPTS="${EXTRA_SSH_OPTS} -o ConnectTimeout=5"
esac

# Filter nodes.  Remove any nodes we can't contact from $node and add
# them to $bad_nodes.
_nodes=""
for _i in $nodes ; do
    if onnode $_i true >/dev/null 2>&1 ; then
	_nodes="${_nodes}${_nodes:+ }${_i}"
    else
	bad_nodes="${bad_nodes}${bad_nodes:+,}${_i}"
    fi
done
nodes="$_nodes"

nodes_comma=$(echo $nodes | sed -e 's@[[:space:]]@,@g')

PATH="$PATH:/sbin:/usr/sbin:/usr/lpp/mmfs/bin"

# list of config files that must exist and that we check are the same 
# on the nodes
CONFIG_FILES_MUST="/etc/krb5.conf /etc/hosts /etc/ctdb/nodes /etc/default/ctdb /etc/resolv.conf /etc/nsswitch.conf /etc/sysctl.conf /etc/samba/smb.conf /etc/fstab /etc/multipath.conf /etc/pam.d/system-auth /etc/default/nfs /etc/exports /etc/vsftpd/vsftpd.conf"

# list of config files that may exist and should be checked that they
# are the same on the nodes
CONFIG_FILES_MAY="/etc/ctdb/public_addresses /etc/ctdb/static-routes"

2>&1

cat <<EOF
--------------------------------------------------------------------
ctdb_diagnostics starting. This script will gather information about
your ctdb cluster. You should send the output of this script along
with any ctdb or clustered Samba bug reports.
--------------------------------------------------------------------
EOF

date

error() {
    msg="$1"
    echo "ERROR: $msg"
    NUM_ERRORS=`expr $NUM_ERRORS + 1`
    echo " ERROR[$NUM_ERRORS]: $msg" >> $ERRORS
}

show_file() {
    fname="$1"
    echo "  ================================"
    echo "  File: $fname"
    echo "  `ls -l $fname 2>&1`"
    cat "$fname" 2>&1 | sed 's/^/  /'
    echo "  ================================"
}

show_all() {
    echo "running $1 on nodes $nodes_comma"
    onnode $nodes_comma "hostname; date; $1 2>&1 | sed 's/^/  /'" 2>&1
}

show_and_compare_files () {

    fmt="$1" ; shift

    for f ; do

	first=true

	for n in $nodes ; do

	    if $first ; then
		onnode $n [ -r "$f" ] || {
		    msg=$(printf "$fmt" "$f" $n)
		    error "$msg"
		    continue 2;
		}

		fstf=/tmp/`basename $f`.node$n
		onnode $n cat $f > $fstf 2>&1

		echo "  ================================"
		echo "  File (on node $n): $f"
		echo "  `onnode $n ls -l $f 2>&1`"
		cat "$fstf" | sed 's/^/  /'
		echo "  ================================"
		first=false
	    else
		echo "Testing for same config file $f on node $n"
		tmpf=/tmp/`basename $f`.node$n
		onnode $n cat $f > $tmpf 2>&1
		diff $diff_opts $fstf $tmpf >/dev/null 2>&1 || {
		    error "File $f is different on node $n"
		    diff -u $diff_opts $fstf $tmpf
		}
		rm -f $tmpf
	    fi
	done

	rm -f $fstf
    done
}

ERRORS="/tmp/diag_err.$$"
NUM_ERRORS=0

cat <<EOF
Diagnosis started on these nodes:
$nodes_comma
EOF

if [ -n "$bad_nodes" ] ; then
    cat <<EOF

NOT RUNNING DIAGNOSTICS on these uncontactable nodes:
$bad_nodes
EOF

fi

cat <<EOF

For reference, here is the nodes file on the current node...
EOF

show_file /etc/ctdb/nodes

cat <<EOF
--------------------------------------------------------------------
Comping critical config files on nodes $nodes_comma
EOF

show_and_compare_files \
    "%s is missing on node %d" \
    $CONFIG_FILES_MUST

show_and_compare_files \
    "Optional file %s is not present on node %d" \
    $CONFIG_FILES_MAY

cat <<EOF
--------------------------------------------------------------------
Checking for clock drift
EOF
t=`date +%s`
for i in $nodes; do
    t2=`onnode $i date +%s`
    d=`expr $t2 - $t`
    if [ $d -gt 30 -o $d -lt -30 ]; then
	error "time on node $i differs by $d seconds"
    fi
done

cat <<EOF
--------------------------------------------------------------------
Showing software versions
EOF
show_all "uname -a"
[ -x /bin/rpm ] && {
    show_all "rpm -qa | egrep 'samba|ctdb|gpfs'"
}
[ -x /usr/bin/dpkg-query ] && {
    show_all "/usr/bin/dpkg-query --show 'ctdb'"
    show_all "/usr/bin/dpkg-query --show 'samba'"
    #show_all "/usr/bin/dpkg-query --show 'gpfs'"
}


cat <<EOF
--------------------------------------------------------------------
Showing ctdb status and recent log entries
EOF
show_all "ctdb status; ctdb ip"
show_all "ctdb statistics"
show_all "ctdb uptime"

echo "Showing log.ctdb"
show_all "test -f /var/log/log.ctdb && tail -100 /var/log/log.ctdb"

echo "Showing log.ctdb"
show_all "test -f /var/log/log.ctdb && tail -100 /var/log/log.ctdb"

show_all "tail -200 /var/log/messages"
show_all "tail -200 /etc/ctdb/state/vacuum.log"
show_all "ls -lRs /var/ctdb"
show_all "ls -lRs /etc/ctdb"


cat <<EOF
--------------------------------------------------------------------
Showing system and process status
EOF
show_all "df"
show_all "df -i"
show_all "mount"
show_all "w"
show_all "ps axfwu"
show_all "dmesg"
show_all "/sbin/lspci"
show_all "dmidecode"
show_all "cat /proc/partitions"
show_all "cat /proc/cpuinfo"
show_all "cat /proc/scsi/scsi"
show_all "/sbin/ifconfig -a"
show_all "/sbin/ifconfig -a"
show_all "/sbin/ip addr list"
show_all "/sbin/route -n"
show_all "netstat -s"
show_all "free"
show_all "crontab -l"
show_all "sysctl -a"
show_all "iptables -L -n"
show_all "iptables -L -n -t nat"
show_all "/usr/sbin/rpcinfo -p"
show_all "/usr/sbin/showmount -a"
show_all "/usr/sbin/showmount -e"
show_all "/usr/sbin/nfsstat -v"
[ -x /sbin/multipath ] && {
    show_all "/sbin/multipath -ll"
}
[ -x /sbin/chkconfig ] && {
    show_all "/sbin/chkconfig --list"
}
[ -x /usr/sbin/getenforce ] && {
    show_all "/usr/sbin/getenforce"
}
[ -d /proc/net/bonding ] && {
    for f in /proc/net/bonding/*; do
	show_all "cat $f"
    done
}

cat <<EOF
--------------------------------------------------------------------
Showing Samba status
EOF
show_all "smbstatus -n -B"
if $no_ads ; then
    echo
    echo "Skipping \"net ads testjoin\" as requested"
    echo
else
    show_all "net ads testjoin"
fi
show_all "net conf list"
show_all "lsof -n | grep smbd"
show_all "lsof -n | grep ctdbd"
show_all "netstat -tan"
if $no_ads ; then
    echo
    echo "Skipping \"net ads info\" as requested"
    echo
else
    show_all "net ads info"
fi
show_all "date"
show_all "smbclient -U% -L 127.0.0.1"
WORKGROUP=`testparm -s --parameter-name=WORKGROUP 2> /dev/null`
show_all id "$WORKGROUP/Administrator"
show_all "wbinfo -p"
show_all "wbinfo --online-status"
show_all "smbd -b"

date
echo "Diagnostics finished with $NUM_ERRORS errors"

[ -r $ERRORS ] && {
    cat $ERRORS
    rm -f $ERRORS
}
exit $NUM_ERRORS