zfs/scripts/zloop.sh

274 lines
6.8 KiB
Bash
Raw Normal View History

#!/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
OpenZFS 8585 - improve batching done in zil_commit() Authored by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Brad Lewis <brad.lewis@delphix.com> Reviewed by: Matt Ahrens <mahrens@delphix.com> Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Dan McDonald <danmcd@joyent.com> Ported-by: Prakash Surya <prakash.surya@delphix.com> Problem ======= The current implementation of zil_commit() can introduce significant latency, beyond what is inherent due to the latency of the underlying storage. The additional latency comes from two main problems: 1. When there's outstanding ZIL blocks being written (i.e. there's already a "writer thread" in progress), then any new calls to zil_commit() will block waiting for the currently oustanding ZIL blocks to complete. The blocks written for each "writer thread" is coined a "batch", and there can only ever be a single "batch" being written at a time. When a batch is being written, any new ZIL transactions will have to wait for the next batch to be written, which won't occur until the current batch finishes. As a result, the underlying storage may not be used as efficiently as possible. While "new" threads enter zil_commit() and are blocked waiting for the next batch, it's possible that the underlying storage isn't fully utilized by the current batch of ZIL blocks. In that case, it'd be better to allow these new threads to generate (and issue) a new ZIL block, such that it could be serviced by the underlying storage concurrently with the other ZIL blocks that are being serviced. 2. Any call to zil_commit() must wait for all ZIL blocks in its "batch" to complete, prior to zil_commit() returning. The size of any given batch is proportional to the number of ZIL transaction in the queue at the time that the batch starts processing the queue; which doesn't occur until the previous batch completes. Thus, if there's a lot of transactions in the queue, the batch could be composed of many ZIL blocks, and each call to zil_commit() will have to wait for all of these writes to complete (even if the thread calling zil_commit() only cared about one of the transactions in the batch). To further complicate the situation, these two issues result in the following side effect: 3. If a given batch takes longer to complete than normal, this results in larger batch sizes, which then take longer to complete and further drive up the latency of zil_commit(). This can occur for a number of reasons, including (but not limited to): transient changes in the workload, and storage latency irregularites. Solution ======== The solution attempted by this change has the following goals: 1. no on-disk changes; maintain current on-disk format. 2. modify the "batch size" to be equal to the "ZIL block size". 3. allow new batches to be generated and issued to disk, while there's already batches being serviced by the disk. 4. allow zil_commit() to wait for as few ZIL blocks as possible. 5. use as few ZIL blocks as possible, for the same amount of ZIL transactions, without introducing significant latency to any individual ZIL transaction. i.e. use fewer, but larger, ZIL blocks. In theory, with these goals met, the new allgorithm will allow the following improvements: 1. new ZIL blocks can be generated and issued, while there's already oustanding ZIL blocks being serviced by the storage. 2. the latency of zil_commit() should be proportional to the underlying storage latency, rather than the incoming synchronous workload. Porting Notes ============= Due to the changes made in commit 119a394ab0, the lifetime of an itx structure differs than in OpenZFS. Specifically, the itx structure is kept around until the data associated with the itx is considered to be safe on disk; this is so that the itx's callback can be called after the data is committed to stable storage. Since OpenZFS doesn't have this itx callback mechanism, it's able to destroy the itx structure immediately after the itx is committed to an lwb (before the lwb is written to disk). To support this difference, and to ensure the itx's callbacks can still be called after the itx's data is on disk, a few changes had to be made: * A list of itxs was added to the lwb structure. This list contains all of the itxs that have been committed to the lwb, such that the callbacks for these itxs can be called from zil_lwb_flush_vdevs_done(), after the data for the itxs is committed to disk. * A list of itxs was added on the stack of the zil_process_commit_list() function; the "nolwb_itxs" list. In some circumstances, an itx may not be committed to an lwb (e.g. if allocating the "next" ZIL block on disk fails), so this list is used to keep track of which itxs fall into this state, such that their callbacks can be called after the ZIL's writer pipeline is "stalled". * The logic to actually call the itx's callback was moved into the zil_itx_destroy() function. Since all consumers of zil_itx_destroy() were effectively performing the same logic (i.e. if callback is non-null, call the callback), it seemed like useful code cleanup to consolidate this logic into a single function. Additionally, the existing Linux tracepoint infrastructure dealing with the ZIL's probes and structures had to be updated to reflect these code changes. Specifically: * The "zil__cw1" and "zil__cw2" probes were removed, so they had to be removed from "trace_zil.h" as well. * Some of the zilog structure's fields were removed, which affected the tracepoint definitions of the structure. * New tracepoints had to be added for the following 3 new probes: * zil__process__commit__itx * zil__process__normal__itx * zil__commit__io__error OpenZFS-issue: https://www.illumos.org/issues/8585 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/5d95a3a Closes #6566
2017-12-05 17:39:16 +00:00
$ZDB -U "$workdir/zpool.cache" -DD ztest >>ztest.ddt 2>&1
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