From e6ec116b67f46e0e7808276476554727b2e6240b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 1 Dec 2009 09:04:42 -0500 Subject: jbd2: Add ENOMEM checking in and for jbd2_journal_write_metadata_buffer() OOM happens. Signed-off-by: "Theodore Ts'o" --- fs/jbd2/commit.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs/jbd2/commit.c') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index d4cfd6d2779..8896c1d4feb 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -636,6 +636,10 @@ void jbd2_journal_commit_transaction(journal_t *journal) JBUFFER_TRACE(jh, "ph3: write metadata"); flags = jbd2_journal_write_metadata_buffer(commit_transaction, jh, &new_jh, blocknr); + if (flags < 0) { + jbd2_journal_abort(journal, flags); + continue; + } set_bit(BH_JWrite, &jh2bh(new_jh)->b_state); wbuf[bufs++] = jh2bh(new_jh); -- cgit v1.2.3-70-g09d2 From 94004ed726f38a841cc51f97c4a3f9eda9fbd0d9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 30 Sep 2009 22:16:33 +0200 Subject: kill wait_on_page_writeback_range All callers really want the more logical filemap_fdatawait_range interface, so convert them to use it and merge wait_on_page_writeback_range into filemap_fdatawait_range. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- Documentation/filesystems/vfs.txt | 2 +- fs/jbd2/commit.c | 2 +- fs/sync.c | 8 ++----- include/linux/fs.h | 2 -- mm/filemap.c | 49 +++++++++++---------------------------- 5 files changed, 18 insertions(+), 45 deletions(-) (limited to 'fs/jbd2/commit.c') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 623f094c9d8..3de2f32edd9 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -472,7 +472,7 @@ __sync_single_inode) to check if ->writepages has been successful in writing out the whole address_space. The Writeback tag is used by filemap*wait* and sync_page* functions, -via wait_on_page_writeback_range, to wait for all writeback to +via filemap_fdatawait_range, to wait for all writeback to complete. While waiting ->sync_page (if defined) will be called on each page that is found to require writeback. diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index d4cfd6d2779..c5edc13ccdd 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -286,7 +286,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, if (err) { /* * Because AS_EIO is cleared by - * wait_on_page_writeback_range(), set it again so + * filemap_fdatawait_range(), set it again so * that user process can get -EIO from fsync(). */ set_bit(AS_EIO, diff --git a/fs/sync.c b/fs/sync.c index b75ca68dc08..36752a68348 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -453,9 +453,7 @@ int do_sync_mapping_range(struct address_space *mapping, loff_t offset, ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { - ret = wait_on_page_writeback_range(mapping, - offset >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); + ret = filemap_fdatawait_range(mapping, offset, endbyte); if (ret < 0) goto out; } @@ -468,9 +466,7 @@ int do_sync_mapping_range(struct address_space *mapping, loff_t offset, } if (flags & SYNC_FILE_RANGE_WAIT_AFTER) { - ret = wait_on_page_writeback_range(mapping, - offset >> PAGE_CACHE_SHIFT, - endbyte >> PAGE_CACHE_SHIFT); + ret = filemap_fdatawait_range(mapping, offset, endbyte); } out: return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index 891f7d642e5..a057f48eb15 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2091,8 +2091,6 @@ extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); -extern int wait_on_page_writeback_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); extern int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); extern int filemap_fdatawrite_range(struct address_space *mapping, diff --git a/mm/filemap.c b/mm/filemap.c index c3d3506ecab..8b4d88f9249 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -260,27 +260,27 @@ int filemap_flush(struct address_space *mapping) EXPORT_SYMBOL(filemap_flush); /** - * wait_on_page_writeback_range - wait for writeback to complete - * @mapping: target address_space - * @start: beginning page index - * @end: ending page index + * filemap_fdatawait_range - wait for writeback to complete + * @mapping: address space structure to wait for + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) * - * Wait for writeback to complete against pages indexed by start->end - * inclusive + * Walk the list of under-writeback pages of the given address space + * in the given range and wait for all of them. */ -int wait_on_page_writeback_range(struct address_space *mapping, - pgoff_t start, pgoff_t end) +int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, + loff_t end_byte) { + pgoff_t index = start_byte >> PAGE_CACHE_SHIFT; + pgoff_t end = end_byte >> PAGE_CACHE_SHIFT; struct pagevec pvec; int nr_pages; int ret = 0; - pgoff_t index; - if (end < start) + if (end_byte < start_byte) return 0; pagevec_init(&pvec, 0); - index = start; while ((index <= end) && (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_WRITEBACK, @@ -310,25 +310,6 @@ int wait_on_page_writeback_range(struct address_space *mapping, return ret; } - -/** - * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range - * @mapping: address space structure to wait for - * @start: offset in bytes where the range starts - * @end: offset in bytes where the range ends (inclusive) - * - * Walk the list of under-writeback pages of the given address space - * in the given range and wait for all of them. - * - * This is just a simple wrapper so that callers don't have to convert offsets - * to page indexes themselves - */ -int filemap_fdatawait_range(struct address_space *mapping, loff_t start, - loff_t end) -{ - return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT, - end >> PAGE_CACHE_SHIFT); -} EXPORT_SYMBOL(filemap_fdatawait_range); /** @@ -345,8 +326,7 @@ int filemap_fdatawait(struct address_space *mapping) if (i_size == 0) return 0; - return wait_on_page_writeback_range(mapping, 0, - (i_size - 1) >> PAGE_CACHE_SHIFT); + return filemap_fdatawait_range(mapping, 0, i_size - 1); } EXPORT_SYMBOL(filemap_fdatawait); @@ -393,9 +373,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) { - int err2 = wait_on_page_writeback_range(mapping, - lstart >> PAGE_CACHE_SHIFT, - lend >> PAGE_CACHE_SHIFT); + int err2 = filemap_fdatawait_range(mapping, + lstart, lend); if (!err) err = err2; } -- cgit v1.2.3-70-g09d2 From cc3e1bea5d87635c519da657303690f5538bb4eb Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 23 Dec 2009 06:52:08 -0500 Subject: ext4, jbd2: Add barriers for file systems with exernal journals This is a bit complicated because we are trying to optimize when we send barriers to the fs data disk. We could just throw in an extra barrier to the data disk whenever we send a barrier to the journal disk, but that's not always strictly necessary. We only need to send a barrier during a commit when there are data blocks which are must be written out due to an inode written in ordered mode, or if fsync() depends on the commit to force data blocks to disk. Finally, before we drop transactions from the beginning of the journal during a checkpoint operation, we need to guarantee that any blocks that were flushed out to the data disk are firmly on the rust platter before we drop the transaction from the journal. Thanks to Oleg Drokin for pointing out this flaw in ext3/ext4. Signed-off-by: "Theodore Ts'o" --- fs/ext4/fsync.c | 16 ++++++++++++++-- fs/jbd2/checkpoint.c | 15 +++++++++++++++ fs/jbd2/commit.c | 19 +++++++++++-------- include/linux/jbd2.h | 1 + 4 files changed, 41 insertions(+), 10 deletions(-) (limited to 'fs/jbd2/commit.c') diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 0b22497d92e..98bd140aad0 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -88,9 +88,21 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) return ext4_force_commit(inode->i_sb); commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; - if (jbd2_log_start_commit(journal, commit_tid)) + if (jbd2_log_start_commit(journal, commit_tid)) { + /* + * When the journal is on a different device than the + * fs data disk, we need to issue the barrier in + * writeback mode. (In ordered mode, the jbd2 layer + * will take care of issuing the barrier. In + * data=journal, all of the data blocks are written to + * the journal device.) + */ + if (ext4_should_writeback_data(inode) && + (journal->j_fs_dev != journal->j_dev) && + (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(inode->i_sb->s_bdev, NULL); jbd2_log_wait_commit(journal, commit_tid); - else if (journal->j_flags & JBD2_BARRIER) + } else if (journal->j_flags & JBD2_BARRIER) blkdev_issue_flush(inode->i_sb->s_bdev, NULL); return ret; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index ca0f5eb62b2..88684937095 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -22,6 +22,7 @@ #include #include #include +#include #include /* @@ -515,6 +516,20 @@ int jbd2_cleanup_journal_tail(journal_t *journal) journal->j_tail_sequence = first_tid; journal->j_tail = blocknr; spin_unlock(&journal->j_state_lock); + + /* + * If there is an external journal, we need to make sure that + * any data blocks that were recently written out --- perhaps + * by jbd2_log_do_checkpoint() --- are flushed out before we + * drop the transactions from the external journal. It's + * unlikely this will be necessary, especially with a + * appropriately sized journal, but we need this to guarantee + * correctness. Fortunately jbd2_cleanup_journal_tail() + * doesn't get called all that often. + */ + if ((journal->j_fs_dev != journal->j_dev) && + (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(journal->j_fs_dev, NULL); if (!(journal->j_flags & JBD2_ABORT)) jbd2_journal_update_superblock(journal, 1); return 0; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 6a10238d2c6..1bc74b6f26d 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -259,6 +259,7 @@ static int journal_submit_data_buffers(journal_t *journal, ret = err; spin_lock(&journal->j_list_lock); J_ASSERT(jinode->i_transaction == commit_transaction); + commit_transaction->t_flushed_data_blocks = 1; jinode->i_flags &= ~JI_COMMIT_RUNNING; wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } @@ -708,8 +709,17 @@ start_journal_io: } } - /* Done it all: now write the commit record asynchronously. */ + /* + * If the journal is not located on the file system device, + * then we must flush the file system device before we issue + * the commit record + */ + if (commit_transaction->t_flushed_data_blocks && + (journal->j_fs_dev != journal->j_dev) && + (journal->j_flags & JBD2_BARRIER)) + blkdev_issue_flush(journal->j_fs_dev, NULL); + /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { err = journal_submit_commit_record(journal, commit_transaction, @@ -720,13 +730,6 @@ start_journal_io: blkdev_issue_flush(journal->j_dev, NULL); } - /* - * This is the right place to wait for data buffers both for ASYNC - * and !ASYNC commit. If commit is ASYNC, we need to wait only after - * the commit block went to disk (which happens above). If commit is - * SYNC, we need to wait for data buffers before we start writing - * commit block, which happens below in such setting. - */ err = journal_finish_inode_data_buffers(journal, commit_transaction); if (err) { printk(KERN_WARNING diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f1011f7f3d4..638ce4554c7 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -653,6 +653,7 @@ struct transaction_s * waiting for it to finish. */ unsigned int t_synchronous_commit:1; + unsigned int t_flushed_data_blocks:1; /* * For use by the filesystem to store fs-specific data -- cgit v1.2.3-70-g09d2