ext4: Test atomic writes allocation and write codepaths with bigalloc

This test does a parallel RWF_ATOMIC IO on a multiple truncated files in
a small FS. The idea is to stress ext4 allocator to ensure we are able
to handle low space scenarios correctly with atomic writes. We brute
force this for different blocksize and clustersizes and after each
iteration we ensure the data was not torn or corrupted using fio crc
verification.

Note that in this test we use overlapping atomic writes of same io size.
Although serializing racing writes is not guaranteed for RWF_ATOMIC,
NVMe and SCSI provide this guarantee as an inseparable feature to
power-fail atomicity. Keeping the iosize as same also ensures that ext4
doesn't tear the write due to racing ioend unwritten conversion.

The value of this test is that we make sure the RWF_ATOMIC is handled
correctly by ext4 as well as test that the block layer doesn't split or
only generate multiple bios for an atomic write.

Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Signed-off-by: Zorro Lang <zlang@kernel.org>

diff --git a/tests/ext4/062 b/tests/ext4/062
new file mode 100755 (executable)
index 0000000..05cce69
--- /dev/null
+++ b/tests/ext4/062
@@ -0,0 +1,203 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2025 IBM Corporation. All Rights Reserved.
+#
+# FS QA Test 062
+#
+# This test does a parallel RWF_ATOMIC IO on a multiple truncated files in a
+# small FS. The idea is to stress ext4 allocator to ensure we are able to
+# handle low space scenarios correctly with atomic writes.. We brute force this
+# for all possible blocksize and clustersizes and after each iteration we
+# ensure the data was not torn or corrupted using fio crc verification.
+#
+# Note that in this test we use overlapping atomic writes of same io size.
+# Although serializing racing writes is not guaranteed for RWF_ATOMIC, NVMe and
+# SCSI provide this guarantee as an inseparable feature to power-fail
+# atomicity. Keeping the iosize as same also ensures that ext4 doesn't tear the
+# write due to racing ioend unwritten conversion.
+#
+# The value of this test is that we make sure the RWF_ATOMIC is handled
+# correctly by ext4 as well as test that the block layer doesn't split or only
+# generate multiple bios for an atomic write.
+#
+
+. ./common/preamble
+. ./common/atomicwrites
+
+_begin_fstest auto rw stress atomicwrites
+
+_require_scratch_write_atomic
+_require_fio_atomic_writes
+_require_aiodio
+
+FSSIZE=$((360*1024*1024))
+FIO_LOAD=$(($(nproc) * LOAD_FACTOR))
+
+# Calculate bs as per bdev atomic write units.
+bdev_awu_min=$(_get_atomic_write_unit_min $SCRATCH_DEV)
+bdev_awu_max=$(_get_atomic_write_unit_max $SCRATCH_DEV)
+bs=$(_max 4096 "$bdev_awu_min")
+
+function create_fio_configs()
+{
+       local bsize=$1
+       create_fio_aw_config $bsize
+       create_fio_verify_config $bsize
+}
+
+function create_fio_verify_config()
+{
+       local bsize=$1
+cat >$fio_verify_config <<EOF
+       [global]
+       direct=1
+       ioengine=libaio
+       rw=read
+       bs=$bsize
+       fallocate=truncate
+       size=$((FSSIZE / 12))
+       iodepth=$FIO_LOAD
+       numjobs=$FIO_LOAD
+       group_reporting=1
+       atomic=1
+
+       verify_only=1
+       verify_state_save=0
+       verify=crc32c
+       verify_fatal=1
+       verify_write_sequence=0
+
+       [verify-job1]
+       filename=$SCRATCH_MNT/testfile-job1
+
+       [verify-job2]
+       filename=$SCRATCH_MNT/testfile-job2
+
+       [verify-job3]
+       filename=$SCRATCH_MNT/testfile-job3
+
+       [verify-job4]
+       filename=$SCRATCH_MNT/testfile-job4
+
+       [verify-job5]
+       filename=$SCRATCH_MNT/testfile-job5
+
+       [verify-job6]
+       filename=$SCRATCH_MNT/testfile-job6
+
+       [verify-job7]
+       filename=$SCRATCH_MNT/testfile-job7
+
+       [verify-job8]
+       filename=$SCRATCH_MNT/testfile-job8
+
+EOF
+}
+
+function create_fio_aw_config()
+{
+       local bsize=$1
+cat >$fio_aw_config <<EOF
+       [global]
+       direct=1
+       ioengine=libaio
+       rw=randwrite
+       bs=$bsize
+       fallocate=truncate
+       size=$((FSSIZE / 12))
+       iodepth=$FIO_LOAD
+       numjobs=$FIO_LOAD
+       group_reporting=1
+       atomic=1
+
+       verify_state_save=0
+       verify=crc32c
+       do_verify=0
+
+       [write-job1]
+       filename=$SCRATCH_MNT/testfile-job1
+
+       [write-job2]
+       filename=$SCRATCH_MNT/testfile-job2
+
+       [write-job3]
+       filename=$SCRATCH_MNT/testfile-job3
+
+       [write-job4]
+       filename=$SCRATCH_MNT/testfile-job4
+
+       [write-job5]
+       filename=$SCRATCH_MNT/testfile-job5
+
+       [write-job6]
+       filename=$SCRATCH_MNT/testfile-job6
+
+       [write-job7]
+       filename=$SCRATCH_MNT/testfile-job7
+
+       [write-job8]
+       filename=$SCRATCH_MNT/testfile-job8
+
+EOF
+}
+
+run_test_one() {
+       local bs=$1
+       local cs=$2
+       local iosize=$3
+
+       MKFS_OPTIONS="-O bigalloc -b $bs -C $cs"
+       _scratch_mkfs_sized "$FSSIZE" >> $seqres.full 2>&1 || return
+       if _try_scratch_mount >> $seqres.full 2>&1; then
+               echo "Testing: bs=$bs cs=$cs iosize=$iosize" >> $seqres.full
+
+               touch $SCRATCH_MNT/f1
+               create_fio_configs $iosize
+
+               cat $fio_aw_config >> $seqres.full
+               cat $fio_verify_config >> $seqres.full
+
+               $FIO_PROG $fio_aw_config >> $seqres.full
+               ret1=$?
+
+               $FIO_PROG $fio_verify_config  >> $seqres.full
+               ret2=$?
+
+               _scratch_unmount
+
+               [[ $ret1 -eq 0 && $ret2 -eq 0 ]] || _fail "fio with atomic write failed"
+       fi
+}
+
+run_test() {
+       local bs=$1
+
+       # cluster sizes above 16 x blocksize are experimental so avoid them
+       # Also, cap cluster size at 128kb to keep it reasonable for large
+       # blocks size
+       max_cs=$(_min $((16 * bs)) "$bdev_awu_max" $((128 * 1024)))
+
+       # Fuzz for combinations of blocksize, clustersize and
+       # iosize that cover most of the cases
+       run_test_one $bs $bs $bs
+       run_test_one $bs $max_cs $bs
+       run_test_one $bs $max_cs $max_cs
+       run_test_one $bs $max_cs $(_max "$((max_cs/2))" $bs)
+}
+
+# Let's create a sample fio config to check whether fio supports all options.
+fio_aw_config=$tmp.aw.fio
+fio_verify_config=$tmp.verify.fio
+fio_out=$tmp.fio.out
+
+create_fio_configs $bs
+_require_fio $fio_aw_config
+
+for ((bs=$bs; bs <= $(_get_page_size); bs = $bs << 1)); do
+       run_test $bs $cs $iosize
+done
+
+# success, all done
+echo Silence is golden
+status=0
+exit

diff --git a/tests/ext4/062.out b/tests/ext4/062.out
new file mode 100644 (file)
index 0000000..a1578f4
--- /dev/null
+++ b/tests/ext4/062.out
@@ -0,0 +1,2 @@
+QA output created by 062
+Silence is golden