user/sven/linux.git/kernel/trace/trace.h, branch v4.8.13

ftrace: Reduce size of function graph entries

2016-07-05T21:28:30Z

Currently ftrace_graph_ent{,_entry} and ftrace_graph_ret{,_entry} struct can have padding bytes at the end due to alignment in 64-bit data type. As these data are recorded so frequently, those paddings waste non-negligible space. As the ring buffer maintains alignment properly for each architecture, just to remove the extra padding using 'packed' attribute. ftrace_graph_ent_entry: 24 -> 20 ftrace_graph_ret_entry: 48 -> 44 Also I moved the 'overrun' field in struct ftrace_graph_ret to minimize the padding in the middle. Tested on x86_64 only. Link: http://lkml.kernel.org/r/1467197808-13578-1-git-send-email-namhyung@kernel.org Cc: Ingo Molnar Cc: linux-arch@vger.kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Steven Rostedt

ftrace: Move toplevel init out of ftrace_init_tracefs()

2016-07-05T14:47:03Z

Commit 345ddcc882d8 ("ftrace: Have set_ftrace_pid use the bitmap like events do") placed ftrace_init_tracefs into the instance creation, and encapsulated the top level updating with an if conditional, as the top level only gets updated at boot up. Unfortunately, this triggers section mismatch errors as the init functions are called from a function that can be called later, and the section mismatch logic is unaware of the if conditional that would prevent it from happening at run time. To make everyone happy, create a separate ftrace_init_tracefs_toplevel() routine that only gets called by init functions, and this will be what calls other init functions for the toplevel directory. Link: http://lkml.kernel.org/r/20160704102139.19cbc0d9@gandalf.local.home Reported-by: kbuild test robot Reported-by: Arnd Bergmann Fixes: 345ddcc882d8 ("ftrace: Have set_ftrace_pid use the bitmap like events do") Signed-off-by: Steven Rostedt

ftrace: Have set_ftrace_pid use the bitmap like events do

2016-06-20T13:54:19Z

Convert set_ftrace_pid to use the bitmap like set_event_pid does. This allows for instances to use the pid filtering as well, and will allow for function-fork option to set if the children of a traced function should be traced or not. Signed-off-by: Steven Rostedt

tracing: Move pid_list write processing into its own function

2016-06-20T13:54:18Z

The addition of PIDs into a pid_list via the write operation of set_event_pid is a bit complex. The same operation will be needed for function tracing pids. Move the code into its own generic function in trace.c, so that we can avoid duplication of this code. Signed-off-by: Steven Rostedt

tracing: Move the pid_list seq_file functions to be global

2016-06-20T13:54:17Z

To allow other aspects of ftrace to use the pid_list logic, we need to reuse the seq_file functions. Making the generic part into functions that can be called by other files will help in this regard. Signed-off-by: Steven Rostedt

tracing: Make the pid filtering helper functions global

2016-06-20T13:54:16Z

Make the functions used for pid filtering global for tracing, such that the function tracer can use the pid code as well. Signed-off-by: Steven Rostedt

tracing: Use temp buffer when filtering events

2016-05-03T21:59:24Z

Filtering of events requires the data to be written to the ring buffer before it can be decided to filter or not. This is because the parameters of the filter are based on the result that is written to the ring buffer and not on the parameters that are passed into the trace functions. The ftrace ring buffer is optimized for writing into the ring buffer and committing. The discard procedure used when filtering decides the event should be discarded is much more heavy weight. Thus, using a temporary filter when filtering events can speed things up drastically. Without a temp buffer we have: # trace-cmd start -p nop # perf stat -r 10 hackbench 50 0.790706626 seconds time elapsed ( +- 0.71% ) # trace-cmd start -e all # perf stat -r 10 hackbench 50 1.566904059 seconds time elapsed ( +- 0.27% ) # trace-cmd start -e all -f 'common_preempt_count==20' # perf stat -r 10 hackbench 50 1.690598511 seconds time elapsed ( +- 0.19% ) # trace-cmd start -e all -f 'common_preempt_count!=20' # perf stat -r 10 hackbench 50 1.707486364 seconds time elapsed ( +- 0.30% ) The first run above is without any tracing, just to get a based figure. hackbench takes ~0.79 seconds to run on the system. The second run enables tracing all events where nothing is filtered. This increases the time by 100% and hackbench takes 1.57 seconds to run. The third run filters all events where the preempt count will equal "20" (this should never happen) thus all events are discarded. This takes 1.69 seconds to run. This is 10% slower than just committing the events! The last run enables all events and filters where the filter will commit all events, and this takes 1.70 seconds to run. The filtering overhead is approximately 10%. Thus, the discard and commit of an event from the ring buffer may be about the same time. With this patch, the numbers change: # trace-cmd start -p nop # perf stat -r 10 hackbench 50 0.778233033 seconds time elapsed ( +- 0.38% ) # trace-cmd start -e all # perf stat -r 10 hackbench 50 1.582102692 seconds time elapsed ( +- 0.28% ) # trace-cmd start -e all -f 'common_preempt_count==20' # perf stat -r 10 hackbench 50 1.309230710 seconds time elapsed ( +- 0.22% ) # trace-cmd start -e all -f 'common_preempt_count!=20' # perf stat -r 10 hackbench 50 1.786001924 seconds time elapsed ( +- 0.20% ) The first run is again the base with no tracing. The second run is all tracing with no filtering. It is a little slower, but that may be well within the noise. The third run shows that discarding all events only took 1.3 seconds. This is a speed up of 23%! The discard is much faster than even the commit. The one downside is shown in the last run. Events that are not discarded by the filter will take longer to add, this is due to the extra copy of the event. Cc: Alexei Starovoitov Signed-off-by: Steven Rostedt

tracing: Have trace_buffer_unlock_commit() call the _regs version with NULL

2016-04-29T21:44:01Z

There's no real difference between trace_buffer_unlock_commit() and trace_buffer_unlock_commit_regs() except that the former passes NULL to ftrace_stack_trace() instead of regs. Have the former be a static inline of the latter which passes NULL for regs. Signed-off-by: Steven Rostedt

tracing: Move trace_buffer_unlock_commit{_regs}() to local header

2016-04-29T20:14:12Z

The functions trace_buffer_unlock_commit() and the _regs() version are only used within the kernel/trace directory. Move them to the local header and remove the export as well. Signed-off-by: Steven Rostedt

tracing: Fold filter_check_discard() into its only user

2016-04-29T20:14:08Z

The function filter_check_discard() is small and only called by one user, its code can be folded into that one caller and make the code a bit less comlplex. Signed-off-by: Steven Rostedt