From 736603ab297506f4396cb5af592004499950fcfd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: jbd2: Add commit time into the commit block Carlo Wood has demonstrated that it's possible to recover deleted files from the journal. Something that will make this easier is if we can put the time of the commit into commit block. Signed-off-by: "Theodore Ts'o" --- include/linux/jbd2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d147f0f9036..ec9cadf5822 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -168,6 +168,8 @@ struct commit_header { unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; + __be64 h_commit_sec; + __be32 h_commit_nsec; }; /* -- cgit v1.2.3 From f4c0a0fdfae708f7aa438c27a380ed4071294e11 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: vfs: export filemap_fdatawrite_range() Make filemap_fdatawrite_range() function public, so that it can later be used in ordered mode rewrite by JBD/JBD2. Signed-off-by: Jan Kara --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index d8e2762ed14..97f992adc62 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1740,6 +1740,8 @@ 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, + loff_t start, loff_t end); extern long do_fsync(struct file *file, int datasync); extern void sync_supers(void); -- cgit v1.2.3 From c851ed540173736e60d48b53b91a16ea5c903896 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: jbd2: Implement data=ordered mode handling via inodes This patch adds necessary framework into JBD2 to be able to track inodes with each transaction and write-out their dirty data during transaction commit time. This new ordered mode brings all sorts of advantages such as possibility to get rid of journal heads and buffer heads for data buffers in ordered mode, better ordering of writes on transaction commit, simplification of some JBD code, no more anonymous pages when truncate of data being committed happens. Also with this new ordered mode, delayed allocation on ordered mode is much simpler. Signed-off-by: Jan Kara --- include/linux/jbd2.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index ec9cadf5822..622c3d8ca4e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -381,6 +381,38 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) bit_spin_unlock(BH_JournalHead, &bh->b_state); } +/* Flags in jbd_inode->i_flags */ +#define __JI_COMMIT_RUNNING 0 +/* Commit of the inode data in progress. We use this flag to protect us from + * concurrent deletion of inode. We cannot use reference to inode for this + * since we cannot afford doing last iput() on behalf of kjournald + */ +#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) + +/** + * struct jbd_inode is the structure linking inodes in ordered mode + * present in a transaction so that we can sync them during commit. + */ +struct jbd2_inode { + /* Which transaction does this inode belong to? Either the running + * transaction or the committing one. [j_list_lock] */ + transaction_t *i_transaction; + + /* Pointer to the running transaction modifying inode's data in case + * there is already a committing transaction touching it. [j_list_lock] */ + transaction_t *i_next_transaction; + + /* List of inodes in the i_transaction [j_list_lock] */ + struct list_head i_list; + + /* VFS inode this inode belongs to [constant during the lifetime + * of the structure] */ + struct inode *i_vfs_inode; + + /* Flags of inode [j_list_lock] */ + unsigned int i_flags; +}; + struct jbd2_revoke_table_s; /** @@ -566,6 +598,12 @@ struct transaction_s */ struct journal_head *t_log_list; + /* + * List of inodes whose data we've modified in data=ordered mode. + * [j_list_lock] + */ + struct list_head t_inode_list; + /* * Protects info related to handles */ @@ -1046,6 +1084,10 @@ extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); +extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode); +extern int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size); +extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); +extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode); /* * journal_head management -- cgit v1.2.3 From 87c89c232c8f7b3820c33c3b9bc803e9358027da Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: jbd2: Remove data=ordered mode support using jbd buffer heads Signed-off-by: Jan Kara --- include/linux/jbd2.h | 29 +++++++---------------------- 1 file changed, 7 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 622c3d8ca4e..3dd20900709 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -542,24 +542,12 @@ struct transaction_s */ struct journal_head *t_reserved_list; - /* - * Doubly-linked circular list of all buffers under writeout during - * commit [j_list_lock] - */ - struct journal_head *t_locked_list; - /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock] */ struct journal_head *t_buffers; - /* - * Doubly-linked circular list of all data buffers still to be - * flushed before this transaction can be committed [j_list_lock] - */ - struct journal_head *t_sync_datalist; - /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) @@ -1044,7 +1032,6 @@ extern int jbd2_journal_extend (handle_t *, int nblocks); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); -extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); @@ -1223,15 +1210,13 @@ static inline int jbd_space_needed(journal_t *journal) /* journaling buffer types */ #define BJ_None 0 /* Not journaled */ -#define BJ_SyncData 1 /* Normal data: flush before commit */ -#define BJ_Metadata 2 /* Normal journaled metadata */ -#define BJ_Forget 3 /* Buffer superseded by this transaction */ -#define BJ_IO 4 /* Buffer is for temporary IO use */ -#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */ -#define BJ_LogCtl 6 /* Buffer contains log descriptors */ -#define BJ_Reserved 7 /* Buffer is reserved for access by journal */ -#define BJ_Locked 8 /* Locked for I/O during commit */ -#define BJ_Types 9 +#define BJ_Metadata 1 /* Normal journaled metadata */ +#define BJ_Forget 2 /* Buffer superseded by this transaction */ +#define BJ_IO 3 /* Buffer is for temporary IO use */ +#define BJ_Shadow 4 /* Buffer contents being shadowed to the log */ +#define BJ_LogCtl 5 /* Buffer contains log descriptors */ +#define BJ_Reserved 6 /* Buffer is reserved for access by journal */ +#define BJ_Types 7 extern int jbd_blocks_per_page(struct inode *inode); -- cgit v1.2.3 From 29a814d2ee0e43c2980f33f91c1311ec06c0aa35 Mon Sep 17 00:00:00 2001 From: Alex Tomas Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: vfs: add hooks for ext4's delayed allocation support Export mpage_bio_submit() and __mpage_writepage() for the benefit of ext4's delayed allocation support. Also change __block_write_full_page so that if buffers that have the BH_Delay flag set it will call get_block() to get the physical block allocated, just as in the !BH_Mapped case. Signed-off-by: Alex Tomas Signed-off-by: "Theodore Ts'o" --- include/linux/mpage.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/mpage.h b/include/linux/mpage.h index 068a0c9946a..5c42821da2d 100644 --- a/include/linux/mpage.h +++ b/include/linux/mpage.h @@ -11,11 +11,21 @@ */ #ifdef CONFIG_BLOCK +struct mpage_data { + struct bio *bio; + sector_t last_block_in_bio; + get_block_t *get_block; + unsigned use_writepage; +}; + struct writeback_control; +struct bio *mpage_bio_submit(int rw, struct bio *bio); int mpage_readpages(struct address_space *mapping, struct list_head *pages, unsigned nr_pages, get_block_t get_block); int mpage_readpage(struct page *page, get_block_t get_block); +int __mpage_writepage(struct page *page, struct writeback_control *wbc, + void *data); int mpage_writepages(struct address_space *mapping, struct writeback_control *wbc, get_block_t get_block); int mpage_writepage(struct page *page, get_block_t *get_block, -- cgit v1.2.3 From e8ced39d5e8911c662d4d69a342b9d053eaaac4e Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: percpu_counter: new function percpu_counter_sum_and_set Delayed allocation need to check free blocks at every write time. percpu_counter_read_positive() is not quit accurate. delayed allocation need a more accurate accounting, but using percpu_counter_sum_positive() is frequently is quite expensive. This patch added a new function to update center counter when sum per-cpu counter, to increase the accurate rate for next percpu_counter_read() and require less calling expensive percpu_counter_sum(). Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- include/linux/percpu_counter.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 9007ccdfc11..20838883535 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc); +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc); + s64 ret = __percpu_counter_sum(fbc, 0); return ret < 0 ? 0 : ret; } +static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) +{ + return __percpu_counter_sum(fbc, 1); +} + + static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc); + return __percpu_counter_sum(fbc, 0); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) -- cgit v1.2.3 From 06d6cf6959d22037fcec598f4f954db5db3d7356 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: mm: Add range_cont mode for writeback Filesystems like ext4 needs to start a new transaction in the writepages for block allocation. This happens with delayed allocation and there is limit to how many credits we can request from the journal layer. So we call write_cache_pages multiple times with wbc->nr_to_write set to the maximum possible value limitted by the max journal credits available. Add a new mode to writeback that enables us to handle this behaviour. In the new mode we update the wbc->range_start to point to the new offset to be written. Next call to call to write_cache_pages will start writeout from specified range_start offset. In the new mode we also limit writing to the specified wbc->range_end. Signed-off-by: Aneesh Kumar K.V Signed-off-by: Mingming Cao Acked-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- include/linux/writeback.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index f462439cc28..0d8573e6b9e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -63,6 +63,7 @@ struct writeback_control { unsigned for_writepages:1; /* This is a writepages() call */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned more_io:1; /* more io to be dispatched */ + unsigned range_cont:1; }; /* -- cgit v1.2.3