| #! /bin/bash |
| # SPDX-License-Identifier: GPL-2.0 |
| # Copyright (c) 2017 Oracle, Inc. All Rights Reserved. |
| # |
| # FS QA Test No. 422 |
| # |
| # Race freeze and rmapbt repair for a while to see if we crash or livelock. |
| # rmapbt repair requires us to freeze the filesystem to stop all filesystem |
| # activity, so we can't have userspace wandering in and thawing it. |
| # |
| . ./common/preamble |
| _begin_fstest dangerous_scrub dangerous_online_repair freeze |
| |
| _register_cleanup "_cleanup" BUS |
| |
| # First kill and wait the freeze loop so it won't try to freeze fs again |
| # Then make sure fs is not frozen |
| # Then kill and wait for the rest of the workers |
| # Because if fs is frozen a killed writer will never exit |
| kill_loops() { |
| local sig=$1 |
| |
| [ -n "$freeze_pid" ] && kill $sig $freeze_pid |
| wait $freeze_pid |
| unset freeze_pid |
| $XFS_IO_PROG -x -c 'thaw' $SCRATCH_MNT |
| [ -n "$stress_pid" ] && kill $sig $stress_pid |
| [ -n "$repair_pid" ] && kill $sig $repair_pid |
| wait |
| unset stress_pid |
| unset repair_pid |
| } |
| |
| # Override the default cleanup function. |
| _cleanup() |
| { |
| kill_loops -9 > /dev/null 2>&1 |
| cd / |
| rm -rf $tmp.* |
| } |
| |
| # Import common functions. |
| . ./common/filter |
| . ./common/fuzzy |
| . ./common/inject |
| |
| # real QA test starts here |
| _supported_fs xfs |
| _require_xfs_scratch_rmapbt |
| _require_xfs_io_command "scrub" |
| _require_xfs_io_error_injection "force_repair" |
| _require_command "$KILLALL_PROG" killall |
| _require_freeze |
| |
| echo "Format and populate" |
| _scratch_mkfs > "$seqres.full" 2>&1 |
| _scratch_mount |
| |
| STRESS_DIR="$SCRATCH_MNT/testdir" |
| mkdir -p $STRESS_DIR |
| |
| for i in $(seq 0 9); do |
| mkdir -p $STRESS_DIR/$i |
| for j in $(seq 0 9); do |
| mkdir -p $STRESS_DIR/$i/$j |
| for k in $(seq 0 9); do |
| echo x > $STRESS_DIR/$i/$j/$k |
| done |
| done |
| done |
| |
| cpus=$(( $($here/src/feature -o) * 4 * LOAD_FACTOR)) |
| |
| echo "Concurrent repair" |
| filter_output() { |
| egrep -v '(Device or resource busy|Invalid argument)' |
| } |
| freeze_loop() { |
| end="$1" |
| |
| while [ "$(date +%s)" -lt $end ]; do |
| $XFS_IO_PROG -x -c 'freeze' -c 'thaw' $SCRATCH_MNT 2>&1 | filter_output |
| done |
| } |
| repair_loop() { |
| end="$1" |
| |
| while [ "$(date +%s)" -lt $end ]; do |
| $XFS_IO_PROG -x -c 'repair rmapbt 0' -c 'repair rmapbt 1' $SCRATCH_MNT 2>&1 | filter_output |
| done |
| } |
| stress_loop() { |
| end="$1" |
| |
| FSSTRESS_ARGS=$(_scale_fsstress_args -p 4 -d $SCRATCH_MNT -n 2000 $FSSTRESS_AVOID) |
| while [ "$(date +%s)" -lt $end ]; do |
| $FSSTRESS_PROG $FSSTRESS_ARGS >> $seqres.full |
| done |
| } |
| $XFS_IO_PROG -x -c 'inject force_repair' $SCRATCH_MNT |
| |
| start=$(date +%s) |
| end=$((start + (30 * TIME_FACTOR) )) |
| |
| echo "Loop started at $(date --date="@${start}"), ending at $(date --date="@${end}")" >> $seqres.full |
| stress_loop $end & |
| stress_pid=$! |
| freeze_loop $end & |
| freeze_pid=$! |
| repair_loop $end & |
| repair_pid=$! |
| |
| # Wait until 2 seconds after the loops should have finished... |
| while [ "$(date +%s)" -lt $((end + 2)) ]; do |
| sleep 1 |
| done |
| |
| # ...and clean up after the loops in case they didn't do it themselves. |
| kill_loops >> $seqres.full 2>&1 |
| |
| echo "Loop finished at $(date)" >> $seqres.full |
| echo "Test done" |
| |
| # success, all done |
| status=0 |
| exit |