From 3a366e614d0837d9fc23f78cdb1a1186ebc3387f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:33 -0800 Subject: block: add missing block_bio_complete() tracepoint bio completion didn't kick block_bio_complete TP. Only dm was explicitly triggering the TP on IO completion. This makes block_bio_complete TP useless for tracers which want to know about bios, and all other bio based drivers skip generating blktrace completion events. This patch makes all bio completions via bio_endio() generate block_bio_complete TP. * Explicit trace_block_bio_complete() invocation removed from dm and the trace point is unexported. * @rq dropped from trace_block_bio_complete(). bios may fly around w/o queue associated. Verifying and accessing the assocaited queue belongs to TP probes. * blktrace now gets both request and bio completions. Make it ignore bio completions if request completion path is happening. This makes all bio based drivers generate blktrace completion events properly and makes the block_bio_complete TP actually useful. v2: With this change, block_bio_complete TP could be invoked on sg commands which have bio's with %NULL bi_bdev. Update TP assignment code to check whether bio->bi_bdev is %NULL before dereferencing. Signed-off-by: Tejun Heo Original-patch-by: Namhyung Kim Cc: Tejun Heo Cc: Steven Rostedt Cc: Alasdair Kergon Cc: dm-devel@redhat.com Cc: Neil Brown Signed-off-by: Jens Axboe --- include/trace/events/block.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 05c5e61f0a7c..8a168db9a645 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -206,7 +206,6 @@ TRACE_EVENT(block_bio_bounce, /** * block_bio_complete - completed all work on the block operation - * @q: queue holding the block operation * @bio: block operation completed * @error: io error value * @@ -215,9 +214,9 @@ TRACE_EVENT(block_bio_bounce, */ TRACE_EVENT(block_bio_complete, - TP_PROTO(struct request_queue *q, struct bio *bio, int error), + TP_PROTO(struct bio *bio, int error), - TP_ARGS(q, bio, error), + TP_ARGS(bio, error), TP_STRUCT__entry( __field( dev_t, dev ) @@ -228,7 +227,8 @@ TRACE_EVENT(block_bio_complete, ), TP_fast_assign( - __entry->dev = bio->bi_bdev->bd_dev; + __entry->dev = bio->bi_bdev ? + bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_sector; __entry->nr_sector = bio->bi_size >> 9; __entry->error = error; -- cgit v1.2.3 From 8c1cf6bb02fda79b0a4b9bd121f6be6d4ce7a15a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:34 -0800 Subject: block: add @req to bio_{front|back}_merge tracepoints bio_{front|back}_merge tracepoints report a bio merging into an existing request but didn't specify which request the bio is being merged into. Add @req to it. This makes it impossible to share the event template with block_bio_queue - split it out. @req isn't used or exported to userland at this point and there is no userland visible behavior change. Later changes will make use of the extra parameter. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ++-- include/trace/events/block.h | 45 +++++++++++++++++++++++++++++++++----------- kernel/trace/blktrace.c | 2 ++ 3 files changed, 38 insertions(+), 13 deletions(-) (limited to 'include/trace') diff --git a/block/blk-core.c b/block/blk-core.c index 4f5aec708be6..66d31687cf6b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1347,7 +1347,7 @@ static bool bio_attempt_back_merge(struct request_queue *q, struct request *req, if (!ll_back_merge_fn(q, req, bio)) return false; - trace_block_bio_backmerge(q, bio); + trace_block_bio_backmerge(q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); @@ -1369,7 +1369,7 @@ static bool bio_attempt_front_merge(struct request_queue *q, if (!ll_front_merge_fn(q, req, bio)) return false; - trace_block_bio_frontmerge(q, bio); + trace_block_bio_frontmerge(q, req, bio); if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) blk_rq_set_mixed_merge(req); diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 8a168db9a645..b408f518a819 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -241,11 +241,11 @@ TRACE_EVENT(block_bio_complete, __entry->nr_sector, __entry->error) ); -DECLARE_EVENT_CLASS(block_bio, +DECLARE_EVENT_CLASS(block_bio_merge, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), - TP_ARGS(q, bio), + TP_ARGS(q, rq, bio), TP_STRUCT__entry( __field( dev_t, dev ) @@ -272,31 +272,33 @@ DECLARE_EVENT_CLASS(block_bio, /** * block_bio_backmerge - merging block operation to the end of an existing operation * @q: queue holding operation + * @rq: request bio is being merged into * @bio: new block operation to merge * * Merging block request @bio to the end of an existing block request * in queue @q. */ -DEFINE_EVENT(block_bio, block_bio_backmerge, +DEFINE_EVENT(block_bio_merge, block_bio_backmerge, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), - TP_ARGS(q, bio) + TP_ARGS(q, rq, bio) ); /** * block_bio_frontmerge - merging block operation to the beginning of an existing operation * @q: queue holding operation + * @rq: request bio is being merged into * @bio: new block operation to merge * * Merging block IO operation @bio to the beginning of an existing block * operation in queue @q. */ -DEFINE_EVENT(block_bio, block_bio_frontmerge, +DEFINE_EVENT(block_bio_merge, block_bio_frontmerge, - TP_PROTO(struct request_queue *q, struct bio *bio), + TP_PROTO(struct request_queue *q, struct request *rq, struct bio *bio), - TP_ARGS(q, bio) + TP_ARGS(q, rq, bio) ); /** @@ -306,11 +308,32 @@ DEFINE_EVENT(block_bio, block_bio_frontmerge, * * About to place the block IO operation @bio into queue @q. */ -DEFINE_EVENT(block_bio, block_bio_queue, +TRACE_EVENT(block_bio_queue, TP_PROTO(struct request_queue *q, struct bio *bio), - TP_ARGS(q, bio) + TP_ARGS(q, bio), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __array( char, rwbs, RWBS_LEN ) + __array( char, comm, TASK_COMM_LEN ) + ), + + TP_fast_assign( + __entry->dev = bio->bi_bdev->bd_dev; + __entry->sector = bio->bi_sector; + __entry->nr_sector = bio->bi_size >> 9; + blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size); + memcpy(__entry->comm, current->comm, TASK_COMM_LEN); + ), + + TP_printk("%d,%d %s %llu + %u [%s]", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, __entry->comm) ); DECLARE_EVENT_CLASS(block_get_rq, diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 190d98fbed27..fb593f6a687e 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -803,6 +803,7 @@ static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error) static void blk_add_trace_bio_backmerge(void *ignore, struct request_queue *q, + struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); @@ -810,6 +811,7 @@ static void blk_add_trace_bio_backmerge(void *ignore, static void blk_add_trace_bio_frontmerge(void *ignore, struct request_queue *q, + struct request *rq, struct bio *bio) { blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); -- cgit v1.2.3 From 5305cb830834549b9203ad4d009ad5483c5e293f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:36 -0800 Subject: block: add block_{touch|dirty}_buffer tracepoint The former is triggered from touch_buffer() and the latter mark_buffer_dirty(). This is part of tracepoint additions to improve visiblity into dirtying / writeback operations for io tracer and userland. v2: Transformed writeback_dirty_buffer to block_dirty_buffer and made it share TP definition with block_touch_buffer. Signed-off-by: Tejun Heo Cc: Fengguang Wu Signed-off-by: Jens Axboe --- fs/buffer.c | 4 ++++ include/trace/events/block.h | 51 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) (limited to 'include/trace') diff --git a/fs/buffer.c b/fs/buffer.c index a8c2dfb68dcd..87ff335fbbe3 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -41,6 +41,7 @@ #include #include #include +#include static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); @@ -55,6 +56,7 @@ EXPORT_SYMBOL(init_buffer); inline void touch_buffer(struct buffer_head *bh) { + trace_block_touch_buffer(bh); mark_page_accessed(bh->b_page); } EXPORT_SYMBOL(touch_buffer); @@ -1119,6 +1121,8 @@ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); + trace_block_dirty_buffer(bh); + /* * Very *carefully* optimize the it-is-already-dirty case. * diff --git a/include/trace/events/block.h b/include/trace/events/block.h index b408f518a819..9961726523d0 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -6,10 +6,61 @@ #include #include +#include #include #define RWBS_LEN 8 +DECLARE_EVENT_CLASS(block_buffer, + + TP_PROTO(struct buffer_head *bh), + + TP_ARGS(bh), + + TP_STRUCT__entry ( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( size_t, size ) + ), + + TP_fast_assign( + __entry->dev = bh->b_bdev->bd_dev; + __entry->sector = bh->b_blocknr; + __entry->size = bh->b_size; + ), + + TP_printk("%d,%d sector=%llu size=%zu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->sector, __entry->size + ) +); + +/** + * block_touch_buffer - mark a buffer accessed + * @bh: buffer_head being touched + * + * Called from touch_buffer(). + */ +DEFINE_EVENT(block_buffer, block_touch_buffer, + + TP_PROTO(struct buffer_head *bh), + + TP_ARGS(bh) +); + +/** + * block_dirty_buffer - mark a buffer dirty + * @bh: buffer_head being dirtied + * + * Called from mark_buffer_dirty(). + */ +DEFINE_EVENT(block_buffer, block_dirty_buffer, + + TP_PROTO(struct buffer_head *bh), + + TP_ARGS(bh) +); + DECLARE_EVENT_CLASS(block_rq_with_error, TP_PROTO(struct request_queue *q, struct request *rq), -- cgit v1.2.3 From 9fb0a7da0c528d9bd49b597aa63b1fe2216c7203 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Jan 2013 13:06:37 -0800 Subject: writeback: add more tracepoints Add tracepoints for page dirtying, writeback_single_inode start, inode dirtying and writeback. For the latter two inode events, a pair of events are defined to denote start and end of the operations (the starting one has _start suffix and the one w/o suffix happens after the operation is complete). These inode ops are FS specific and can be non-trivial and having enclosing tracepoints is useful for external tracers. This is part of tracepoint additions to improve visiblity into dirtying / writeback operations for io tracer and userland. v2: writeback_dirty_inode[_start] TPs may be called for files on pseudo FSes w/ unregistered bdi. Check whether bdi->dev is %NULL before dereferencing. v3: buffer dirtying moved to a block TP. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 16 +++++- include/trace/events/writeback.h | 116 +++++++++++++++++++++++++++++++++++++++ mm/page-writeback.c | 2 + 3 files changed, 132 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 310972b72a66..359494ea1bde 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -318,8 +318,14 @@ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) static int write_inode(struct inode *inode, struct writeback_control *wbc) { - if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) - return inode->i_sb->s_op->write_inode(inode, wbc); + int ret; + + if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { + trace_writeback_write_inode_start(inode, wbc); + ret = inode->i_sb->s_op->write_inode(inode, wbc); + trace_writeback_write_inode(inode, wbc); + return ret; + } return 0; } @@ -450,6 +456,8 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) WARN_ON(!(inode->i_state & I_SYNC)); + trace_writeback_single_inode_start(inode, wbc, nr_to_write); + ret = do_writepages(mapping, wbc); /* @@ -1150,8 +1158,12 @@ void __mark_inode_dirty(struct inode *inode, int flags) * dirty the inode itself */ if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + trace_writeback_dirty_inode_start(inode, flags); + if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags); + + trace_writeback_dirty_inode(inode, flags); } /* diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index b453d92c2253..6a16fd2e70ed 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -32,6 +32,115 @@ struct wb_writeback_work; +TRACE_EVENT(writeback_dirty_page, + + TP_PROTO(struct page *page, struct address_space *mapping), + + TP_ARGS(page, mapping), + + TP_STRUCT__entry ( + __array(char, name, 32) + __field(unsigned long, ino) + __field(pgoff_t, index) + ), + + TP_fast_assign( + strncpy(__entry->name, + mapping ? dev_name(mapping->backing_dev_info->dev) : "(unknown)", 32); + __entry->ino = mapping ? mapping->host->i_ino : 0; + __entry->index = page->index; + ), + + TP_printk("bdi %s: ino=%lu index=%lu", + __entry->name, + __entry->ino, + __entry->index + ) +); + +DECLARE_EVENT_CLASS(writeback_dirty_inode_template, + + TP_PROTO(struct inode *inode, int flags), + + TP_ARGS(inode, flags), + + TP_STRUCT__entry ( + __array(char, name, 32) + __field(unsigned long, ino) + __field(unsigned long, flags) + ), + + TP_fast_assign( + struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info; + + /* may be called for files on pseudo FSes w/ unregistered bdi */ + strncpy(__entry->name, + bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); + __entry->ino = inode->i_ino; + __entry->flags = flags; + ), + + TP_printk("bdi %s: ino=%lu flags=%s", + __entry->name, + __entry->ino, + show_inode_state(__entry->flags) + ) +); + +DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, + + TP_PROTO(struct inode *inode, int flags), + + TP_ARGS(inode, flags) +); + +DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, + + TP_PROTO(struct inode *inode, int flags), + + TP_ARGS(inode, flags) +); + +DECLARE_EVENT_CLASS(writeback_write_inode_template, + + TP_PROTO(struct inode *inode, struct writeback_control *wbc), + + TP_ARGS(inode, wbc), + + TP_STRUCT__entry ( + __array(char, name, 32) + __field(unsigned long, ino) + __field(int, sync_mode) + ), + + TP_fast_assign( + strncpy(__entry->name, + dev_name(inode->i_mapping->backing_dev_info->dev), 32); + __entry->ino = inode->i_ino; + __entry->sync_mode = wbc->sync_mode; + ), + + TP_printk("bdi %s: ino=%lu sync_mode=%d", + __entry->name, + __entry->ino, + __entry->sync_mode + ) +); + +DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, + + TP_PROTO(struct inode *inode, struct writeback_control *wbc), + + TP_ARGS(inode, wbc) +); + +DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, + + TP_PROTO(struct inode *inode, struct writeback_control *wbc), + + TP_ARGS(inode, wbc) +); + DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), TP_ARGS(bdi, work), @@ -479,6 +588,13 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, ) ); +DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, + TP_PROTO(struct inode *inode, + struct writeback_control *wbc, + unsigned long nr_to_write), + TP_ARGS(inode, wbc, nr_to_write) +); + DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0713bfbf0954..3734cefd4de4 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1982,6 +1982,8 @@ int __set_page_dirty_no_writeback(struct page *page) */ void account_page_dirtied(struct page *page, struct address_space *mapping) { + trace_writeback_dirty_page(page, mapping); + if (mapping_cap_account_dirty(mapping)) { __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); -- cgit v1.2.3