#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
# Copyright (c) 2019 Red Hat, Inc.  All Rights Reserved.
#
# FS QA Test No. 563
#
# This test verifies that cgroup aware writeback properly accounts I/Os in
# various scenarios. We perform reads/writes from different combinations of
# cgroups and verify that pages are accounted against the group that brought
# them into cache.
#

seq=`basename $0`
seqres=$RESULT_DIR/$seq
echo "QA output created by $seq"

here=`pwd`
tmp=/tmp/$$
status=1	# failure is the default!
trap "_cleanup; exit \$status" 0 1 2 3 15

_cleanup()
{
	cd /
	rm -f $tmp.*

	echo $$ > $cgdir/cgroup.procs
	rmdir $cgdir/$seq-cg* > /dev/null 2>&1
	umount $SCRATCH_MNT > /dev/null 2>&1
	_destroy_loop_device $LOOP_DEV > /dev/null 2>&1
}

# get standard environment, filters and checks
. ./common/rc
. ./common/filter
. ./common/cgroup2

# remove previous $seqres.full before test
rm -f $seqres.full

# real QA test starts here

# Modify as appropriate.
_supported_fs generic
_require_scratch_nocheck
_require_cgroup2 io
_require_loop

# cgroup v2 writeback is only support on block devices so far
_require_block_device $SCRATCH_DEV

cgdir=$CGROUP2_PATH
iosize=$((1024 * 1024 * 8))

# Check cgroup read/write charges against expected values. Allow for some
# tolerance as different filesystems seem to account slightly differently.
check_cg()
{
	cgroot=$1
	cgname=$(basename $cgroot)
	expectedread=$2
	expectedwrite=$3
	readtol=$4
	writetol=$5
	rbytes=0
	wbytes=0

	iobytes=`cat $cgroot/io.stat | grep $smajor:$sminor`
	if [ $? == 0 ]; then
		rbytes=`echo $iobytes | awk '{ print $2 }' | \
			awk -F = '{ print $2 }'`
		wbytes=`echo $iobytes | awk '{ print $3 }' | \
			awk -F = '{ print $2 }'`
	fi

	_within_tolerance "read" $rbytes $expectedread $readtol -v
	_within_tolerance "write" $wbytes $expectedwrite $writetol -v
}

# Move current process to another cgroup.
switch_cg()
{
	mkdir -p $1
	echo $$ > $1/cgroup.procs
}

# Reset cgroup state for a new test.
reset()
{
	echo $$ > $cgdir/cgroup.procs
	rmdir $cgdir/$seq-cg* > /dev/null 2>&1
	$XFS_IO_PROG -fc "pwrite 0 $iosize" $SCRATCH_MNT/file \
		>> $seqres.full 2>&1
	umount $SCRATCH_MNT || _fail "umount failed"
	_mount $LOOP_DEV $SCRATCH_MNT || _fail "mount failed"
	stat $SCRATCH_MNT/file > /dev/null
}

# cgroup I/O accounting doesn't work on partitions. Use a loop device to rule
# that out.
LOOP_DEV=$(_create_loop_device $SCRATCH_DEV)
smajor=$((0x`stat -L -c %t $LOOP_DEV`))
sminor=$((0x`stat -L -c %T $LOOP_DEV`))

_mkfs_dev $LOOP_DEV >> $seqres.full 2>&1
_mount $LOOP_DEV $SCRATCH_MNT || _fail "mount failed"

drop_io_cgroup=
grep -q -w io $cgdir/cgroup.subtree_control || drop_io_cgroup=1

echo "+io" > $cgdir/cgroup.subtree_control || _fail "subtree control"

# Read and write from a single group.
echo "read/write"
reset
switch_cg $cgdir/$seq-cg
$XFS_IO_PROG -c "pread 0 $iosize" -c "pwrite 0 $iosize" -c fsync \
	$SCRATCH_MNT/file >> $seqres.full 2>&1
switch_cg $cgdir
$XFS_IO_PROG -c fsync $SCRATCH_MNT/file
check_cg $cgdir/$seq-cg $iosize $iosize 5% 5%

# Write from one cgroup then read and write from a second. Writes are charged to
# the first group and nothing to the second.
echo "write -> read/write"
reset
switch_cg $cgdir/$seq-cg
$XFS_IO_PROG -c "pwrite 0 $iosize" $SCRATCH_MNT/file >> $seqres.full 2>&1
switch_cg $cgdir/$seq-cg-2
$XFS_IO_PROG -c "pread 0 $iosize" -c "pwrite 0 $iosize" $SCRATCH_MNT/file \
	>> $seqres.full 2>&1
switch_cg $cgdir
$XFS_IO_PROG -c fsync $SCRATCH_MNT/file
# Use a fixed value tolerance for the expected value of zero here
# because filesystems might perform a small number of metadata reads to
# complete the write. On ext2/3 with 1k block size, the read bytes is
# as large as 33792.
check_cg $cgdir/$seq-cg 0 $iosize 33792 5%
check_cg $cgdir/$seq-cg-2 0 0 0 0

# Read from one cgroup, read & write from a second. Both reads and writes are
# charged to the first group and nothing to the second.
echo "read -> read/write"
reset
switch_cg $cgdir/$seq-cg
$XFS_IO_PROG -c "pread 0 $iosize" $SCRATCH_MNT/file >> $seqres.full 2>&1
switch_cg $cgdir/$seq-cg-2
$XFS_IO_PROG -c "pread 0 $iosize" -c "pwrite 0 $iosize" $SCRATCH_MNT/file \
	>> $seqres.full 2>&1
switch_cg $cgdir
$XFS_IO_PROG -c fsync $SCRATCH_MNT/file
check_cg $cgdir/$seq-cg $iosize $iosize 5% 5%
check_cg $cgdir/$seq-cg-2 0 0 0 0

if [ "$drop_io_cgroup" = 1 ]; then
	echo "-io" > $cgdir/cgroup.subtree_control || _fail "subtree control"
fi

# success, all done
status=0
exit