From 100a8fdbf525bb11796692a713c267be6523a890 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 29 Jul 2014 11:50:48 +0100 Subject: thermal: trace: Trace temperature changes Create a new event to trace the temperature of a thermal zone. Using this event trace the temperature changes of the thermal zone every-time it is updated. Cc: Zhang Rui Cc: Eduardo Valentin Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Punit Agrawal Signed-off-by: Eduardo Valentin --- include/trace/events/thermal.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/trace/events/thermal.h (limited to 'include/trace') diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h new file mode 100644 index 000000000000..8c5ca96eccd6 --- /dev/null +++ b/include/trace/events/thermal.h @@ -0,0 +1,38 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM thermal + +#if !defined(_TRACE_THERMAL_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_THERMAL_H + +#include +#include + +TRACE_EVENT(thermal_temperature, + + TP_PROTO(struct thermal_zone_device *tz), + + TP_ARGS(tz), + + TP_STRUCT__entry( + __string(thermal_zone, tz->type) + __field(int, id) + __field(int, temp_prev) + __field(int, temp) + ), + + TP_fast_assign( + __assign_str(thermal_zone, tz->type); + __entry->id = tz->id; + __entry->temp_prev = tz->last_temperature; + __entry->temp = tz->temperature; + ), + + TP_printk("thermal_zone=%s id=%d temp_prev=%d temp=%d", + __get_str(thermal_zone), __entry->id, __entry->temp_prev, + __entry->temp) +); + +#endif /* _TRACE_THERMAL_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 39811569e43a81417bc0ddca3d0c7658c3dcd4b0 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 29 Jul 2014 11:50:49 +0100 Subject: thermal: trace: Trace when a cooling device's state is updated Introduce and use an event to trace when a cooling device's state is updated. This is useful to follow the effect of governor decisions on cooling devices. Cc: Zhang Rui Cc: Eduardo Valentin Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Punit Agrawal Signed-off-by: Eduardo Valentin --- include/trace/events/thermal.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h index 8c5ca96eccd6..894a79ea0686 100644 --- a/include/trace/events/thermal.h +++ b/include/trace/events/thermal.h @@ -32,6 +32,25 @@ TRACE_EVENT(thermal_temperature, __entry->temp) ); +TRACE_EVENT(cdev_update, + + TP_PROTO(struct thermal_cooling_device *cdev, unsigned long target), + + TP_ARGS(cdev, target), + + TP_STRUCT__entry( + __string(type, cdev->type) + __field(unsigned long, target) + ), + + TP_fast_assign( + __assign_str(type, cdev->type); + __entry->target = target; + ), + + TP_printk("type=%s target=%lu", __get_str(type), __entry->target) +); + #endif /* _TRACE_THERMAL_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 208cd822a19e683bc890f6708786f2420e172d76 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 29 Jul 2014 11:50:50 +0100 Subject: thermal: trace: Trace when temperature is above a trip point Create a new event to trace when the temperature is above a trip point. Use the trace-point when handling non-critical and critical trip pionts. Cc: Zhang Rui Cc: Eduardo Valentin Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Punit Agrawal Signed-off-by: Eduardo Valentin --- include/trace/events/thermal.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/thermal.h b/include/trace/events/thermal.h index 894a79ea0686..0f4f95d63c03 100644 --- a/include/trace/events/thermal.h +++ b/include/trace/events/thermal.h @@ -51,6 +51,32 @@ TRACE_EVENT(cdev_update, TP_printk("type=%s target=%lu", __get_str(type), __entry->target) ); +TRACE_EVENT(thermal_zone_trip, + + TP_PROTO(struct thermal_zone_device *tz, int trip, + enum thermal_trip_type trip_type), + + TP_ARGS(tz, trip, trip_type), + + TP_STRUCT__entry( + __string(thermal_zone, tz->type) + __field(int, id) + __field(int, trip) + __field(enum thermal_trip_type, trip_type) + ), + + TP_fast_assign( + __assign_str(thermal_zone, tz->type); + __entry->id = tz->id; + __entry->trip = trip; + __entry->trip_type = trip_type; + ), + + TP_printk("thermal_zone=%s id=%d trip=%d trip_type=%d", + __get_str(thermal_zone), __entry->id, __entry->trip, + __entry->trip_type) +); + #endif /* _TRACE_THERMAL_H */ /* This part must be outside protection */ -- cgit v1.2.3 From e963bb1de415ab06693357336c1bec664753e1e2 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Mon, 1 Sep 2014 22:22:13 -0400 Subject: ext4: improve extents status tree trace point This commit improves the trace point of extents status tree. We rename trace_ext4_es_shrink_enter in ext4_es_count() because it is also used in ext4_es_scan() and we can not identify them from the result. Further this commit fixes a variable name in trace point in order to keep consistency with others. Cc: Andreas Dilger Cc: Jan Kara Reviewed-by: Jan Kara Signed-off-by: Zheng Liu Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index d4f70a7fe876..849aaba75dc8 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2369,7 +2369,7 @@ TRACE_EVENT(ext4_es_lookup_extent_exit, show_extent_status(__entry->found ? __entry->status : 0)) ); -TRACE_EVENT(ext4_es_shrink_enter, +DECLARE_EVENT_CLASS(ext4__es_shrink_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt), @@ -2391,26 +2391,38 @@ TRACE_EVENT(ext4_es_shrink_enter, __entry->nr_to_scan, __entry->cache_cnt) ); -TRACE_EVENT(ext4_es_shrink_exit, - TP_PROTO(struct super_block *sb, int shrunk_nr, int cache_cnt), +DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_count, + TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), + + TP_ARGS(sb, nr_to_scan, cache_cnt) +); + +DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_scan_enter, + TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), + + TP_ARGS(sb, nr_to_scan, cache_cnt) +); + +TRACE_EVENT(ext4_es_shrink_scan_exit, + TP_PROTO(struct super_block *sb, int nr_shrunk, int cache_cnt), - TP_ARGS(sb, shrunk_nr, cache_cnt), + TP_ARGS(sb, nr_shrunk, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) - __field( int, shrunk_nr ) + __field( int, nr_shrunk ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; - __entry->shrunk_nr = shrunk_nr; + __entry->nr_shrunk = nr_shrunk; __entry->cache_cnt = cache_cnt; ), - TP_printk("dev %d,%d shrunk_nr %d cache_cnt %d", + TP_printk("dev %d,%d nr_shrunk %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->shrunk_nr, __entry->cache_cnt) + __entry->nr_shrunk, __entry->cache_cnt) ); TRACE_EVENT(ext4_collapse_range, -- cgit v1.2.3 From eb68d0e2fc5a4e5c06324ea5f485fccbae626d05 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Mon, 1 Sep 2014 22:26:49 -0400 Subject: ext4: track extent status tree shrinker delay statictics This commit adds some statictics in extent status tree shrinker. The purpose to add these is that we want to collect more details when we encounter a stall caused by extent status tree shrinker. Here we count the following statictics: stats: the number of all objects on all extent status trees the number of reclaimable objects on lru list cache hits/misses the last sorted interval the number of inodes on lru list average: scan time for shrinking some objects the number of shrunk objects maximum: the inode that has max nr. of objects on lru list the maximum scan time for shrinking some objects The output looks like below: $ cat /proc/fs/ext4/sda1/es_shrinker_info stats: 28228 objects 6341 reclaimable objects 5281/631 cache hits/misses 586 ms last sorted interval 250 inodes on lru list average: 153 us scan time 128 shrunk objects maximum: 255 inode (255 objects, 198 reclaimable) 125723 us max scan time If the lru list has never been sorted, the following line will not be printed: 586ms last sorted interval If there is an empty lru list, the following lines also will not be printed: 250 inodes on lru list ... maximum: 255 inode (255 objects, 198 reclaimable) 0 us max scan time Meanwhile in this commit a new trace point is defined to print some details in __ext4_es_shrink(). Cc: Andreas Dilger Cc: Jan Kara Reviewed-by: Jan Kara Signed-off-by: Zheng Liu Signed-off-by: Theodore Ts'o --- include/trace/events/ext4.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 849aaba75dc8..ff4bd1b35246 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2450,6 +2450,37 @@ TRACE_EVENT(ext4_collapse_range, __entry->offset, __entry->len) ); +TRACE_EVENT(ext4_es_shrink, + TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time, + int skip_precached, int nr_skipped, int retried), + + TP_ARGS(sb, nr_shrunk, scan_time, skip_precached, nr_skipped, retried), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( int, nr_shrunk ) + __field( unsigned long long, scan_time ) + __field( int, skip_precached ) + __field( int, nr_skipped ) + __field( int, retried ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->nr_shrunk = nr_shrunk; + __entry->scan_time = div_u64(scan_time, 1000); + __entry->skip_precached = skip_precached; + __entry->nr_skipped = nr_skipped; + __entry->retried = retried; + ), + + TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu skip_precached %d " + "nr_skipped %d retried %d", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, + __entry->scan_time, __entry->skip_precached, + __entry->nr_skipped, __entry->retried) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From d7e29933969e5ca7c112ce1368a07911f4485dc2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 27 Oct 2014 09:15:54 -0700 Subject: rcu: Make rcu_barrier() understand about missing rcuo kthreads Commit 35ce7f29a44a (rcu: Create rcuo kthreads only for onlined CPUs) avoids creating rcuo kthreads for CPUs that never come online. This fixes a bug in many instances of firmware: Instead of lying about their age, these systems instead lie about the number of CPUs that they have. Before commit 35ce7f29a44a, this could result in huge numbers of useless rcuo kthreads being created. It appears that experience indicates that I should have told the people suffering from this problem to fix their broken firmware, but I instead produced what turned out to be a partial fix. The missing piece supplied by this commit makes sure that rcu_barrier() knows not to post callbacks for no-CBs CPUs that have not yet come online, because otherwise rcu_barrier() will hang on systems having firmware that lies about the number of CPUs. It is tempting to simply have rcu_barrier() refuse to post a callback on any no-CBs CPU that does not have an rcuo kthread. This unfortunately does not work because rcu_barrier() is required to wait for all pending callbacks. It is therefore required to wait even for those callbacks that cannot possibly be invoked. Even if doing so hangs the system. Given that posting a callback to a no-CBs CPU that does not yet have an rcuo kthread can hang rcu_barrier(), It is tempting to report an error in this case. Unfortunately, this will result in false positives at boot time, when it is perfectly legal to post callbacks to the boot CPU before the scheduler has started, in other words, before it is legal to invoke rcu_barrier(). So this commit instead has rcu_barrier() avoid posting callbacks to CPUs having neither rcuo kthread nor pending callbacks, and has it complain bitterly if it finds CPUs having no rcuo kthread but some pending callbacks. And when rcu_barrier() does find CPUs having no rcuo kthread but pending callbacks, as noted earlier, it has no choice but to hang indefinitely. Reported-by: Yanko Kaneti Reported-by: Jay Vosburgh Reported-by: Meelis Roos Reported-by: Eric B Munson Signed-off-by: Paul E. McKenney Tested-by: Eric B Munson Tested-by: Jay Vosburgh Tested-by: Yanko Kaneti Tested-by: Kevin Fenzi Tested-by: Meelis Roos --- include/trace/events/rcu.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 9b56f37148cf..e335e7d8c6c2 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -660,18 +660,18 @@ TRACE_EVENT(rcu_torture_read, /* * Tracepoint for _rcu_barrier() execution. The string "s" describes * the _rcu_barrier phase: - * "Begin": rcu_barrier_callback() started. - * "Check": rcu_barrier_callback() checking for piggybacking. - * "EarlyExit": rcu_barrier_callback() piggybacked, thus early exit. - * "Inc1": rcu_barrier_callback() piggyback check counter incremented. - * "Offline": rcu_barrier_callback() found offline CPU - * "OnlineNoCB": rcu_barrier_callback() found online no-CBs CPU. - * "OnlineQ": rcu_barrier_callback() found online CPU with callbacks. - * "OnlineNQ": rcu_barrier_callback() found online CPU, no callbacks. + * "Begin": _rcu_barrier() started. + * "Check": _rcu_barrier() checking for piggybacking. + * "EarlyExit": _rcu_barrier() piggybacked, thus early exit. + * "Inc1": _rcu_barrier() piggyback check counter incremented. + * "OfflineNoCB": _rcu_barrier() found callback on never-online CPU + * "OnlineNoCB": _rcu_barrier() found online no-CBs CPU. + * "OnlineQ": _rcu_barrier() found online CPU with callbacks. + * "OnlineNQ": _rcu_barrier() found online CPU, no callbacks. * "IRQ": An rcu_barrier_callback() callback posted on remote CPU. * "CB": An rcu_barrier_callback() invoked a callback, not the last. * "LastCB": An rcu_barrier_callback() invoked the last callback. - * "Inc2": rcu_barrier_callback() piggyback check counter incremented. + * "Inc2": _rcu_barrier() piggyback check counter incremented. * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument * is the count of remaining callbacks, and "done" is the piggybacking count. */ -- cgit v1.2.3