On Thu, Dec 13, 2018 at 01:28:44PM -0500, Dennis Zhou wrote:
> This test exposed a race condition with shutting down a request_queue
> and the new blkg association. The issue ended up being that while the
> request_queue will just start failing requests, blkg destruction sets
> the q->root_blkg to %NULL. This caused a NPE when trying to reference
> it. So to help prevent this from happening again, integrate Ming's test
> into blktests so that it can more easily be ran.
>
> Signed-off-by: Dennis Zhou <dennis@xxxxxxxxxx>
> Cc: Ming Lei <ming.lei@xxxxxxxxxx>
> ---
> v2:
> - Change scheduler retrieving logic based on Ming's comment
>
> tests/block/022 | 90 +++++++++++++++++++++++++++++++++++++++++++++
> tests/block/022.out | 2 +
> 2 files changed, 92 insertions(+)
> create mode 100755 tests/block/022
> create mode 100644 tests/block/022.out
>
> diff --git a/tests/block/022 b/tests/block/022
> new file mode 100755
> index 0000000..84336e0
> --- /dev/null
> +++ b/tests/block/022
> @@ -0,0 +1,90 @@
> +#!/bin/bash
> +# SPDX-License-Identifier: GPL-3.0+
> +# Copyright (C) 2018 Ming Lei
> +#
> +# Regression test for patch "blkcg: handle dying request_queue when associating
> +# a blkg"
> +#
> +# This tries to expose the race condition between blkg association and
> +# request_queue shutdown. When a request_queue is shutdown, the corresponding
> +# blkgs are destroyed. Any further associations should fail gracefully and not
> +# cause a kernel panic.
> +
> +. tests/block/rc
> +. common/scsi_debug
> +. common/cgroup
> +
> +DESCRIPTION="test graceful shutdown of scsi_debug devices with running fio jobs"
> +QUICK=1
> +
> +requires() {
> + _have_cgroup2_controller io && _have_scsi_debug && _have_fio
> +}
> +
> +scsi_debug_stress_remove() {
> + scsi_debug_path="/sys/bus/pseudo/drivers/scsi_debug"
> + count=21
> +
> + runtime=12
> + nr_fio_jobs=8
> + scsi_dbg_ndelay=10000
> +
> + # set higher aio limit
> + echo 524288 > /proc/sys/fs/aio-max-nr
> +
> + #figure out the CAN_QUEUE
> + can_queue=$(((count + 1) * (count / 2) / 2))
> +
> + rmmod scsi_debug > /dev/null 2>&1
> + modprobe scsi_debug virtual_gb=128 max_luns=$count \
> + ndelay=$scsi_dbg_ndelay max_queue=$can_queue
> +
> + # figure out scsi_debug disks
> + hosts=$(ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter0/host*)
> + hostname=$(basename "$hosts")
> + host=$(echo "$hostname" | grep -o -E '[0-9]+')
> +
> + sdisks=$(ls -d $scsi_debug_path/adapter*/"$hostname"/target*/*/block/*)
> + disks=""
> + for sd in $sdisks; do
> + disks+="/dev/"$(basename "$sd")
> + disks+=" "
> + done
> +
> + fio_jobs=""
> + cnt=0
> + for sd in $disks; do
> + cnt=$((cnt+1))
> + fio_jobs=$fio_jobs" --name=job1 --filename=$sd: "
> + dev_name=$(basename "$sd")
> + q_path=/sys/block/$dev_name/queue
> +
> + scheds=($(sed 's/[][]//g' "$q_path/scheduler"))
> + sched_idx=$((cnt % ${#scheds[@]}))
> + echo "${scheds[$sched_idx]}" > "$q_path/scheduler"
> + echo $cnt > "$q_path/../device/queue_depth"
> + done
> +
> + fio --rw=randread --size=128G --direct=1 --ioengine=libaio \
> + --iodepth=2048 --numjobs=$nr_fio_jobs --bs=4k \
> + --group_reporting=1 --group_reporting=1 --runtime=$runtime \
> + --loops=10000 "$fio_jobs" > "$FULL" 2>&1 &
> +
> + sleep 7
> + for sd in $disks; do
> + dev_name=$(basename "$sd")
> + dpath=/sys/block/$dev_name/device
> + [ -f "$dpath/delete" ] && echo 1 > "$dpath/delete"
> + done
> +
> + wait
> +}
> +
> +
> +test() {
> + echo "Running ${TEST_NAME}"
> +
> + scsi_debug_stress_remove
> +
> + echo "Test complete"
> +}
> diff --git a/tests/block/022.out b/tests/block/022.out
> new file mode 100644
> index 0000000..14d43cb
> --- /dev/null
> +++ b/tests/block/022.out
> @@ -0,0 +1,2 @@
> +Running block/022
> +Test complete
> --
> 2.17.1
>
Reviewed-by: Ming Lei <ming.lei@xxxxxxxxxx>
thanks,
Ming
