All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 00/12 v2] ring-buffer/tracing: Remove disabling of ring buffer while reading trace file
@ 2020-03-19 23:22 Steven Rostedt
  2020-03-19 23:22 ` [PATCH 01/12 v2] selftest/ftrace: Fix function trigger test to handle trace not disabling the tracer Steven Rostedt
                   ` (12 more replies)
  0 siblings, 13 replies; 36+ messages in thread
From: Steven Rostedt @ 2020-03-19 23:22 UTC (permalink / raw)
  To: linux-kernel
  Cc: Ingo Molnar, Andrew Morton, Peter Zijlstra, Masami Hiramatsu,
	Alexei Starovoitov, Peter Wu, Jonathan Corbet, Tom Zanussi,
	Shuah Khan, bpf


When the ring buffer was first written for ftrace, there was two
human readable files to read it. One was a standard "producer/consumer"
file (trace_pipe), which would consume data from the ring buffer as
it read it, and the other was a "static iterator" that would not
consume the events, such that the file could be read multiple times
and return the same output each time.

The "static iterator" was never meant to be read while there was an
active writer to the ring buffer. If writing was enabled, then it
would disable the writer when the trace file was opened.

There has been some complaints about this by the BPF folks, that did
not realize this little bit of information and it was requested that
the "trace" file does not stop the writing to the ring buffer.

This patch series attempts to satisfy that request, by creating a
temporary buffer in each of the per cpu iterators to place the
read event into, such that it can be passed to users without worrying
about a writer to corrupt the event while it was being written out.
It also uses the fact that the ring buffer is broken up into pages,
where each page has its own timestamp that gets updated when a
writer crosses over to it. By copying it to the temp buffer, and
doing a "before and after" test of the time stamp with memory barriers,
can allow the events to be saved.

Changes since v1:

 - Added fix to selftest first, where these changes wont break it

 - Changed comment in trace_find_next_entry() to better explain what
   it was doing, as pointed out by Masami Hiramatsu.

 - Allocated the iterator temp buffer when the iterator is created,
   as Masami pointed out, it would be better than allocating it each
   time it was used. It is initiated as 128 bytes as most trace events
   are less than that, but will be expanded if needed. Note that
   function is only used when latency measurements are needed (seeing
   two events at once).

Steven Rostedt (VMware) (12):
      selftest/ftrace: Fix function trigger test to handle trace not disabling the tracer
      tracing: Save off entry when peeking at next entry
      ring-buffer: Have ring_buffer_empty() not depend on tracing stopped
      ring-buffer: Rename ring_buffer_read() to read_buffer_iter_advance()
      ring-buffer: Add page_stamp to iterator for synchronization
      ring-buffer: Have rb_iter_head_event() handle concurrent writer
      ring-buffer: Do not die if rb_iter_peek() fails more than thrice
      ring-buffer: Optimize rb_iter_head_event()
      ring-buffer: Do not disable recording when there is an iterator
      tracing: Do not disable tracing when reading the trace file
      ring-buffer/tracing: Have iterator acknowledge dropped events
      tracing: Have the document reflect that the trace file keeps tracing enabled

----
 Documentation/trace/ftrace.rst                     |  13 +-
 include/linux/ring_buffer.h                        |   4 +-
 include/linux/trace_events.h                       |   2 +
 kernel/trace/ring_buffer.c                         | 196 +++++++++++++++------
 kernel/trace/trace.c                               |  68 +++++--
 kernel/trace/trace_functions_graph.c               |   2 +-
 kernel/trace/trace_output.c                        |  15 +-
 .../test.d/ftrace/func_traceonoff_triggers.tc      |   2 +-
 8 files changed, 211 insertions(+), 91 deletions(-)

^ permalink raw reply	[flat|nested] 36+ messages in thread

end of thread, other threads:[~2020-04-03 13:16 UTC | newest]

Thread overview: 36+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-03-19 23:22 [PATCH 00/12 v2] ring-buffer/tracing: Remove disabling of ring buffer while reading trace file Steven Rostedt
2020-03-19 23:22 ` [PATCH 01/12 v2] selftest/ftrace: Fix function trigger test to handle trace not disabling the tracer Steven Rostedt
2020-03-19 23:22 ` [PATCH 02/12 v2] tracing: Save off entry when peeking at next entry Steven Rostedt
2020-03-20  2:57   ` Masami Hiramatsu
2020-03-26  9:12   ` [tracing] cd8f62b481: BUG:sleeping_function_called_from_invalid_context_at_mm/slab.h kernel test robot
2020-03-26  9:12     ` kernel test robot
2020-04-01 14:07     ` Masami Hiramatsu
2020-04-01 14:07       ` Masami Hiramatsu
2020-04-01 14:21       ` Steven Rostedt
2020-04-01 14:21         ` Steven Rostedt
2020-04-01 15:04         ` Steven Rostedt
2020-04-01 15:04           ` Steven Rostedt
2020-04-02  7:19           ` Masami Hiramatsu
2020-04-02  7:19             ` Masami Hiramatsu
2020-04-02 18:14             ` Steven Rostedt
2020-04-02 18:14               ` Steven Rostedt
2020-04-03  6:47               ` Masami Hiramatsu
2020-04-03  6:47                 ` Masami Hiramatsu
2020-04-03 13:16                 ` Steven Rostedt
2020-04-03 13:16                   ` Steven Rostedt
2020-03-19 23:22 ` [PATCH 03/12 v2] ring-buffer: Have ring_buffer_empty() not depend on tracing stopped Steven Rostedt
2020-03-19 23:22 ` [PATCH 04/12 v2] ring-buffer: Rename ring_buffer_read() to read_buffer_iter_advance() Steven Rostedt
2020-03-19 23:22 ` [PATCH 05/12 v2] ring-buffer: Add page_stamp to iterator for synchronization Steven Rostedt
2020-03-19 23:22 ` [PATCH 06/12 v2] ring-buffer: Have rb_iter_head_event() handle concurrent writer Steven Rostedt
2020-03-19 23:22 ` [PATCH 07/12 v2] ring-buffer: Do not die if rb_iter_peek() fails more than thrice Steven Rostedt
2020-03-19 23:22 ` [PATCH 08/12 v2] ring-buffer: Optimize rb_iter_head_event() Steven Rostedt
2020-03-19 23:22 ` [PATCH 09/12 v2] ring-buffer: Do not disable recording when there is an iterator Steven Rostedt
2020-03-19 23:22 ` [PATCH 10/12 v2] tracing: Do not disable tracing when reading the trace file Steven Rostedt
2020-03-19 23:22 ` [PATCH 11/12 v2] ring-buffer/tracing: Have iterator acknowledge dropped events Steven Rostedt
2020-03-19 23:22 ` [PATCH 12/12 v2] tracing: Have the document reflect that the trace file keeps tracing enabled Steven Rostedt
2020-03-21 19:13 ` [PATCH 00/12 v2] ring-buffer/tracing: Remove disabling of ring buffer while reading trace file David Laight
2020-03-22 18:07   ` Steven Rostedt
2020-03-27  1:46   ` Steven Rostedt
2020-03-27 10:07     ` David Laight
2020-03-27 14:30       ` Steven Rostedt
2020-03-27 14:56         ` David Laight

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.