The patch titled
Subject: ocfs2: do not change i_size in write_end for direct io
has been added to the -mm tree. Its filename is
ocfs2-do-not-change-i_size-in-write_end-for-direct-io.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/ocfs2-do-not-change-i_size-in-write_end-for-direct-io.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/ocfs2-do-not-change-i_size-in-write_end-for-direct-io.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Ryan Ding <ryan.ding@xxxxxxxxxx>
Subject: ocfs2: do not change i_size in write_end for direct io
To support direct io in ocfs2_write_begin_nolock & ocfs2_write_end_nolock.
Append direct io do not change i_size in get block phase. It only move to
orphan when starting write. After data is written to disk, it will delete
itself from orphan and update i_size. So skip i_size change section in
write_begin for direct io.
And when there is no extents alloc, no meta data changes needed for direct
io (since write_begin start trans for 2 reason: alloc extents & change
i_size. Now none of them needed). So we can skip start trans procedure.
Signed-off-by: Ryan Ding <ryan.ding@xxxxxxxxxx>
Reviewed-by: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Cc: Joseph Qi <joseph.qi@xxxxxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/ocfs2/aops.c | 79 ++++++++++++++++++++++++++--------------------
1 file changed, 46 insertions(+), 33 deletions(-)
diff -puN fs/ocfs2/aops.c~ocfs2-do-not-change-i_size-in-write_end-for-direct-io fs/ocfs2/aops.c
--- a/fs/ocfs2/aops.c~ocfs2-do-not-change-i_size-in-write_end-for-direct-io
+++ a/fs/ocfs2/aops.c
@@ -2036,8 +2036,10 @@ static int ocfs2_expand_nonsparse_inode(
if (ret)
mlog_errno(ret);
- wc->w_first_new_cpos =
- ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+ /* There is no wc if this is call from direct. */
+ if (wc)
+ wc->w_first_new_cpos =
+ ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
return ret;
}
@@ -2128,14 +2130,17 @@ try_again:
}
}
- if (ocfs2_sparse_alloc(osb))
- ret = ocfs2_zero_tail(inode, di_bh, pos);
- else
- ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
- wc);
- if (ret) {
- mlog_errno(ret);
- goto out;
+ /* Direct io change i_size late, should not zero tail here. */
+ if (type != OCFS2_WRITE_DIRECT) {
+ if (ocfs2_sparse_alloc(osb))
+ ret = ocfs2_zero_tail(inode, di_bh, pos);
+ else
+ ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+ len, wc);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
}
ret = ocfs2_check_range_for_refcount(inode, pos, len);
@@ -2196,8 +2201,9 @@ try_again:
credits = ocfs2_calc_extend_credits(inode->i_sb,
&di->id2.i_list);
-
- }
+ } else if (type == OCFS2_WRITE_DIRECT)
+ /* direct write needs not to start trans if no extents alloc. */
+ goto success;
/*
* We have to zero sparse allocated clusters, unwritten extent clusters,
@@ -2395,12 +2401,14 @@ int ocfs2_write_end_nolock(struct addres
handle_t *handle = wc->w_handle;
struct page *tmppage;
- ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- copied = ret;
- mlog_errno(ret);
- goto out;
+ if (handle) {
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
+ wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ copied = ret;
+ mlog_errno(ret);
+ goto out;
+ }
}
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
@@ -2443,25 +2451,29 @@ int ocfs2_write_end_nolock(struct addres
}
if (page_has_buffers(tmppage)) {
- if (ocfs2_should_order_data(inode))
- ocfs2_jbd2_file_inode(wc->w_handle, inode);
+ if (handle && ocfs2_should_order_data(inode))
+ ocfs2_jbd2_file_inode(handle, inode);
block_commit_write(tmppage, from, to);
}
}
out_write_size:
- pos += copied;
- if (pos > i_size_read(inode)) {
- i_size_write(inode, pos);
- mark_inode_dirty(inode);
- }
- inode->i_blocks = ocfs2_inode_sector_count(inode);
- di->i_size = cpu_to_le64((u64)i_size_read(inode));
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
- di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
- ocfs2_update_inode_fsync_trans(handle, inode, 1);
- ocfs2_journal_dirty(handle, wc->w_di_bh);
+ /* Direct io do not update i_size here. */
+ if (wc->w_type != OCFS2_WRITE_DIRECT) {
+ pos += copied;
+ if (pos > i_size_read(inode)) {
+ i_size_write(inode, pos);
+ mark_inode_dirty(inode);
+ }
+ inode->i_blocks = ocfs2_inode_sector_count(inode);
+ di->i_size = cpu_to_le64((u64)i_size_read(inode));
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+ di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ ocfs2_update_inode_fsync_trans(handle, inode, 1);
+ }
+ if (handle)
+ ocfs2_journal_dirty(handle, wc->w_di_bh);
out:
/* unlock pages before dealloc since it needs acquiring j_trans_barrier
@@ -2471,7 +2483,8 @@ out:
*/
ocfs2_unlock_pages(wc);
- ocfs2_commit_trans(osb, handle);
+ if (handle)
+ ocfs2_commit_trans(osb, handle);
ocfs2_run_deallocs(osb, &wc->w_dealloc);
_
Patches currently in -mm which might be from ryan.ding@xxxxxxxxxx are
ocfs2-add-ocfs2_write_type_t-type-to-identify-the-caller-of-write.patch
ocfs2-use-c_new-to-indicate-newly-allocated-extents.patch
ocfs2-test-target-page-before-change-it.patch
ocfs2-do-not-change-i_size-in-write_end-for-direct-io.patch
ocfs2-return-the-physical-address-in-ocfs2_write_cluster.patch
ocfs2-record-unwritten-extents-when-populate-write-desc.patch
ocfs2-fix-sparse-file-data-ordering-issue-in-direct-io.patch
ocfs2-code-clean-up-for-direct-io.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
