[mirror_zfs-debian.git] / scripts / zloop.sh

#!/bin/bash

#
# CDDL HEADER START
#
# This file and its contents are supplied under the terms of the
# Common Development and Distribution License ("CDDL"), version 1.0.
# You may only use this file in accordance with the terms of version
# 1.0 of the CDDL.
#
# A full copy of the text of the CDDL should have accompanied this
# source.  A copy of the CDDL is also available via the Internet at
# http://www.illumos.org/license/CDDL.
#
# CDDL HEADER END
#

#
# Copyright (c) 2015 by Delphix. All rights reserved.
# Copyright (C) 2016 Lawrence Livermore National Security, LLC.
#

basedir=$(dirname "$0")

SCRIPT_COMMON=common.sh
if [ -f "${basedir}/${SCRIPT_COMMON}" ]; then
	. "${basedir}/${SCRIPT_COMMON}"
else
	echo "Missing helper script ${SCRIPT_COMMON}" && exit 1
fi

# shellcheck disable=SC2034
PROG=zloop.sh

DEFAULTWORKDIR=/var/tmp
DEFAULTCOREDIR=/var/tmp/zloop

function usage
{
	echo -e "\n$0 [-t <timeout>] [ -s <vdev size> ] [-c <dump directory>]" \
	    "[ -- [extra ztest parameters]]\n" \
	    "\n" \
	    "  This script runs ztest repeatedly with randomized arguments.\n" \
	    "  If a crash is encountered, the ztest logs, any associated\n" \
	    "  vdev files, and core file (if one exists) are moved to the\n" \
	    "  output directory ($DEFAULTCOREDIR by default). Any options\n" \
	    "  after the -- end-of-options marker will be passed to ztest.\n" \
	    "\n" \
	    "  Options:\n" \
	    "    -t  Total time to loop for, in seconds. If not provided,\n" \
	    "        zloop runs forever.\n" \
	    "    -s  Size of vdev devices.\n" \
	    "    -f  Specify working directory for ztest vdev files.\n" \
	    "    -c  Specify a core dump directory to use.\n" \
	    "    -h  Print this help message.\n" \
	    "" >&2
}

function or_die
{
	# shellcheck disable=SC2068
	$@
	# shellcheck disable=SC2181
	if [[ $? -ne 0 ]]; then
		# shellcheck disable=SC2145
		echo "Command failed: $@"
		exit 1
	fi
}

# core file helpers
origcorepattern="$(cat /proc/sys/kernel/core_pattern)"
coreglob="$(egrep -o '^([^|%[:space:]]*)' /proc/sys/kernel/core_pattern)*"

if [[ $coreglob = "*" ]]; then
        echo "Setting core file pattern..."
        echo "core" > /proc/sys/kernel/core_pattern
        coreglob="$(egrep -o '^([^|%[:space:]]*)' \
            /proc/sys/kernel/core_pattern)*"
fi

function core_file
{
	# shellcheck disable=SC2012 disable=2086
        printf "%s" "$(ls -tr1 $coreglob 2> /dev/null | head -1)"
}

function core_prog
{
	prog=$ZTEST
	core_id=$($GDB --batch -c "$1" | grep "Core was generated by" | \
	    tr  \' ' ')
	# shellcheck disable=SC2076
	if [[ "$core_id" =~ "zdb "  ]]; then
		prog=$ZDB
	fi
	printf "%s" "$prog"
}

function store_core
{
	core="$(core_file)"
	if [[ $ztrc -ne 0 ]] || [[ -f "$core" ]]; then
		coreid=$(date "+zloop-%y%m%d-%H%M%S")
		foundcrashes=$((foundcrashes + 1))

		dest=$coredir/$coreid
		or_die mkdir -p "$dest"
		or_die mkdir -p "$dest/vdev"

		echo "*** ztest crash found - moving logs to $dest"

		or_die mv ztest.history "$dest/"
		or_die mv ztest.ddt "$dest/"
		or_die mv ztest.out "$dest/"
		or_die mv "$workdir/ztest*" "$dest/vdev/"
		or_die mv "$workdir/zpool.cache" "$dest/vdev/"

		# check for core
		if [[ -f "$core" ]]; then
			coreprog=$(core_prog "$core")
			corestatus=$($GDB --batch --quiet \
			    -ex "set print thread-events off" \
			    -ex "printf \"*\n* Backtrace \n*\n\"" \
			    -ex "bt" \
			    -ex "printf \"*\n* Libraries \n*\n\"" \
			    -ex "info sharedlib" \
			    -ex "printf \"*\n* Threads (full) \n*\n\"" \
			    -ex "info threads" \
			    -ex "printf \"*\n* Backtraces \n*\n\"" \
			    -ex "thread apply all bt" \
			    -ex "printf \"*\n* Backtraces (full) \n*\n\"" \
			    -ex "thread apply all bt full" \
			    -ex "quit" "$coreprog" "$core" | grep -v "New LWP")

			# Dump core + logs to stored directory
			echo "$corestatus" >>"$dest/status"
			or_die mv "$core" "$dest/"

			# Record info in cores logfile
			echo "*** core @ $coredir/$coreid/$core:" | \
			    tee -a ztest.cores
			echo "$corestatus" | tee -a ztest.cores
			echo "" | tee -a ztest.cores
		fi
		echo "continuing..."
	fi
}

# parse arguments
# expected format: zloop [-t timeout] [-c coredir] [-- extra ztest args]
coredir=$DEFAULTCOREDIR
workdir=$DEFAULTWORKDIR
timeout=0
size="512m"
while getopts ":ht:s:c:f:" opt; do
	case $opt in
		t ) [[ $OPTARG -gt 0 ]] && timeout=$OPTARG ;;
		s ) [[ $OPTARG ]] && size=$OPTARG ;;
		c ) [[ $OPTARG ]] && coredir=$OPTARG ;;
		f ) [[ $OPTARG ]] && workdir=$(readlink -f "$OPTARG") ;;
		h ) usage
		    exit 2
		    ;;
		* ) echo "Invalid argument: -$OPTARG";
		    usage
		    exit 1
	esac
done
# pass remaining arguments on to ztest
shift $((OPTIND - 1))

# enable core dumps
ulimit -c unlimited

if [[ -f "$(core_file)" ]]; then
	echo -n "There's a core dump here you might want to look at first... "
	core_file
	exit 1
fi

if [[ ! -d $coredir ]]; then
	echo "core dump directory ($coredir) does not exist, creating it."
	or_die mkdir -p "$coredir"
fi

if [[ ! -w $coredir ]]; then
	echo "core dump directory ($coredir) is not writable."
	exit 1
fi

or_die rm -f ztest.history
or_die rm -f ztest.ddt
or_die rm -f ztest.cores

ztrc=0		# ztest return value
foundcrashes=0	# number of crashes found so far
starttime=$(date +%s)
curtime=$starttime

# if no timeout was specified, loop forever.
while [[ $timeout -eq 0 ]] || [[ $curtime -le $((starttime + timeout)) ]]; do
	zopt="-VVVVV"

	# switch between common arrangements & fully randomized
	if [[ $((RANDOM % 2)) -eq 0 ]]; then
		mirrors=2
		raidz=0
		parity=1
		vdevs=2
	else
		mirrors=$(((RANDOM % 3) * 1))
		parity=$(((RANDOM % 3) + 1))
		raidz=$((((RANDOM % 9) + parity + 1) * (RANDOM % 2)))
		vdevs=$(((RANDOM % 3) + 3))
	fi
	align=$(((RANDOM % 2) * 3 + 9))
	runtime=$((RANDOM % 100))
	passtime=$((RANDOM % (runtime / 3 + 1) + 10))

	zopt="$zopt -m $mirrors"
	zopt="$zopt -r $raidz"
	zopt="$zopt -R $parity"
	zopt="$zopt -v $vdevs"
	zopt="$zopt -a $align"
	zopt="$zopt -T $runtime"
	zopt="$zopt -P $passtime"
	zopt="$zopt -s $size"
	zopt="$zopt -f $workdir"

	# shellcheck disable=SC2124
	cmd="$ZTEST $zopt $@"
	desc="$(date '+%m/%d %T') $cmd"
	echo "$desc" | tee -a ztest.history
	echo "$desc" >>ztest.out
	$cmd >>ztest.out 2>&1
	ztrc=$?
	egrep '===|WARNING' ztest.out >>ztest.history
	$ZDB -U "$workdir/zpool.cache" -DD ztest >>ztest.ddt

	store_core

	curtime=$(date +%s)
done

echo "zloop finished, $foundcrashes crashes found"

#restore core pattern
echo "$origcorepattern" > /proc/sys/kernel/core_pattern

uptime >>ztest.out

if [[ $foundcrashes -gt 0 ]]; then
	exit 1
fi
Commit	Line	Data
cae5b340 AX	1	#!/bin/bash
	2
	3	#
	4	# CDDL HEADER START
	5	#
	6	# This file and its contents are supplied under the terms of the
	7	# Common Development and Distribution License ("CDDL"), version 1.0.
	8	# You may only use this file in accordance with the terms of version
	9	# 1.0 of the CDDL.
	10	#
	11	# A full copy of the text of the CDDL should have accompanied this
	12	# source. A copy of the CDDL is also available via the Internet at
	13	# http://www.illumos.org/license/CDDL.
	14	#
	15	# CDDL HEADER END
	16	#
	17
	18	#
	19	# Copyright (c) 2015 by Delphix. All rights reserved.
	20	# Copyright (C) 2016 Lawrence Livermore National Security, LLC.
	21	#
	22
	23	basedir=$(dirname "$0")
	24
	25	SCRIPT_COMMON=common.sh
	26	if [ -f "${basedir}/${SCRIPT_COMMON}" ]; then
	27	. "${basedir}/${SCRIPT_COMMON}"
	28	else
	29	echo "Missing helper script ${SCRIPT_COMMON}" && exit 1
	30	fi
	31
	32	# shellcheck disable=SC2034
	33	PROG=zloop.sh
	34
	35	DEFAULTWORKDIR=/var/tmp
	36	DEFAULTCOREDIR=/var/tmp/zloop
	37
	38	function usage
	39	{
8ec27e97	40	echo -e "\n$0 [-t <timeout>] [ -s <vdev size> ] [-c <dump directory>]" \
cae5b340 AX	41	"[ -- [extra ztest parameters]]\n" \
	42	"\n" \
	43	" This script runs ztest repeatedly with randomized arguments.\n" \
	44	" If a crash is encountered, the ztest logs, any associated\n" \
	45	" vdev files, and core file (if one exists) are moved to the\n" \
	46	" output directory ($DEFAULTCOREDIR by default). Any options\n" \
	47	" after the -- end-of-options marker will be passed to ztest.\n" \
	48	"\n" \
	49	" Options:\n" \
	50	" -t Total time to loop for, in seconds. If not provided,\n" \
	51	" zloop runs forever.\n" \
8ec27e97	52	" -s Size of vdev devices.\n" \
cae5b340 AX	53	" -f Specify working directory for ztest vdev files.\n" \
	54	" -c Specify a core dump directory to use.\n" \
	55	" -h Print this help message.\n" \
	56	"" >&2
	57	}
	58
	59	function or_die
	60	{
	61	# shellcheck disable=SC2068
	62	$@
	63	# shellcheck disable=SC2181
	64	if [[ $? -ne 0 ]]; then
	65	# shellcheck disable=SC2145
	66	echo "Command failed: $@"
	67	exit 1
	68	fi
	69	}
	70
	71	# core file helpers
	72	origcorepattern="$(cat /proc/sys/kernel/core_pattern)"
	73	coreglob="$(egrep -o '^([^\|%[:space:]])' /proc/sys/kernel/core_pattern)"
	74
	75	if [[ $coreglob = "*" ]]; then
	76	echo "Setting core file pattern..."
	77	echo "core" > /proc/sys/kernel/core_pattern
	78	coreglob="$(egrep -o '^([^\|%[:space:]]*)' \
	79	/proc/sys/kernel/core_pattern)*"
	80	fi
	81
	82	function core_file
	83	{
	84	# shellcheck disable=SC2012 disable=2086
	85	printf "%s" "$(ls -tr1 $coreglob 2> /dev/null \| head -1)"
	86	}
	87
	88	function core_prog
	89	{
	90	prog=$ZTEST
	91	core_id=$($GDB --batch -c "$1" \| grep "Core was generated by" \| \
	92	tr \' ' ')
	93	# shellcheck disable=SC2076
	94	if [[ "$core_id" =~ "zdb " ]]; then
	95	prog=$ZDB
	96	fi
	97	printf "%s" "$prog"
	98	}
	99
	100	function store_core
	101	{
	102	core="$(core_file)"
	103	if [[ $ztrc -ne 0 ]] \|\| [[ -f "$core" ]]; then
	104	coreid=$(date "+zloop-%y%m%d-%H%M%S")
	105	foundcrashes=$((foundcrashes + 1))
	106
	107	dest=$coredir/$coreid
	108	or_die mkdir -p "$dest"
	109	or_die mkdir -p "$dest/vdev"
	110
	111	echo "*** ztest crash found - moving logs to $dest"
	112
	113	or_die mv ztest.history "$dest/"
	114	or_die mv ztest.ddt "$dest/"
	115	or_die mv ztest.out "$dest/"
	116	or_die mv "$workdir/ztest*" "$dest/vdev/"
117	or_die mv "$workdir/zpool.cache" "$dest/vdev/"
118
119	# check for core
120	if [[ -f "$core" ]]; then
121	coreprog=$(core_prog "$core")
122	corestatus=$($GDB --batch --quiet \
123	-ex "set print thread-events off" \
124	-ex "printf \"\n Backtrace \n*\n\"" \
125	-ex "bt" \
126	-ex "printf \"\n Libraries \n*\n\"" \
127	-ex "info sharedlib" \
128	-ex "printf \"\n Threads (full) \n*\n\"" \
129	-ex "info threads" \
130	-ex "printf \"\n Backtraces \n*\n\"" \
131	-ex "thread apply all bt" \
132	-ex "printf \"\n Backtraces (full) \n*\n\"" \
133	-ex "thread apply all bt full" \
134	-ex "quit" "$coreprog" "$core" \| grep -v "New LWP")
135
136	# Dump core + logs to stored directory
137	echo "$corestatus" >>"$dest/status"
138	or_die mv "$core" "$dest/"
139
140	# Record info in cores logfile
141	echo "*** core @ $coredir/$coreid/$core:" \| \
142	tee -a ztest.cores
143	echo "$corestatus" \| tee -a ztest.cores
144	echo "" \| tee -a ztest.cores
145	fi
146	echo "continuing..."
147	fi
148	}
149
150	# parse arguments
151	# expected format: zloop [-t timeout] [-c coredir] [-- extra ztest args]
152	coredir=$DEFAULTCOREDIR
153	workdir=$DEFAULTWORKDIR
154	timeout=0
8ec27e97 AX	155	size="512m"
8ec27e97 AX	156	while getopts ":ht:s:c:f:" opt; do
cae5b340 AX	157	case $opt in
cae5b340 AX	158	t ) [[ $OPTARG -gt 0 ]] && timeout=$OPTARG ;;
8ec27e97	159	s ) [[ $OPTARG ]] && size=$OPTARG ;;
cae5b340 AX	160	c ) [[ $OPTARG ]] && coredir=$OPTARG ;;
	161	f ) [[ $OPTARG ]] && workdir=$(readlink -f "$OPTARG") ;;
	162	h ) usage
	163	exit 2
	164	;;
	165	* ) echo "Invalid argument: -$OPTARG";
	166	usage
	167	exit 1
	168	esac
	169	done
	170	# pass remaining arguments on to ztest
	171	shift $((OPTIND - 1))
	172
	173	# enable core dumps
	174	ulimit -c unlimited
	175
	176	if [[ -f "$(core_file)" ]]; then
	177	echo -n "There's a core dump here you might want to look at first... "
	178	core_file
	179	exit 1
	180	fi
	181
	182	if [[ ! -d $coredir ]]; then
	183	echo "core dump directory ($coredir) does not exist, creating it."
	184	or_die mkdir -p "$coredir"
	185	fi
	186
	187	if [[ ! -w $coredir ]]; then
	188	echo "core dump directory ($coredir) is not writable."
	189	exit 1
	190	fi
	191
	192	or_die rm -f ztest.history
	193	or_die rm -f ztest.ddt
	194	or_die rm -f ztest.cores
	195
	196	ztrc=0 # ztest return value
	197	foundcrashes=0 # number of crashes found so far
	198	starttime=$(date +%s)
	199	curtime=$starttime
	200
	201	# if no timeout was specified, loop forever.
	202	while [[ $timeout -eq 0 ]] \|\| [[ $curtime -le $((starttime + timeout)) ]]; do
	203	zopt="-VVVVV"
	204
	205	# switch between common arrangements & fully randomized
	206	if [[ $((RANDOM % 2)) -eq 0 ]]; then
	207	mirrors=2
	208	raidz=0
	209	parity=1
	210	vdevs=2
	211	else
	212	mirrors=$(((RANDOM % 3) * 1))
	213	parity=$(((RANDOM % 3) + 1))
	214	raidz=$((((RANDOM % 9) + parity + 1) * (RANDOM % 2)))
	215	vdevs=$(((RANDOM % 3) + 3))
	216	fi
	217	align=$(((RANDOM % 2) * 3 + 9))
	218	runtime=$((RANDOM % 100))
	219	passtime=$((RANDOM % (runtime / 3 + 1) + 10))
cae5b340 AX	220
	221	zopt="$zopt -m $mirrors"
	222	zopt="$zopt -r $raidz"
	223	zopt="$zopt -R $parity"
	224	zopt="$zopt -v $vdevs"
	225	zopt="$zopt -a $align"
	226	zopt="$zopt -T $runtime"
	227	zopt="$zopt -P $passtime"
	228	zopt="$zopt -s $size"
	229	zopt="$zopt -f $workdir"
	230
	231	# shellcheck disable=SC2124
	232	cmd="$ZTEST $zopt $@"
	233	desc="$(date '+%m/%d %T') $cmd"
	234	echo "$desc" \| tee -a ztest.history
	235	echo "$desc" >>ztest.out
	236	$cmd >>ztest.out 2>&1
	237	ztrc=$?
	238	egrep '===\|WARNING' ztest.out >>ztest.history
	239	$ZDB -U "$workdir/zpool.cache" -DD ztest >>ztest.ddt
	240
	241	store_core
	242
	243	curtime=$(date +%s)
	244	done
	245
	246	echo "zloop finished, $foundcrashes crashes found"
	247
	248	#restore core pattern
	249	echo "$origcorepattern" > /proc/sys/kernel/core_pattern
	250
	251	uptime >>ztest.out
	252
	253	if [[ $foundcrashes -gt 0 ]]; then
	254	exit 1
	255	fi