Re: [RFC PATCH v9 0/3] migrate ocfs2 DIO from buffer_head to iomap

From: Joseph Qi

Date: Fri Nov 20 2026 - 20:13:38 EST


Thanks for this work.
I'll apply this series on top of next-20261119 and run a full test first.

Thanks,
Joseph

On 11/20/26 2:00 PM, Heming Zhao wrote:
> This patch set migrates ocfs2 Direct I/O (DIO) from buffer_head mode
> to iomap mode. It is based on commit aebb72744764 (v7.4-rc3), and
> also incorporates Joseph's code and ideas from [1]:
>
> V9 changelog:
>
> Address sashiko's review comments [3] (all changes are in patch [3/3]):
>
> ocfs2_file_write_to_iter():
> - switch pr lock to ex when DIO falls back to buffered IO
> - Fall back to buffered I/O for a direct write when block size is smaller
> than the page size and the write does not cover whole pages
> - clear orphan when rw_lock is still held
>
> ocfs2_dio_wr_map_blocks may use a value beyand u32 to call
> ocfs2_clusters_to_blocks()
>
> initialize oi->ip_dio_orphan_pid and oi->ip_dio_orphan_end in
> ocfs2_inode_init_once()
>
> --------------
> # test report
>
> This patch set has been tested on 7.4-rc3 kernel
>
> ## ltp
>
> runltp -f dio -d /mnt/ocfs2/
>
> results: passed
>
> ## xfstests
>
> ./check -g quick -T -b -s ocfs2 -e generic/081 \
> -e generic/266 -e generic/272 -e generic/281 \
> -e generic/338 -e generic/347 -e generic/361 \
> -e generic/628 -e generic/629 -e generic/648 -e generic/650
>
> OCFS2_MKFS_LOCAL_OPT="-b 2K -C 4K --fs-features=local --fs-feature-level=max-features"
> Failures: generic/003 generic/056 generic/091 generic/094 generic/177
> generic/211 generic/225 generic/263 generic/321 generic/322 generic/329
> generic/331 generic/370 generic/376 generic/424 generic/448 generic/467
> generic/477 generic/481 generic/498 generic/510 generic/512 generic/513
> generic/534 generic/537 generic/552 generic/557 generic/563 generic/578
> generic/588 generic/607 generic/620 generic/630 generic/755 generic/760
> generic/771 generic/777 generic/779 generic/784
> Failed 39 of 632 tests
>
> OCFS2_MKFS_LOCAL_OPT="-b 4K -C 4K --fs-features=local --fs-feature-level=max-features"
> Failures: generic/003 generic/056 generic/070 generic/091 generic/094
> generic/177 generic/211 generic/225 generic/263 generic/321 generic/322
> generic/329 generic/331 generic/370 generic/376 generic/424 generic/448
> generic/467 generic/477 generic/481 generic/498 generic/510 generic/512
> generic/513 generic/534 generic/537 generic/552 generic/557 generic/563
> generic/578 generic/588 generic/607 generic/620 generic/630 generic/755
> generic/760 generic/771 generic/777 generic/779 generic/784
> Failed 40 of 632 tests
>
> OCFS2_MKFS_LOCAL_OPT="-b 2K -C 8K --fs-features=local --fs-feature-level=max-features"
> Failures: generic/003 generic/056 generic/075 generic/091 generic/094
> generic/112 generic/177 generic/211 generic/225 generic/263 generic/321
> generic/322 generic/329 generic/331 generic/370 generic/376 generic/424
> generic/448 generic/467 generic/477 generic/481 generic/498 generic/510
> generic/512 generic/513 generic/534 generic/537 generic/552 generic/557
> generic/563 generic/564 generic/578 generic/588 generic/607 generic/620
> generic/630 generic/755 generic/759 generic/760 generic/771 generic/777
> generic/779 generic/784 ocfs2/001
> Failed 44 of 632 tests
>
> ## fio
>
> (4k blocksize 4k clustersize, local mount)
>
> fio --direct=1 --iodepth=32 --rw=write --ioengine=libaio --bs=128k --size=1g \
> --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> before patch: write: IOPS=32.2k, BW=4028MiB/s
> after patch: write: IOPS=38.6k, BW=4824MiB/s
>
> fio --direct=1 --iodepth=32 --rw=read --ioengine=libaio --bs=128k --size=1g \
> --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> before patch: read: IOPS=49.1k, BW=6132MiB/s
> after patch: read: IOPS=50.9k, BW=6360MiB/s
>
> fio --direct=1 --iodepth=32 --rw=randwrite --ioengine=libaio --bs=4k \
> --size=1g --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> before patch: write: IOPS=14.4k, BW=56.4MiB/s
> after patch: write: IOPS=14.4k, BW=56.1MiB/s
>
> fio --direct=1 --iodepth=32 --rw=randwrite --ioengine=libaio --bs=4k \
> --size=1g --numjobs=4 --runtime=100 --group_reporting --filename=/mnt/ocfs2/write.1g --name=tst
> before patch: read: IOPS=382k, BW=1492MiB/s
> after patch: read: IOPS=419k, BW=1637MiB/s
>
> ------
> [1]:
> https://gitee.com/anolis/storage-cloud-kernel/commit/ea3fe75e2060118ba093e90b1cd34fa382914b29
>
> [2]:
> https://sashiko.dev/#/patchset/20261103135605.22943-1-heming.zhao%40suse.com
>
> [3]:
> v1 patch set:
> https://lore.kernel.org/ocfs2-devel/20260724052559.15409-1-heming.zhao@xxxxxxxx/
> v2 patch set:
> https://lore.kernel.org/ocfs2-devel/20260727061802.18485-1-heming.zhao@xxxxxxxx/
> v3 patch set:
> https://lore.kernel.org/ocfs2-devel/20261018143319.22329-1-heming.zhao@xxxxxxxx/
> v3 sashiko review:
> https://sashiko.dev/#/patchset/20261018143319.22329-1-heming.zhao%40suse.com
> v4 patch set:
> https://lore.kernel.org/ocfs2-devel/20261103135605.22943-1-heming.zhao@xxxxxxxx/
> v4 sashiko review:
> https://sashiko.dev/#/patchset/20261103135605.22943-1-heming.zhao%40suse.com
> v5 patch set:
> https://lore.kernel.org/ocfs2-devel/20261105071930.16399-1-heming.zhao@xxxxxxxx/
> v5 sashiko review:
> https://sashiko.dev/#/patchset/20261105071930.16399-1-heming.zhao%40suse.com
> v6 patch set:
> https://lore.kernel.org/ocfs2-devel/20261115154013.9379-1-heming.zhao@xxxxxxxx/
> v6 sashiko review:
> https://sashiko.dev/#/patchset/20261115154013.9379-1-heming.zhao%40suse.com
> v7 patch set:
> https://lore.kernel.org/ocfs2-devel/20261118002050.9019-1-heming.zhao@xxxxxxxx/
> v7 sashiko review:
> - https://sashiko.dev/#/patchset/20261117150053.18417-1-heming.zhao%40suse.com
> - https://sashiko.dev/#/patchset/20261118002050.9019-1-heming.zhao%40suse.com
> v8 patch set:
> https://lore.kernel.org/ocfs2-devel/20261119064029.11910-1-heming.zhao@xxxxxxxx/
> v8 sashiko review:
> https://sashiko.dev/#/patchset/20261119064029.11910-1-heming.zhao%40suse.com
>
> -----------------------
>
> Heming Zhao (3):
> ocfs2: Add new ocfs2_map_blocks() to introduce iomap feature
> ocfs2: switch DIO read path from buffer_head to iomap
> ocfs2: switch dio write path from buffer_head to iomap
>
> fs/ocfs2/Kconfig | 2 +-
> fs/ocfs2/aops.c | 1685 ++++++++++++++++++++++++++++++++---------
> fs/ocfs2/aops.h | 43 +-
> fs/ocfs2/extent_map.c | 34 +-
> fs/ocfs2/extent_map.h | 3 +
> fs/ocfs2/file.c | 314 +++++++-
> fs/ocfs2/inode.h | 9 +
> fs/ocfs2/mmap.c | 2 +-
> fs/ocfs2/ocfs2.h | 25 +-
> fs/ocfs2/super.c | 3 +
> 10 files changed, 1690 insertions(+), 430 deletions(-)
>