The patch titled
Subject: ocfs2: wait for orphan recovery first once append O_DIRECT write crash
has been added to the -mm tree. Its filename is
ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash.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: Joseph Qi <joseph.qi@xxxxxxxxxx>
Subject: ocfs2: wait for orphan recovery first once append O_DIRECT write crash
If one node has crashed with orphan entry leftover, another node which do
append O_DIRECT write to the same file will override the
i_dio_orphaned_slot. Then the old entry won't be cleaned forever. If
this case happens, we let it wait for orphan recovery first.
Signed-off-by: Joseph Qi <joseph.qi@xxxxxxxxxx>
Cc: Weiwei Wang <wangww631@xxxxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxxx>
Cc: Xuejiufei <xuejiufei@xxxxxxxxxx>
Cc: alex chen <alex.chen@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/ocfs2/inode.h | 2 ++
fs/ocfs2/journal.c | 2 ++
fs/ocfs2/namei.c | 37 +++++++++++++++++++++++++++++++++++++
fs/ocfs2/super.c | 2 ++
4 files changed, 43 insertions(+)
diff -puN fs/ocfs2/inode.h~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash fs/ocfs2/inode.h
--- a/fs/ocfs2/inode.h~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash
+++ a/fs/ocfs2/inode.h
@@ -81,6 +81,8 @@ struct ocfs2_inode_info
tid_t i_sync_tid;
tid_t i_datasync_tid;
+ wait_queue_head_t append_dio_wq;
+
struct dquot *i_dquot[MAXQUOTAS];
};
diff -puN fs/ocfs2/journal.c~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash fs/ocfs2/journal.c
--- a/fs/ocfs2/journal.c~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash
+++ a/fs/ocfs2/journal.c
@@ -2205,6 +2205,8 @@ static int ocfs2_recover_orphans(struct
ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
if (ret)
mlog_errno(ret);
+
+ wake_up(&OCFS2_I(inode)->append_dio_wq);
} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
next:
diff -puN fs/ocfs2/namei.c~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash fs/ocfs2/namei.c
--- a/fs/ocfs2/namei.c~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash
+++ a/fs/ocfs2/namei.c
@@ -2578,6 +2578,27 @@ leave:
return status;
}
+static int ocfs2_dio_orphan_recovered(struct inode *inode)
+{
+ int ret;
+ struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di = NULL;
+
+ ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ return 0;
+ }
+
+ di = (struct ocfs2_dinode *) di_bh->b_data;
+ ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+
+ return ret;
+}
+
+#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
struct inode *inode)
{
@@ -2587,13 +2608,29 @@ int ocfs2_add_inode_to_orphan(struct ocf
struct buffer_head *di_bh = NULL;
int status = 0;
handle_t *handle = NULL;
+ struct ocfs2_dinode *di = NULL;
+restart:
status = ocfs2_inode_lock(inode, &di_bh, 1);
if (status < 0) {
mlog_errno(status);
goto bail;
}
+ di = (struct ocfs2_dinode *) di_bh->b_data;
+ /*
+ * Another append dio crashed?
+ * If so, wait for recovery first.
+ */
+ if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+ ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+ wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
+ ocfs2_dio_orphan_recovered(inode),
+ msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
+ goto restart;
+ }
+
status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
OCFS2_I(inode)->ip_blkno,
orphan_name,
diff -puN fs/ocfs2/super.c~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash fs/ocfs2/super.c
--- a/fs/ocfs2/super.c~ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash
+++ a/fs/ocfs2/super.c
@@ -1776,6 +1776,8 @@ static void ocfs2_inode_init_once(void *
ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
ocfs2_lock_res_init_once(&oi->ip_open_lockres);
+ init_waitqueue_head(&oi->append_dio_wq);
+
ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
&ocfs2_inode_caching_ops);
_
Patches currently in -mm which might be from joseph.qi@xxxxxxxxxx are
ocfs2-fix-snprintf-format-specifier-in-dlmdebugc.patch
ocfs2-fix-journal-commit-deadlock-in-ocfs2_convert_inline_data_to_extents.patch
ocfs2-add-a-mount-option-journal_async_commit-on-ocfs2-filesystem.patch
linux-next.patch
ocfs2-prepare-some-interfaces-used-in-append-direct-io.patch
ocfs2-add-functions-to-add-and-remove-inode-in-orphan-dir.patch
ocfs2-add-orphan-recovery-types-in-ocfs2_recover_orphans.patch
ocfs2-implement-ocfs2_direct_io_write.patch
ocfs2-implement-ocfs2_direct_io_write-fix.patch
ocfs2-allocate-blocks-in-ocfs2_direct_io_get_blocks.patch
ocfs2-do-not-fallback-to-buffer-i-o-write-if-appending.patch
ocfs2-complete-the-rest-request-through-buffer-io.patch
ocfs2-wait-for-orphan-recovery-first-once-append-o_direct-write-crash.patch
ocfs2-set-append-dio-as-a-ro-compat-feature.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
