OpenCloudOS-Kernel/kernel/trace/trace_functions_graph.c

1630 lines
39 KiB
C
Raw Normal View History

/*
*
* Function graph tracer.
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
* Copyright (c) 2008-2009 Frederic Weisbecker <fweisbec@gmail.com>
* Mostly borrowed from function tracer which
* is Copyright (c) Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/fs.h>
#include "trace.h"
#include "trace_output.h"
static bool kill_ftrace_graph;
/**
* ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
*
* ftrace_graph_stop() is called when a severe error is detected in
* the function graph tracing. This function is called by the critical
* paths of function graph to keep those paths from doing any more harm.
*/
bool ftrace_graph_is_dead(void)
{
return kill_ftrace_graph;
}
/**
* ftrace_graph_stop - set to permanently disable function graph tracincg
*
* In case of an error int function graph tracing, this is called
* to try to keep function graph tracing from causing any more harm.
* Usually this is pretty severe and this is called to try to at least
* get a warning out to the user.
*/
void ftrace_graph_stop(void)
{
kill_ftrace_graph = true;
}
/* When set, irq functions will be ignored */
static int ftrace_graph_skip_irqs;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct fgraph_cpu_data {
pid_t last_pid;
int depth;
int depth_irq;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
int ignore;
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
unsigned long enter_funcs[FTRACE_RETFUNC_DEPTH];
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
};
struct fgraph_data {
struct fgraph_cpu_data __percpu *cpu_data;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
/* Place to preserve last processed entry. */
struct ftrace_graph_ent_entry ent;
struct ftrace_graph_ret_entry ret;
int failed;
int cpu;
};
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
#define TRACE_GRAPH_INDENT 2
static unsigned int max_depth;
static struct tracer_opt trace_opts[] = {
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/* Display overruns? (for self-debug purpose) */
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
{ TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) },
/* Display CPU ? */
{ TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) },
/* Display Overhead ? */
{ TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) },
/* Display proc name/pid */
{ TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) },
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/* Display duration of execution */
{ TRACER_OPT(funcgraph-duration, TRACE_GRAPH_PRINT_DURATION) },
/* Display absolute time of an entry */
{ TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
/* Display interrupts */
{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
/* Display function name after trailing } */
{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
{ } /* Empty entry */
};
static struct tracer_flags tracer_flags = {
/* Don't display overruns, proc, or tail by default */
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
.val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS,
.opts = trace_opts
};
static struct trace_array *graph_array;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/*
* DURATION column is being also used to display IRQ signs,
* following values are used by print_graph_irq and others
* to fill in space into DURATION column.
*/
enum {
FLAGS_FILL_FULL = 1 << TRACE_GRAPH_PRINT_FILL_SHIFT,
FLAGS_FILL_START = 2 << TRACE_GRAPH_PRINT_FILL_SHIFT,
FLAGS_FILL_END = 3 << TRACE_GRAPH_PRINT_FILL_SHIFT,
};
static enum print_line_t
print_graph_duration(unsigned long long duration, struct trace_seq *s,
u32 flags);
/* Add a function return address to the trace stack on thread info.*/
int
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
unsigned long frame_pointer)
{
unsigned long long calltime;
int index;
if (unlikely(ftrace_graph_is_dead()))
return -EBUSY;
if (!current->ret_stack)
return -EBUSY;
/*
* We must make sure the ret_stack is tested before we read
* anything else.
*/
smp_rmb();
/* The return trace stack is full */
if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
atomic_inc(&current->trace_overrun);
return -EBUSY;
}
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
/*
* The curr_ret_stack is an index to ftrace return stack of
* current task. Its value should be in [0, FTRACE_RETFUNC_
* DEPTH) when the function graph tracer is used. To support
* filtering out specific functions, it makes the index
* negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
* so when it sees a negative index the ftrace will ignore
* the record. And the index gets recovered when returning
* from the filtered function by adding the FTRACE_NOTRACE_
* DEPTH and then it'll continue to record functions normally.
*
* The curr_ret_stack is initialized to -1 and get increased
* in this function. So it can be less than -1 only if it was
* filtered out via ftrace_graph_notrace_addr() which can be
* set from set_graph_notrace file in debugfs by user.
*/
if (current->curr_ret_stack < -1)
return -EBUSY;
calltime = trace_clock_local();
index = ++current->curr_ret_stack;
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
if (ftrace_graph_notrace_addr(func))
current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
barrier();
current->ret_stack[index].ret = ret;
current->ret_stack[index].func = func;
current->ret_stack[index].calltime = calltime;
current->ret_stack[index].subtime = 0;
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
current->ret_stack[index].fp = frame_pointer;
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
*depth = current->curr_ret_stack;
return 0;
}
/* Retrieve a function return address to the trace stack on thread info.*/
static void
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
unsigned long frame_pointer)
{
int index;
index = current->curr_ret_stack;
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
/*
* A negative index here means that it's just returned from a
* notrace'd function. Recover index to get an original
* return address. See ftrace_push_return_trace().
*
* TODO: Need to check whether the stack gets corrupted.
*/
if (index < 0)
index += FTRACE_NOTRACE_DEPTH;
if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
ftrace_graph_stop();
WARN_ON(1);
/* Might as well panic, otherwise we have no where to go */
*ret = (unsigned long)panic;
return;
}
#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY)
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
/*
* The arch may choose to record the frame pointer used
* and check it here to make sure that it is what we expect it
* to be. If gcc does not set the place holder of the return
* address in the frame pointer, and does a copy instead, then
* the function graph trace will fail. This test detects this
* case.
*
* Currently, x86_32 with optimize for size (-Os) makes the latest
* gcc do the above.
*
* Note, -mfentry does not use frame pointers, and this test
* is not needed if CC_USING_FENTRY is set.
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
*/
if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
ftrace_graph_stop();
WARN(1, "Bad frame pointer: expected %lx, received %lx\n"
" from func %ps return to %lx\n",
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
current->ret_stack[index].fp,
frame_pointer,
(void *)current->ret_stack[index].func,
current->ret_stack[index].ret);
*ret = (unsigned long)panic;
return;
}
#endif
*ret = current->ret_stack[index].ret;
trace->func = current->ret_stack[index].func;
trace->calltime = current->ret_stack[index].calltime;
trace->overrun = atomic_read(&current->trace_overrun);
trace->depth = index;
}
/*
* Send the trace to the ring-buffer.
* @return the original return address.
*/
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
{
struct ftrace_graph_ret trace;
unsigned long ret;
function-graph: add stack frame test In case gcc does something funny with the stack frames, or the return from function code, we would like to detect that. An arch may implement passing of a variable that is unique to the function and can be saved on entering a function and can be tested when exiting the function. Usually the frame pointer can be used for this purpose. This patch also implements this for x86. Where it passes in the stack frame of the parent function, and will test that frame on exit. There was a case in x86_32 with optimize for size (-Os) where, for a few functions, gcc would align the stack frame and place a copy of the return address into it. The function graph tracer modified the copy and not the actual return address. On return from the funtion, it did not go to the tracer hook, but returned to the parent. This broke the function graph tracer, because the return of the parent (where gcc did not do this funky manipulation) returned to the location that the child function was suppose to. This caused strange kernel crashes. This test detected the problem and pointed out where the issue was. This modifies the parameters of one of the functions that the arch specific code calls, so it includes changes to arch code to accommodate the new prototype. Note, I notice that the parsic arch implements its own push_return_trace. This is now a generic function and the ftrace_push_return_trace should be used instead. This patch does not touch that code. Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Helge Deller <deller@gmx.de> Cc: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-19 00:45:08 +08:00
ftrace_pop_return_trace(&trace, &ret, frame_pointer);
trace.rettime = trace_clock_local();
barrier();
current->curr_ret_stack--;
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
/*
* The curr_ret_stack can be less than -1 only if it was
* filtered out and it's about to return from the function.
* Recover the index and continue to trace normal functions.
*/
if (current->curr_ret_stack < -1) {
current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
return ret;
}
tracing/fgraph: Adjust fgraph depth before calling trace return callback While debugging the virtual cputime with the function graph tracer with a max_depth of 1 (most common use of the max_depth so far), I found that I was missing kernel execution because of a race condition. The code for the return side of the function has a slight race: ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); ftrace_graph_return(&trace); barrier(); current->curr_ret_stack--; The ftrace_pop_return_trace() initializes the trace structure for the callback. The ftrace_graph_return() uses the trace structure for its own use as that structure is on the stack and is local to this function. Then the curr_ret_stack is decremented which is what the trace.depth is set to. If an interrupt comes in after the ftrace_graph_return() but before the curr_ret_stack, then the called function will get a depth of 2. If max_depth is set to 1 this function will be ignored. The problem is that the trace has already been called, and the timestamp for that trace will not reflect the time the function was about to re-enter userspace. Calls to the interrupt will not be traced because the max_depth has prevented this. To solve this issue, the ftrace_graph_return() can safely be moved after the current->curr_ret_stack has been updated. This way the timestamp for the return callback will reflect the actual time. If an interrupt comes in after the curr_ret_stack update and ftrace_graph_return(), it will be traced. It may look a little confusing to see it within the other function, but at least it will not be lost. Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-01-30 06:30:31 +08:00
/*
* The trace should run after decrementing the ret counter
* in case an interrupt were to come in. We don't want to
* lose the interrupt if max_depth is set.
*/
ftrace_graph_return(&trace);
if (unlikely(!ret)) {
ftrace_graph_stop();
WARN_ON(1);
/* Might as well panic. What else to do? */
ret = (unsigned long)panic;
}
return ret;
}
int __trace_graph_entry(struct trace_array *tr,
struct ftrace_graph_ent *trace,
unsigned long flags,
int pc)
{
struct ftrace_event_call *call = &event_funcgraph_entry;
struct ring_buffer_event *event;
struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ftrace_graph_ent_entry *entry;
if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return 0;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
sizeof(*entry), flags, pc);
if (!event)
return 0;
entry = ring_buffer_event_data(event);
entry->graph_ent = *trace;
tracing: Update event filters for multibuffer The trace event filters are still tied to event calls rather than event files, which means you don't get what you'd expect when using filters in the multibuffer case: Before: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 2048 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 Setting the filter in tracing/instances/test1/events shouldn't affect the same event in tracing/events as it does above. After: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 We'd like to just move the filter directly from ftrace_event_call to ftrace_event_file, but there are a couple cases that don't yet have multibuffer support and therefore have to continue using the current event_call-based filters. For those cases, a new USE_CALL_FILTER bit is added to the event_call flags, whose main purpose is to keep the old behavior for those cases until they can be updated with multibuffer support; at that point, the USE_CALL_FILTER flag (and the new associated call_filter_check_discard() function) can go away. The multibuffer support also made filter_current_check_discard() redundant, so this change removes that function as well and replaces it with filter_check_discard() (or call_filter_check_discard() as appropriate). Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:34:17 +08:00
if (!call_filter_check_discard(call, entry, buffer, event))
tracing: Cache comms only after an event occurred Whenever an event is registered, the comm of tasks are saved at every task switch instead of saving them at every event. But if an event isn't executed much, the comm cache will be filled up by tasks that did not record the event and you lose out on the comms that did. Here's an example, if you enable the following events: echo 1 > /debug/tracing/events/kvm/kvm_cr/enable echo 1 > /debug/tracing/events/net/net_dev_xmit/enable Note, there's no kvm running on this machine so the first event will never be triggered, but because it is enabled, the storing of comms will continue. If we now disable the network event: echo 0 > /debug/tracing/events/net/net_dev_xmit/enable and look at the trace: cat /debug/tracing/trace sshd-2672 [001] ..s2 375.731616: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.731617: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 375.859356: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.859357: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 375.947351: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.947352: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 376.035383: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 376.035383: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 377.563806: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=226 rc=0 sshd-2672 [001] ..s1 377.563807: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=226 rc=0 sshd-2672 [001] ..s2 377.563834: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6be0 len=114 rc=0 sshd-2672 [001] ..s1 377.563842: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6be0 len=114 rc=0 We see that process 2672 which triggered the events has the comm "sshd". But if we run hackbench for a bit and look again: cat /debug/tracing/trace <...>-2672 [001] ..s2 375.731616: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.731617: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 375.859356: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.859357: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 375.947351: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.947352: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 376.035383: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 376.035383: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 377.563806: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=226 rc=0 <...>-2672 [001] ..s1 377.563807: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=226 rc=0 <...>-2672 [001] ..s2 377.563834: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6be0 len=114 rc=0 <...>-2672 [001] ..s1 377.563842: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6be0 len=114 rc=0 The stored "sshd" comm has been flushed out and we get a useless "<...>". But by only storing comms after a trace event occurred, we can run hackbench all day and still get the same output. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-10-12 00:14:25 +08:00
__buffer_unlock_commit(buffer, event);
return 1;
}
static inline int ftrace_graph_ignore_irqs(void)
{
if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
return 0;
return in_irq();
}
int trace_graph_entry(struct ftrace_graph_ent *trace)
{
struct trace_array *tr = graph_array;
struct trace_array_cpu *data;
unsigned long flags;
long disabled;
int ret;
int cpu;
int pc;
if (!ftrace_trace_task(current))
return 0;
/* trace it when it is-nested-in or is a function enabled. */
if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
ftrace_graph_ignore_irqs()) || (trace->depth < 0) ||
(max_depth && trace->depth >= max_depth))
return 0;
ftrace: Add set_graph_notrace filter The set_graph_notrace filter is analogous to set_ftrace_notrace and can be used for eliminating uninteresting part of function graph trace output. It also works with set_graph_function nicely. # cd /sys/kernel/debug/tracing/ # echo do_page_fault > set_graph_function # perf ftrace live true 2) | do_page_fault() { 2) | __do_page_fault() { 2) 0.381 us | down_read_trylock(); 2) 0.055 us | __might_sleep(); 2) 0.696 us | find_vma(); 2) | handle_mm_fault() { 2) | handle_pte_fault() { 2) | __do_fault() { 2) | filemap_fault() { 2) | find_get_page() { 2) 0.033 us | __rcu_read_lock(); 2) 0.035 us | __rcu_read_unlock(); 2) 1.696 us | } 2) 0.031 us | __might_sleep(); 2) 2.831 us | } 2) | _raw_spin_lock() { 2) 0.046 us | add_preempt_count(); 2) 0.841 us | } 2) 0.033 us | page_add_file_rmap(); 2) | _raw_spin_unlock() { 2) 0.057 us | sub_preempt_count(); 2) 0.568 us | } 2) | unlock_page() { 2) 0.084 us | page_waitqueue(); 2) 0.126 us | __wake_up_bit(); 2) 1.117 us | } 2) 7.729 us | } 2) 8.397 us | } 2) 8.956 us | } 2) 0.085 us | up_read(); 2) + 12.745 us | } 2) + 13.401 us | } ... # echo handle_mm_fault > set_graph_notrace # perf ftrace live true 1) | do_page_fault() { 1) | __do_page_fault() { 1) 0.205 us | down_read_trylock(); 1) 0.041 us | __might_sleep(); 1) 0.344 us | find_vma(); 1) 0.069 us | up_read(); 1) 4.692 us | } 1) 5.311 us | } ... Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-14 16:24:26 +08:00
/*
* Do not trace a function if it's filtered by set_graph_notrace.
* Make the index of ret stack negative to indicate that it should
* ignore further functions. But it needs its own ret stack entry
* to recover the original index in order to continue tracing after
* returning from the function.
*/
if (ftrace_graph_notrace_addr(trace->func))
return 1;
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
ret = __trace_graph_entry(tr, trace, flags, pc);
} else {
ret = 0;
}
atomic_dec(&data->disabled);
local_irq_restore(flags);
return ret;
}
static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
function-graph: Add tracing_thresh support to function_graph tracer Add support for tracing_thresh to the function_graph tracer. This version of this feature isolates the checks into new entry and return functions, to avoid adding more conditional code into the main function_graph paths. When the tracing_thresh is set and the function graph tracer is enabled, only the functions that took longer than the time in microseconds that was set in tracing_thresh are recorded. To do this efficiently, only the function exits are recorded: [tracing]# echo 100 > tracing_thresh [tracing]# echo function_graph > current_tracer [tracing]# cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) ! 119.214 us | } /* smp_apic_timer_interrupt */ 1) <========== | 0) ! 101.527 us | } /* __rcu_process_callbacks */ 0) ! 126.461 us | } /* rcu_process_callbacks */ 0) ! 145.111 us | } /* __do_softirq */ 0) ! 149.667 us | } /* do_softirq */ 0) ! 168.817 us | } /* irq_exit */ 0) ! 248.254 us | } /* smp_apic_timer_interrupt */ Also, add support for specifying tracing_thresh on the kernel command line. When used like so: "tracing_thresh=200 ftrace=function_graph" this can be used to analyse system startup. It is important to disable tracing soon after boot, in order to avoid losing the trace data. Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Tim Bird <tim.bird@am.sony.com> LKML-Reference: <4B87098B.4040308@am.sony.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-26 07:36:43 +08:00
{
if (tracing_thresh)
return 1;
else
return trace_graph_entry(trace);
}
static void
__trace_graph_function(struct trace_array *tr,
unsigned long ip, unsigned long flags, int pc)
{
u64 time = trace_clock_local();
struct ftrace_graph_ent ent = {
.func = ip,
.depth = 0,
};
struct ftrace_graph_ret ret = {
.func = ip,
.depth = 0,
.calltime = time,
.rettime = time,
};
__trace_graph_entry(tr, &ent, flags, pc);
__trace_graph_return(tr, &ret, flags, pc);
}
void
trace_graph_function(struct trace_array *tr,
unsigned long ip, unsigned long parent_ip,
unsigned long flags, int pc)
{
__trace_graph_function(tr, ip, flags, pc);
}
void __trace_graph_return(struct trace_array *tr,
struct ftrace_graph_ret *trace,
unsigned long flags,
int pc)
{
struct ftrace_event_call *call = &event_funcgraph_exit;
struct ring_buffer_event *event;
struct ring_buffer *buffer = tr->trace_buffer.buffer;
struct ftrace_graph_ret_entry *entry;
if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->ret = *trace;
tracing: Update event filters for multibuffer The trace event filters are still tied to event calls rather than event files, which means you don't get what you'd expect when using filters in the multibuffer case: Before: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 2048 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 Setting the filter in tracing/instances/test1/events shouldn't affect the same event in tracing/events as it does above. After: # echo 'bytes_alloc > 8192' > /sys/kernel/debug/tracing/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # mkdir /sys/kernel/debug/tracing/instances/test1 # echo 'bytes_alloc > 2048' > /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/filter bytes_alloc > 8192 # cat /sys/kernel/debug/tracing/instances/test1/events/kmem/kmalloc/filter bytes_alloc > 2048 We'd like to just move the filter directly from ftrace_event_call to ftrace_event_file, but there are a couple cases that don't yet have multibuffer support and therefore have to continue using the current event_call-based filters. For those cases, a new USE_CALL_FILTER bit is added to the event_call flags, whose main purpose is to keep the old behavior for those cases until they can be updated with multibuffer support; at that point, the USE_CALL_FILTER flag (and the new associated call_filter_check_discard() function) can go away. The multibuffer support also made filter_current_check_discard() redundant, so this change removes that function as well and replaces it with filter_check_discard() (or call_filter_check_discard() as appropriate). Link: http://lkml.kernel.org/r/f16e9ce4270c62f46b2e966119225e1c3cca7e60.1382620672.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-10-24 21:34:17 +08:00
if (!call_filter_check_discard(call, entry, buffer, event))
tracing: Cache comms only after an event occurred Whenever an event is registered, the comm of tasks are saved at every task switch instead of saving them at every event. But if an event isn't executed much, the comm cache will be filled up by tasks that did not record the event and you lose out on the comms that did. Here's an example, if you enable the following events: echo 1 > /debug/tracing/events/kvm/kvm_cr/enable echo 1 > /debug/tracing/events/net/net_dev_xmit/enable Note, there's no kvm running on this machine so the first event will never be triggered, but because it is enabled, the storing of comms will continue. If we now disable the network event: echo 0 > /debug/tracing/events/net/net_dev_xmit/enable and look at the trace: cat /debug/tracing/trace sshd-2672 [001] ..s2 375.731616: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.731617: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 375.859356: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.859357: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 375.947351: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 375.947352: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 376.035383: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s1 376.035383: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 sshd-2672 [001] ..s2 377.563806: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=226 rc=0 sshd-2672 [001] ..s1 377.563807: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=226 rc=0 sshd-2672 [001] ..s2 377.563834: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6be0 len=114 rc=0 sshd-2672 [001] ..s1 377.563842: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6be0 len=114 rc=0 We see that process 2672 which triggered the events has the comm "sshd". But if we run hackbench for a bit and look again: cat /debug/tracing/trace <...>-2672 [001] ..s2 375.731616: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.731617: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 375.859356: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.859357: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 375.947351: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 375.947352: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 376.035383: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s1 376.035383: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=242 rc=0 <...>-2672 [001] ..s2 377.563806: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6de0 len=226 rc=0 <...>-2672 [001] ..s1 377.563807: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6de0 len=226 rc=0 <...>-2672 [001] ..s2 377.563834: net_dev_xmit: dev=eth0 skbaddr=ffff88005cbb6be0 len=114 rc=0 <...>-2672 [001] ..s1 377.563842: net_dev_xmit: dev=br0 skbaddr=ffff88005cbb6be0 len=114 rc=0 The stored "sshd" comm has been flushed out and we get a useless "<...>". But by only storing comms after a trace event occurred, we can run hackbench all day and still get the same output. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2012-10-12 00:14:25 +08:00
__buffer_unlock_commit(buffer, event);
}
void trace_graph_return(struct ftrace_graph_ret *trace)
{
struct trace_array *tr = graph_array;
struct trace_array_cpu *data;
unsigned long flags;
long disabled;
int cpu;
int pc;
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = per_cpu_ptr(tr->trace_buffer.data, cpu);
disabled = atomic_inc_return(&data->disabled);
if (likely(disabled == 1)) {
pc = preempt_count();
__trace_graph_return(tr, trace, flags, pc);
}
atomic_dec(&data->disabled);
local_irq_restore(flags);
}
void set_graph_array(struct trace_array *tr)
{
graph_array = tr;
/* Make graph_array visible before we start tracing */
smp_mb();
}
static void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
function-graph: Add tracing_thresh support to function_graph tracer Add support for tracing_thresh to the function_graph tracer. This version of this feature isolates the checks into new entry and return functions, to avoid adding more conditional code into the main function_graph paths. When the tracing_thresh is set and the function graph tracer is enabled, only the functions that took longer than the time in microseconds that was set in tracing_thresh are recorded. To do this efficiently, only the function exits are recorded: [tracing]# echo 100 > tracing_thresh [tracing]# echo function_graph > current_tracer [tracing]# cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) ! 119.214 us | } /* smp_apic_timer_interrupt */ 1) <========== | 0) ! 101.527 us | } /* __rcu_process_callbacks */ 0) ! 126.461 us | } /* rcu_process_callbacks */ 0) ! 145.111 us | } /* __do_softirq */ 0) ! 149.667 us | } /* do_softirq */ 0) ! 168.817 us | } /* irq_exit */ 0) ! 248.254 us | } /* smp_apic_timer_interrupt */ Also, add support for specifying tracing_thresh on the kernel command line. When used like so: "tracing_thresh=200 ftrace=function_graph" this can be used to analyse system startup. It is important to disable tracing soon after boot, in order to avoid losing the trace data. Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Tim Bird <tim.bird@am.sony.com> LKML-Reference: <4B87098B.4040308@am.sony.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-26 07:36:43 +08:00
{
if (tracing_thresh &&
(trace->rettime - trace->calltime < tracing_thresh))
return;
else
trace_graph_return(trace);
}
static int graph_trace_init(struct trace_array *tr)
{
int ret;
set_graph_array(tr);
function-graph: Add tracing_thresh support to function_graph tracer Add support for tracing_thresh to the function_graph tracer. This version of this feature isolates the checks into new entry and return functions, to avoid adding more conditional code into the main function_graph paths. When the tracing_thresh is set and the function graph tracer is enabled, only the functions that took longer than the time in microseconds that was set in tracing_thresh are recorded. To do this efficiently, only the function exits are recorded: [tracing]# echo 100 > tracing_thresh [tracing]# echo function_graph > current_tracer [tracing]# cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) ! 119.214 us | } /* smp_apic_timer_interrupt */ 1) <========== | 0) ! 101.527 us | } /* __rcu_process_callbacks */ 0) ! 126.461 us | } /* rcu_process_callbacks */ 0) ! 145.111 us | } /* __do_softirq */ 0) ! 149.667 us | } /* do_softirq */ 0) ! 168.817 us | } /* irq_exit */ 0) ! 248.254 us | } /* smp_apic_timer_interrupt */ Also, add support for specifying tracing_thresh on the kernel command line. When used like so: "tracing_thresh=200 ftrace=function_graph" this can be used to analyse system startup. It is important to disable tracing soon after boot, in order to avoid losing the trace data. Acked-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Tim Bird <tim.bird@am.sony.com> LKML-Reference: <4B87098B.4040308@am.sony.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-26 07:36:43 +08:00
if (tracing_thresh)
ret = register_ftrace_graph(&trace_graph_thresh_return,
&trace_graph_thresh_entry);
else
ret = register_ftrace_graph(&trace_graph_return,
&trace_graph_entry);
if (ret)
return ret;
tracing_start_cmdline_record();
return 0;
}
static void graph_trace_reset(struct trace_array *tr)
{
tracing_stop_cmdline_record();
unregister_ftrace_graph();
}
static int graph_trace_update_thresh(struct trace_array *tr)
{
graph_trace_reset(tr);
return graph_trace_init(tr);
}
static int max_bytes_for_cpu;
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
static enum print_line_t
print_graph_cpu(struct trace_seq *s, int cpu)
{
int ret;
/*
* Start with a space character - to make it stand out
* to the right a bit when trace output is pasted into
* email:
*/
ret = trace_seq_printf(s, " %*d) ", max_bytes_for_cpu, cpu);
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
return TRACE_TYPE_HANDLED;
}
#define TRACE_GRAPH_PROCINFO_LENGTH 14
static enum print_line_t
print_graph_proc(struct trace_seq *s, pid_t pid)
{
char comm[TASK_COMM_LEN];
/* sign + log10(MAX_INT) + '\0' */
char pid_str[11];
int spaces = 0;
int ret;
int len;
int i;
trace_find_cmdline(pid, comm);
comm[7] = '\0';
sprintf(pid_str, "%d", pid);
/* 1 stands for the "-" character */
len = strlen(comm) + strlen(pid_str) + 1;
if (len < TRACE_GRAPH_PROCINFO_LENGTH)
spaces = TRACE_GRAPH_PROCINFO_LENGTH - len;
/* First spaces to align center */
for (i = 0; i < spaces / 2; i++) {
ret = trace_seq_putc(s, ' ');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
ret = trace_seq_printf(s, "%s-%s", comm, pid_str);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Last spaces to align center */
for (i = 0; i < spaces - (spaces / 2); i++) {
ret = trace_seq_putc(s, ' ');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
return TRACE_TYPE_HANDLED;
}
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
static enum print_line_t
print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
{
if (!trace_seq_putc(s, ' '))
return 0;
return trace_print_lat_fmt(s, entry);
}
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
/* If the pid changed since the last trace, output this event */
static enum print_line_t
verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
{
pid_t prev_pid;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
pid_t *last_pid;
int ret;
if (!data)
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
return TRACE_TYPE_HANDLED;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
if (*last_pid == pid)
return TRACE_TYPE_HANDLED;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
prev_pid = *last_pid;
*last_pid = pid;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
if (prev_pid == -1)
return TRACE_TYPE_HANDLED;
/*
* Context-switch trace line:
------------------------------------------
| 1) migration/0--1 => sshd-1755
------------------------------------------
*/
ret = trace_seq_puts(s,
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
" ------------------------------------------\n");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
ret = print_graph_cpu(s, cpu);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
ret = print_graph_proc(s, prev_pid);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
ret = trace_seq_puts(s, " => ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
ret = print_graph_proc(s, pid);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
ret = trace_seq_puts(s,
"\n ------------------------------------------\n\n");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
static struct ftrace_graph_ret_entry *
get_return_for_leaf(struct trace_iterator *iter,
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
struct ftrace_graph_ent_entry *curr)
{
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct fgraph_data *data = iter->private;
struct ring_buffer_iter *ring_iter = NULL;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
struct ring_buffer_event *event;
struct ftrace_graph_ret_entry *next;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
/*
* If the previous output failed to write to the seq buffer,
* then we just reuse the data from before.
*/
if (data && data->failed) {
curr = &data->ent;
next = &data->ret;
} else {
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
ring_iter = trace_buffer_iter(iter, iter->cpu);
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
/* First peek to compare current entry and the next one */
if (ring_iter)
event = ring_buffer_iter_peek(ring_iter, NULL);
else {
/*
* We need to consume the current entry to see
* the next one.
*/
ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu,
ring-buffer: Add place holder recording of dropped events Currently, when the ring buffer drops events, it does not record the fact that it did so. It does inform the writer that the event was dropped by returning a NULL event, but it does not put in any place holder where the event was dropped. This is not a trivial thing to add because the ring buffer mostly runs in overwrite (flight recorder) mode. That is, when the ring buffer is full, new data will overwrite old data. In a produce/consumer mode, where new data is simply dropped when the ring buffer is full, it is trivial to add the placeholder for dropped events. When there's more room to write new data, then a special event can be added to notify the reader about the dropped events. But in overwrite mode, any new write can overwrite events. A place holder can not be inserted into the ring buffer since there never may be room. A reader could also come in at anytime and miss the placeholder. Luckily, the way the ring buffer works, the read side can find out if events were lost or not, and how many events. Everytime a write takes place, if it overwrites the header page (the next read) it updates a "overrun" variable that keeps track of the number of lost events. When a reader swaps out a page from the ring buffer, it can record this number, perfom the swap, and then check to see if the number changed, and take the diff if it has, which would be the number of events dropped. This can be stored by the reader and returned to callers of the reader. Since the reader page swap will fail if the writer moved the head page since the time the reader page set up the swap, this gives room to record the overruns without worrying about races. If the reader sets up the pages, records the overrun, than performs the swap, if the swap succeeds, then the overrun variable has not been updated since the setup before the swap. For binary readers of the ring buffer, a flag is set in the header of each sub page (sub buffer) of the ring buffer. This flag is embedded in the size field of the data on the sub buffer, in the 31st bit (the size can be 32 or 64 bits depending on the architecture), but only 27 bits needs to be used for the actual size (less actually). We could add a new field in the sub buffer header to also record the number of events dropped since the last read, but this will change the format of the binary ring buffer a bit too much. Perhaps this change can be made if the information on the number of events dropped is considered important enough. Note, the notification of dropped events is only used by consuming reads or peeking at the ring buffer. Iterating over the ring buffer does not keep this information because the necessary data is only available when a page swap is made, and the iterator does not swap out pages. Cc: Robert Richter <robert.richter@amd.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-01 01:21:56 +08:00
NULL, NULL);
event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu,
ring-buffer: Add place holder recording of dropped events Currently, when the ring buffer drops events, it does not record the fact that it did so. It does inform the writer that the event was dropped by returning a NULL event, but it does not put in any place holder where the event was dropped. This is not a trivial thing to add because the ring buffer mostly runs in overwrite (flight recorder) mode. That is, when the ring buffer is full, new data will overwrite old data. In a produce/consumer mode, where new data is simply dropped when the ring buffer is full, it is trivial to add the placeholder for dropped events. When there's more room to write new data, then a special event can be added to notify the reader about the dropped events. But in overwrite mode, any new write can overwrite events. A place holder can not be inserted into the ring buffer since there never may be room. A reader could also come in at anytime and miss the placeholder. Luckily, the way the ring buffer works, the read side can find out if events were lost or not, and how many events. Everytime a write takes place, if it overwrites the header page (the next read) it updates a "overrun" variable that keeps track of the number of lost events. When a reader swaps out a page from the ring buffer, it can record this number, perfom the swap, and then check to see if the number changed, and take the diff if it has, which would be the number of events dropped. This can be stored by the reader and returned to callers of the reader. Since the reader page swap will fail if the writer moved the head page since the time the reader page set up the swap, this gives room to record the overruns without worrying about races. If the reader sets up the pages, records the overrun, than performs the swap, if the swap succeeds, then the overrun variable has not been updated since the setup before the swap. For binary readers of the ring buffer, a flag is set in the header of each sub page (sub buffer) of the ring buffer. This flag is embedded in the size field of the data on the sub buffer, in the 31st bit (the size can be 32 or 64 bits depending on the architecture), but only 27 bits needs to be used for the actual size (less actually). We could add a new field in the sub buffer header to also record the number of events dropped since the last read, but this will change the format of the binary ring buffer a bit too much. Perhaps this change can be made if the information on the number of events dropped is considered important enough. Note, the notification of dropped events is only used by consuming reads or peeking at the ring buffer. Iterating over the ring buffer does not keep this information because the necessary data is only available when a page swap is made, and the iterator does not swap out pages. Cc: Robert Richter <robert.richter@amd.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Luis Claudio R. Goncalves" <lclaudio@uudg.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-04-01 01:21:56 +08:00
NULL, NULL);
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
if (!event)
return NULL;
next = ring_buffer_event_data(event);
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
if (data) {
/*
* Save current and next entries for later reference
* if the output fails.
*/
data->ent = *curr;
/*
* If the next event is not a return type, then
* we only care about what type it is. Otherwise we can
* safely copy the entire event.
*/
if (next->ent.type == TRACE_GRAPH_RET)
data->ret = *next;
else
data->ret.ent.type = next->ent.type;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
}
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
if (next->ent.type != TRACE_GRAPH_RET)
return NULL;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
if (curr->ent.pid != next->ent.pid ||
curr->graph_ent.func != next->ret.func)
return NULL;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
/* this is a leaf, now advance the iterator */
if (ring_iter)
ring_buffer_read(ring_iter, NULL);
return next;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
}
static int print_graph_abs_time(u64 t, struct trace_seq *s)
{
unsigned long usecs_rem;
usecs_rem = do_div(t, NSEC_PER_SEC);
usecs_rem /= 1000;
return trace_seq_printf(s, "%5lu.%06lu | ",
(unsigned long)t, usecs_rem);
}
static enum print_line_t
print_graph_irq(struct trace_iterator *iter, unsigned long addr,
enum trace_type type, int cpu, pid_t pid, u32 flags)
{
int ret;
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
if (addr < (unsigned long)__irqentry_text_start ||
addr >= (unsigned long)__irqentry_text_end)
return TRACE_TYPE_UNHANDLED;
if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
/* Absolute time */
if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
ret = print_graph_abs_time(iter->ts, s);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Cpu */
if (flags & TRACE_GRAPH_PRINT_CPU) {
ret = print_graph_cpu(s, cpu);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Proc */
if (flags & TRACE_GRAPH_PRINT_PROC) {
ret = print_graph_proc(s, pid);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
ret = trace_seq_puts(s, " | ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Latency format */
if (trace_flags & TRACE_ITER_LATENCY_FMT) {
ret = print_graph_lat_fmt(s, ent);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
}
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/* No overhead */
ret = print_graph_duration(0, s, flags | FLAGS_FILL_START);
if (ret != TRACE_TYPE_HANDLED)
return ret;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
if (type == TRACE_GRAPH_ENT)
ret = trace_seq_puts(s, "==========>");
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
else
ret = trace_seq_puts(s, "<==========");
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
ret = print_graph_duration(0, s, flags | FLAGS_FILL_END);
if (ret != TRACE_TYPE_HANDLED)
return ret;
ret = trace_seq_putc(s, '\n');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
enum print_line_t
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
{
unsigned long nsecs_rem = do_div(duration, 1000);
/* log10(ULONG_MAX) + '\0' */
char usecs_str[21];
char nsecs_str[5];
int ret, len;
int i;
sprintf(usecs_str, "%lu", (unsigned long) duration);
/* Print msecs */
ret = trace_seq_printf(s, "%s", usecs_str);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
len = strlen(usecs_str);
/* Print nsecs (we don't want to exceed 7 numbers) */
if (len < 7) {
size_t slen = min_t(size_t, sizeof(nsecs_str), 8UL - len);
snprintf(nsecs_str, slen, "%03lu", nsecs_rem);
ret = trace_seq_printf(s, ".%s", nsecs_str);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
len += strlen(nsecs_str);
}
ret = trace_seq_puts(s, " us ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/* Print remaining spaces to fit the row's width */
for (i = len; i < 7; i++) {
ret = trace_seq_putc(s, ' ');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
return TRACE_TYPE_HANDLED;
}
static enum print_line_t
print_graph_duration(unsigned long long duration, struct trace_seq *s,
u32 flags)
{
int ret = -1;
if (!(flags & TRACE_GRAPH_PRINT_DURATION) ||
!(trace_flags & TRACE_ITER_CONTEXT_INFO))
return TRACE_TYPE_HANDLED;
/* No real adata, just filling the column with spaces */
switch (flags & TRACE_GRAPH_PRINT_FILL_MASK) {
case FLAGS_FILL_FULL:
ret = trace_seq_puts(s, " | ");
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
case FLAGS_FILL_START:
ret = trace_seq_puts(s, " ");
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
case FLAGS_FILL_END:
ret = trace_seq_puts(s, " |");
return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
}
/* Signal a overhead of time execution to the output */
if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
/* Duration exceeded 100 usecs */
if (duration > 100000ULL)
ret = trace_seq_puts(s, "! ");
/* Duration exceeded 10 usecs */
else if (duration > 10000ULL)
ret = trace_seq_puts(s, "+ ");
}
/*
* The -1 means we either did not exceed the duration tresholds
* or we dont want to print out the overhead. Either way we need
* to fill out the space.
*/
if (ret == -1)
ret = trace_seq_puts(s, " ");
/* Catching here any failure happenned above */
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
ret = trace_print_graph_duration(duration, s);
if (ret != TRACE_TYPE_HANDLED)
return ret;
ret = trace_seq_puts(s, "| ");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
}
/* Case of a leaf function on its call entry */
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
static enum print_line_t
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
print_graph_entry_leaf(struct trace_iterator *iter,
struct ftrace_graph_ent_entry *entry,
struct ftrace_graph_ret_entry *ret_entry,
struct trace_seq *s, u32 flags)
{
struct fgraph_data *data = iter->private;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
struct ftrace_graph_ret *graph_ret;
struct ftrace_graph_ent *call;
unsigned long long duration;
int ret;
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
int i;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
graph_ret = &ret_entry->ret;
call = &entry->graph_ent;
duration = graph_ret->rettime - graph_ret->calltime;
if (data) {
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
/*
* Comments display at + 1 to depth. Since
* this is a leaf function, keep the comments
* equal to this depth.
*/
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
cpu_data->depth = call->depth - 1;
/* No need to keep this function around for this depth */
if (call->depth < FTRACE_RETFUNC_DEPTH)
cpu_data->enter_funcs[call->depth] = 0;
}
/* Overhead and duration */
ret = print_graph_duration(duration, s, flags);
if (ret == TRACE_TYPE_PARTIAL_LINE)
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
/* Function */
for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
ret = trace_seq_putc(s, ' ');
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
ret = trace_seq_printf(s, "%ps();\n", (void *)call->func);
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
static enum print_line_t
print_graph_entry_nested(struct trace_iterator *iter,
struct ftrace_graph_ent_entry *entry,
struct trace_seq *s, int cpu, u32 flags)
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
{
struct ftrace_graph_ent *call = &entry->graph_ent;
struct fgraph_data *data = iter->private;
int ret;
int i;
if (data) {
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
cpu_data->depth = call->depth;
/* Save this function pointer to see if the exit matches */
if (call->depth < FTRACE_RETFUNC_DEPTH)
cpu_data->enter_funcs[call->depth] = call->func;
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/* No time */
ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
if (ret != TRACE_TYPE_HANDLED)
return ret;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
/* Function */
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
ret = trace_seq_putc(s, ' ');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
ret = trace_seq_printf(s, "%ps() {\n", (void *)call->func);
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
/*
* we already consumed the current entry to check the next one
* and see if this is a leaf.
*/
return TRACE_TYPE_NO_CONSUME;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
static enum print_line_t
print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
int type, unsigned long addr, u32 flags)
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
{
struct fgraph_data *data = iter->private;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
struct trace_entry *ent = iter->ent;
int cpu = iter->cpu;
int ret;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
/* Pid */
if (verif_pid(s, ent->pid, cpu, data) == TRACE_TYPE_PARTIAL_LINE)
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
return TRACE_TYPE_PARTIAL_LINE;
if (type) {
/* Interrupt */
ret = print_graph_irq(iter, addr, type, cpu, ent->pid, flags);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
return 0;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/* Absolute time */
if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
ret = print_graph_abs_time(iter->ts, s);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
/* Cpu */
if (flags & TRACE_GRAPH_PRINT_CPU) {
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
ret = print_graph_cpu(s, cpu);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
/* Proc */
if (flags & TRACE_GRAPH_PRINT_PROC) {
ret = print_graph_proc(s, ent->pid);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
ret = trace_seq_puts(s, " | ");
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
/* Latency format */
if (trace_flags & TRACE_ITER_LATENCY_FMT) {
ret = print_graph_lat_fmt(s, ent);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
}
return 0;
}
/*
* Entry check for irq code
*
* returns 1 if
* - we are inside irq code
* - we just entered irq code
*
* retunns 0 if
* - funcgraph-interrupts option is set
* - we are not inside irq code
*/
static int
check_irq_entry(struct trace_iterator *iter, u32 flags,
unsigned long addr, int depth)
{
int cpu = iter->cpu;
int *depth_irq;
struct fgraph_data *data = iter->private;
/*
* If we are either displaying irqs, or we got called as
* a graph event and private data does not exist,
* then we bypass the irq check.
*/
if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
(!data))
return 0;
depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
/*
* We are inside the irq code
*/
if (*depth_irq >= 0)
return 1;
if ((addr < (unsigned long)__irqentry_text_start) ||
(addr >= (unsigned long)__irqentry_text_end))
return 0;
/*
* We are entering irq code.
*/
*depth_irq = depth;
return 1;
}
/*
* Return check for irq code
*
* returns 1 if
* - we are inside irq code
* - we just left irq code
*
* returns 0 if
* - funcgraph-interrupts option is set
* - we are not inside irq code
*/
static int
check_irq_return(struct trace_iterator *iter, u32 flags, int depth)
{
int cpu = iter->cpu;
int *depth_irq;
struct fgraph_data *data = iter->private;
/*
* If we are either displaying irqs, or we got called as
* a graph event and private data does not exist,
* then we bypass the irq check.
*/
if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
(!data))
return 0;
depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
/*
* We are not inside the irq code.
*/
if (*depth_irq == -1)
return 0;
/*
* We are inside the irq code, and this is returning entry.
* Let's not trace it and clear the entry depth, since
* we are out of irq code.
*
* This condition ensures that we 'leave the irq code' once
* we are out of the entry depth. Thus protecting us from
* the RETURN entry loss.
*/
if (*depth_irq >= depth) {
*depth_irq = -1;
return 1;
}
/*
* We are inside the irq code, and this is not the entry.
*/
return 1;
}
static enum print_line_t
print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
struct trace_iterator *iter, u32 flags)
{
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct fgraph_data *data = iter->private;
struct ftrace_graph_ent *call = &field->graph_ent;
struct ftrace_graph_ret_entry *leaf_ret;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
static enum print_line_t ret;
int cpu = iter->cpu;
if (check_irq_entry(iter, flags, call->func, call->depth))
return TRACE_TYPE_HANDLED;
if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func, flags))
return TRACE_TYPE_PARTIAL_LINE;
leaf_ret = get_return_for_leaf(iter, field);
if (leaf_ret)
ret = print_graph_entry_leaf(iter, field, leaf_ret, s, flags);
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
else
ret = print_graph_entry_nested(iter, field, s, cpu, flags);
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
if (data) {
/*
* If we failed to write our output, then we need to make
* note of it. Because we already consumed our entry.
*/
if (s->full) {
data->failed = 1;
data->cpu = cpu;
} else
data->failed = 0;
}
return ret;
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
}
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
static enum print_line_t
print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
struct trace_entry *ent, struct trace_iterator *iter,
u32 flags)
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
{
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
unsigned long long duration = trace->rettime - trace->calltime;
struct fgraph_data *data = iter->private;
pid_t pid = ent->pid;
int cpu = iter->cpu;
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
int func_match = 1;
int ret;
int i;
if (check_irq_return(iter, flags, trace->depth))
return TRACE_TYPE_HANDLED;
if (data) {
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
/*
* Comments display at + 1 to depth. This is the
* return from a function, we now want the comments
* to display at the same level of the bracket.
*/
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
cpu_data->depth = trace->depth - 1;
if (trace->depth < FTRACE_RETFUNC_DEPTH) {
if (cpu_data->enter_funcs[trace->depth] != trace->func)
func_match = 0;
cpu_data->enter_funcs[trace->depth] = 0;
}
}
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
if (print_graph_prologue(iter, s, 0, 0, flags))
ftrace: add cpu annotation for function graph tracer Impact: enhancement for function graph tracer When run on a SMP box, the function graph tracer is confusing because it shows the different CPUS as changes in the trace. This patch adds the annotation of 'CPU[###]' where ### is a three digit number. The output will look similar to this: CPU[001] dput() { CPU[000] } 726 CPU[001] } 487 CPU[000] do_softirq() { CPU[001] } 2221 CPU[000] __do_softirq() { CPU[000] __local_bh_disable() { CPU[001] unroll_tree_refs() { CPU[000] } 569 CPU[001] } 501 CPU[000] rcu_process_callbacks() { CPU[001] kfree() { What makes this nice is that now you can grep the file and produce readable format for a particular CPU. # cat /debug/tracing/trace > /tmp/trace # grep '^CPU\[000\]' /tmp/trace > /tmp/trace0 # grep '^CPU\[001\]' /tmp/trace > /tmp/trace1 Will give you: # head /tmp/trace0 CPU[000] ------------8<---------- thread sshd-3899 ------------8<---------- CPU[000] inotify_dentry_parent_queue_event() { CPU[000] } 2531 CPU[000] inotify_inode_queue_event() { CPU[000] } 505 CPU[000] } 69626 CPU[000] } 73089 CPU[000] audit_syscall_exit() { CPU[000] path_put() { CPU[000] dput() { # head /tmp/trace1 CPU[001] ------------8<---------- thread pcscd-3446 ------------8<---------- CPU[001] } 4186 CPU[001] dput() { CPU[001] } 543 CPU[001] vfs_permission() { CPU[001] inode_permission() { CPU[001] shmem_permission() { CPU[001] generic_permission() { CPU[001] } 501 CPU[001] } 2205 Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 13:16:27 +08:00
return TRACE_TYPE_PARTIAL_LINE;
/* Overhead and duration */
ret = print_graph_duration(duration, s, flags);
if (ret == TRACE_TYPE_PARTIAL_LINE)
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-graph-tracer: adjustments of the trace informations Impact: increase the visual qualities of the call-graph-tracer output This patch applies various trace output formatting changes: - CPU is now a decimal number, followed by a parenthesis. - Overhead is now on the second column (gives a good visibility) - Cost is now on the third column, can't exceed 9999.99 us. It is followed by a virtual line based on a "|" character. - Functions calls are now the last column on the right. This way, we haven't dynamic column (which flow is harder to follow) on its right. - CPU and Overhead have their own option flag. They are default-on but you can disable them easily: echo nofuncgraph-cpu > trace_options echo nofuncgraph-overhead > trace_options TODO: _ Refactoring of the thread switch output. _ Give a default-off option to output the thread and its pid on each row. _ Provide headers _ .... Here is an example of the new trace style: 0) | mutex_unlock() { 0) 0.639 us | __mutex_unlock_slowpath(); 0) 1.607 us | } 0) | remove_wait_queue() { 0) 0.616 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.779 us | } 0) 0.495 us | n_tty_set_room(); 0) ! 9999.999 us | } 0) | tty_ldisc_deref() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.616 us | _spin_unlock_irqrestore(); 0) 2.793 us | } 0) | current_fs_time() { 0) 0.488 us | current_kernel_time(); 0) 0.495 us | timespec_trunc(); 0) 2.486 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) ! 9999.999 us | } 0) | sys_read() { 0) 0.796 us | fget_light(); 0) | vfs_read() { 0) | rw_verify_area() { 0) | security_file_permission() { 0) 0.488 us | cap_file_permission(); 0) 1.720 us | } 0) 3. 4 us | } 0) | tty_read() { 0) 0.488 us | tty_paranoia_check(); 0) | tty_ldisc_ref_wait() { 0) | tty_ldisc_try() { 0) 0.615 us | _spin_lock_irqsave(); 0) 0.615 us | _spin_unlock_irqrestore(); 0) 5.436 us | } 0) 6.427 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-28 07:42:46 +08:00
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
/* Closing brace */
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
ret = trace_seq_putc(s, ' ');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
/*
* If the return function does not have a matching entry,
* then the entry was lost. Instead of just printing
* the '}' and letting the user guess what function this
* belongs to, write out the function name. Always do
* that if the funcgraph-tail option is enabled.
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
*/
if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL)) {
ret = trace_seq_puts(s, "}\n");
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
} else {
ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
ftrace: Add function names to dangling } in function graph tracer The function graph tracer is currently the most invasive tracer in the ftrace family. It can easily overflow the buffer even with 10megs per CPU. This means that events can often be lost. On start up, or after events are lost, if the function return is recorded but the function enter was lost, all we get to see is the exiting '}'. Here is how a typical trace output starts: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } 0) ! 567.961 us | } 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } 0) ! 603.361 us | } 0) ! 613.574 us | } 0) ! 623.554 us | } 0) 3.653 us | fget_light(); 0) | sock_poll() { There are a series of '}' with no matching "func() {". There's no information to what functions these ending brackets belong to. This patch adds a stack on the per cpu structure used in outputting the function graph tracer to keep track of what function was outputted. Then on a function exit event, it checks the depth to see if the function exit has a matching entry event. If it does, then it only prints the '}', otherwise it adds the function name after the '}'. This allows function exit events to show what function they belong to at trace output startup, when the entry was lost due to ring buffer overflow, or even after a new task is scheduled in. Here is what the above trace will look like after this patch: [tracing] cat trace # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) + 91.897 us | } (irq_exit) 0) ! 567.961 us | } (smp_apic_timer_interrupt) 0) <========== | 0) ! 579.083 us | _raw_spin_lock_irqsave(); 0) 4.694 us | _raw_spin_unlock_irqrestore(); 0) ! 594.862 us | } (add_wait_queue) 0) ! 603.361 us | } (__pollwait) 0) ! 613.574 us | } (tcp_poll) 0) ! 623.554 us | } (sock_poll) 0) 3.653 us | fget_light(); 0) | sock_poll() { Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-02-27 06:08:16 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
tracing/function-graph-tracer: enhancements for the trace output Impact: enhance the output of the graph-tracer This patch applies some ideas of Ingo Molnar and Steven Rostedt. * Output leaf functions in one line with parenthesis, semicolon and duration output. * Add a second column (after cpu) for an overhead sign. if duration > 100 us, "!" if duration > 10 us, "+" else " " * Print output in us with remaining nanosec: u.n * Print duration on the right end, following the indentation of the functions. Use also visual clues: "-" on entry call (no duration to output) and "+" on return (duration output). The name of the tracer has been fixed as well: function-branch becomes function_branch. Here is an example of the new output: CPU[000] dequeue_entity() { - CPU[000] update_curr() { - CPU[000] update_min_vruntime(); + 0.512 us CPU[000] } + 1.504 us CPU[000] clear_buddies(); + 0.481 us CPU[000] update_min_vruntime(); + 0.504 us CPU[000] } + 4.557 us CPU[000] hrtick_update() { - CPU[000] hrtick_start_fair(); + 0.489 us CPU[000] } + 1.443 us CPU[000] + } + 14.655 us CPU[000] + } + 15.678 us CPU[000] + } + 16.686 us CPU[000] msecs_to_jiffies(); + 0.481 us CPU[000] put_prev_task_fair(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.482 us CPU[000] pick_next_task_rt(); + 0.504 us CPU[000] pick_next_task_fair(); + 0.481 us CPU[000] pick_next_task_idle(); + 0.489 us CPU[000] _spin_trylock(); + 0.655 us CPU[000] _spin_unlock(); + 0.609 us CPU[000] ------------8<---------- thread bash-2794 ------------8<---------- CPU[000] finish_task_switch() { - CPU[000] _spin_unlock_irq(); + 0.722 us CPU[000] } + 2.369 us CPU[000] ! } + 501972.605 us CPU[000] ! } + 501973.763 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.670 us CPU[000] _spin_unlock_irqrestore(); + 0.699 us CPU[000] copy_to_user() { - CPU[000] might_fault() { - CPU[000] __might_sleep(); + 0.503 us CPU[000] } + 1.632 us CPU[000] __copy_to_user_ll(); + 0.542 us CPU[000] } + 3.858 us CPU[000] tty_audit_add_data() { - CPU[000] _spin_lock_irq(); + 0.609 us CPU[000] _spin_unlock_irq(); + 0.624 us CPU[000] } + 3.196 us CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.625 us CPU[000] + } + 13.611 us CPU[000] copy_from_read_buf() { - CPU[000] _spin_lock_irqsave(); + 0.624 us CPU[000] _spin_unlock_irqrestore(); + 0.616 us CPU[000] } + 2.820 us CPU[000] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-27 08:46:33 +08:00
/* Overrun */
if (flags & TRACE_GRAPH_PRINT_OVERRUN) {
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
ret = trace_seq_printf(s, " (Overruns: %lu)\n",
trace->overrun);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
ret = print_graph_irq(iter, trace->func, TRACE_GRAPH_RET,
cpu, pid, flags);
if (ret == TRACE_TYPE_PARTIAL_LINE)
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
return TRACE_TYPE_HANDLED;
}
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
static enum print_line_t
print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
struct trace_iterator *iter, u32 flags)
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
{
unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK);
struct fgraph_data *data = iter->private;
struct trace_event *event;
int depth = 0;
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
int ret;
int i;
if (data)
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
if (print_graph_prologue(iter, s, 0, 0, flags))
return TRACE_TYPE_PARTIAL_LINE;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
/* No time */
ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL);
if (ret != TRACE_TYPE_HANDLED)
return ret;
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
/* Indentation */
if (depth > 0)
for (i = 0; i < (depth + 1) * TRACE_GRAPH_INDENT; i++) {
ret = trace_seq_putc(s, ' ');
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
/* The comment */
ret = trace_seq_puts(s, "/* ");
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
switch (iter->ent->type) {
case TRACE_BPRINT:
ret = trace_print_bprintk_msg_only(iter);
if (ret != TRACE_TYPE_HANDLED)
return ret;
break;
case TRACE_PRINT:
ret = trace_print_printk_msg_only(iter);
if (ret != TRACE_TYPE_HANDLED)
return ret;
break;
default:
event = ftrace_find_event(ent->type);
if (!event)
return TRACE_TYPE_UNHANDLED;
ret = event->funcs->trace(iter, sym_flags, event);
if (ret != TRACE_TYPE_HANDLED)
return ret;
}
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
/* Strip ending newline */
if (s->buffer[s->len - 1] == '\n') {
s->buffer[s->len - 1] = '\0';
s->len--;
}
ret = trace_seq_puts(s, " */\n");
tracing/function-graph-tracer: handle ftrace_printk entries Handle the TRACE_PRINT entries from the function grapg tracer and output them as a C comment just below the function that called it, as if it was a comment inside this function. Example with an ftrace_printk inside might_sleep() function: void __might_sleep(char *file, int line) { static unsigned long prev_jiffy; /* ratelimiting */ ftrace_printk("Hi I'm a comment in might_sleep() :-)"); A chunk of a resulting trace: 0) | _reiserfs_free_block() { 0) | reiserfs_read_bitmap_block() { 0) | __bread() { 0) | __getblk() { 0) | __find_get_block() { 0) 0.698 us | mark_page_accessed(); 0) 2.267 us | } 0) | __might_sleep() { 0) | /* Hi I'm a comment in might_sleep() :-) */ 0) 1.321 us | } 0) 5.872 us | } 0) 7.313 us | } 0) 8.718 us | } And this patch brings two minor fixes: - The newline after a switch-out task has disappeared - The "|" sign just before the cpu number on task-switch has been deleted. 0) 0.616 us | pick_next_task_rt(); 0) 1.457 us | _spin_trylock(); 0) 0.653 us | _spin_unlock(); 0) 0.728 us | _spin_trylock(); 0) 0.631 us | _spin_unlock(); 0) 0.729 us | native_load_sp0(); 0) 0.593 us | native_load_tls(); ------------------------------------------ 0) cat-2834 => migrati-3 ------------------------------------------ 0) | finish_task_switch() { 0) 0.841 us | _spin_unlock_irq(); 0) 0.616 us | post_schedule_rt(); 0) 3.882 us | } Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-12-04 06:45:11 +08:00
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
enum print_line_t
tracing, function_graph: Remove dependency of abstime and duration fields on latency The display of absolute time and duration fields is based on the latency field. This was added during the irqsoff/wakeup tracers graph support changes. It's causing confusion in what fields will be displayed for the function_graph tracer itself. So I'm removing this depency, and adding absolute time and duration fields to the preemptirqsoff preemptoff irqsoff wakeup tracers. With following commands: # echo function_graph > ./current_tracer # cat trace This is what it looked like before: # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 0) 0.068 us | } /* page_add_file_rmap */ 0) | _raw_spin_unlock() { ... This is what it looks like now: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) 0.068 us | } /* add_preempt_count */ 0) 0.993 us | } /* vfsmount_lock_local_lock */ ... For preemptirqsoff preemptoff irqsoff wakeup tracers, this is what it looked like before: SNIP # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / _-=> lock-depth # |||| / # CPU TASK/PID ||||| DURATION FUNCTION CALLS # | | | ||||| | | | | | | 1) <idle>-0 | d..1 0.000 us | acpi_idle_enter_simple(); ... This is what it looks like now: SNIP # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / # TIME CPU TASK/PID |||| DURATION FUNCTION CALLS # | | | | |||| | | | | | | 19.847735 | 1) <idle>-0 | d..1 0.000 us | acpi_idle_enter_simple(); ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/1307113131-10045-2-git-send-email-jolsa@redhat.com Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-06-03 22:58:47 +08:00
print_graph_function_flags(struct trace_iterator *iter, u32 flags)
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
{
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct ftrace_graph_ent_entry *field;
struct fgraph_data *data = iter->private;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
int cpu = iter->cpu;
int ret;
if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
return TRACE_TYPE_HANDLED;
}
/*
* If the last output failed, there's a possibility we need
* to print out the missing entry which would never go out.
*/
if (data && data->failed) {
field = &data->ent;
iter->cpu = data->cpu;
ret = print_graph_entry(field, s, iter, flags);
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
ret = TRACE_TYPE_NO_CONSUME;
}
iter->cpu = cpu;
return ret;
}
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
switch (entry->type) {
case TRACE_GRAPH_ENT: {
/*
* print_graph_entry() may consume the current event,
* thus @field may become invalid, so we need to save it.
* sizeof(struct ftrace_graph_ent_entry) is very small,
* it can be safely saved at the stack.
*/
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct ftrace_graph_ent_entry saved;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
trace_assign_type(field, entry);
saved = *field;
return print_graph_entry(&saved, s, iter, flags);
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
case TRACE_GRAPH_RET: {
struct ftrace_graph_ret_entry *field;
trace_assign_type(field, entry);
return print_graph_return(&field->ret, s, entry, iter, flags);
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
}
case TRACE_STACK:
case TRACE_FN:
/* dont trace stack and functions as comments */
return TRACE_TYPE_UNHANDLED;
tracing/function-return-tracer: set a more human readable output Impact: feature This patch sets a C-like output for the function graph tracing. For this aim, we now call two handler for each function: one on the entry and one other on return. This way we can draw a well-ordered call stack. The pid of the previous trace is loosely stored to be compared against the one of the current trace to see if there were a context switch. Without this little feature, the call tree would seem broken at some locations. We could use the sched_tracer to capture these sched_events but this way of processing is much more simpler. 2 spaces have been chosen for indentation to fit the screen while deep calls. The time of execution in nanosecs is printed just after closed braces, it seems more easy this way to find the corresponding function. If the time was printed as a first column, it would be not so easy to find the corresponding function if it is called on a deep depth. I plan to output the return value but on 32 bits CPU, the return value can be 32 or 64, and its difficult to guess on which case we are. I don't know what would be the better solution on X86-32: only print eax (low-part) or even edx (high-part). Actually it's thee same problem when a function return a 8 bits value, the high part of eax could contain junk values... Here is an example of trace: sys_read() { fget_light() { } 526 vfs_read() { rw_verify_area() { security_file_permission() { cap_file_permission() { } 519 } 1564 } 2640 do_sync_read() { pipe_read() { __might_sleep() { } 511 pipe_wait() { prepare_to_wait() { } 760 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { update_min_vruntime() { } 504 } 1587 clear_buddies() { } 512 add_cfs_task_weight() { } 519 update_min_vruntime() { } 511 } 5602 dequeue_entity() { update_curr() { update_min_vruntime() { } 496 } 1631 clear_buddies() { } 496 update_min_vruntime() { } 527 } 4580 hrtick_update() { hrtick_start_fair() { } 488 } 1489 } 13700 } 14949 } 16016 msecs_to_jiffies() { } 496 put_prev_task_fair() { } 504 pick_next_task_fair() { } 489 pick_next_task_rt() { } 496 pick_next_task_fair() { } 489 pick_next_task_idle() { } 489 ------------8<---------- thread 4 ------------8<---------- finish_task_switch() { } 1203 do_softirq() { __do_softirq() { __local_bh_disable() { } 669 rcu_process_callbacks() { __rcu_process_callbacks() { cpu_quiet() { rcu_start_batch() { } 503 } 1647 } 3128 __rcu_process_callbacks() { } 542 } 5362 _local_bh_enable() { } 587 } 8880 } 9986 kthread_should_stop() { } 669 deactivate_task() { dequeue_task() { dequeue_task_fair() { dequeue_entity() { update_curr() { calc_delta_mine() { } 511 update_min_vruntime() { } 511 } 2813 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-26 07:57:25 +08:00
default:
return print_graph_comment(s, entry, iter, flags);
}
return TRACE_TYPE_HANDLED;
}
static enum print_line_t
print_graph_function(struct trace_iterator *iter)
{
tracing, function_graph: Remove dependency of abstime and duration fields on latency The display of absolute time and duration fields is based on the latency field. This was added during the irqsoff/wakeup tracers graph support changes. It's causing confusion in what fields will be displayed for the function_graph tracer itself. So I'm removing this depency, and adding absolute time and duration fields to the preemptirqsoff preemptoff irqsoff wakeup tracers. With following commands: # echo function_graph > ./current_tracer # cat trace This is what it looked like before: # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 0) 0.068 us | } /* page_add_file_rmap */ 0) | _raw_spin_unlock() { ... This is what it looks like now: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) 0.068 us | } /* add_preempt_count */ 0) 0.993 us | } /* vfsmount_lock_local_lock */ ... For preemptirqsoff preemptoff irqsoff wakeup tracers, this is what it looked like before: SNIP # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / _-=> lock-depth # |||| / # CPU TASK/PID ||||| DURATION FUNCTION CALLS # | | | ||||| | | | | | | 1) <idle>-0 | d..1 0.000 us | acpi_idle_enter_simple(); ... This is what it looks like now: SNIP # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / # TIME CPU TASK/PID |||| DURATION FUNCTION CALLS # | | | | |||| | | | | | | 19.847735 | 1) <idle>-0 | d..1 0.000 us | acpi_idle_enter_simple(); ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/1307113131-10045-2-git-send-email-jolsa@redhat.com Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-06-03 22:58:47 +08:00
return print_graph_function_flags(iter, tracer_flags.val);
}
static enum print_line_t
print_graph_function_event(struct trace_iterator *iter, int flags,
struct trace_event *event)
{
return print_graph_function(iter);
}
static void print_lat_header(struct seq_file *s, u32 flags)
{
static const char spaces[] = " " /* 16 spaces */
" " /* 4 spaces */
" "; /* 17 spaces */
int size = 0;
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
size += 16;
if (flags & TRACE_GRAPH_PRINT_CPU)
size += 4;
if (flags & TRACE_GRAPH_PRINT_PROC)
size += 17;
seq_printf(s, "#%.*s _-----=> irqs-off \n", size, spaces);
seq_printf(s, "#%.*s / _----=> need-resched \n", size, spaces);
seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
seq_printf(s, "#%.*s|| / _--=> preempt-depth \n", size, spaces);
tracing, function_graph: Remove lock-depth from latency trace The lock_depth was removed in commit e6e1e25 tracing: Remove lock_depth from event entry Removing the lock_depth info from function_graph latency header. With following commands: # echo function_graph > ./current_tracer # echo 1 > options/latency-format # cat trace This is what it looked like before: # tracer: function_graph # # function_graph latency trace v1.1.5 on 3.0.0-rc1-tip+ # -------------------------------------------------------------------- # latency: 0 us, #59756/311298, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) # ----------------- # | task: -0 (uid:0 nice:0 policy:0 rt_prio:0) # ----------------- # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / _-=> lock-depth # |||| / # CPU||||| DURATION FUNCTION CALLS # | ||||| | | | | | | 0) .... 0.068 us | } /* __rcu_read_unlock */ ... This is what it looks like now: # tracer: function_graph # # function_graph latency trace v1.1.5 on 3.0.0-rc1-tip+ # -------------------------------------------------------------------- # latency: 0 us, #59747/1744610, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2) # ----------------- # | task: -0 (uid:0 nice:0 policy:0 rt_prio:0) # ----------------- # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / # CPU|||| DURATION FUNCTION CALLS # | |||| | | | | | | 0) ..s. 1.641 us | } /* __rcu_process_callbacks */ ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/1307113131-10045-5-git-send-email-jolsa@redhat.com Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-06-03 22:58:50 +08:00
seq_printf(s, "#%.*s||| / \n", size, spaces);
}
static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
{
int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
if (lat)
print_lat_header(s, flags);
/* 1st line */
seq_putc(s, '#');
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
seq_puts(s, " TIME ");
if (flags & TRACE_GRAPH_PRINT_CPU)
seq_puts(s, " CPU");
if (flags & TRACE_GRAPH_PRINT_PROC)
seq_puts(s, " TASK/PID ");
if (lat)
seq_puts(s, "||||");
if (flags & TRACE_GRAPH_PRINT_DURATION)
seq_puts(s, " DURATION ");
seq_puts(s, " FUNCTION CALLS\n");
/* 2nd line */
seq_putc(s, '#');
if (flags & TRACE_GRAPH_PRINT_ABS_TIME)
seq_puts(s, " | ");
if (flags & TRACE_GRAPH_PRINT_CPU)
seq_puts(s, " | ");
if (flags & TRACE_GRAPH_PRINT_PROC)
seq_puts(s, " | | ");
if (lat)
seq_puts(s, "||||");
if (flags & TRACE_GRAPH_PRINT_DURATION)
seq_puts(s, " | | ");
seq_puts(s, " | | | |\n");
}
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
static void print_graph_headers(struct seq_file *s)
{
print_graph_headers_flags(s, tracer_flags.val);
}
void print_graph_headers_flags(struct seq_file *s, u32 flags)
{
struct trace_iterator *iter = s->private;
if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
return;
if (trace_flags & TRACE_ITER_LATENCY_FMT) {
/* print nothing if the buffers are empty */
if (trace_empty(iter))
return;
print_trace_header(s, iter);
tracing, function_graph: Remove dependency of abstime and duration fields on latency The display of absolute time and duration fields is based on the latency field. This was added during the irqsoff/wakeup tracers graph support changes. It's causing confusion in what fields will be displayed for the function_graph tracer itself. So I'm removing this depency, and adding absolute time and duration fields to the preemptirqsoff preemptoff irqsoff wakeup tracers. With following commands: # echo function_graph > ./current_tracer # cat trace This is what it looked like before: # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 0) 0.068 us | } /* page_add_file_rmap */ 0) | _raw_spin_unlock() { ... This is what it looks like now: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 0) 0.068 us | } /* add_preempt_count */ 0) 0.993 us | } /* vfsmount_lock_local_lock */ ... For preemptirqsoff preemptoff irqsoff wakeup tracers, this is what it looked like before: SNIP # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / _-=> lock-depth # |||| / # CPU TASK/PID ||||| DURATION FUNCTION CALLS # | | | ||||| | | | | | | 1) <idle>-0 | d..1 0.000 us | acpi_idle_enter_simple(); ... This is what it looks like now: SNIP # # _-----=> irqs-off # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / # TIME CPU TASK/PID |||| DURATION FUNCTION CALLS # | | | | |||| | | | | | | 19.847735 | 1) <idle>-0 | d..1 0.000 us | acpi_idle_enter_simple(); ... Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/1307113131-10045-2-git-send-email-jolsa@redhat.com Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-06-03 22:58:47 +08:00
}
__print_graph_headers_flags(s, flags);
}
void graph_trace_open(struct trace_iterator *iter)
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
{
/* pid and depth on the last trace processed */
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct fgraph_data *data;
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
int cpu;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
iter->private = NULL;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
goto out_err;
data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
if (!data->cpu_data)
goto out_err_free;
for_each_possible_cpu(cpu) {
pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
*pid = -1;
*depth = 0;
*ignore = 0;
*depth_irq = -1;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
}
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
iter->private = data;
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
return;
out_err_free:
kfree(data);
out_err:
pr_warning("function graph tracer: not enough memory\n");
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
}
void graph_trace_close(struct trace_iterator *iter)
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
{
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
struct fgraph_data *data = iter->private;
if (data) {
free_percpu(data->cpu_data);
kfree(data);
}
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
}
static int
func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
{
if (bit == TRACE_GRAPH_PRINT_IRQS)
ftrace_graph_skip_irqs = !set;
return 0;
}
static struct trace_event_functions graph_functions = {
.trace = print_graph_function_event,
};
static struct trace_event graph_trace_entry_event = {
.type = TRACE_GRAPH_ENT,
.funcs = &graph_functions,
};
static struct trace_event graph_trace_ret_event = {
.type = TRACE_GRAPH_RET,
.funcs = &graph_functions
};
static struct tracer graph_trace __tracer_data = {
.name = "function_graph",
.update_thresh = graph_trace_update_thresh,
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
.open = graph_trace_open,
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
.pipe_open = graph_trace_open,
tracing/function-graph-tracer: various fixes and features This patch brings various bugfixes: - Drop the first irrelevant task switch on the very beginning of a trace. - Drop the OVERHEAD word from the headers, the DURATION word is sufficient and will not overlap other columns. - Make the headers fit well their respective columns whatever the selected options. Ie, default options: # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 0.646 us | } 1) | mem_cgroup_del_lru_list() { 1) 0.624 us | lookup_page_cgroup(); 1) 1.970 us | } echo funcgraph-proc > trace_options # tracer: function_graph # # CPU TASK/PID DURATION FUNCTION CALLS # | | | | | | | | | 0) bash-2937 | 0.895 us | } 0) bash-2937 | 0.888 us | __rcu_read_unlock(); 0) bash-2937 | 0.864 us | conv_uni_to_pc(); 0) bash-2937 | 1.015 us | __rcu_read_lock(); echo nofuncgraph-cpu > trace_options echo nofuncgraph-proc > trace_options # tracer: function_graph # # DURATION FUNCTION CALLS # | | | | | | 3.752 us | native_pud_val(); 0.616 us | native_pud_val(); 0.624 us | native_pmd_val(); About features, one can now disable the duration (this will hide the overhead too for convenient reasons and because on doesn't need overhead if it hasn't the duration): echo nofuncgraph-duration > trace_options # tracer: function_graph # # FUNCTION CALLS # | | | | cap_vm_enough_memory() { __vm_enough_memory() { vm_acct_memory(); } } } And at last, an option to print the absolute time: //Restart from default options echo funcgraph-abstime > trace_options # tracer: function_graph # # TIME CPU DURATION FUNCTION CALLS # | | | | | | | | 261.339774 | 1) + 42.823 us | } 261.339775 | 1) 1.045 us | _spin_lock_irq(); 261.339777 | 1) 0.940 us | _spin_lock_irqsave(); 261.339778 | 1) 0.752 us | _spin_unlock_irqrestore(); 261.339780 | 1) 0.857 us | _spin_unlock_irq(); 261.339782 | 1) | flush_to_ldisc() { 261.339783 | 1) | tty_ldisc_ref() { 261.339783 | 1) | tty_ldisc_try() { 261.339784 | 1) 1.075 us | _spin_lock_irqsave(); 261.339786 | 1) 0.842 us | _spin_unlock_irqrestore(); 261.339788 | 1) 4.211 us | } 261.339788 | 1) 5.662 us | } The format is seconds.usecs. I guess no one needs the nanosec precision here, the main goal is to have an overview about the general timings of events, and to see the place when the trace switches from one cpu to another. ie: 274.874760 | 1) 0.676 us | _spin_unlock(); 274.874762 | 1) 0.609 us | native_load_sp0(); 274.874763 | 1) 0.602 us | native_load_tls(); 274.878739 | 0) 0.722 us | } 274.878740 | 0) 0.714 us | native_pmd_val(); 274.878741 | 0) 0.730 us | native_pmd_val(); Here there is a 4000 usecs difference when we switch the cpu. Changes in V2: - Completely fix the first pointless task switch. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 09:04:53 +08:00
.close = graph_trace_close,
tracing: Fix function graph trace_pipe to properly display failed entries There is a case where the graph tracer might get confused and omits displaying of a single record. This applies mostly with the trace_pipe since it is unlikely that the trace_seq buffer will overflow with the trace file. As the function_graph tracer goes through the trace entries keeping a pointer to the current record: current -> func1 ENTRY func2 ENTRY func2 RETURN func1 RETURN When an function ENTRY is encountered, it moves the pointer to the next entry to check if the function is a nested or leaf function. func1 ENTRY current -> func2 ENTRY func2 RETURN func1 RETURN If the rest of the writing of the function fills the trace_seq buffer, then the trace_pipe read will ignore this entry. The next read will Now start at the current location, but the first entry (func1) will be discarded. This patch keeps a copy of the current entry in the iterator private storage and will keep track of when the trace_seq buffer fills. When the trace_seq buffer fills, it will reuse the copy of the entry in the next iteration. [ This patch has been largely modified by Steven Rostedt in order to clean it up and simplify it. The original idea and concept was from Jirka and for that, this patch will go under his name to give him the credit he deserves. But because this was modify by Steven Rostedt anything wrong with the patch should be blamed on Steven. ] Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1259067458-27143-1-git-send-email-jolsa@redhat.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-24 20:57:38 +08:00
.pipe_close = graph_trace_close,
.init = graph_trace_init,
.reset = graph_trace_reset,
.print_line = print_graph_function,
.print_header = print_graph_headers,
.flags = &tracer_flags,
.set_flag = func_graph_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_function_graph,
#endif
};
static ssize_t
graph_depth_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
unsigned long val;
int ret;
ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
if (ret)
return ret;
max_depth = val;
*ppos += cnt;
return cnt;
}
static ssize_t
graph_depth_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
char buf[15]; /* More than enough to hold UINT_MAX + "\n"*/
int n;
n = sprintf(buf, "%d\n", max_depth);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, n);
}
static const struct file_operations graph_depth_fops = {
.open = tracing_open_generic,
.write = graph_depth_write,
.read = graph_depth_read,
.llseek = generic_file_llseek,
};
static __init int init_graph_debugfs(void)
{
struct dentry *d_tracer;
d_tracer = tracing_init_dentry();
if (!d_tracer)
return 0;
trace_create_file("max_graph_depth", 0644, d_tracer,
NULL, &graph_depth_fops);
return 0;
}
fs_initcall(init_graph_debugfs);
static __init int init_graph_trace(void)
{
max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
if (!register_ftrace_event(&graph_trace_entry_event)) {
pr_warning("Warning: could not register graph trace events\n");
return 1;
}
if (!register_ftrace_event(&graph_trace_ret_event)) {
pr_warning("Warning: could not register graph trace events\n");
return 1;
}
return register_tracer(&graph_trace);
}
core_initcall(init_graph_trace);