shared: cgroup aware writeback accounting test

A test to perform reads/writes under various cgroups and verify that
I/Os are accounted properly according to cgroup aware writeback.
This is a generic test, but not all commonly used local filesystems
support cgroup aware writeback at the moment (i.e., XFS). Therefore,
this test currently requires ext4 or btrfs for the time being.

The common/cgroup2 file is copied from a separate cgroup related
patch from Shaohua Li that never made it upstream.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Reviewed-by: Eryu Guan <guaneryu@gmail.com>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>

common/cgroup2

@@ -0,0 +1,15 @@
+# cgroup2 specific common functions
+
+export CGROUP2_PATH="${CGROUP2_PATH:-/sys/fs/cgroup}"
+
+_require_cgroup2()
+{
+	if [ ! -f "${CGROUP2_PATH}/cgroup.subtree_control" ]; then
+		_notrun "Test requires cgroup2 enabled"
+	fi
+	if [[ ! $(cat ${CGROUP2_PATH}/cgroup.controllers) =~ $1 ]]; then
+		_notrun "Cgroup2 doesn't support $1 controller $1"
+	fi
+}
+
+/bin/true

tests/shared/011

@@ -0,0 +1,141 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2019 Red Hat, Inc.  All Rights Reserved.
+#
+# FS QA Test No. 011
+#
+# 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
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/filter
+. ./common/cgroup2
+
+# remove previous $seqres.full before test
+rm -f $seqres.full
+
+# real QA test starts here
+
+# Modify as appropriate.
+_supported_fs ext4 btrfs
+_supported_os Linux
+_require_scratch
+_require_cgroup2 io
+
+smajor=$((0x`stat -L -c %t $SCRATCH_DEV`))
+sminor=$((0x`stat -L -c %T $SCRATCH_DEV`))
+cgdir=$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
+	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 5% -v
+	_within_tolerance "write" $wbytes $expectedwrite 5% -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
+	_scratch_cycle_mount || _fail "mount failed"
+	stat $SCRATCH_MNT/file > /dev/null
+}
+
+_scratch_mkfs >> $seqres.full 2>&1
+_scratch_mount
+
+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
+
+# 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
+check_cg $cgdir/$seq-cg 0 $iosize
+check_cg $cgdir/$seq-cg-2 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
+check_cg $cgdir/$seq-cg-2 0 0
+
+echo "-io" > $cgdir/cgroup.subtree_control || _fail "subtree control"
+
+# success, all done
+status=0
+exit

tests/shared/011.out

@@ -0,0 +1,14 @@
+QA output created by 011
+read/write
+read is in range
+write is in range
+write -> read/write
+read is in range
+write is in range
+read is in range
+write is in range
+read -> read/write
+read is in range
+write is in range
+read is in range
+write is in range

tests/shared/group

@@ -13,6 +13,7 @@
 008 auto stress dedupe
 009 auto stress dedupe
 010 auto stress dedupe
+011 auto quick
 032 mkfs auto quick
 272 auto enospc rw
 289 auto quick