On Sun, Feb 05, 2017 at 02:21:44PM +0800, Xiong Zhou wrote:
> Mount TEST_DEV as non-DAX, SCRATCH_DEV as DAX, then
> do some IO between them. In this case we use mmap
> and dio/buffered IO read/write test programme.
>
> Signed-off-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Yep, this is fine.
> Signed-off-by: Xiong Zhou <xzhou@xxxxxxxxxx>
<>
> diff --git a/tests/generic/407 b/tests/generic/407
<>
> +do_tests()
> +{
> + # less than page size
> + t_mmap_dio_dax 1024
> + # page size
> + t_mmap_dio_dax `src/feature -s`
> + # bigger sizes, for PMD faults
> + t_mmap_dio_dax $((16 * 1024 * 1024))
> + t_mmap_dio_dax $((64 * 1024 * 1024))
> +}
> +
> +# make fs 2Mb aligned for PMD fault testing
> +if [[ $FSTYP =~ ext ]] ; then
> + _scratch_mkfs "-E stride=512,stripe_width=1" \
> + > /dev/null 2>&1
> +elif [[ $FSTYP =~ xfs ]] ; then
> + _scratch_mkfs "-d su=2m,sw=1" > /dev/null 2>&1
> +fi
> +
> +# mount SCRATCH_DEV with dax option, TEST_DEV not
> +export MOUNT_OPTIONS=""
> +export TEST_FS_MOUNT_OPTS=""
> +_test_cycle_mount
> +_fs_options $TEST_DEV | grep -qw "dax" && \
> + _notrun "we need $TEST_DEV mount without dax"
> +_scratch_mount "-o dax"
> +
> +tsize=$((64 * 1024 * 1024))
Ugh - for some reason 64 MiB files for me don't get PMDs on ext4 because the
ext4 block allocator gives us misaligned blocks. I'll follow up with them in
a new thread on the ext4 list and I'll cc you, Xiong.
If we up this to 128 MiB, so
tsize=$((128 * 1024 * 1024))
I get PMDs for both ext4 and XFS. Can we make this one change before
applying?
The rest looks good to me. Thanks for the tests!
Reviewed-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
--
To unsubscribe from this list: send the line "unsubscribe fstests" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
