From 41f2df62894bfcd3bf868af916b32b90aa7168dc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 17 Jun 2010 08:54:16 +0200 Subject: block: BARRIER request should imply SYNC A barrier request should by defintion have priority in get_request and let the queue be unplugged immediately as it's blocking all forward progress due to the queue draining. Most filesystems already get this implicitly by the way how submit_bh treats the buffer_ordered flag, and gfs2 sets it explicitly. But btrfs and XFS are still forgetting to set the flag, as is blkdev_issue_flush and some places in DM/MD. For XFS on metadata heavy workloads this gives a consistent speedup in the 2-3% range. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 68ca1b0491af..598878831497 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -136,7 +136,7 @@ struct inodes_stat_t { * SWRITE_SYNC * SWRITE_SYNC_PLUG Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer. * See SWRITE. - * WRITE_BARRIER Like WRITE, but tells the block layer that all + * WRITE_BARRIER Like WRITE_SYNC, but tells the block layer that all * previously submitted writes must be safely on storage * before this one is started. Also guarantees that when * this write is complete, it itself is also safely on @@ -159,7 +159,7 @@ struct inodes_stat_t { #define SWRITE_SYNC_PLUG \ (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_BARRIER (WRITE | (1 << BIO_RW_BARRIER)) +#define WRITE_BARRIER (WRITE_SYNC | (1 << BIO_RW_BARRIER)) /* * These aren't really reads or writes, they pass down information about -- cgit v1.2.2 From 7b6d91daee5cac6402186ff224c3af39d79f4a0e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 7 Aug 2010 18:20:39 +0200 Subject: block: unify flags for struct bio and struct request Remove the current bio flags and reuse the request flags for the bio, too. This allows to more easily trace the type of I/O from the filesystem down to the block driver. There were two flags in the bio that were missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've renamed two request flags that had a superflous RW in them. Note that the flags are in bio.h despite having the REQ_ name - as blkdev.h includes bio.h that is the only way to go for now. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 598878831497..c5c92943c767 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -144,29 +144,31 @@ struct inodes_stat_t { * of this IO. * */ -#define RW_MASK 1 -#define RWA_MASK 2 -#define READ 0 -#define WRITE 1 -#define READA 2 /* read-ahead - don't block if no resources */ -#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ -#define READ_SYNC (READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG)) -#define READ_META (READ | (1 << BIO_RW_META)) -#define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_ODIRECT_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) -#define WRITE_META (WRITE | (1 << BIO_RW_META)) -#define SWRITE_SYNC_PLUG \ - (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) -#define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) -#define WRITE_BARRIER (WRITE_SYNC | (1 << BIO_RW_BARRIER)) +#define RW_MASK 1 +#define RWA_MASK 2 + +#define READ 0 +#define WRITE 1 +#define READA 2 /* readahead - don't block if no resources */ +#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ + +#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) +#define READ_META (READ | REQ_META) +#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE) +#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) +#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC) +#define WRITE_META (WRITE | REQ_META) +#define WRITE_BARRIER (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ + REQ_HARDBARRIER) +#define SWRITE_SYNC_PLUG (SWRITE | REQ_SYNC | REQ_NOIDLE) +#define SWRITE_SYNC (SWRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) /* * These aren't really reads or writes, they pass down information about * parts of device that are now unused by the file system. */ -#define DISCARD_NOBARRIER (WRITE | (1 << BIO_RW_DISCARD)) -#define DISCARD_BARRIER (DISCARD_NOBARRIER | (1 << BIO_RW_BARRIER)) +#define DISCARD_NOBARRIER (WRITE | REQ_DISCARD) +#define DISCARD_BARRIER (WRITE | REQ_DISCARD | REQ_HARDBARRIER) #define SEL_IN 1 #define SEL_OUT 2 -- cgit v1.2.2 From aca27ba9618276dd2f777bcd5a1419589ccf1ca8 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Aug 2010 13:14:33 +0200 Subject: bio, fs: update RWA_MASK, READA and SWRITE to match the corresponding BIO_RW_* bits Commit a82afdf (block: use the same failfast bits for bio and request) moved BIO_RW_* bits around such that they match up with REQ_* bits. Unfortunately, fs.h hard coded RW_MASK, RWA_MASK, READ, WRITE, READA and SWRITE as 0, 1, 2 and 3, and expected them to match with BIO_RW_* bits. READ/WRITE didn't change but BIO_RW_AHEAD was moved to bit 4 instead of bit 1, breaking RWA_MASK, READA and SWRITE. This patch updates RWA_MASK, READA and SWRITE such that they match the BIO_RW_* bits again. A follow up patch will update the definitions to directly use BIO_RW_* bits so that this kind of breakage won't happen again. Neil also spotted missing RWA_MASK conversion. Stable: The offending commit a82afdf was released with v2.6.32, so this patch should be applied to all kernels since then but it must _NOT_ be applied to kernels earlier than that. Signed-off-by: Tejun Heo Reported-and-bisected-by: Vladislav Bolkhovitin Root-caused-by: Neil Brown Cc: stable@kernel.org Signed-off-by: Jens Axboe --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c5c92943c767..55dad7bca25b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -145,12 +145,12 @@ struct inodes_stat_t { * */ #define RW_MASK 1 -#define RWA_MASK 2 +#define RWA_MASK 16 #define READ 0 #define WRITE 1 -#define READA 2 /* readahead - don't block if no resources */ -#define SWRITE 3 /* for ll_rw_block() - wait for buffer lock */ +#define READA 16 /* readahead - don't block if no resources */ +#define SWRITE 17 /* for ll_rw_block(), wait for buffer lock */ #define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) #define READ_META (READ | REQ_META) -- cgit v1.2.2 From 7cc015811ef8992dfcce314d0ed9642bc18143d1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 3 Aug 2010 13:14:58 +0200 Subject: bio, fs: separate out bio_types.h and define READ/WRITE constants in terms of BIO_RW_* flags linux/fs.h hard coded READ/WRITE constants which should match BIO_RW_* flags. This is fragile and caused breakage during BIO_RW_* flag rearrangement. The hardcoding is to avoid include dependency hell. Create linux/bio_types.h which contatins definitions for bio data structures and flags and include it from bio.h and fs.h, and make fs.h define all READ/WRITE related constants in terms of BIO_RW_* flags. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/fs.h | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 55dad7bca25b..c53911277210 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -8,6 +8,7 @@ #include #include +#include /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -117,7 +118,7 @@ struct inodes_stat_t { * immediately wait on this read without caring about * unplugging. * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this + * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. * SWRITE Like WRITE, but a special case for ll_rw_block() that @@ -144,13 +145,13 @@ struct inodes_stat_t { * of this IO. * */ -#define RW_MASK 1 -#define RWA_MASK 16 +#define RW_MASK REQ_WRITE +#define RWA_MASK REQ_RAHEAD #define READ 0 -#define WRITE 1 -#define READA 16 /* readahead - don't block if no resources */ -#define SWRITE 17 /* for ll_rw_block(), wait for buffer lock */ +#define WRITE RW_MASK +#define READA RWA_MASK +#define SWRITE (WRITE | READA) #define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) #define READ_META (READ | REQ_META) @@ -2200,7 +2201,6 @@ static inline void insert_inode_hash(struct inode *inode) { extern void file_move(struct file *f, struct list_head *list); extern void file_kill(struct file *f); #ifdef CONFIG_BLOCK -struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); #endif @@ -2267,7 +2267,6 @@ static inline int xip_truncate_page(struct address_space *mapping, loff_t from) #endif #ifdef CONFIG_BLOCK -struct bio; typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); void dio_end_io(struct bio *bio, int error); -- cgit v1.2.2