From 3ae72562ad917df36a1b1247d749240e3b4865db Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Wed, 19 Jun 2019 23:45:09 -0400 Subject: ext4: optimize case-insensitive lookups Temporarily cache a casefolded version of the file name under lookup in ext4_filename, to avoid repeatedly casefolding it. I got up to 30% speedup on lookups of large directories (>100k entries), depending on the length of the string under lookup. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Theodore Ts'o --- include/linux/unicode.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/unicode.h b/include/linux/unicode.h index aec2c6d800aa..990aa97d8049 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -17,6 +17,9 @@ int utf8_strncmp(const struct unicode_map *um, int utf8_strncasecmp(const struct unicode_map *um, const struct qstr *s1, const struct qstr *s2); +int utf8_strncasecmp_folded(const struct unicode_map *um, + const struct qstr *cf, + const struct qstr *s1); int utf8_normalize(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen); -- cgit v1.2.3 From aa0bfcd939c30617385ffa28682c062d78050eba Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Thu, 20 Jun 2019 17:05:37 -0400 Subject: mm: add filemap_fdatawait_range_keep_errors() In the spirit of filemap_fdatawait_range() and filemap_fdatawait_keep_errors(), introduce filemap_fdatawait_range_keep_errors() which both takes a range upon which to wait and does not clear errors from the address space. Signed-off-by: Ross Zwisler Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara Cc: stable@vger.kernel.org --- include/linux/fs.h | 2 ++ mm/filemap.c | 22 ++++++++++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f7fdfe93e25d..79fec8a8413f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2712,6 +2712,8 @@ extern int filemap_flush(struct address_space *); extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); static inline int filemap_fdatawait(struct address_space *mapping) { diff --git a/mm/filemap.c b/mm/filemap.c index df2006ba0cfa..e87252ca0835 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -553,6 +553,28 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, } EXPORT_SYMBOL(filemap_fdatawait_range); +/** + * filemap_fdatawait_range_keep_errors - 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) + * + * Walk the list of under-writeback pages of the given address space in the + * given range and wait for all of them. Unlike filemap_fdatawait_range(), + * this function does not clear error status of the address space. + * + * Use this function if callers don't handle errors themselves. Expected + * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), + * fsfreeze(8) + */ +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) +{ + __filemap_fdatawait_range(mapping, start_byte, end_byte); + return filemap_check_and_keep_errors(mapping); +} +EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); + /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for -- cgit v1.2.3 From 6ba0e7dc64a5adcda2fbe65adc466891795d639e Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Thu, 20 Jun 2019 17:24:56 -0400 Subject: jbd2: introduce jbd2_inode dirty range scoping Currently both journal_submit_inode_data_buffers() and journal_finish_inode_data_buffers() operate on the entire address space of each of the inodes associated with a given journal entry. The consequence of this is that if we have an inode where we are constantly appending dirty pages we can end up waiting for an indefinite amount of time in journal_finish_inode_data_buffers() while we wait for all the pages under writeback to be written out. The easiest way to cause this type of workload is do just dd from /dev/zero to a file until it fills the entire filesystem. This can cause journal_finish_inode_data_buffers() to wait for the duration of the entire dd operation. We can improve this situation by scoping each of the inode dirty ranges associated with a given transaction. We do this via the jbd2_inode structure so that the scoping is contained within jbd2 and so that it follows the lifetime and locking rules for that structure. This allows us to limit the writeback & wait in journal_submit_inode_data_buffers() and journal_finish_inode_data_buffers() respectively to the dirty range for a given struct jdb2_inode, keeping us from waiting forever if the inode in question is still being appended to. Signed-off-by: Ross Zwisler Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara Cc: stable@vger.kernel.org --- fs/jbd2/commit.c | 23 +++++++++++++++++------ fs/jbd2/journal.c | 4 ++++ fs/jbd2/transaction.c | 49 ++++++++++++++++++++++++++++--------------------- include/linux/jbd2.h | 22 ++++++++++++++++++++++ 4 files changed, 71 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index c8c1d6cc6e5d..132fb92098c7 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -187,14 +187,15 @@ static int journal_wait_on_commit_record(journal_t *journal, * use writepages() because with delayed allocation we may be doing * block allocation in writepages(). */ -static int journal_submit_inode_data_buffers(struct address_space *mapping) +static int journal_submit_inode_data_buffers(struct address_space *mapping, + loff_t dirty_start, loff_t dirty_end) { int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = mapping->nrpages * 2, - .range_start = 0, - .range_end = i_size_read(mapping->host), + .range_start = dirty_start, + .range_end = dirty_end, }; ret = generic_writepages(mapping, &wbc); @@ -218,6 +219,9 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + loff_t dirty_start = jinode->i_dirty_start; + loff_t dirty_end = jinode->i_dirty_end; + if (!(jinode->i_flags & JI_WRITE_DATA)) continue; mapping = jinode->i_vfs_inode->i_mapping; @@ -230,7 +234,8 @@ static int journal_submit_data_buffers(journal_t *journal, * only allocated blocks here. */ trace_jbd2_submit_inode_data(jinode->i_vfs_inode); - err = journal_submit_inode_data_buffers(mapping); + err = journal_submit_inode_data_buffers(mapping, dirty_start, + dirty_end); if (!ret) ret = err; spin_lock(&journal->j_list_lock); @@ -257,12 +262,16 @@ static int journal_finish_inode_data_buffers(journal_t *journal, /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + loff_t dirty_start = jinode->i_dirty_start; + loff_t dirty_end = jinode->i_dirty_end; + if (!(jinode->i_flags & JI_WAIT_DATA)) continue; jinode->i_flags |= JI_COMMIT_RUNNING; spin_unlock(&journal->j_list_lock); - err = filemap_fdatawait_keep_errors( - jinode->i_vfs_inode->i_mapping); + err = filemap_fdatawait_range_keep_errors( + jinode->i_vfs_inode->i_mapping, dirty_start, + dirty_end); if (!ret) ret = err; spin_lock(&journal->j_list_lock); @@ -282,6 +291,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal, &jinode->i_transaction->t_inode_list); } else { jinode->i_transaction = NULL; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; } } spin_unlock(&journal->j_list_lock); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 38b426c5ed03..17f679aeba7c 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -94,6 +94,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_add_write); EXPORT_SYMBOL(jbd2_journal_inode_add_wait); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); @@ -2574,6 +2576,8 @@ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) jinode->i_next_transaction = NULL; jinode->i_vfs_inode = inode; jinode->i_flags = 0; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; INIT_LIST_HEAD(&jinode->i_list); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 8ca4fddc705f..990e7b5062e7 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2565,7 +2565,7 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) * File inode in the inode list of the handle's transaction */ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, - unsigned long flags) + unsigned long flags, loff_t start_byte, loff_t end_byte) { transaction_t *transaction = handle->h_transaction; journal_t *journal; @@ -2577,26 +2577,17 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); - /* - * First check whether inode isn't already on the transaction's - * lists without taking the lock. Note that this check is safe - * without the lock as we cannot race with somebody removing inode - * from the transaction. The reason is that we remove inode from the - * transaction only in journal_release_jbd_inode() and when we commit - * the transaction. We are guarded from the first case by holding - * a reference to the inode. We are safe against the second case - * because if jinode->i_transaction == transaction, commit code - * cannot touch the transaction because we hold reference to it, - * and if jinode->i_next_transaction == transaction, commit code - * will only file the inode where we want it. - */ - if ((jinode->i_transaction == transaction || - jinode->i_next_transaction == transaction) && - (jinode->i_flags & flags) == flags) - return 0; - spin_lock(&journal->j_list_lock); jinode->i_flags |= flags; + + if (jinode->i_dirty_end) { + jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte); + jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte); + } else { + jinode->i_dirty_start = start_byte; + jinode->i_dirty_end = end_byte; + } + /* Is inode already attached where we need it? */ if (jinode->i_transaction == transaction || jinode->i_next_transaction == transaction) @@ -2631,12 +2622,28 @@ done: int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode) { return jbd2_journal_file_inode(handle, jinode, - JI_WRITE_DATA | JI_WAIT_DATA); + JI_WRITE_DATA | JI_WAIT_DATA, 0, LLONG_MAX); } int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode) { - return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA); + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, 0, + LLONG_MAX); +} + +int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *jinode, loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, + JI_WRITE_DATA | JI_WAIT_DATA, start_byte, + start_byte + length - 1); +} + +int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode, + loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, + start_byte, start_byte + length - 1); } /* diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 5c04181b7c6d..0e0393e7f41a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -451,6 +451,22 @@ struct jbd2_inode { * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; + + /** + * @i_dirty_start: + * + * Offset in bytes where the dirty range for this inode starts. + * [j_list_lock] + */ + loff_t i_dirty_start; + + /** + * @i_dirty_end: + * + * Inclusive offset in bytes where the dirty range for this inode + * ends. [j_list_lock] + */ + loff_t i_dirty_end; }; struct jbd2_revoke_table_s; @@ -1397,6 +1413,12 @@ extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode); extern int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode); +extern int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *inode, loff_t start_byte, + loff_t length); +extern int jbd2_journal_inode_ranged_wait(handle_t *handle, + struct jbd2_inode *inode, loff_t start_byte, + loff_t length); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); -- cgit v1.2.3 From 9382cde8cd8fb941fc333b644a5772d02e1ff924 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 20 Jun 2019 17:32:21 -0400 Subject: jbd2: drop declaration of journal_sync_buffer() The journal_sync_buffer() function was never carried over from jbd to jbd2. So get rid of the vestigal declaration of this (non-existent) function. Signed-off-by: Theodore Ts'o Reviewed-by: Darrick J. Wong --- fs/jbd2/journal.c | 3 --- include/linux/jbd2.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 17f679aeba7c..953990eb70a9 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -66,9 +66,6 @@ EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); EXPORT_SYMBOL(jbd2_journal_forget); -#if 0 -EXPORT_SYMBOL(journal_sync_buffer); -#endif EXPORT_SYMBOL(jbd2_journal_flush); EXPORT_SYMBOL(jbd2_journal_revoke); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0e0393e7f41a..df03825ad1a1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1373,7 +1373,6 @@ void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); -extern void journal_sync_buffer (struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); -- cgit v1.2.3