From b3aa1584e9f3449b0669ab2beb9b9bf99874e1d6 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 9 Apr 2012 10:44:57 -0700 Subject: workqueue: Fix workqueue_execute_end() comment workqueue_execute_end() is called after the callback function, not before. Signed-off-by: Stephen Boyd Acked-by: Tejun Heo Signed-off-by: Jiri Kosina --- include/trace/events/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h index 7d497291c85d..4018f5058f27 100644 --- a/include/trace/events/workqueue.h +++ b/include/trace/events/workqueue.h @@ -103,7 +103,7 @@ TRACE_EVENT(workqueue_execute_start, ); /** - * workqueue_execute_end - called immediately before the workqueue callback + * workqueue_execute_end - called immediately after the workqueue callback * @work: pointer to struct work_struct * * Allows to track workqueue execution. -- cgit v1.2.3 From 2db938bee32e7469ca8ed9bfb3a05535f28c680d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 21 Feb 2011 17:25:37 +0100 Subject: jbd: Refine commit writeout logic Currently we write out all journal buffers in WRITE_SYNC mode. This improves performance for fsync heavy workloads but hinders performance when writes are mostly asynchronous, most noticably it slows down readers and users complain about slow desktop response etc. So submit writes as asynchronous in the normal case and only submit writes as WRITE_SYNC if we detect someone is waiting for current transaction commit. I've gathered some numbers to back this change. The first is the read latency test. It measures time to read 1 MB after several seconds of sleeping in presence of streaming writes. Top 10 times (out of 90) in us: Before After 2131586 697473 1709932 557487 1564598 535642 1480462 347573 1478579 323153 1408496 222181 1388960 181273 1329565 181070 1252486 172832 1223265 172278 Average: 619377 82180 So the improvement in both maximum and average latency is massive. I've measured fsync throughput by: fs_mark -n 100 -t 1 -s 16384 -d /mnt/fsync/ -S 1 -L 4 in presence of streaming reader. The numbers (fsyncs/s) are: Before After 9.9 6.3 6.8 6.0 6.3 6.2 5.8 6.1 So fsync performance seems unharmed by this change. Signed-off-by: Jan Kara --- include/trace/events/jbd.h | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/jbd.h b/include/trace/events/jbd.h index aff64d82d713..9305e1b5edc3 100644 --- a/include/trace/events/jbd.h +++ b/include/trace/events/jbd.h @@ -36,19 +36,17 @@ DECLARE_EVENT_CLASS(jbd_commit, TP_STRUCT__entry( __field( dev_t, dev ) - __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %d,%d transaction %d sync %d", + TP_printk("dev %d,%d transaction %d", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->transaction, __entry->sync_commit) + __entry->transaction) ); DEFINE_EVENT(jbd_commit, jbd_start_commit, @@ -87,19 +85,17 @@ TRACE_EVENT(jbd_drop_transaction, TP_STRUCT__entry( __field( dev_t, dev ) - __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %d,%d transaction %d sync %d", + TP_printk("dev %d,%d transaction %d", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->transaction, __entry->sync_commit) + __entry->transaction) ); TRACE_EVENT(jbd_end_commit, @@ -109,21 +105,19 @@ TRACE_EVENT(jbd_end_commit, TP_STRUCT__entry( __field( dev_t, dev ) - __field( char, sync_commit ) __field( int, transaction ) __field( int, head ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; __entry->head = journal->j_tail_sequence; ), - TP_printk("dev %d,%d transaction %d sync %d head %d", + TP_printk("dev %d,%d transaction %d head %d", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->transaction, __entry->sync_commit, __entry->head) + __entry->transaction, __entry->head) ); TRACE_EVENT(jbd_do_submit_data, @@ -133,19 +127,17 @@ TRACE_EVENT(jbd_do_submit_data, TP_STRUCT__entry( __field( dev_t, dev ) - __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; - __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), - TP_printk("dev %d,%d transaction %d sync %d", + TP_printk("dev %d,%d transaction %d", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->transaction, __entry->sync_commit) + __entry->transaction) ); TRACE_EVENT(jbd_cleanup_journal_tail, -- cgit v1.2.3 From ec2e3031b65f23f66840b5c89c4b83076831a435 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Wed, 18 Apr 2012 11:41:11 +0100 Subject: ASoC: dapm: Add API call to query valid DAPM paths In preparation for ASoC DSP support. Add a DAPM API call to determine whether a DAPM audio path is valid between source and sink widgets. This also takes into account all kcontrol mux and mixer settings in between the source and sink widgets to validate the audio path. This will be used by the DSP core to determine the runtime DAI mappings between FE and BE DAIs in order to run PCM operations. Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/trace/events/asoc.h | 80 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h index ab26f8aa3c78..6d8efb1cc8ce 100644 --- a/include/trace/events/asoc.h +++ b/include/trace/events/asoc.h @@ -7,6 +7,8 @@ #include #include +#define DAPM_DIRECT "(direct)" + struct snd_soc_jack; struct snd_soc_codec; struct snd_soc_platform; @@ -241,6 +243,84 @@ TRACE_EVENT(snd_soc_dapm_walk_done, (int)__entry->path_checks, (int)__entry->neighbour_checks) ); +TRACE_EVENT(snd_soc_dapm_output_path, + + TP_PROTO(struct snd_soc_dapm_widget *widget, + struct snd_soc_dapm_path *path), + + TP_ARGS(widget, path), + + TP_STRUCT__entry( + __string( wname, widget->name ) + __string( pname, path->name ? path->name : DAPM_DIRECT) + __string( psname, path->sink->name ) + __field( int, path_sink ) + __field( int, path_connect ) + ), + + TP_fast_assign( + __assign_str(wname, widget->name); + __assign_str(pname, path->name ? path->name : DAPM_DIRECT); + __assign_str(psname, path->sink->name); + __entry->path_connect = path->connect; + __entry->path_sink = (int)path->sink; + ), + + TP_printk("%c%s -> %s -> %s\n", + (int) __entry->path_sink && + (int) __entry->path_connect ? '*' : ' ', + __get_str(wname), __get_str(pname), __get_str(psname)) +); + +TRACE_EVENT(snd_soc_dapm_input_path, + + TP_PROTO(struct snd_soc_dapm_widget *widget, + struct snd_soc_dapm_path *path), + + TP_ARGS(widget, path), + + TP_STRUCT__entry( + __string( wname, widget->name ) + __string( pname, path->name ? path->name : DAPM_DIRECT) + __string( psname, path->source->name ) + __field( int, path_source ) + __field( int, path_connect ) + ), + + TP_fast_assign( + __assign_str(wname, widget->name); + __assign_str(pname, path->name ? path->name : DAPM_DIRECT); + __assign_str(psname, path->source->name); + __entry->path_connect = path->connect; + __entry->path_source = (int)path->source; + ), + + TP_printk("%c%s <- %s <- %s\n", + (int) __entry->path_source && + (int) __entry->path_connect ? '*' : ' ', + __get_str(wname), __get_str(pname), __get_str(psname)) +); + +TRACE_EVENT(snd_soc_dapm_connected, + + TP_PROTO(int paths, int stream), + + TP_ARGS(paths, stream), + + TP_STRUCT__entry( + __field( int, paths ) + __field( int, stream ) + ), + + TP_fast_assign( + __entry->paths = paths; + __entry->stream = stream; + ), + + TP_printk("%s: found %d paths\n", + __entry->stream ? "capture" : "playback", __entry->paths) +); + TRACE_EVENT(snd_soc_jack_irq, TP_PROTO(const char *name), -- cgit v1.2.3 From c97f3bdd26080c2cb2a648c37b6dcb8eac2f91e7 Mon Sep 17 00:00:00 2001 From: Liam Girdwood Date: Mon, 23 Apr 2012 10:31:15 +0100 Subject: ASoC: dapm: Fix x86_64 build warning. Fixes the following build warning on x86_64. In file included from include/trace/ftrace.h:567:0, from include/trace/define_trace.h:86, from include/trace/events/asoc.h:410, from sound/soc/soc-core.c:45: include/trace/events/asoc.h: In function 'ftrace_raw_event_snd_soc_dapm_output_path': include/trace/events/asoc.h:246:1: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] include/trace/events/asoc.h: In function 'ftrace_raw_event_snd_soc_dapm_input_path': include/trace/events/asoc.h:275:1: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast] Signed-off-by: Liam Girdwood Signed-off-by: Mark Brown --- include/trace/events/asoc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/asoc.h b/include/trace/events/asoc.h index 6d8efb1cc8ce..5fc2dcdd21cd 100644 --- a/include/trace/events/asoc.h +++ b/include/trace/events/asoc.h @@ -263,7 +263,7 @@ TRACE_EVENT(snd_soc_dapm_output_path, __assign_str(pname, path->name ? path->name : DAPM_DIRECT); __assign_str(psname, path->sink->name); __entry->path_connect = path->connect; - __entry->path_sink = (int)path->sink; + __entry->path_sink = (long)path->sink; ), TP_printk("%c%s -> %s -> %s\n", @@ -292,7 +292,7 @@ TRACE_EVENT(snd_soc_dapm_input_path, __assign_str(pname, path->name ? path->name : DAPM_DIRECT); __assign_str(psname, path->source->name); __entry->path_connect = path->connect; - __entry->path_source = (int)path->source; + __entry->path_source = (long)path->source; ), TP_printk("%c%s <- %s <- %s\n", -- cgit v1.2.3 From 2fdbb31b662787f78bb78b3e4e18f1a072058ffc Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 23 Feb 2012 15:58:29 -0800 Subject: rcu: Add RCU_FAST_NO_HZ tracing for idle exit Traces of rcu_prep_idle events can be confusing because rcu_cleanup_after_idle() does no tracing. This commit therefore adds this tracing. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 337099783f37..aaa55e1b8c48 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -292,6 +292,7 @@ TRACE_EVENT(rcu_dyntick, * "More callbacks": Still more callbacks, try again to clear them out. * "Callbacks drained": All callbacks processed, off to dyntick idle! * "Timer": Timer fired to cause CPU to continue processing callbacks. + * "Cleanup after idle": Idle exited, timer canceled. */ TRACE_EVENT(rcu_prep_idle, -- cgit v1.2.3 From 6791e36c4a40e8930e08669e60077eea6770c429 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Arve=20Hj=C3=B8nnev=C3=A5g?= Date: Sun, 29 Apr 2012 22:53:02 +0200 Subject: PM / Sleep: Add wakeup_source_activate and wakeup_source_deactivate tracepoints MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add tracepoints to wakeup_source_activate and wakeup_source_deactivate. Useful for checking that specific wakeup sources overlap as expected. Signed-off-by: Arve Hjønnevåg Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/trace/events/power.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/power.h b/include/trace/events/power.h index cae9a94f025d..0c9783841a30 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -65,6 +65,40 @@ TRACE_EVENT(machine_suspend, TP_printk("state=%lu", (unsigned long)__entry->state) ); +DECLARE_EVENT_CLASS(wakeup_source, + + TP_PROTO(const char *name, unsigned int state), + + TP_ARGS(name, state), + + TP_STRUCT__entry( + __string( name, name ) + __field( u64, state ) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->state = state; + ), + + TP_printk("%s state=0x%lx", __get_str(name), + (unsigned long)__entry->state) +); + +DEFINE_EVENT(wakeup_source, wakeup_source_activate, + + TP_PROTO(const char *name, unsigned int state), + + TP_ARGS(name, state) +); + +DEFINE_EVENT(wakeup_source, wakeup_source_deactivate, + + TP_PROTO(const char *name, unsigned int state), + + TP_ARGS(name, state) +); + #ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED /* -- cgit v1.2.3 From cc1676d917f32504dbadc858fa790bc524c9f0da Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 3 May 2012 14:47:56 +0200 Subject: writeback: Move requeueing when I_SYNC set to writeback_sb_inodes() When writeback_single_inode() is called on inode which has I_SYNC already set while doing WB_SYNC_NONE, inode is moved to b_more_io list. However this makes sense only if the caller is flusher thread. For other callers of writeback_single_inode() it doesn't really make sense and may be even wrong - flusher thread may be doing WB_SYNC_ALL writeback in parallel. So we move requeueing from writeback_single_inode() to writeback_sb_inodes(). Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara Signed-off-by: Fengguang Wu --- include/trace/events/writeback.h | 36 +++++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 7b81887b023f..b453d92c2253 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -372,6 +372,35 @@ TRACE_EVENT(balance_dirty_pages, ) ); +TRACE_EVENT(writeback_sb_inodes_requeue, + + TP_PROTO(struct inode *inode), + TP_ARGS(inode), + + TP_STRUCT__entry( + __array(char, name, 32) + __field(unsigned long, ino) + __field(unsigned long, state) + __field(unsigned long, dirtied_when) + ), + + TP_fast_assign( + strncpy(__entry->name, + dev_name(inode_to_bdi(inode)->dev), 32); + __entry->ino = inode->i_ino; + __entry->state = inode->i_state; + __entry->dirtied_when = inode->dirtied_when; + ), + + TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu", + __entry->name, + __entry->ino, + show_inode_state(__entry->state), + __entry->dirtied_when, + (jiffies - __entry->dirtied_when) / HZ + ) +); + DECLARE_EVENT_CLASS(writeback_congest_waited_template, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), @@ -450,13 +479,6 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, ) ); -DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_requeue, - 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, -- cgit v1.2.3 From 21e52e15666323078b8517a4312712579176b56f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 30 Apr 2012 14:16:19 -0700 Subject: rcu: Make RCU_FAST_NO_HZ handle timer migration The current RCU_FAST_NO_HZ assumes that timers do not migrate unless a CPU goes offline, in which case it assumes that the CPU will have to come out of dyntick-idle mode (cancelling the timer) in order to go offline. This is important because when RCU_FAST_NO_HZ permits a CPU to enter dyntick-idle mode despite having RCU callbacks pending, it posts a timer on that CPU to force a wakeup on that CPU. This wakeup ensures that the CPU will eventually handle the end of the grace period, including invoking its RCU callbacks. However, Pascal Chapperon's test setup shows that the timer handler rcu_idle_gp_timer_func() really does get invoked in some cases. This is problematic because this can cause the CPU that entered dyntick-idle mode despite still having RCU callbacks pending to remain in dyntick-idle mode indefinitely, which means that its RCU callbacks might never be invoked. This situation can result in grace-period delays or even system hangs, which matches Pascal's observations of slow boot-up and shutdown (https://lkml.org/lkml/2012/4/5/142). See also the bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=806548 This commit therefore causes the "should never be invoked" timer handler rcu_idle_gp_timer_func() to use smp_call_function_single() to wake up the CPU for which the timer was intended, allowing that CPU to invoke its RCU callbacks in a timely manner. Reported-by: Pascal Chapperon Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/trace/events/rcu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/trace') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index aaa55e1b8c48..1480900c511c 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -292,6 +292,7 @@ TRACE_EVENT(rcu_dyntick, * "More callbacks": Still more callbacks, try again to clear them out. * "Callbacks drained": All callbacks processed, off to dyntick idle! * "Timer": Timer fired to cause CPU to continue processing callbacks. + * "Demigrate": Timer fired on wrong CPU, woke up correct CPU. * "Cleanup after idle": Idle exited, timer canceled. */ TRACE_EVENT(rcu_prep_idle, -- cgit v1.2.3 From 9754e39c7bc51328f145e933bfb0df47cd67b6e9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sat, 7 Apr 2012 12:33:03 +0200 Subject: jbd: Split updating of journal superblock and marking journal empty There are three case of updating journal superblock. In the first case, we want to mark journal as empty (setting s_sequence to 0), in the second case we want to update log tail, in the third case we want to update s_errno. Split these cases into separate functions. It makes the code slightly more straightforward and later patches will make the distinction even more important. Signed-off-by: Jan Kara --- include/trace/events/jbd.h | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/jbd.h b/include/trace/events/jbd.h index 9305e1b5edc3..d9658a940a39 100644 --- a/include/trace/events/jbd.h +++ b/include/trace/events/jbd.h @@ -169,24 +169,20 @@ TRACE_EVENT(jbd_cleanup_journal_tail, __entry->block_nr, __entry->freed) ); -TRACE_EVENT(jbd_update_superblock_end, - TP_PROTO(journal_t *journal, int wait), +TRACE_EVENT(journal_write_superblock, + TP_PROTO(journal_t *journal), - TP_ARGS(journal, wait), + TP_ARGS(journal), TP_STRUCT__entry( __field( dev_t, dev ) - __field( int, wait ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; - __entry->wait = wait; ), - TP_printk("dev %d,%d wait %d", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->wait) + TP_printk("dev %d,%d", MAJOR(__entry->dev), MINOR(__entry->dev)) ); #endif /* _TRACE_JBD_H */ -- cgit v1.2.3 From fd2cbd4dfa3db477dd6226d387d3f1911d36a6a9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Sat, 7 Apr 2012 11:05:19 +0200 Subject: jbd: Write journal superblock with WRITE_FUA after checkpointing If journal superblock is written only in disk's caches and other transaction starts reusing space of the transaction cleaned from the log, it can happen blocks of a new transaction reach the disk before journal superblock. When power failure happens in such case, subsequent journal replay would still try to replay the old transaction but some of it's blocks may be already overwritten by the new transaction. For this reason we must use WRITE_FUA when updating log tail and we must first write new log tail to disk and update in-memory information only after that. Signed-off-by: Jan Kara --- include/trace/events/jbd.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/jbd.h b/include/trace/events/jbd.h index d9658a940a39..da6f2591c25e 100644 --- a/include/trace/events/jbd.h +++ b/include/trace/events/jbd.h @@ -170,19 +170,22 @@ TRACE_EVENT(jbd_cleanup_journal_tail, ); TRACE_EVENT(journal_write_superblock, - TP_PROTO(journal_t *journal), + TP_PROTO(journal_t *journal, int write_op), - TP_ARGS(journal), + TP_ARGS(journal, write_op), TP_STRUCT__entry( __field( dev_t, dev ) + __field( int, write_op ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; + __entry->write_op = write_op; ), - TP_printk("dev %d,%d", MAJOR(__entry->dev), MINOR(__entry->dev)) + TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev), + MINOR(__entry->dev), __entry->write_op) ); #endif /* _TRACE_JBD_H */ -- cgit v1.2.3 From 1523299d5817773e344d135d4b1c485f269400bc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 15:41:24 -0800 Subject: userns: Convert ext3 to use kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/trace/events/ext3.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/ext3.h b/include/trace/events/ext3.h index 7b53c0573dc9..15d11a39be47 100644 --- a/include/trace/events/ext3.h +++ b/include/trace/events/ext3.h @@ -24,8 +24,8 @@ TRACE_EVENT(ext3_free_inode, __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; - __entry->uid = inode->i_uid; - __entry->gid = inode->i_gid; + __entry->uid = i_uid_read(inode); + __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; ), -- cgit v1.2.3 From 08cefc7ab839cf3ece44b8033968a4732eac06d8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 15:41:49 -0800 Subject: userns: Convert ext4 to user kuid/kgid where appropriate Acked-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/trace/events/ext4.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 319538bf17d2..69d8a69ea831 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -36,8 +36,8 @@ TRACE_EVENT(ext4_free_inode, __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; - __entry->uid = inode->i_uid; - __entry->gid = inode->i_gid; + __entry->uid = i_uid_read(inode); + __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; ), -- cgit v1.2.3 From e709ffd6169ccd259eb5874e853303e91e94e829 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 29 May 2012 15:06:18 -0700 Subject: mm: remove swap token code The swap token code no longer fits in with the current VM model. It does not play well with cgroups or the better NUMA placement code in development, since we have only one swap token globally. It also has the potential to mess with scalability of the system, by increasing the number of non-reclaimable pages on the active and inactive anon LRU lists. Last but not least, the swap token code has been broken for a year without complaints, as reported by Konstantin Khlebnikov. This suggests we no longer have much use for it. The days of sub-1G memory systems with heavy use of swap are over. If we ever need thrashing reducing code in the future, we will have to implement something that does scale. Signed-off-by: Rik van Riel Cc: Konstantin Khlebnikov Acked-by: Johannes Weiner Cc: Mel Gorman Cc: Hugh Dickins Acked-by: Bob Picco Acked-by: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 82 ------------------------------------------- 1 file changed, 82 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f64560e204bc..572195459d58 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -395,88 +395,6 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive, show_reclaim_flags(__entry->reclaim_flags)) ); -TRACE_EVENT(replace_swap_token, - TP_PROTO(struct mm_struct *old_mm, - struct mm_struct *new_mm), - - TP_ARGS(old_mm, new_mm), - - TP_STRUCT__entry( - __field(struct mm_struct*, old_mm) - __field(unsigned int, old_prio) - __field(struct mm_struct*, new_mm) - __field(unsigned int, new_prio) - ), - - TP_fast_assign( - __entry->old_mm = old_mm; - __entry->old_prio = old_mm ? old_mm->token_priority : 0; - __entry->new_mm = new_mm; - __entry->new_prio = new_mm->token_priority; - ), - - TP_printk("old_token_mm=%p old_prio=%u new_token_mm=%p new_prio=%u", - __entry->old_mm, __entry->old_prio, - __entry->new_mm, __entry->new_prio) -); - -DECLARE_EVENT_CLASS(put_swap_token_template, - TP_PROTO(struct mm_struct *swap_token_mm), - - TP_ARGS(swap_token_mm), - - TP_STRUCT__entry( - __field(struct mm_struct*, swap_token_mm) - ), - - TP_fast_assign( - __entry->swap_token_mm = swap_token_mm; - ), - - TP_printk("token_mm=%p", __entry->swap_token_mm) -); - -DEFINE_EVENT(put_swap_token_template, put_swap_token, - TP_PROTO(struct mm_struct *swap_token_mm), - TP_ARGS(swap_token_mm) -); - -DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token, - TP_PROTO(struct mm_struct *swap_token_mm), - TP_ARGS(swap_token_mm), - TP_CONDITION(swap_token_mm != NULL) -); - -TRACE_EVENT_CONDITION(update_swap_token_priority, - TP_PROTO(struct mm_struct *mm, - unsigned int old_prio, - struct mm_struct *swap_token_mm), - - TP_ARGS(mm, old_prio, swap_token_mm), - - TP_CONDITION(mm->token_priority != old_prio), - - TP_STRUCT__entry( - __field(struct mm_struct*, mm) - __field(unsigned int, old_prio) - __field(unsigned int, new_prio) - __field(struct mm_struct*, swap_token_mm) - __field(unsigned int, swap_token_prio) - ), - - TP_fast_assign( - __entry->mm = mm; - __entry->old_prio = old_prio; - __entry->new_prio = mm->token_priority; - __entry->swap_token_mm = swap_token_mm; - __entry->swap_token_prio = swap_token_mm ? swap_token_mm->token_priority : 0; - ), - - TP_printk("mm=%p old_prio=%u new_prio=%u swap_token_mm=%p token_prio=%u", - __entry->mm, __entry->old_prio, __entry->new_prio, - __entry->swap_token_mm, __entry->swap_token_prio) -); - #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ -- cgit v1.2.3 From c53919adc045bf803252e912f23028a68525753d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 29 May 2012 15:06:19 -0700 Subject: mm: vmscan: remove lumpy reclaim This series removes lumpy reclaim and some stalling logic that was unintentionally being used by memory compaction. The end result is that stalling on dirty pages during page reclaim now depends on wait_iff_congested(). Four kernels were compared 3.3.0 vanilla 3.4.0-rc2 vanilla 3.4.0-rc2 lumpyremove-v2 is patch one from this series 3.4.0-rc2 nosync-v2r3 is the full series Removing lumpy reclaim saves almost 900 bytes of text whereas the full series removes 1200 bytes. text data bss dec hex filename 6740375 1927944 2260992 10929311 a6c49f vmlinux-3.4.0-rc2-vanilla 6739479 1927944 2260992 10928415 a6c11f vmlinux-3.4.0-rc2-lumpyremove-v2 6739159 1927944 2260992 10928095 a6bfdf vmlinux-3.4.0-rc2-nosync-v2 There are behaviour changes in the series and so tests were run with monitoring of ftrace events. This disrupts results so the performance results are distorted but the new behaviour should be clearer. fs-mark running in a threaded configuration showed little of interest as it did not push reclaim aggressively FS-Mark Multi Threaded 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 Files/s min 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) Files/s mean 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) Files/s stddev 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) 0.00 ( 0.00%) Files/s max 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) 3.20 ( 0.00%) Overhead min 508667.00 ( 0.00%) 521350.00 (-2.49%) 544292.00 (-7.00%) 547168.00 (-7.57%) Overhead mean 551185.00 ( 0.00%) 652690.73 (-18.42%) 991208.40 (-79.83%) 570130.53 (-3.44%) Overhead stddev 18200.69 ( 0.00%) 331958.29 (-1723.88%) 1579579.43 (-8578.68%) 9576.81 (47.38%) Overhead max 576775.00 ( 0.00%) 1846634.00 (-220.17%) 6901055.00 (-1096.49%) 585675.00 (-1.54%) MMTests Statistics: duration Sys Time Running Test (seconds) 309.90 300.95 307.33 298.95 User+Sys Time Running Test (seconds) 319.32 309.67 315.69 307.51 Total Elapsed Time (seconds) 1187.85 1193.09 1191.98 1193.73 MMTests Statistics: vmstat Page Ins 80532 82212 81420 79480 Page Outs 111434984 111456240 111437376 111582628 Swap Ins 0 0 0 0 Swap Outs 0 0 0 0 Direct pages scanned 44881 27889 27453 34843 Kswapd pages scanned 25841428 25860774 25861233 25843212 Kswapd pages reclaimed 25841393 25860741 25861199 25843179 Direct pages reclaimed 44881 27889 27453 34843 Kswapd efficiency 99% 99% 99% 99% Kswapd velocity 21754.791 21675.460 21696.029 21649.127 Direct efficiency 100% 100% 100% 100% Direct velocity 37.783 23.375 23.031 29.188 Percentage direct scans 0% 0% 0% 0% ftrace showed that there was no stalling on writeback or pages submitted for IO from reclaim context. postmark was similar and while it was more interesting, it also did not push reclaim heavily. POSTMARK 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 Transactions per second: 16.00 ( 0.00%) 20.00 (25.00%) 18.00 (12.50%) 17.00 ( 6.25%) Data megabytes read per second: 18.80 ( 0.00%) 24.27 (29.10%) 22.26 (18.40%) 20.54 ( 9.26%) Data megabytes written per second: 35.83 ( 0.00%) 46.25 (29.08%) 42.42 (18.39%) 39.14 ( 9.24%) Files created alone per second: 28.00 ( 0.00%) 38.00 (35.71%) 34.00 (21.43%) 30.00 ( 7.14%) Files create/transact per second: 8.00 ( 0.00%) 10.00 (25.00%) 9.00 (12.50%) 8.00 ( 0.00%) Files deleted alone per second: 556.00 ( 0.00%) 1224.00 (120.14%) 3062.00 (450.72%) 6124.00 (1001.44%) Files delete/transact per second: 8.00 ( 0.00%) 10.00 (25.00%) 9.00 (12.50%) 8.00 ( 0.00%) MMTests Statistics: duration Sys Time Running Test (seconds) 113.34 107.99 109.73 108.72 User+Sys Time Running Test (seconds) 145.51 139.81 143.32 143.55 Total Elapsed Time (seconds) 1159.16 899.23 980.17 1062.27 MMTests Statistics: vmstat Page Ins 13710192 13729032 13727944 13760136 Page Outs 43071140 42987228 42733684 42931624 Swap Ins 0 0 0 0 Swap Outs 0 0 0 0 Direct pages scanned 0 0 0 0 Kswapd pages scanned 9941613 9937443 9939085 9929154 Kswapd pages reclaimed 9940926 9936751 9938397 9928465 Direct pages reclaimed 0 0 0 0 Kswapd efficiency 99% 99% 99% 99% Kswapd velocity 8576.567 11051.058 10140.164 9347.109 Direct efficiency 100% 100% 100% 100% Direct velocity 0.000 0.000 0.000 0.000 It looks like here that the full series regresses performance but as ftrace showed no usage of wait_iff_congested() or sync reclaim I am assuming it's a disruption due to monitoring. Other data such as memory usage, page IO, swap IO all looked similar. Running a benchmark with a plain DD showed nothing very interesting. The full series stalled in wait_iff_congested() slightly less but stall times on vanilla kernels were marginal. Running a benchmark that hammered on file-backed mappings showed stalls due to congestion but not in sync writebacks MICRO 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 MMTests Statistics: duration Sys Time Running Test (seconds) 308.13 294.50 298.75 299.53 User+Sys Time Running Test (seconds) 330.45 316.28 318.93 320.79 Total Elapsed Time (seconds) 1814.90 1833.88 1821.14 1832.91 MMTests Statistics: vmstat Page Ins 108712 120708 97224 110344 Page Outs 155514576 156017404 155813676 156193256 Swap Ins 0 0 0 0 Swap Outs 0 0 0 0 Direct pages scanned 2599253 1550480 2512822 2414760 Kswapd pages scanned 69742364 71150694 68839041 69692533 Kswapd pages reclaimed 34824488 34773341 34796602 34799396 Direct pages reclaimed 53693 94750 61792 75205 Kswapd efficiency 49% 48% 50% 49% Kswapd velocity 38427.662 38797.901 37799.972 38022.889 Direct efficiency 2% 6% 2% 3% Direct velocity 1432.174 845.464 1379.807 1317.446 Percentage direct scans 3% 2% 3% 3% Page writes by reclaim 0 0 0 0 Page writes file 0 0 0 0 Page writes anon 0 0 0 0 Page reclaim immediate 0 0 0 1218 Page rescued immediate 0 0 0 0 Slabs scanned 15360 16384 13312 16384 Direct inode steals 0 0 0 0 Kswapd inode steals 4340 4327 1630 4323 FTrace Reclaim Statistics: congestion_wait Direct number congest waited 0 0 0 0 Direct time congest waited 0ms 0ms 0ms 0ms Direct full congest waited 0 0 0 0 Direct number conditional waited 900 870 754 789 Direct time conditional waited 0ms 0ms 0ms 20ms Direct full conditional waited 0 0 0 0 KSwapd number congest waited 2106 2308 2116 1915 KSwapd time congest waited 139924ms 157832ms 125652ms 132516ms KSwapd full congest waited 1346 1530 1202 1278 KSwapd number conditional waited 12922 16320 10943 14670 KSwapd time conditional waited 0ms 0ms 0ms 0ms KSwapd full conditional waited 0 0 0 0 Reclaim statistics are not radically changed. The stall times in kswapd are massive but it is clear that it is due to calls to congestion_wait() and that is almost certainly the call in balance_pgdat(). Otherwise stalls due to dirty pages are non-existant. I ran a benchmark that stressed high-order allocation. This is very artifical load but was used in the past to evaluate lumpy reclaim and compaction. Generally I look at allocation success rates and latency figures. STRESS-HIGHALLOC 3.3.0-vanilla rc2-vanilla lumpyremove-v2r3 nosync-v2r3 Pass 1 81.00 ( 0.00%) 28.00 (-53.00%) 24.00 (-57.00%) 28.00 (-53.00%) Pass 2 82.00 ( 0.00%) 39.00 (-43.00%) 38.00 (-44.00%) 43.00 (-39.00%) while Rested 88.00 ( 0.00%) 87.00 (-1.00%) 88.00 ( 0.00%) 88.00 ( 0.00%) MMTests Statistics: duration Sys Time Running Test (seconds) 740.93 681.42 685.14 684.87 User+Sys Time Running Test (seconds) 2922.65 3269.52 3281.35 3279.44 Total Elapsed Time (seconds) 1161.73 1152.49 1159.55 1161.44 MMTests Statistics: vmstat Page Ins 4486020 2807256 2855944 2876244 Page Outs 7261600 7973688 7975320 7986120 Swap Ins 31694 0 0 0 Swap Outs 98179 0 0 0 Direct pages scanned 53494 57731 34406 113015 Kswapd pages scanned 6271173 1287481 1278174 1219095 Kswapd pages reclaimed 2029240 1281025 1260708 1201583 Direct pages reclaimed 1468 14564 16649 92456 Kswapd efficiency 32% 99% 98% 98% Kswapd velocity 5398.133 1117.130 1102.302 1049.641 Direct efficiency 2% 25% 48% 81% Direct velocity 46.047 50.092 29.672 97.306 Percentage direct scans 0% 4% 2% 8% Page writes by reclaim 1616049 0 0 0 Page writes file 1517870 0 0 0 Page writes anon 98179 0 0 0 Page reclaim immediate 103778 27339 9796 17831 Page rescued immediate 0 0 0 0 Slabs scanned 1096704 986112 980992 998400 Direct inode steals 223 215040 216736 247881 Kswapd inode steals 175331 61548 68444 63066 Kswapd skipped wait 21991 0 1 0 THP fault alloc 1 135 125 134 THP collapse alloc 393 311 228 236 THP splits 25 13 7 8 THP fault fallback 0 0 0 0 THP collapse fail 3 5 7 7 Compaction stalls 865 1270 1422 1518 Compaction success 370 401 353 383 Compaction failures 495 869 1069 1135 Compaction pages moved 870155 3828868 4036106 4423626 Compaction move failure 26429 23865 29742 27514 Success rates are completely hosed for 3.4-rc2 which is almost certainly due to commit fe2c2a106663 ("vmscan: reclaim at order 0 when compaction is enabled"). I expected this would happen for kswapd and impair allocation success rates (https://lkml.org/lkml/2012/1/25/166) but I did not anticipate this much a difference: 80% less scanning, 37% less reclaim by kswapd In comparison, reclaim/compaction is not aggressive and gives up easily which is the intended behaviour. hugetlbfs uses __GFP_REPEAT and would be much more aggressive about reclaim/compaction than THP allocations are. The stress test above is allocating like neither THP or hugetlbfs but is much closer to THP. Mainline is now impaired in terms of high order allocation under heavy load although I do not know to what degree as I did not test with __GFP_REPEAT. Keep this in mind for bugs related to hugepage pool resizing, THP allocation and high order atomic allocation failures from network devices. In terms of congestion throttling, I see the following for this test FTrace Reclaim Statistics: congestion_wait Direct number congest waited 3 0 0 0 Direct time congest waited 0ms 0ms 0ms 0ms Direct full congest waited 0 0 0 0 Direct number conditional waited 957 512 1081 1075 Direct time conditional waited 0ms 0ms 0ms 0ms Direct full conditional waited 0 0 0 0 KSwapd number congest waited 36 4 3 5 KSwapd time congest waited 3148ms 400ms 300ms 500ms KSwapd full congest waited 30 4 3 5 KSwapd number conditional waited 88514 197 332 542 KSwapd time conditional waited 4980ms 0ms 0ms 0ms KSwapd full conditional waited 49 0 0 0 The "conditional waited" times are the most interesting as this is directly impacted by the number of dirty pages encountered during scan. As lumpy reclaim is no longer scanning contiguous ranges, it is finding fewer dirty pages. This brings wait times from about 5 seconds to 0. kswapd itself is still calling congestion_wait() so it'll still stall but it's a lot less. In terms of the type of IO we were doing, I see this FTrace Reclaim Statistics: mm_vmscan_writepage Direct writes anon sync 0 0 0 0 Direct writes anon async 0 0 0 0 Direct writes file sync 0 0 0 0 Direct writes file async 0 0 0 0 Direct writes mixed sync 0 0 0 0 Direct writes mixed async 0 0 0 0 KSwapd writes anon sync 0 0 0 0 KSwapd writes anon async 91682 0 0 0 KSwapd writes file sync 0 0 0 0 KSwapd writes file async 822629 0 0 0 KSwapd writes mixed sync 0 0 0 0 KSwapd writes mixed async 0 0 0 0 In 3.2, kswapd was doing a bunch of async writes of pages but reclaim/compaction was never reaching a point where it was doing sync IO. This does not guarantee that reclaim/compaction was not calling wait_on_page_writeback() but I would consider it unlikely. It indicates that merging patches 2 and 3 to stop reclaim/compaction calling wait_on_page_writeback() should be safe. This patch: Lumpy reclaim had a purpose but in the mind of some, it was to kick the system so hard it trashed. For others the purpose was to complicate vmscan.c. Over time it was giving softer shoes and a nicer attitude but memory compaction needs to step up and replace it so this patch sends lumpy reclaim to the farm. The tracepoint format changes for isolating LRU pages with this patch applied. Furthermore reclaim/compaction can no longer queue dirty pages in pageout() if the underlying BDI is congested. Lumpy reclaim used this logic and reclaim/compaction was using it in error. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: KOSAKI Motohiro Cc: Konstantin Khlebnikov Cc: Hugh Dickins Cc: Ying Han Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 26 ++++---------------------- 1 file changed, 4 insertions(+), 22 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 572195459d58..bdaf32f8a874 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -263,22 +263,16 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_taken, - unsigned long nr_lumpy_taken, - unsigned long nr_lumpy_dirty, - unsigned long nr_lumpy_failed, isolate_mode_t isolate_mode, int file), - TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file), + TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file), TP_STRUCT__entry( __field(int, order) __field(unsigned long, nr_requested) __field(unsigned long, nr_scanned) __field(unsigned long, nr_taken) - __field(unsigned long, nr_lumpy_taken) - __field(unsigned long, nr_lumpy_dirty) - __field(unsigned long, nr_lumpy_failed) __field(isolate_mode_t, isolate_mode) __field(int, file) ), @@ -288,22 +282,16 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template, __entry->nr_requested = nr_requested; __entry->nr_scanned = nr_scanned; __entry->nr_taken = nr_taken; - __entry->nr_lumpy_taken = nr_lumpy_taken; - __entry->nr_lumpy_dirty = nr_lumpy_dirty; - __entry->nr_lumpy_failed = nr_lumpy_failed; __entry->isolate_mode = isolate_mode; __entry->file = file; ), - TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu contig_taken=%lu contig_dirty=%lu contig_failed=%lu file=%d", + TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d", __entry->isolate_mode, __entry->order, __entry->nr_requested, __entry->nr_scanned, __entry->nr_taken, - __entry->nr_lumpy_taken, - __entry->nr_lumpy_dirty, - __entry->nr_lumpy_failed, __entry->file) ); @@ -313,13 +301,10 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_taken, - unsigned long nr_lumpy_taken, - unsigned long nr_lumpy_dirty, - unsigned long nr_lumpy_failed, isolate_mode_t isolate_mode, int file), - TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file) + TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file) ); @@ -329,13 +314,10 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate, unsigned long nr_requested, unsigned long nr_scanned, unsigned long nr_taken, - unsigned long nr_lumpy_taken, - unsigned long nr_lumpy_dirty, - unsigned long nr_lumpy_failed, isolate_mode_t isolate_mode, int file), - TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file) + TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file) ); -- cgit v1.2.3 From 41ac1999c3e3563e1810b14878a869c79c9368bb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 29 May 2012 15:06:19 -0700 Subject: mm: vmscan: do not stall on writeback during memory compaction This patch stops reclaim/compaction entering sync reclaim as this was only intended for lumpy reclaim and an oversight. Page migration has its own logic for stalling on writeback pages if necessary and memory compaction is already using it. Waiting on page writeback is bad for a number of reasons but the primary one is that waiting on writeback to a slow device like USB can take a considerable length of time. Page reclaim instead uses wait_iff_congested() to throttle if too many dirty pages are being scanned. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: KOSAKI Motohiro Cc: Konstantin Khlebnikov Cc: Hugh Dickins Cc: Ying Han Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index bdaf32f8a874..82f693395ac5 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -13,7 +13,7 @@ #define RECLAIM_WB_ANON 0x0001u #define RECLAIM_WB_FILE 0x0002u #define RECLAIM_WB_MIXED 0x0010u -#define RECLAIM_WB_SYNC 0x0004u +#define RECLAIM_WB_SYNC 0x0004u /* Unused, all reclaim async */ #define RECLAIM_WB_ASYNC 0x0008u #define show_reclaim_flags(flags) \ @@ -27,13 +27,13 @@ #define trace_reclaim_flags(page, sync) ( \ (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ - (sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ + (RECLAIM_WB_ASYNC) \ ) -#define trace_shrink_flags(file, sync) ( \ - (sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_MIXED : \ - (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) | \ - (sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \ +#define trace_shrink_flags(file, sync) \ + ( \ + (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ + (RECLAIM_WB_ASYNC) \ ) TRACE_EVENT(mm_vmscan_kswapd_sleep, -- cgit v1.2.3 From 23b9da55c5b0feb484bd5e8615f4eb1ce4169453 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 29 May 2012 15:06:20 -0700 Subject: mm: vmscan: remove reclaim_mode_t There is little motiviation for reclaim_mode_t once RECLAIM_MODE_[A]SYNC and lumpy reclaim have been removed. This patch gets rid of reclaim_mode_t as well and improves the documentation about what reclaim/compaction is and when it is triggered. Signed-off-by: Mel Gorman Acked-by: Rik van Riel Acked-by: KOSAKI Motohiro Cc: Konstantin Khlebnikov Cc: Hugh Dickins Cc: Ying Han Cc: Andy Whitcroft Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/vmscan.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 82f693395ac5..bab3b87e4064 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -25,12 +25,12 @@ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" -#define trace_reclaim_flags(page, sync) ( \ +#define trace_reclaim_flags(page) ( \ (page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ ) -#define trace_shrink_flags(file, sync) \ +#define trace_shrink_flags(file) \ ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ -- cgit v1.2.3