linux.git/block/blktrace.c, branch master

tracing/blktrace: move the tracing file to kernel/trace

2009-02-09T09:51:02+00:00

Impact: cleanup

Move blktrace.c to kernel/trace, also move its config entry.

Signed-off-by: Frederic Weisbecker 
Acked-by: Arnaldo Carvalho de Melo 
Acked-by: Jens Axboe 
Signed-off-by: Ingo Molnar

trace: Call tracing_reset_online_cpus before tracer->init()

2009-02-06T00:01:41+00:00

Impact: cleanup

To make it easy for ftrace plugin writers, as this was open coded in
the existing plugins

Signed-off-by: Arnaldo Carvalho de Melo 
Acked-by: Frédéric Weisbecker 
Signed-off-by: Ingo Molnar

tracing: Introduce trace_buffer_{lock_reserve,unlock_commit}

2009-02-06T00:01:41+00:00

Impact: new API

These new functions do what previously was being open coded, reducing
the number of details ftrace plugin writers have to worry about.

It also standardizes the handling of stacktrace, userstacktrace and
other trace options we may introduce in the future.

With this patch, for instance, the blk tracer (and some others already
in the tree) can use the "userstacktrace" /d/tracing/trace_options
facility.

$ codiff /tmp/vmlinux.before /tmp/vmlinux.after
linux-2.6-tip/kernel/trace/trace.c:
  trace_vprintk              |   -5
  trace_graph_return         |  -22
  trace_graph_entry          |  -26
  trace_function             |  -45
  __ftrace_trace_stack       |  -27
  ftrace_trace_userstack     |  -29
  tracing_sched_switch_trace |  -66
  tracing_stop               |   +1
  trace_seq_to_user          |   -1
  ftrace_trace_special       |  -63
  ftrace_special             |   +1
  tracing_sched_wakeup_trace |  -70
  tracing_reset_online_cpus  |   -1
 13 functions changed, 2 bytes added, 355 bytes removed, diff: -353

linux-2.6-tip/block/blktrace.c:
  __blk_add_trace |  -58
 1 function changed, 58 bytes removed, diff: -58

linux-2.6-tip/kernel/trace/trace.c:
  trace_buffer_lock_reserve  |  +88
  trace_buffer_unlock_commit |  +86
 2 functions changed, 174 bytes added, diff: +174

/tmp/vmlinux.after:
 16 functions changed, 176 bytes added, 413 bytes removed, diff: -237

Signed-off-by: Arnaldo Carvalho de Melo 
Acked-by: Frédéric Weisbecker 
Signed-off-by: Ingo Molnar

ring_buffer: remove unused flags parameter

2009-02-06T00:01:40+00:00

Impact: API change, cleanup

>From ring_buffer_{lock_reserve,unlock_commit}.

$ codiff /tmp/vmlinux.before /tmp/vmlinux.after
linux-2.6-tip/kernel/trace/trace.c:
  trace_vprintk              |  -14
  trace_graph_return         |  -14
  trace_graph_entry          |  -10
  trace_function             |   -8
  __ftrace_trace_stack       |   -8
  ftrace_trace_userstack     |   -8
  tracing_sched_switch_trace |   -8
  ftrace_trace_special       |  -12
  tracing_sched_wakeup_trace |   -8
 9 functions changed, 90 bytes removed, diff: -90

linux-2.6-tip/block/blktrace.c:
  __blk_add_trace |   -1
 1 function changed, 1 bytes removed, diff: -1

/tmp/vmlinux.after:
 10 functions changed, 91 bytes removed, diff: -91

Signed-off-by: Arnaldo Carvalho de Melo 
Acked-by: Frédéric Weisbecker 
Signed-off-by: Ingo Molnar

trace: Remove unused trace_array_cpu parameter

2009-02-05T13:35:47+00:00

Impact: cleanup

Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Steven Rostedt 
Signed-off-by: Ingo Molnar

trace: assign defaults at register_ftrace_event

2009-02-05T13:35:46+00:00

Impact: simplification of tracers

As all tracers are doing this we might as well do it in
register_ftrace_event and save one branch each time we call these
callbacks.

Signed-off-by: Arnaldo Carvalho de Melo 
Acked-by: Frederic Weisbecker 
Acked-by: Steven Rostedt 
Signed-off-by: Ingo Molnar

trace: make the trace_event callbacks return enum print_line_t

2009-02-04T19:48:39+00:00

As they actually all return these enumerators.

Reported-by: Frederic Weisbecker 
Signed-off-by: Arnaldo Carvalho de Melo 
Acked-by: Frederic Weisbecker 
Signed-off-by: Ingo Molnar

trace: judicious error checking of trace_seq results

2009-02-04T19:48:30+00:00

Impact: bugfix and cleanup

Some callsites were returning either TRACE_ITER_PARTIAL_LINE if the
trace_seq routines (trace_seq_printf, etc) returned 0 meaning its buffer
was full, or zero otherwise.

But...

/* Return values for print_line callback */
enum print_line_t {
        TRACE_TYPE_PARTIAL_LINE = 0,    /* Retry after flushing the seq */
        TRACE_TYPE_HANDLED      = 1,
        TRACE_TYPE_UNHANDLED    = 2     /* Relay to other output functions */
};

In other cases the return value was not being relayed at all.

Most of the time it didn't hurt because the page wasn't get filled, but
for correctness sake, handle the return values everywhere.

Signed-off-by: Arnaldo Carvalho de Melo 
Acked-by: Frederic Weisbecker 
Signed-off-by: Ingo Molnar

blktrace: fix coding style in recent patches

2009-02-03T15:21:34+00:00

Impact: cleanup

Reported-by: Ingo Molnar 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Ingo Molnar

blkftrace: binary tracing, synthesizing old format

2009-02-03T13:03:53+00:00

Impact: new feature

With this and a blkrawverify modified not to verify the sequence numbers
we can start using the userspace tools to verify that the data produced
with the ftrace plugin works as expected.

Example:

[root@f10-1 ~]# echo 1 > /sys/block/sda/sda1/trace/enable
[root@f10-1 ~]# echo bin > /d/tracing/trace_options
[root@f10-1 ~]# echo blk > /d/tracing/current_tracer
[root@f10-1 ~]# cat /d/tracing/trace_pipe > sda1.blktrace.0
^C
[root@f10-1 ~]# ./blkrawverify --noseq sda1
Verifying sda1
    CPU 0
Wrote output to sda1.verify.out
[root@f10-1 ~]# cat sda1.verify.out

---------------
Verifying sda1
    ---------------------
    Summary for cpu 0:
          1349 valid +          0 invalid (100.0%) processed

[root@f10-1 ~]#

Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Ingo Molnar