[mirror_zfs.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.
#

BASE_DIR=$(dirname "$0")
SCRIPT_COMMON=common.sh
if [ -f "${BASE_DIR}/${SCRIPT_COMMON}" ]; then
	. "${BASE_DIR}/${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
		df -h "$workdir" >>ztest.out
		coreid=$(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
}

rngdpid=""
function on_exit
{
	if [ -n "$rngdpid" ]; then
		kill -9 "$rngdpid"
	fi
}
trap on_exit EXIT

# parse arguments
# expected format: zloop [-t timeout] [-c coredir] [-- extra ztest args]
coredir=$DEFAULTCOREDIR
basedir=$DEFAULTWORKDIR
rundir="zloop-run"
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 ) [[ $OPTARG ]] && basedir=$(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

# start rngd in the background so we don't run out of entropy
or_die read -r rngdpid < <(rngd -f -r /dev/urandom & echo $!)

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"

	# start each run with an empty directory
	workdir="$basedir/$rundir"
	or_die rm -rf "$workdir"
	or_die mkdir "$workdir"

	# 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 [[ $foundcrashes -gt 0 ]]; then
	exit 1
fi
Commit	Line	Data
9c13b489	1	#!/bin/bash
541a0901 BB	2
	3	#
	4	# CDDL HEADER START
	5	#
	6	# This file and its contents are supplied under the terms of the
	7	# Common Development and Distribution License ("CDDL"), version 1.0.
	8	# You may only use this file in accordance with the terms of version
	9	# 1.0 of the CDDL.
	10	#
	11	# A full copy of the text of the CDDL should have accompanied this
	12	# source. A copy of the CDDL is also available via the Internet at
	13	# http://www.illumos.org/license/CDDL.
	14	#
	15	# CDDL HEADER END
	16	#
	17
	18	#
	19	# Copyright (c) 2015 by Delphix. All rights reserved.
	20	# Copyright (C) 2016 Lawrence Livermore National Security, LLC.
	21	#
	22
c8f9061f	23	BASE_DIR=$(dirname "$0")
541a0901	24	SCRIPT_COMMON=common.sh
c8f9061f BB	25	if [ -f "${BASE_DIR}/${SCRIPT_COMMON}" ]; then
c8f9061f BB	26	. "${BASE_DIR}/${SCRIPT_COMMON}"
541a0901 BB	27	else
	28	echo "Missing helper script ${SCRIPT_COMMON}" && exit 1
	29	fi
	30
c552fbc5	31	# shellcheck disable=SC2034
541a0901 BB	32	PROG=zloop.sh
	33
	34	DEFAULTWORKDIR=/var/tmp
	35	DEFAULTCOREDIR=/var/tmp/zloop
	36
	37	function usage
	38	{
aea899a6	39	echo -e "\n$0 [-t <timeout>] [ -s <vdev size> ] [-c <dump directory>]" \
541a0901 BB	40	"[ -- [extra ztest parameters]]\n" \
	41	"\n" \
	42	" This script runs ztest repeatedly with randomized arguments.\n" \
	43	" If a crash is encountered, the ztest logs, any associated\n" \
	44	" vdev files, and core file (if one exists) are moved to the\n" \
	45	" output directory ($DEFAULTCOREDIR by default). Any options\n" \
	46	" after the -- end-of-options marker will be passed to ztest.\n" \
	47	"\n" \
	48	" Options:\n" \
	49	" -t Total time to loop for, in seconds. If not provided,\n" \
	50	" zloop runs forever.\n" \
aea899a6	51	" -s Size of vdev devices.\n" \
541a0901 BB	52	" -f Specify working directory for ztest vdev files.\n" \
	53	" -c Specify a core dump directory to use.\n" \
	54	" -h Print this help message.\n" \
	55	"" >&2
	56	}
	57
	58	function or_die
	59	{
c552fbc5	60	# shellcheck disable=SC2068
541a0901	61	$@
c552fbc5	62	# shellcheck disable=SC2181
541a0901	63	if [[ $? -ne 0 ]]; then
c552fbc5	64	# shellcheck disable=SC2145
541a0901 BB	65	echo "Command failed: $@"
	66	exit 1
	67	fi
	68	}
	69
20da0566 GN	70	# core file helpers
	71	origcorepattern="$(cat /proc/sys/kernel/core_pattern)"
	72	coreglob="$(egrep -o '^([^\|%[:space:]])' /proc/sys/kernel/core_pattern)"
	73
	74	if [[ $coreglob = "*" ]]; then
	75	echo "Setting core file pattern..."
	76	echo "core" > /proc/sys/kernel/core_pattern
0c313d2f GN	77	coreglob="$(egrep -o '^([^\|%[:space:]]*)' \
0c313d2f GN	78	/proc/sys/kernel/core_pattern)*"
20da0566 GN	79	fi
	80
	81	function core_file
	82	{
c552fbc5	83	# shellcheck disable=SC2012 disable=2086
20da0566 GN	84	printf "%s" "$(ls -tr1 $coreglob 2> /dev/null \| head -1)"
	85	}
	86
0c313d2f GN	87	function core_prog
	88	{
	89	prog=$ZTEST
c552fbc5	90	core_id=$($GDB --batch -c "$1" \| grep "Core was generated by" \| \
0c313d2f	91	tr \' ' ')
c552fbc5	92	# shellcheck disable=SC2076
0c313d2f GN	93	if [[ "$core_id" =~ "zdb " ]]; then
	94	prog=$ZDB
	95	fi
	96	printf "%s" "$prog"
	97	}
	98
541a0901 BB	99	function store_core
541a0901 BB	100	{
20da0566 GN	101	core="$(core_file)"
20da0566 GN	102	if [[ $ztrc -ne 0 ]] \|\| [[ -f "$core" ]]; then
5df5d06a	103	df -h "$workdir" >>ztest.out
541a0901	104	coreid=$(date "+zloop-%y%m%d-%H%M%S")
c552fbc5	105	foundcrashes=$((foundcrashes + 1))
541a0901 BB	106
541a0901 BB	107	dest=$coredir/$coreid
c552fbc5 GDN	108	or_die mkdir -p "$dest"
c552fbc5 GDN	109	or_die mkdir -p "$dest/vdev"
541a0901 BB	110
	111	echo "*** ztest crash found - moving logs to $dest"
	112
c552fbc5 GDN	113	or_die mv ztest.history "$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/"
541a0901 BB	118
541a0901 BB	119	# check for core
20da0566	120	if [[ -f "$core" ]]; then
c552fbc5	121	coreprog=$(core_prog "$core")
541a0901 BB	122	corestatus=$($GDB --batch --quiet \
	123	-ex "set print thread-events off" \
	124	-ex "printf \"\n Backtrace \n*\n\"" \
	125	-ex "bt" \
	126	-ex "printf \"\n Libraries \n*\n\"" \
	127	-ex "info sharedlib" \
	128	-ex "printf \"\n Threads (full) \n*\n\"" \
	129	-ex "info threads" \
	130	-ex "printf \"\n Backtraces \n*\n\"" \
	131	-ex "thread apply all bt" \
	132	-ex "printf \"\n Backtraces (full) \n*\n\"" \
	133	-ex "thread apply all bt full" \
c552fbc5	134	-ex "quit" "$coreprog" "$core" \| grep -v "New LWP")
541a0901 BB	135
541a0901 BB	136	# Dump core + logs to stored directory
c552fbc5 GDN	137	echo "$corestatus" >>"$dest/status"
c552fbc5 GDN	138	or_die mv "$core" "$dest/"
541a0901 BB	139
541a0901 BB	140	# Record info in cores logfile
20da0566	141	echo "*** core @ $coredir/$coreid/$core:" \| \
541a0901 BB	142	tee -a ztest.cores
	143	echo "$corestatus" \| tee -a ztest.cores
	144	echo "" \| tee -a ztest.cores
	145	fi
	146	echo "continuing..."
	147	fi
	148	}
	149
4807c0ba TC	150	rngdpid=""
	151	function on_exit
	152	{
	153	if [ -n "$rngdpid" ]; then
	154	kill -9 "$rngdpid"
	155	fi
	156	}
	157	trap on_exit EXIT
	158
541a0901 BB	159	# parse arguments
	160	# expected format: zloop [-t timeout] [-c coredir] [-- extra ztest args]
	161	coredir=$DEFAULTCOREDIR
5df5d06a DB	162	basedir=$DEFAULTWORKDIR
5df5d06a DB	163	rundir="zloop-run"
541a0901	164	timeout=0
aea899a6 BB	165	size="512m"
aea899a6 BB	166	while getopts ":ht:s:c:f:" opt; do
541a0901 BB	167	case $opt in
541a0901 BB	168	t ) [[ $OPTARG -gt 0 ]] && timeout=$OPTARG ;;
aea899a6	169	s ) [[ $OPTARG ]] && size=$OPTARG ;;
541a0901	170	c ) [[ $OPTARG ]] && coredir=$OPTARG ;;
5df5d06a	171	f ) [[ $OPTARG ]] && basedir=$(readlink -f "$OPTARG") ;;
541a0901 BB	172	h ) usage
	173	exit 2
	174	;;
	175	* ) echo "Invalid argument: -$OPTARG";
	176	usage
	177	exit 1
	178	esac
	179	done
	180	# pass remaining arguments on to ztest
	181	shift $((OPTIND - 1))
	182
	183	# enable core dumps
	184	ulimit -c unlimited
	185
20da0566 GN	186	if [[ -f "$(core_file)" ]]; then
20da0566 GN	187	echo -n "There's a core dump here you might want to look at first... "
c552fbc5	188	core_file
541a0901 BB	189	exit 1
	190	fi
	191
	192	if [[ ! -d $coredir ]]; then
	193	echo "core dump directory ($coredir) does not exist, creating it."
c552fbc5	194	or_die mkdir -p "$coredir"
541a0901 BB	195	fi
	196
	197	if [[ ! -w $coredir ]]; then
	198	echo "core dump directory ($coredir) is not writable."
	199	exit 1
	200	fi
	201
	202	or_die rm -f ztest.history
	203	or_die rm -f ztest.ddt
	204	or_die rm -f ztest.cores
	205
4807c0ba TC	206	# start rngd in the background so we don't run out of entropy
	207	or_die read -r rngdpid < <(rngd -f -r /dev/urandom & echo $!)
	208
541a0901 BB	209	ztrc=0 # ztest return value
	210	foundcrashes=0 # number of crashes found so far
	211	starttime=$(date +%s)
	212	curtime=$starttime
	213
	214	# if no timeout was specified, loop forever.
c552fbc5	215	while [[ $timeout -eq 0 ]] \|\| [[ $curtime -le $((starttime + timeout)) ]]; do
541a0901 BB	216	zopt="-VVVVV"
541a0901 BB	217
5df5d06a DB	218	# start each run with an empty directory
	219	workdir="$basedir/$rundir"
	220	or_die rm -rf "$workdir"
	221	or_die mkdir "$workdir"
	222
541a0901 BB	223	# switch between common arrangements & fully randomized
	224	if [[ $((RANDOM % 2)) -eq 0 ]]; then
	225	mirrors=2
	226	raidz=0
	227	parity=1
	228	vdevs=2
	229	else
	230	mirrors=$(((RANDOM % 3) * 1))
	231	parity=$(((RANDOM % 3) + 1))
	232	raidz=$((((RANDOM % 9) + parity + 1) * (RANDOM % 2)))
	233	vdevs=$(((RANDOM % 3) + 3))
	234	fi
	235	align=$(((RANDOM % 2) * 3 + 9))
	236	runtime=$((RANDOM % 100))
	237	passtime=$((RANDOM % (runtime / 3 + 1) + 10))
541a0901 BB	238
	239	zopt="$zopt -m $mirrors"
	240	zopt="$zopt -r $raidz"
	241	zopt="$zopt -R $parity"
	242	zopt="$zopt -v $vdevs"
	243	zopt="$zopt -a $align"
	244	zopt="$zopt -T $runtime"
	245	zopt="$zopt -P $passtime"
	246	zopt="$zopt -s $size"
	247	zopt="$zopt -f $workdir"
	248
c552fbc5	249	# shellcheck disable=SC2124
541a0901 BB	250	cmd="$ZTEST $zopt $@"
	251	desc="$(date '+%m/%d %T') $cmd"
	252	echo "$desc" \| tee -a ztest.history
	253	echo "$desc" >>ztest.out
	254	$cmd >>ztest.out 2>&1
	255	ztrc=$?
	256	egrep '===\|WARNING' ztest.out >>ztest.history
c552fbc5	257	$ZDB -U "$workdir/zpool.cache" -DD ztest >>ztest.ddt
541a0901 BB	258
	259	store_core
	260
	261	curtime=$(date +%s)
	262	done
	263
	264	echo "zloop finished, $foundcrashes crashes found"
	265
20da0566 GN	266	#restore core pattern
	267	echo "$origcorepattern" > /proc/sys/kernel/core_pattern
	268
541a0901 BB	269	uptime >>ztest.out
	270
	271	if [[ $foundcrashes -gt 0 ]]; then
	272	exit 1
	273	fi