Currently, a perf session entails two steps: first 'perf record' or
'perf trace record' records the perf data to disk, then 'perf report'
or 'perf trace report' reads the saved data from disk and reports the
results.
This experimental patchset makes some changes to perf that instead
allow the perf data to be piped directly from the record step to the
report step, without ever touching the disk.
This is especially useful for 'perf trace' - adding this capability
means that the trace scripts are no longer relegated to simple
post-processing, but can be run in a continuous 'live mode', forever
processing the event stream and e.g. periodically dumping current
results, essentially becoming special-purpose 'top' applications, or
continuously scanning the event stream for arbitrarily complex
conditions to flag, etc...
Being able to feed the event stream over a pipe also makes it possible
to do things like trace over the network using e.g. netcat.
It turns out that perf is pretty close to being able to do this
already, with the exception of the header data; most of the work of
this patchset deals with changing that. It does so in a mainly
additive way: it doesn't make any changes to the existing disk format
or normal disk-mode processing, just adds special treatment for the
cases when 'perf [trace] record' records to stdout or 'perf [trace]
report reads from stdin.
v2 changes:
- any script in the 'perf trace -l' list can now be run in 'live mode'
automatically by simply specifying the script name [with options] e.g.
$ perf trace syscall-counts
will run both ends of the the syscall-counts script with a pipe in
between, a more usable shorthand for:
$ perf trace record syscall-counts -o - | perf trace report syscall-counts -i -
which itself is shorthand for:
perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter -o - | perf trace -i - -s ~/libexec/perf-core/scripts/python/syscall-counts.py
- adds and use a term_clear() function for the 'top' scripts (thanks
to Ingo Monlar for the suggestion)
Here are some quick examples. Basically using '-' as the filename to
the -o and -i options send/read the data from stdout/stdin:
Here's a simple 'perf record' | 'perf report' run:
root@tropicana:~# perf record -o - -c 1 -f -a -M -R -e raw_syscalls:sys_enter | perf report -i -
^C# Samples: 376819
#
# Overhead Command Shared Object Symbol
# ........ ............... ................. ......
#
99.94% perf [kernel.kallsyms] [k] syscall_trace_enter
0.04% Xorg [kernel.kallsyms] [k] syscall_trace_enter
0.00% hald-addon-stor [kernel.kallsyms] [k] syscall_trace_enter
0.00% gvfsd-trash [kernel.kallsyms] [k] syscall_trace_enter
0.00% nautilus [kernel.kallsyms] [k] syscall_trace_enter
0.00% firefox [kernel.kallsyms] [k] syscall_trace_enter
0.00% gnome-screensav [kernel.kallsyms] [k] syscall_trace_enter
0.00% wterm [kernel.kallsyms] [k] syscall_trace_enter
0.00% mysqld [kernel.kallsyms] [k] syscall_trace_enter
0.00% gnome-settings- [kernel.kallsyms] [k] syscall_trace_enter
0.00% update-notifier [kernel.kallsyms] [k] syscall_trace_enter
0.00% apache2 [kernel.kallsyms] [k] syscall_trace_enter
#
# (For a higher level overview, try: perf report --sort comm,dso)
#
Included in this patchset are a couple of 'top' scripts, rwtop and
sctop, that are essentially just modifications of existing scripts.
The original scripts were modified to add a 3-second timer and a
screen clear after each print iteration. In the handler for the
timer, the previous screen contents are erased, the current output
summary is printed, and the state is cleared and begun anew, ad
infinitum.
Here are the new scripts as shown in the perf trace list:
root@tropicana:~# perf trace -l
List of available trace scripts:
workqueue-stats workqueue stats (ins/exe/create/destroy)
wakeup-latency system-wide min/max/avg wakeup latency
rw-by-file <comm> r/w activity for a program, by file
rwtop [interval] system-wide r/w top
failed-syscalls [comm] system-wide failed syscalls
rw-by-pid system-wide r/w activity
syscall-counts-by-pid [comm] system-wide syscall counts, by pid
failed-syscalls-by-pid [comm] system-wide failed syscalls, by pid
sctop [comm] [interval] syscall top
syscall-counts [comm] system-wide syscall counts
And here's a sample of the output of the 'sctop' Python script:
root@tropicana:~# perf trace sctop
syscall events:
event count
---------------------------------------- ----------
sys_read 383576
sys_poll 144
sys_futex 97
sys_brk 33
sys_write 20
sys_select 11
sys_open 10
sys_inotify_add_watch 4
sys_setitimer 4
sys_writev 4
sys_wait4 1
sys_exit 1
56 1
sys_alarm 1
sys_ioctl 1
15 1
sys_rt_sigaction 1
sys_close 1
^C
perf trace Python script stopped
This shows just the last iteration - the script in real life
continuously erases and displays the previous interval's results.
Note that the scripts in this patchset will only show the syscall
numbers in the output, not the names as shown here - I just happened
to have the 'export some syscall metadata' patches previously posted
applied as well when I ran this script.
Lastly, here's an example that uses netcat to run the 'rwtop' Perl
script over the network:
On the system collecting the data and printing the output every 3
seconds:
root@tropicana:~# nc -l -p 7777 | perf trace report rwtop -i -
On the system being traced:
root@tropicana:~# perf trace record rwtop -o - | nc localhost 7777
read counts by pid:
pid comm # reads bytes_req bytes_read
------ -------------------- ---------- ---------- ----------
9580 nc 606 4964352 5382144
9578 perf 72256 3178656 3178448
9575 nc 379 3104768 3104768
5856 Xorg 148 386320 3980
6265 metacity 105 430080 1440
6325 gnome-screensav 110 450560 1024
6261 gnome-settings- 3 12288 32
6678 wterm 5 20480 32
write counts by pid:
pid comm # writes bytes_written
------ -------------------- ---------- -------------
9580 nc 657 5382144
9575 nc 379 3104768
perf trace Perl script stopped
I just noticed a hashtable error in this script when running it over
netcat just now, which is part of the reason it's an RFC patchset - it
still needs more testing, though other than that I haven't seen many
problems with it.
Tom
Tom Zanussi (11):
perf: add pipe-specific header read/write and event processing code
perf record: introduce special handling for pipe output
perf report: introduce special handling for pipe input
perf trace: introduce special handling for pipe input
perf: convert perf header attrs into attr events
perf: convert perf event types into event type events
perf: convert perf tracing data into a tracing_data event
perf: convert perf header build_ids into build_id events
perf trace/scripting: rwtop and sctop scripts
perf trace/scripting: enable scripting shell scripts for live mode
perf trace: invoke live mode automatically if record/report not
specified
tools/perf/builtin-record.c | 68 ++++-
tools/perf/builtin-report.c | 16 +-
tools/perf/builtin-trace.c | 75 ++++-
.../perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm | 6 +
tools/perf/scripts/perl/bin/failed-syscalls-record | 2 +-
tools/perf/scripts/perl/bin/failed-syscalls-report | 8 +-
tools/perf/scripts/perl/bin/rw-by-file-record | 3 +-
tools/perf/scripts/perl/bin/rw-by-file-report | 8 +-
tools/perf/scripts/perl/bin/rw-by-pid-record | 2 +-
tools/perf/scripts/perl/bin/rw-by-pid-report | 2 +-
tools/perf/scripts/perl/bin/rwtop-record | 2 +
tools/perf/scripts/perl/bin/rwtop-report | 23 ++
tools/perf/scripts/perl/bin/wakeup-latency-record | 2 +-
tools/perf/scripts/perl/bin/wakeup-latency-report | 2 +-
tools/perf/scripts/perl/bin/workqueue-stats-record | 2 +-
tools/perf/scripts/perl/bin/workqueue-stats-report | 2 +-
tools/perf/scripts/perl/rwtop.pl | 177 ++++++++++
.../python/Perf-Trace-Util/lib/Perf/Trace/Util.py | 3 +
.../python/bin/failed-syscalls-by-pid-record | 2 +-
.../python/bin/failed-syscalls-by-pid-report | 8 +-
tools/perf/scripts/python/bin/sctop-record | 2 +
tools/perf/scripts/python/bin/sctop-report | 24 ++
.../python/bin/syscall-counts-by-pid-record | 2 +-
.../python/bin/syscall-counts-by-pid-report | 8 +-
.../perf/scripts/python/bin/syscall-counts-record | 2 +-
.../perf/scripts/python/bin/syscall-counts-report | 8 +-
tools/perf/scripts/python/sctop.py | 78 +++++
tools/perf/util/event.h | 35 ++
tools/perf/util/header.c | 361 ++++++++++++++++++--
tools/perf/util/header.h | 38 ++-
tools/perf/util/session.c | 192 ++++++++++-
tools/perf/util/session.h | 10 +-
tools/perf/util/trace-event-info.c | 24 ++
tools/perf/util/trace-event-read.c | 89 +++---
tools/perf/util/trace-event.h | 4 +-
35 files changed, 1184 insertions(+), 106 deletions(-)
create mode 100644 tools/perf/scripts/perl/bin/rwtop-record
create mode 100644 tools/perf/scripts/perl/bin/rwtop-report
create mode 100644 tools/perf/scripts/perl/rwtop.pl
create mode 100644 tools/perf/scripts/python/bin/sctop-record
create mode 100644 tools/perf/scripts/python/bin/sctop-report
create mode 100644 tools/perf/scripts/python/sctop.py
Adds special treatment for stdout - if the user specifies '-o -' to
perf record, the intent is that the event stream be written to stdout
rather than to a disk file.
Also, redirect stdout of forked child to stderr - in pipe mode, stdout
of the forked child interferes with the stdout perf stream, so
redirect it to stderr where it can still be seen but won't be mixed in
with the perf output.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-record.c | 18 +++++++++++++++---
1 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 2654b61..0723fa1 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -36,6 +36,7 @@ static unsigned int page_size;
static unsigned int mmap_pages = 128;
static int freq = 1000;
static int output;
+static int pipe_output = 0;
static const char *output_name = "perf.data";
static int group = 0;
static unsigned int realtime_prio = 0;
@@ -450,7 +451,9 @@ static int __cmd_record(int argc, const char **argv)
exit(-1);
}
- if (!stat(output_name, &st) && st.st_size) {
+ if (!strcmp(output_name, "-"))
+ pipe_output = 1;
+ else if (!stat(output_name, &st) && st.st_size) {
if (!force) {
if (!append_file) {
pr_err("Error, output file %s exists, use -A "
@@ -475,7 +478,10 @@ static int __cmd_record(int argc, const char **argv)
else
flags |= O_TRUNC;
- output = open(output_name, flags, S_IRUSR|S_IWUSR);
+ if (pipe_output)
+ output = STDOUT_FILENO;
+ else
+ output = open(output_name, flags, S_IRUSR | S_IWUSR);
if (output < 0) {
perror("failed to create output file");
exit(-1);
@@ -514,6 +520,8 @@ static int __cmd_record(int argc, const char **argv)
}
if (!child_pid) {
+ if (pipe_output)
+ dup2(2, 1);
close(child_ready_pipe[0]);
close(go_pipe[1]);
fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -565,7 +573,11 @@ static int __cmd_record(int argc, const char **argv)
open_counters(cpumap[i]);
}
- if (file_new) {
+ if (pipe_output) {
+ err = perf_header__write_pipe(output);
+ if (err < 0)
+ return err;
+ } else if (file_new) {
err = perf_header__write(&session->header, output, false);
if (err < 0)
return err;
--
1.6.4.GIT
Bypasses the attr perf header code and replaces it with a synthesized
event and processing function that accomplishes the same thing, used
when reading/writing perf data to/from a pipe.
Making the attrs into events allows them to be streamed over a pipe
along with the rest of the header data (in later patches). It also
paves the way to allowing events to be added and removed from perf
sessions dynamically.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-record.c | 10 +++++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 10 +++++-
tools/perf/util/header.c | 79 +++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/header.h | 8 ++++
tools/perf/util/session.c | 26 ++++++++++++++
tools/perf/util/session.h | 3 +-
8 files changed, 136 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0723fa1..1f0abe2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -585,6 +585,16 @@ static int __cmd_record(int argc, const char **argv)
post_processing_offset = lseek(output, 0, SEEK_CUR);
+ if (pipe_output) {
+ err = event__synthesize_attrs(&session->header,
+ process_synthesized_event,
+ session);
+ if (err < 0) {
+ pr_err("Couldn't synthesize attrs.\n");
+ return err;
+ }
+ }
+
err = event__synthesize_kernel_mmap(process_synthesized_event,
session, "_text");
if (err < 0) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index a104121..0bb5d85 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -265,6 +265,7 @@ static struct perf_event_ops event_ops = {
.fork = event__process_task,
.lost = event__process_lost,
.read = process_read_event,
+ .attr = event__process_attr,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 718fddd..bb28973 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -104,6 +104,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
.comm = event__process_comm,
+ .attr = event__process_attr,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 03cdfd9..8a2ded3 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -84,7 +84,14 @@ struct build_id_event {
};
enum perf_header_event_type { /* above any possible kernel type */
- PERF_RECORD_HEADER_MAX = 64,
+ PERF_RECORD_HEADER_ATTR = 64,
+ PERF_RECORD_HEADER_MAX
+};
+
+struct attr_event {
+ struct perf_event_header header;
+ struct perf_event_attr attr;
+ u64 id[];
};
typedef union event_union {
@@ -96,6 +103,7 @@ typedef union event_union {
struct lost_event lost;
struct read_event read;
struct sample_event sample;
+ struct attr_event attr;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8d05337..e361739 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -807,3 +807,82 @@ perf_header__find_attr(u64 id, struct perf_header *header)
return NULL;
}
+
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ event_t *ev;
+ size_t size;
+ int err;
+
+ size = sizeof(struct perf_event_attr);
+ size = ALIGN(size, sizeof(u64));
+ size += sizeof(struct perf_event_header);
+ size += ids * sizeof(u64);
+
+ ev = malloc(size);
+
+ ev->attr.attr = *attr;
+ memcpy(ev->attr.id, id, ids * sizeof(u64));
+
+ ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+ ev->attr.header.size = size;
+
+ err = process(ev, session);
+
+ free(ev);
+
+ return err;
+}
+
+int event__synthesize_attrs(struct perf_header *self,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ struct perf_header_attr *attr;
+ int i, err = 0;
+
+ for (i = 0; i < self->attrs; i++) {
+ attr = self->attr[i];
+
+ err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
+ process, session);
+ if (err) {
+ pr_debug("failed to create perf header attribute\n");
+ return err;
+ }
+ }
+
+ return err;
+}
+
+int event__process_attr(event_t *self, struct perf_session *session)
+{
+ struct perf_header_attr *attr;
+ unsigned int i, ids, n_ids;
+
+ attr = perf_header_attr__new(&self->attr.attr);
+ if (attr == NULL)
+ return -ENOMEM;
+
+ ids = self->header.size;
+ ids -= (void *)&self->attr.id - (void *)self;
+ n_ids = ids / sizeof(u64);
+
+ for (i = 0; i < n_ids; i++) {
+ if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
+ perf_header_attr__delete(attr);
+ return -ENOMEM;
+ }
+ }
+
+ if (perf_header__add_attr(&session->header, attr) < 0) {
+ perf_header_attr__delete(attr);
+ return -ENOMEM;
+ }
+
+ perf_session__update_sample_type(session);
+
+ return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 0ce25cc..79ab267 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -95,4 +95,12 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
const char *name, bool is_kallsyms);
int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+ event__handler_t process,
+ struct perf_session *session);
+int event__synthesize_attrs(struct perf_header *self,
+ event__handler_t process,
+ struct perf_session *session);
+int event__process_attr(event_t *self, struct perf_session *session);
+
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b767e95..2d977d1 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -210,6 +210,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->throttle = process_event_stub;
if (handler->unthrottle == NULL)
handler->unthrottle = process_event_stub;
+ if (handler->attr == NULL)
+ handler->attr = process_event_stub;
}
static const char *event__name[] = {
@@ -223,6 +225,7 @@ static const char *event__name[] = {
[PERF_RECORD_FORK] = "FORK",
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
+ [PERF_RECORD_HEADER_ATTR] = "ATTR",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -289,6 +292,26 @@ static void event__read_swap(event_t *self)
self->read.id = bswap_64(self->read.id);
}
+static void event__attr_swap(event_t *self)
+{
+ size_t size;
+
+ self->attr.attr.type = bswap_32(self->attr.attr.type);
+ self->attr.attr.size = bswap_32(self->attr.attr.size);
+ self->attr.attr.config = bswap_64(self->attr.attr.config);
+ self->attr.attr.sample_period = bswap_64(self->attr.attr.sample_period);
+ self->attr.attr.sample_type = bswap_64(self->attr.attr.sample_type);
+ self->attr.attr.read_format = bswap_64(self->attr.attr.read_format);
+ self->attr.attr.wakeup_events = bswap_32(self->attr.attr.wakeup_events);
+ self->attr.attr.bp_type = bswap_32(self->attr.attr.bp_type);
+ self->attr.attr.bp_addr = bswap_64(self->attr.attr.bp_addr);
+ self->attr.attr.bp_len = bswap_64(self->attr.attr.bp_len);
+
+ size = self->header.size;
+ size -= (void *)&self->attr.id - (void *)self;
+ mem_bswap_64(self->attr.id, size);
+}
+
typedef void (*event__swap_op)(event_t *self);
static event__swap_op event__swap_ops[] = {
@@ -299,6 +322,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_LOST] = event__all64_swap,
[PERF_RECORD_READ] = event__read_swap,
[PERF_RECORD_SAMPLE] = event__all64_swap,
+ [PERF_RECORD_HEADER_ATTR] = event__attr_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -339,6 +363,8 @@ static int perf_session__process_event(struct perf_session *self,
return ops->throttle(event, self);
case PERF_RECORD_UNTHROTTLE:
return ops->unthrottle(event, self);
+ case PERF_RECORD_HEADER_ATTR:
+ return ops->attr(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 8385fb5..07ee8f2 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -44,7 +44,8 @@ struct perf_event_ops {
lost,
read,
throttle,
- unthrottle;
+ unthrottle,
+ attr;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
--
1.6.4.GIT
Bypasses the build_id perf header code and replaces it with a
synthesized event and processing function that accomplishes the same
thing, used when reading/writing perf data to/from a pipe.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-record.c | 15 ++++++-
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 2 +
tools/perf/util/header.c | 90 +++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/header.h | 7 +++
tools/perf/util/session.c | 6 +++
tools/perf/util/session.h | 3 +-
8 files changed, 121 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0c6a971..9a5be5d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -427,10 +427,19 @@ static int process_buildids(void)
static void atexit_header(void)
{
- session->header.data_size += bytes_written;
+ if (!pipe_output) {
+ session->header.data_size += bytes_written;
- process_buildids();
- perf_header__write(&session->header, output, true);
+ process_buildids();
+ perf_header__write(&session->header, output, true);
+ } else {
+ int err;
+
+ err = event__synthesize_build_ids(process_synthesized_event,
+ session);
+ if (err < 0)
+ pr_err("Couldn't synthesize build ids.\n");
+ }
}
static int __cmd_record(int argc, const char **argv)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 48a02a1..8f71ee7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -268,6 +268,7 @@ static struct perf_event_ops event_ops = {
.attr = event__process_attr,
.event_type = event__process_event_type,
.tracing_data = event__process_tracing_data,
+ .build_id = event__process_build_id,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 1863d7c..4a6ffb2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -107,6 +107,7 @@ static struct perf_event_ops event_ops = {
.attr = event__process_attr,
.event_type = event__process_event_type,
.tracing_data = event__process_tracing_data,
+ .build_id = event__process_build_id,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index e982e34..2dcef07 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -87,6 +87,7 @@ enum perf_header_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_ATTR = 64,
PERF_RECORD_HEADER_EVENT_TYPE = 65,
PERF_RECORD_HEADER_TRACING_DATA = 66,
+ PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_HEADER_MAX
};
@@ -125,6 +126,7 @@ typedef union event_union {
struct attr_event attr;
struct event_type_event event_type;
struct tracing_data_event tracing_data;
+ struct build_id_event build_id;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c6874ec..628173b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -986,3 +986,93 @@ int event__process_tracing_data(event_t *self,
return size_read + padding;
}
+
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ event_t ev;
+ size_t len;
+ int err = 0;
+
+ if (!pos->hit)
+ return err;
+
+ memset(&ev, 0, sizeof(ev));
+
+ len = pos->long_name_len + 1;
+ len = ALIGN(len, NAME_ALIGN);
+ memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+ ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
+ ev.build_id.header.misc = misc;
+ ev.build_id.header.size = sizeof(ev.build_id) + len;
+ memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+
+ err = process(&ev, session);
+
+ return err;
+}
+
+static int __event_synthesize_build_ids(struct list_head *head, u16 misc,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ struct dso *pos;
+
+ dsos__for_each_with_build_id(pos, head) {
+ int err;
+ if (!pos->hit)
+ continue;
+
+ err = event__synthesize_build_id(pos, misc, process, session);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
+int event__synthesize_build_ids(event__handler_t process,
+ struct perf_session *session)
+{
+ int err;
+
+ if (!dsos__read_build_ids(true))
+ return 0;
+
+ err = __event_synthesize_build_ids(&dsos__kernel,
+ PERF_RECORD_MISC_KERNEL,
+ process, session);
+ if (err == 0)
+ err = __event_synthesize_build_ids(&dsos__user,
+ PERF_RECORD_MISC_USER,
+ process, session);
+
+ if (err < 0) {
+ pr_debug("failed to synthesize build ids\n");
+ return err;
+ }
+
+ dsos__cache_build_ids();
+
+ return 0;
+}
+
+int event__process_build_id(event_t *self,
+ struct perf_session *session __unused)
+{
+ struct list_head *head = &dsos__user;
+ struct dso *dso;
+
+ if (self->build_id.header.misc & PERF_RECORD_MISC_KERNEL)
+ head = &dsos__kernel;
+
+ dso = __dsos__findnew(head, self->build_id.filename);
+ if (dso != NULL) {
+ dso__set_build_id(dso, &self->build_id.build_id);
+ if (head == &dsos__kernel && self->build_id.filename[0] == '[')
+ dso->kernel = 1;
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index be758ca..f827ef2 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -118,4 +118,11 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
int event__process_tracing_data(event_t *self,
struct perf_session *session);
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+ event__handler_t process,
+ struct perf_session *session);
+int event__synthesize_build_ids(event__handler_t process,
+ struct perf_session *session);
+int event__process_build_id(event_t *self, struct perf_session *session);
+
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d5c2b3c..be16ea4 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -216,6 +216,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->event_type = process_event_stub;
if (handler->tracing_data == NULL)
handler->tracing_data = process_event_stub;
+ if (handler->build_id == NULL)
+ handler->build_id = process_event_stub;
}
static const char *event__name[] = {
@@ -232,6 +234,7 @@ static const char *event__name[] = {
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
+ [PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -342,6 +345,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_HEADER_ATTR] = event__attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap,
+ [PERF_RECORD_HEADER_BUILD_ID] = NULL,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -390,6 +394,8 @@ static int perf_session__process_event(struct perf_session *self,
/* setup for reading amidst mmap */
lseek(self->fd, offset + head, SEEK_SET);
return ops->tracing_data(event, self);
+ case PERF_RECORD_HEADER_BUILD_ID:
+ return ops->build_id(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 88a2c35..4f925e6 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -47,7 +47,8 @@ struct perf_event_ops {
unthrottle,
attr,
event_type,
- tracing_data;
+ tracing_data,
+ build_id;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
--
1.6.4.GIT
It should be possible to run any perf trace script in 'live mode'.
This requires being able to pass in e.g. '-i -' or other args, which
the current shell scripts aren't equipped to handle. In a few cases,
there are required or optional args that also need special handling.
This patch makes changes the current set of shell scripts as
necessary.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/scripts/perl/bin/failed-syscalls-record | 2 +-
tools/perf/scripts/perl/bin/failed-syscalls-report | 8 +++++++-
tools/perf/scripts/perl/bin/rw-by-file-record | 3 ++-
tools/perf/scripts/perl/bin/rw-by-file-report | 8 +++++++-
tools/perf/scripts/perl/bin/rw-by-pid-record | 2 +-
tools/perf/scripts/perl/bin/rw-by-pid-report | 2 +-
tools/perf/scripts/perl/bin/wakeup-latency-record | 2 +-
tools/perf/scripts/perl/bin/wakeup-latency-report | 2 +-
tools/perf/scripts/perl/bin/workqueue-stats-record | 2 +-
tools/perf/scripts/perl/bin/workqueue-stats-report | 2 +-
.../python/bin/failed-syscalls-by-pid-record | 2 +-
.../python/bin/failed-syscalls-by-pid-report | 8 +++++++-
.../python/bin/syscall-counts-by-pid-record | 2 +-
.../python/bin/syscall-counts-by-pid-report | 8 +++++++-
.../perf/scripts/python/bin/syscall-counts-record | 2 +-
.../perf/scripts/python/bin/syscall-counts-report | 8 +++++++-
16 files changed, 47 insertions(+), 16 deletions(-)
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index f8885d3..6ad9b8f 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-report b/tools/perf/scripts/perl/bin/failed-syscalls-report
index 8bfc660..f634608 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-report
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide failed syscalls
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record
index b25056e..a828679 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-record
+++ b/tools/perf/scripts/perl/bin/rw-by-file-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write
+perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report
index eddb9cc..d83070b 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-report
+++ b/tools/perf/scripts/perl/bin/rw-by-file-report
@@ -1,7 +1,13 @@
#!/bin/bash
# description: r/w activity for a program, by file
# args: <comm>
-perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $1
+if [ $# -lt 1 ] ; then
+ echo "usage: rw-by-file <comm>"
+ exit
+fi
+comm=$1
+shift
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record
index 8903979..63976bf 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-record
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write
+perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report
index 7f44c25..7ef4698 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-report
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: system-wide r/w activity
-perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record
index 6abedda..9c0cf58 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-record
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-record
@@ -1,5 +1,5 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup
+perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup $@
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report
index fce3adc..a0d898f 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-report
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: system-wide min/max/avg wakeup latency
-perf trace -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
index fce6637..c2a1a94 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion
+perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report
index 71cfbd1..3508113 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-report
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: workqueue stats (ins/exe/create/destroy)
-perf trace -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index f8885d3..6ad9b8f 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
index 1e0c0a8..8c128ef 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide failed syscalls, by pid
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 45a8c50..27ccffa 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
index f8044d1..c53362e 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide syscall counts, by pid
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 45a8c50..27ccffa 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report
index a366aa6..8c21552 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide syscall counts
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts.py $comm
--
1.6.4.GIT
Currently, live mode is invoked by explicitly invoking the record and
report sides and connecting them with a pipe e.g.
$ perf trace record rwtop -o - | perf trace report rwtop 5 -i -
In terms of usability, it's not that bad, but it does require the user
to type and remember more than necessary.
This patch allows the user to accomplish the same thing without
specifying the separate record/report steps or the pipe. So the same
command as above can be accomplished more simply as:
$ perf trace rwtop 5
Notice that the '-i -' and '-o -' aren't required in this case -
they're added internally, and that any extra arguments are passed
along to the report script (but not to the record script).
The overall effect is that any of the scripts listed in 'perf trace
-l' can now be used directly in live mode, with the expected
arguments, by simply specifying the script and args to 'perf trace'.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-trace.c | 59 ++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 59 insertions(+), 0 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 4a6ffb2..1e6ad0c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -561,6 +561,65 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
suffix = REPORT_SUFFIX;
}
+ if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
+ char *record_script_path, *report_script_path;
+ int live_pipe[2];
+ pid_t pid;
+
+ record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+ if (!record_script_path) {
+ fprintf(stderr, "record script not found\n");
+ return -1;
+ }
+
+ report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+ if (!report_script_path) {
+ fprintf(stderr, "report script not found\n");
+ return -1;
+ }
+
+ if (pipe(live_pipe) < 0) {
+ perror("failed to create pipe");
+ exit(-1);
+ }
+
+ pid = fork();
+ if (pid < 0) {
+ perror("failed to fork");
+ exit(-1);
+ }
+
+ if (!pid) {
+ dup2(live_pipe[1], 1);
+ close(live_pipe[0]);
+
+ __argv = malloc(5 * sizeof(const char *));
+ __argv[0] = "/bin/sh";
+ __argv[1] = record_script_path;
+ __argv[2] = "-o";
+ __argv[3] = "-";
+ __argv[4] = NULL;
+
+ execvp("/bin/sh", (char **)__argv);
+ exit(-1);
+ }
+
+ dup2(live_pipe[0], 0);
+ close(live_pipe[1]);
+
+ __argv = malloc((argc + 3) * sizeof(const char *));
+ __argv[0] = "/bin/sh";
+ __argv[1] = report_script_path;
+ for (i = 2; i < argc; i++)
+ __argv[i] = argv[i];
+ __argv[i++] = "-i";
+ __argv[i++] = "-";
+ __argv[i++] = NULL;
+
+ execvp("/bin/sh", (char **)__argv);
+ exit(-1);
+ }
+
if (suffix) {
script_path = get_script_path(argv[2], suffix);
if (!script_path) {
--
1.6.4.GIT
Bypasses the tracing_data perf header code and replaces it with a
synthesized event and processing function that accomplishes the same
thing, used when reading/writing perf data to/from a pipe.
The tracing data is pretty large, and this patch doesn't attempt to
break it down into component events. The tracing_data event itself
doesn't actually contain the tracing data, rather it arranges for the
event processing code to skip over it after it's read, using the skip
return value added to the event processing loop in a previous patch.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-record.c | 16 ++++++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 7 +++
tools/perf/util/header.c | 52 +++++++++++++++++++++
tools/perf/util/header.h | 6 ++
tools/perf/util/session.c | 13 +++++
tools/perf/util/session.h | 3 +-
tools/perf/util/trace-event-info.c | 24 ++++++++++
tools/perf/util/trace-event-read.c | 89 ++++++++++++++++++------------------
tools/perf/util/trace-event.h | 4 +-
11 files changed, 170 insertions(+), 46 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c1682d1..0c6a971 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -105,6 +105,11 @@ static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
pc->data_tail = tail;
}
+static void advance_output(size_t size)
+{
+ bytes_written += size;
+}
+
static void write_output(void *buf, size_t size)
{
while (size) {
@@ -600,6 +605,17 @@ static int __cmd_record(int argc, const char **argv)
pr_err("Couldn't synthesize event_types.\n");
return err;
}
+
+ err = event__synthesize_tracing_data(output, attrs,
+ nr_counters,
+ process_synthesized_event,
+ session);
+ if (err <= 0) {
+ pr_err("Couldn't record tracing data.\n");
+ return err;
+ }
+
+ advance_output(err);
}
err = event__synthesize_kernel_mmap(process_synthesized_event,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d319f83..48a02a1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -267,6 +267,7 @@ static struct perf_event_ops event_ops = {
.read = process_read_event,
.attr = event__process_attr,
.event_type = event__process_event_type,
+ .tracing_data = event__process_tracing_data,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 2489565..1863d7c 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -106,6 +106,7 @@ static struct perf_event_ops event_ops = {
.comm = event__process_comm,
.attr = event__process_attr,
.event_type = event__process_event_type,
+ .tracing_data = event__process_tracing_data,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 52cb0e9..e982e34 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -86,6 +86,7 @@ struct build_id_event {
enum perf_header_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_ATTR = 64,
PERF_RECORD_HEADER_EVENT_TYPE = 65,
+ PERF_RECORD_HEADER_TRACING_DATA = 66,
PERF_RECORD_HEADER_MAX
};
@@ -107,6 +108,11 @@ struct event_type_event {
struct perf_trace_event_type event_type;
};
+struct tracing_data_event {
+ struct perf_event_header header;
+ u32 size;
+};
+
typedef union event_union {
struct perf_event_header header;
struct ip_event ip;
@@ -118,6 +124,7 @@ typedef union event_union {
struct sample_event sample;
struct attr_event attr;
struct event_type_event event_type;
+ struct tracing_data_event tracing_data;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4463799..c6874ec 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -934,3 +934,55 @@ int event__process_event_type(event_t *self,
return 0;
}
+
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+ int nb_events,
+ event__handler_t process,
+ struct perf_session *session __unused)
+{
+ event_t ev;
+ ssize_t size = 0, aligned_size = 0, padding;
+ int err = 0;
+
+ memset(&ev, 0, sizeof(ev));
+
+ ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
+ size = read_tracing_data_size(fd, pattrs, nb_events);
+ if (size <= 0)
+ return size;
+ aligned_size = ALIGN(size, sizeof(u64));
+ padding = aligned_size - size;
+ ev.tracing_data.header.size = sizeof(ev.tracing_data);
+ ev.tracing_data.size = aligned_size;
+
+ process(&ev, session);
+
+ err = read_tracing_data(fd, pattrs, nb_events);
+ write_padded(fd, NULL, 0, padding);
+
+ return aligned_size;
+}
+
+int event__process_tracing_data(event_t *self,
+ struct perf_session *session)
+{
+ ssize_t size_read, padding, size = self->tracing_data.size;
+ off_t offset = lseek(session->fd, 0, SEEK_CUR);
+ char buf[BUFSIZ];
+
+ /* setup for reading amidst mmap */
+ lseek(session->fd, offset + sizeof(struct tracing_data_event),
+ SEEK_SET);
+
+ size_read = trace_report(session->fd);
+
+ padding = ALIGN(size_read, sizeof(u64)) - size_read;
+
+ if (read(session->fd, buf, padding) < 0)
+ die("reading input file");
+
+ if (size_read + padding != size)
+ die("tracing data size mismatch");
+
+ return size_read + padding;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index dbedaf0..be758ca 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -111,5 +111,11 @@ int event__synthesize_event_types(event__handler_t process,
int event__process_event_type(event_t *self,
struct perf_session *session);
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+ int nb_events,
+ event__handler_t process,
+ struct perf_session *session);
+int event__process_tracing_data(event_t *self,
+ struct perf_session *session);
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7c3b355..d5c2b3c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -214,6 +214,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->attr = process_event_stub;
if (handler->event_type == NULL)
handler->event_type = process_event_stub;
+ if (handler->tracing_data == NULL)
+ handler->tracing_data = process_event_stub;
}
static const char *event__name[] = {
@@ -229,6 +231,7 @@ static const char *event__name[] = {
[PERF_RECORD_SAMPLE] = "SAMPLE",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
+ [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -321,6 +324,11 @@ static void event__event_type_swap(event_t *self)
bswap_64(self->event_type.event_type.event_id);
}
+static void event__tracing_data_swap(event_t *self)
+{
+ self->tracing_data.size = bswap_32(self->tracing_data.size);
+}
+
typedef void (*event__swap_op)(event_t *self);
static event__swap_op event__swap_ops[] = {
@@ -333,6 +341,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_SAMPLE] = event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = event__attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
+ [PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -377,6 +386,10 @@ static int perf_session__process_event(struct perf_session *self,
return ops->attr(event, self);
case PERF_RECORD_HEADER_EVENT_TYPE:
return ops->event_type(event, self);
+ case PERF_RECORD_HEADER_TRACING_DATA:
+ /* setup for reading amidst mmap */
+ lseek(self->fd, offset + head, SEEK_SET);
+ return ops->tracing_data(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0f0abfd..88a2c35 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,7 +46,8 @@ struct perf_event_ops {
throttle,
unthrottle,
attr,
- event_type;
+ event_type,
+ tracing_data;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 5ea8973..30cd9b5 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -154,10 +154,17 @@ static void put_tracing_file(char *file)
free(file);
}
+static ssize_t calc_data_size;
+
static ssize_t write_or_die(const void *buf, size_t len)
{
int ret;
+ if (calc_data_size) {
+ calc_data_size += len;
+ return len;
+ }
+
ret = write(output_fd, buf, len);
if (ret < 0)
die("writing to '%s'", output_file);
@@ -526,3 +533,20 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
return 0;
}
+
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+ int nb_events)
+{
+ ssize_t size;
+ int err = 0;
+
+ calc_data_size = 1;
+ err = read_tracing_data(fd, pattrs, nb_events);
+ size = calc_data_size - 1;
+ calc_data_size = 0;
+
+ if (err < 0)
+ return err;
+
+ return size;
+}
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 7cd1193..44889c9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -50,14 +50,37 @@ static int long_size;
static unsigned long page_size;
+static ssize_t calc_data_size;
+
+static int do_read(int fd, void *buf, int size)
+{
+ int rsize = size;
+
+ while (size) {
+ int ret = read(fd, buf, size);
+
+ if (ret <= 0)
+ return -1;
+
+ size -= ret;
+ buf += ret;
+ }
+
+ return rsize;
+}
+
static int read_or_die(void *data, int size)
{
int r;
- r = read(input_fd, data, size);
- if (r != size)
+ r = do_read(input_fd, data, size);
+ if (r <= 0)
die("reading input file (size expected=%d received=%d)",
size, r);
+
+ if (calc_data_size)
+ calc_data_size += r;
+
return r;
}
@@ -82,56 +105,28 @@ static char *read_string(void)
char buf[BUFSIZ];
char *str = NULL;
int size = 0;
- int i;
off_t r;
+ char c;
for (;;) {
- r = read(input_fd, buf, BUFSIZ);
+ r = read(input_fd, &c, 1);
if (r < 0)
die("reading input file");
if (!r)
die("no data");
- for (i = 0; i < r; i++) {
- if (!buf[i])
- break;
- }
- if (i < r)
- break;
+ buf[size++] = c;
- if (str) {
- size += BUFSIZ;
- str = realloc(str, size);
- if (!str)
- die("malloc of size %d", size);
- memcpy(str + (size - BUFSIZ), buf, BUFSIZ);
- } else {
- size = BUFSIZ;
- str = malloc_or_die(size);
- memcpy(str, buf, size);
- }
+ if (!c)
+ break;
}
- /* trailing \0: */
- i++;
-
- /* move the file descriptor to the end of the string */
- r = lseek(input_fd, -(r - i), SEEK_CUR);
- if (r == (off_t)-1)
- die("lseek");
-
- if (str) {
- size += i;
- str = realloc(str, size);
- if (!str)
- die("malloc of size %d", size);
- memcpy(str + (size - i), buf, i);
- } else {
- size = i;
- str = malloc_or_die(i);
- memcpy(str, buf, i);
- }
+ if (calc_data_size)
+ calc_data_size += size;
+
+ str = malloc_or_die(size);
+ memcpy(str, buf, size);
return str;
}
@@ -459,7 +454,7 @@ struct record *trace_read_data(int cpu)
return data;
}
-void trace_report(int fd)
+ssize_t trace_report(int fd)
{
char buf[BUFSIZ];
char test[] = { 23, 8, 68 };
@@ -467,6 +462,9 @@ void trace_report(int fd)
int show_version = 0;
int show_funcs = 0;
int show_printk = 0;
+ ssize_t size;
+
+ calc_data_size = 1;
input_fd = fd;
@@ -499,14 +497,17 @@ void trace_report(int fd)
read_proc_kallsyms();
read_ftrace_printk();
+ size = calc_data_size - 1;
+ calc_data_size = 0;
+
if (show_funcs) {
print_funcs();
- return;
+ return size;
}
if (show_printk) {
print_printk();
- return;
+ return size;
}
- return;
+ return size;
}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index c3269b9..0cb5866 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -162,7 +162,7 @@ struct record *trace_read_data(int cpu);
void parse_set_info(int nr_cpus, int long_sz);
-void trace_report(int fd);
+ssize_t trace_report(int fd);
void *malloc_or_die(unsigned int size);
@@ -258,6 +258,8 @@ void *raw_field_ptr(struct event *event, const char *name, void *data);
unsigned long long eval_flag(const char *flag);
int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+ int nb_events);
/* taken from kernel/trace/trace.h */
enum trace_flag_type {
--
1.6.4.GIT
Adds special treatment for stdin - if the user specifies '-i -' to
perf trace, the intent is that the event stream be read from stdin
rather than from a disk file.
The actual handling of the '-' filename is done by the session; this
just adds a signal handler to stop reporting, and turns off
interference by the pager.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-trace.c | 12 +++++++++++-
1 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 407041d..718fddd 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -106,8 +106,17 @@ static struct perf_event_ops event_ops = {
.comm = event__process_comm,
};
+extern volatile int session_done;
+
+static void sig_handler(int sig __unused)
+{
+ session_done = 1;
+}
+
static int __cmd_trace(struct perf_session *session)
{
+ signal(SIGINT, sig_handler);
+
return perf_session__process_events(session, &event_ops);
}
@@ -580,7 +589,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
if (session == NULL)
return -ENOMEM;
- if (!perf_session__has_traces(session, "record -R"))
+ if (strcmp(input_name, "-") &&
+ !perf_session__has_traces(session, "record -R"))
return -EINVAL;
if (generate_script_lang) {
--
1.6.4.GIT
A couple of scripts, one in Python and the other in Perl, that
demonstrate 'live mode' tracing. For each, the output of the perf
event stream is fed continuously to the script, which continuously
aggregates the data and reports the current results every 3 seconds,
or at the optionally specified interval. After the current results
are displayed, the aggregations are cleared and the cycle begins anew.
To run the scripts, simply pipe the output of the 'perf trace record'
step as input to the corresponding 'perf trace report' step, using '-'
as the filename to -o and -i:
$ perf trace record sctop -o - | perf trace report sctop -i -
Also adds clear_term() utility functions to the Util.pm and Util.py
utility modules, for use by any script to clear the screen.
Signed-off-by: Tom Zanussi <[email protected]>
---
.../perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm | 6 +
tools/perf/scripts/perl/bin/rwtop-record | 2 +
tools/perf/scripts/perl/bin/rwtop-report | 23 +++
tools/perf/scripts/perl/rwtop.pl | 177 ++++++++++++++++++++
.../python/Perf-Trace-Util/lib/Perf/Trace/Util.py | 3 +
tools/perf/scripts/python/bin/sctop-record | 2 +
tools/perf/scripts/python/bin/sctop-report | 24 +++
tools/perf/scripts/python/sctop.py | 78 +++++++++
8 files changed, 315 insertions(+), 0 deletions(-)
create mode 100644 tools/perf/scripts/perl/bin/rwtop-record
create mode 100644 tools/perf/scripts/perl/bin/rwtop-report
create mode 100644 tools/perf/scripts/perl/rwtop.pl
create mode 100644 tools/perf/scripts/python/bin/sctop-record
create mode 100644 tools/perf/scripts/python/bin/sctop-report
create mode 100644 tools/perf/scripts/python/sctop.py
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
index f869c48..d94b40c 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
@@ -15,6 +15,7 @@ our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );
our @EXPORT = qw(
avg nsecs nsecs_secs nsecs_nsecs nsecs_usecs print_nsecs
+clear_term
);
our $VERSION = '0.01';
@@ -55,6 +56,11 @@ sub nsecs_str {
return $str;
}
+sub clear_term
+{
+ print "\x1b[H\x1b[2J";
+}
+
1;
__END__
=head1 NAME
diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
new file mode 100644
index 0000000..63976bf
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report
new file mode 100644
index 0000000..93e698c
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -0,0 +1,23 @@
+#!/bin/bash
+# description: system-wide r/w top
+# args: [interval]
+n_args=0
+for i in "$@"
+do
+ if expr match "$i" "-" > /dev/null ; then
+ break
+ fi
+ n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 1 ] ; then
+ echo "usage: rwtop-report [interval]"
+ exit
+fi
+if [ "$n_args" -gt 0 ] ; then
+ interval=$1
+ shift
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rwtop.pl $interval
+
+
+
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
new file mode 100644
index 0000000..ec2ab49
--- /dev/null
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -0,0 +1,177 @@
+#!/usr/bin/perl -w
+# (c) 2010, Tom Zanussi <[email protected]>
+# Licensed under the terms of the GNU GPL License version 2
+
+# read/write top
+#
+# Periodically displays system-wide r/w call activity, broken down by
+# pid. If an [interval] arg is specified, the display will be
+# refreshed every [interval] seconds. The default interval is 3
+# seconds.
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+
+my $default_interval = 3;
+my $nlines = 20;
+my $print_thread;
+
+my %reads;
+my %writes;
+
+my $interval = shift;
+if (!$interval) {
+ $interval = $default_interval;
+}
+
+sub syscalls::sys_exit_read
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $ret) = @_;
+
+ if ($ret > 0) {
+ $reads{$common_pid}{bytes_read} += $ret;
+ } else {
+ if (!defined ($reads{$common_pid}{bytes_read})) {
+ $reads{$common_pid}{bytes_read} = 0;
+ }
+ $reads{$common_pid}{errors}{$ret}++;
+ }
+}
+
+sub syscalls::sys_enter_read
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $fd, $buf, $count) = @_;
+
+ $reads{$common_pid}{bytes_requested} += $count;
+ $reads{$common_pid}{total_reads}++;
+ $reads{$common_pid}{comm} = $common_comm;
+}
+
+sub syscalls::sys_exit_write
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $ret) = @_;
+
+ if ($ret <= 0) {
+ $writes{$common_pid}{errors}{$ret}++;
+ }
+}
+
+sub syscalls::sys_enter_write
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $fd, $buf, $count) = @_;
+
+ $writes{$common_pid}{bytes_written} += $count;
+ $writes{$common_pid}{total_writes}++;
+ $writes{$common_pid}{comm} = $common_comm;
+}
+
+sub trace_begin
+{
+ $SIG{ALRM} = \&print_totals;
+ alarm 1;
+}
+
+sub trace_end
+{
+ print_unhandled();
+ print_totals();
+}
+
+sub print_totals
+{
+ my $count;
+
+ $count = 0;
+
+ clear_term();
+
+ printf("\nread counts by pid:\n\n");
+
+ printf("%6s %20s %10s %10s %10s\n", "pid", "comm",
+ "# reads", "bytes_req", "bytes_read");
+ printf("%6s %-20s %10s %10s %10s\n", "------", "--------------------",
+ "----------", "----------", "----------");
+
+ foreach my $pid (sort {$reads{$b}{bytes_read} <=>
+ $reads{$a}{bytes_read}} keys %reads) {
+ my $comm = $reads{$pid}{comm};
+ my $total_reads = $reads{$pid}{total_reads};
+ my $bytes_requested = $reads{$pid}{bytes_requested};
+ my $bytes_read = $reads{$pid}{bytes_read};
+
+ printf("%6s %-20s %10s %10s %10s\n", $pid, $comm,
+ $total_reads, $bytes_requested, $bytes_read);
+
+ if (++$count == $nlines) {
+ last;
+ }
+ }
+
+ $count = 0;
+
+ printf("\nwrite counts by pid:\n\n");
+
+ printf("%6s %20s %10s %13s\n", "pid", "comm",
+ "# writes", "bytes_written");
+ printf("%6s %-20s %10s %13s\n", "------", "--------------------",
+ "----------", "-------------");
+
+ foreach my $pid (sort {$writes{$b}{bytes_written} <=>
+ $writes{$a}{bytes_written}} keys %writes) {
+ my $comm = $writes{$pid}{comm};
+ my $total_writes = $writes{$pid}{total_writes};
+ my $bytes_written = $writes{$pid}{bytes_written};
+
+ printf("%6s %-20s %10s %13s\n", $pid, $comm,
+ $total_writes, $bytes_written);
+
+ if (++$count == $nlines) {
+ last;
+ }
+ }
+
+ %reads = ();
+ %writes = ();
+ alarm $interval;
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+ if ((scalar keys %unhandled) == 0) {
+ return;
+ }
+
+ print "\nunhandled events:\n\n";
+
+ printf("%-40s %10s\n", "event", "count");
+ printf("%-40s %10s\n", "----------------------------------------",
+ "-----------");
+
+ foreach my $event_name (keys %unhandled) {
+ printf("%-40s %10d\n", $event_name, $unhandled{$event_name});
+ }
+}
+
+sub trace_unhandled
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm) = @_;
+
+ $unhandled{$event_name}++;
+}
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 83e9143..9689bc0 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -23,3 +23,6 @@ def nsecs_nsecs(nsecs):
def nsecs_str(nsecs):
str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
return str
+
+def clear_term():
+ print("\x1b[H\x1b[2J")
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
new file mode 100644
index 0000000..27ccffa
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report
new file mode 100644
index 0000000..b01c842
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -0,0 +1,24 @@
+#!/bin/bash
+# description: syscall top
+# args: [comm] [interval]
+n_args=0
+for i in "$@"
+do
+ if expr match "$i" "-" > /dev/null ; then
+ break
+ fi
+ n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 2 ] ; then
+ echo "usage: sctop-report [comm] [interval]"
+ exit
+fi
+if [ "$n_args" -gt 1 ] ; then
+ comm=$1
+ interval=$2
+ shift 2
+elif [ "$n_args" -gt 0 ] ; then
+ interval=$1
+ shift
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/sctop.py $comm $interval
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
new file mode 100644
index 0000000..6cafad4
--- /dev/null
+++ b/tools/perf/scripts/python/sctop.py
@@ -0,0 +1,78 @@
+# system call top
+# (c) 2010, Tom Zanussi <[email protected]>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Periodically displays system-wide system call totals, broken down by
+# syscall. If a [comm] arg is specified, only syscalls called by
+# [comm] are displayed. If an [interval] arg is specified, the display
+# will be refreshed every [interval] seconds. The default interval is
+# 3 seconds.
+
+import thread
+import time
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+usage = "perf trace -s syscall-counts.py [comm] [interval]\n";
+
+for_comm = None
+default_interval = 3
+interval = default_interval
+
+if len(sys.argv) > 3:
+ sys.exit(usage)
+
+if len(sys.argv) > 2:
+ for_comm = sys.argv[1]
+ interval = int(sys.argv[2])
+elif len(sys.argv) > 1:
+ try:
+ interval = int(sys.argv[1])
+ except ValueError:
+ for_comm = sys.argv[1]
+ interval = default_interval
+
+syscalls = autodict()
+
+def trace_begin():
+ thread.start_new_thread(print_syscall_totals, (interval,))
+ pass
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+ common_secs, common_nsecs, common_pid, common_comm,
+ id, args):
+ if for_comm is not None:
+ if common_comm != for_comm:
+ return
+ try:
+ syscalls[id] += 1
+ except TypeError:
+ syscalls[id] = 1
+
+def print_syscall_totals(interval):
+ while 1:
+ clear_term()
+ if for_comm is not None:
+ print "\nsyscall events for %s:\n\n" % (for_comm),
+ else:
+ print "\nsyscall events:\n\n",
+
+ print "%-40s %10s\n" % ("event", "count"),
+ print "%-40s %10s\n" % ("----------------------------------------", \
+ "----------"),
+
+ for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
+ reverse = True):
+ try:
+ print "%-40d %10d\n" % (id, val),
+ except TypeError:
+ pass
+ syscalls.clear()
+ time.sleep(interval)
--
1.6.4.GIT
This patch makes several changes to allow the perf event stream to be
sent and received over a pipe:
- adds pipe-specific versions of the header read/write code
- adds pipe-specific version of the event processing code
- adds a range of event types to be used for header or other pseudo
events, above the range used by the kernel
- checks the return value of event handlers, which they can use to
skip over large events during event processing rather than actually
reading them into event objects.
- unifies the multiple do_read() functions and updates its users.
Note that none of these changes affect the existing perf data file
format or processing - this code only comes into play if perf output
is sent to stdout (or is read from stdin).
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-record.c | 2 +-
tools/perf/util/event.h | 4 +
tools/perf/util/header.c | 78 +++++++++++++++++++------
tools/perf/util/header.h | 8 ++-
tools/perf/util/session.c | 135 ++++++++++++++++++++++++++++++++++++++++---
tools/perf/util/session.h | 4 +
6 files changed, 202 insertions(+), 29 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 60ecdd3..2654b61 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -488,7 +488,7 @@ static int __cmd_record(int argc, const char **argv)
}
if (!file_new) {
- err = perf_header__read(&session->header, output);
+ err = perf_header__read(session, output);
if (err < 0)
return err;
}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a33b949..03cdfd9 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -83,6 +83,10 @@ struct build_id_event {
char filename[];
};
+enum perf_header_event_type { /* above any possible kernel type */
+ PERF_RECORD_HEADER_MAX = 64,
+};
+
typedef union event_union {
struct perf_event_header header;
struct ip_event ip;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6c9aa16..8d05337 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -427,6 +427,25 @@ out_free:
return err;
}
+int perf_header__write_pipe(int fd)
+{
+ struct perf_pipe_file_header f_header;
+ int err;
+
+ f_header = (struct perf_pipe_file_header){
+ .magic = PERF_MAGIC,
+ .size = sizeof(f_header),
+ };
+
+ err = do_write(fd, &f_header, sizeof(f_header));
+ if (err < 0) {
+ pr_debug("failed to write perf pipe header\n");
+ return err;
+ }
+
+ return 0;
+}
+
int perf_header__write(struct perf_header *self, int fd, bool at_exit)
{
struct perf_file_header f_header;
@@ -518,25 +537,10 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
return 0;
}
-static int do_read(int fd, void *buf, size_t size)
-{
- while (size) {
- int ret = read(fd, buf, size);
-
- if (ret <= 0)
- return -1;
-
- size -= ret;
- buf += ret;
- }
-
- return 0;
-}
-
static int perf_header__getbuffer64(struct perf_header *self,
int fd, void *buf, size_t size)
{
- if (do_read(fd, buf, size))
+ if (do_read(fd, buf, size) <= 0)
return -1;
if (self->needs_swap)
@@ -592,7 +596,7 @@ int perf_file_header__read(struct perf_file_header *self,
{
lseek(fd, 0, SEEK_SET);
- if (do_read(fd, self, sizeof(*self)) ||
+ if (do_read(fd, self, sizeof(*self)) <= 0 ||
memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
return -1;
@@ -662,13 +666,51 @@ static int perf_file_section__process(struct perf_file_section *self,
return 0;
}
-int perf_header__read(struct perf_header *self, int fd)
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+ struct perf_header *ph, int fd)
{
+ if (do_read(fd, self, sizeof(*self)) <= 0 ||
+ memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+ return -1;
+
+ if (self->size != sizeof(*self)) {
+ u64 size = bswap_64(self->size);
+
+ if (size != sizeof(*self))
+ return -1;
+
+ ph->needs_swap = true;
+ }
+
+ return 0;
+}
+
+static int perf_header__read_pipe(struct perf_session *session, int fd)
+{
+ struct perf_header *self = &session->header;
+ struct perf_pipe_file_header f_header;
+
+ if (perf_file_header__read_pipe(&f_header, self, fd) < 0) {
+ pr_debug("incompatible file format\n");
+ return -EINVAL;
+ }
+
+ session->fd = fd;
+
+ return 0;
+}
+
+int perf_header__read(struct perf_session *session, int fd)
+{
+ struct perf_header *self = &session->header;
struct perf_file_header f_header;
struct perf_file_attr f_attr;
u64 f_id;
int nr_attrs, nr_ids, i, j;
+ if (session->fd_pipe)
+ return perf_header__read_pipe(session, fd);
+
if (perf_file_header__read(&f_header, self, fd) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 82a6af7..0ce25cc 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,11 @@ struct perf_file_header {
DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
};
+struct perf_pipe_file_header {
+ u64 magic;
+ u64 size;
+};
+
struct perf_header;
int perf_file_header__read(struct perf_file_header *self,
@@ -60,8 +65,9 @@ struct perf_header {
int perf_header__init(struct perf_header *self);
void perf_header__exit(struct perf_header *self);
-int perf_header__read(struct perf_header *self, int fd);
+int perf_header__read(struct perf_session *session, int fd);
int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_header__write_pipe(int fd);
int perf_header__add_attr(struct perf_header *self,
struct perf_header_attr *attr);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 76b4ac6..b767e95 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,16 @@ static int perf_session__open(struct perf_session *self, bool force)
{
struct stat input_stat;
+ if (!strcmp(self->filename, "-")) {
+ self->fd_pipe = true;
+ self->fd = STDIN_FILENO;
+
+ if (perf_header__read(self, self->fd) < 0)
+ pr_err("incompatible file format");
+
+ return 0;
+ }
+
self->fd = open(self->filename, O_RDONLY);
if (self->fd < 0) {
pr_err("failed to open file: %s", self->filename);
@@ -38,7 +48,7 @@ static int perf_session__open(struct perf_session *self, bool force)
goto out_close;
}
- if (perf_header__read(&self->header, self->fd) < 0) {
+ if (perf_header__read(self, self->fd) < 0) {
pr_err("incompatible file format");
goto out_close;
}
@@ -57,6 +67,11 @@ static inline int perf_session__create_kernel_maps(struct perf_session *self)
return map_groups__create_kernel_maps(&self->kmaps, self->vmlinux_maps);
}
+void perf_session__update_sample_type(struct perf_session *self)
+{
+ self->sample_type = perf_header__sample_type(&self->header);
+}
+
struct perf_session *perf_session__new(const char *filename, int mode, bool force)
{
size_t len = filename ? strlen(filename) + 1 : 0;
@@ -90,7 +105,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
goto out_delete;
}
- self->sample_type = perf_header__sample_type(&self->header);
+ perf_session__update_sample_type(self);
out:
return self;
out_free:
@@ -210,14 +225,17 @@ static const char *event__name[] = {
[PERF_RECORD_SAMPLE] = "SAMPLE",
};
-unsigned long event__total[PERF_RECORD_MAX];
+unsigned long event__total[PERF_RECORD_HEADER_MAX];
void event__print_totals(void)
{
int i;
- for (i = 0; i < PERF_RECORD_MAX; ++i)
+ for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+ if (!event__name[i])
+ continue;
pr_info("%10s events: %10ld\n",
event__name[i], event__total[i]);
+ }
}
void mem_bswap_64(void *src, int byte_size)
@@ -281,7 +299,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_LOST] = event__all64_swap,
[PERF_RECORD_READ] = event__read_swap,
[PERF_RECORD_SAMPLE] = event__all64_swap,
- [PERF_RECORD_MAX] = NULL,
+ [PERF_RECORD_HEADER_MAX] = NULL,
};
static int perf_session__process_event(struct perf_session *self,
@@ -291,7 +309,7 @@ static int perf_session__process_event(struct perf_session *self,
{
trace_event(event);
- if (event->header.type < PERF_RECORD_MAX) {
+ if (event->header.type < PERF_RECORD_HEADER_MAX) {
dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
offset + head, event->header.size,
event__name[event->header.type]);
@@ -386,6 +404,101 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
return thread;
}
+int do_read(int fd, void *buf, size_t size)
+{
+ void *buf_start = buf;
+
+ while (size) {
+ int ret = read(fd, buf, size);
+
+ if (ret <= 0)
+ return ret;
+
+ size -= ret;
+ buf += ret;
+ }
+
+ return buf - buf_start;
+}
+
+#define session_done() (*(volatile int *)(&session_done))
+volatile int session_done;
+
+static int __perf_session__process_pipe_events(struct perf_session *self,
+ struct perf_event_ops *ops)
+{
+ event_t event;
+ uint32_t size;
+ int skip = 0;
+ u64 head;
+ int err;
+ void *p;
+
+ perf_event_ops__fill_defaults(ops);
+
+ head = 0;
+more:
+ err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+ if (err <= 0) {
+ if (err == 0)
+ goto done;
+
+ pr_err("failed to read event header\n");
+ goto out_err;
+ }
+
+ if (self->header.needs_swap)
+ perf_event_header__bswap(&event.header);
+
+ size = event.header.size;
+ if (size == 0)
+ size = 8;
+
+ p = &event;
+ p += sizeof(struct perf_event_header);
+
+ err = do_read(self->fd, p, size - sizeof(struct perf_event_header));
+ if (err <= 0) {
+ if (err == 0) {
+ pr_err("unexpected end of event stream\n");
+ goto done;
+ }
+
+ pr_err("failed to read event data\n");
+ goto out_err;
+ }
+
+ if (size == 0 ||
+ (skip = perf_session__process_event(self, &event, ops,
+ 0, head)) < 0) {
+ dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+ head, event.header.size, event.header.type);
+ /*
+ * assume we lost track of the stream, check alignment, and
+ * increment a single u64 in the hope to catch on again 'soon'.
+ */
+ if (unlikely(head & 7))
+ head &= ~7ULL;
+
+ size = 8;
+ }
+
+ head += size;
+
+ dump_printf("\n%#Lx [%#x]: event: %d\n",
+ head, event.header.size, event.header.type);
+
+ if (skip > 0)
+ head += skip;
+
+ if (!session_done())
+ goto more;
+done:
+ err = 0;
+out_err:
+ return err;
+}
+
int __perf_session__process_events(struct perf_session *self,
u64 data_offset, u64 data_size,
u64 file_size, struct perf_event_ops *ops)
@@ -503,9 +616,13 @@ out_getcwd_err:
self->cwdlen = strlen(self->cwd);
}
- err = __perf_session__process_events(self, self->header.data_offset,
- self->header.data_size,
- self->size, ops);
+ if (!self->fd_pipe)
+ err = __perf_session__process_events(self,
+ self->header.data_offset,
+ self->header.data_size,
+ self->size, ops);
+ else
+ err = __perf_session__process_pipe_events(self, ops);
out_err:
return err;
}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 631f815..8385fb5 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -27,6 +27,7 @@ struct perf_session {
u64 sample_type;
struct ref_reloc_sym ref_reloc_sym;
int fd;
+ bool fd_pipe;
int cwdlen;
char *cwd;
char filename[0];
@@ -87,6 +88,9 @@ static inline struct map *
return map_groups__new_module(&self->kmaps, start, filename);
}
+int do_read(int fd, void *buf, size_t size);
+void perf_session__update_sample_type(struct perf_session *self);
+
#ifdef NO_NEWT_SUPPORT
static inline void perf_session__browse_hists(struct rb_root *hists __used,
u64 session_total __used,
--
1.6.4.GIT
Adds special treatment for stdin - if the user specifies '-i -' to
perf report, the intent is that the event stream be written to stdin
rather than from a disk file.
The actual handling of the '-' filename is done by the session; this
just adds a signal handler to stop reporting, and turns off
interference by the pager.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-report.c | 12 +++++++++++-
1 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 6ab1698..a104121 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -267,6 +267,13 @@ static struct perf_event_ops event_ops = {
.read = process_read_event,
};
+extern volatile int session_done;
+
+static void sig_handler(int sig __attribute__((__unused__)))
+{
+ session_done = 1;
+}
+
static int __cmd_report(void)
{
int ret = -EINVAL;
@@ -274,6 +281,8 @@ static int __cmd_report(void)
struct rb_node *next;
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+ signal(SIGINT, sig_handler);
+
session = perf_session__new(input_name, O_RDONLY, force);
if (session == NULL)
return -ENOMEM;
@@ -461,7 +470,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
{
argc = parse_options(argc, argv, options, report_usage, 0);
- setup_browser();
+ if (strcmp(input_name, "-") != 0)
+ setup_browser();
if (symbol__init() < 0)
return -1;
--
1.6.4.GIT
Bypasses the event type perf header code and replaces it with a
synthesized event and processing function that accomplishes the same
thing, used when reading/writing perf data to/from a pipe.
Signed-off-by: Tom Zanussi <[email protected]>
---
tools/perf/builtin-record.c | 7 +++++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 14 +++++++++
tools/perf/util/header.c | 62 ++++++++++++++++++++++++++++++++++++++-----
tools/perf/util/header.h | 9 ++++++
tools/perf/util/session.c | 12 ++++++++
tools/perf/util/session.h | 3 +-
8 files changed, 101 insertions(+), 8 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 1f0abe2..c1682d1 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -593,6 +593,13 @@ static int __cmd_record(int argc, const char **argv)
pr_err("Couldn't synthesize attrs.\n");
return err;
}
+
+ err = event__synthesize_event_types(process_synthesized_event,
+ session);
+ if (err < 0) {
+ pr_err("Couldn't synthesize event_types.\n");
+ return err;
+ }
}
err = event__synthesize_kernel_mmap(process_synthesized_event,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0bb5d85..d319f83 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -266,6 +266,7 @@ static struct perf_event_ops event_ops = {
.lost = event__process_lost,
.read = process_read_event,
.attr = event__process_attr,
+ .event_type = event__process_event_type,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index bb28973..2489565 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -105,6 +105,7 @@ static struct perf_event_ops event_ops = {
.sample = process_sample_event,
.comm = event__process_comm,
.attr = event__process_attr,
+ .event_type = event__process_event_type,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8a2ded3..52cb0e9 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@ struct build_id_event {
enum perf_header_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_ATTR = 64,
+ PERF_RECORD_HEADER_EVENT_TYPE = 65,
PERF_RECORD_HEADER_MAX
};
@@ -94,6 +95,18 @@ struct attr_event {
u64 id[];
};
+#define MAX_EVENT_NAME 64
+
+struct perf_trace_event_type {
+ u64 event_id;
+ char name[MAX_EVENT_NAME];
+};
+
+struct event_type_event {
+ struct perf_event_header header;
+ struct perf_trace_event_type event_type;
+};
+
typedef union event_union {
struct perf_event_header header;
struct ip_event ip;
@@ -104,6 +117,7 @@ typedef union event_union {
struct read_event read;
struct sample_event sample;
struct attr_event attr;
+ struct event_type_event event_type;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e361739..4463799 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -99,13 +99,6 @@ int perf_header__add_attr(struct perf_header *self,
return 0;
}
-#define MAX_EVENT_NAME 64
-
-struct perf_trace_event_type {
- u64 event_id;
- char name[MAX_EVENT_NAME];
-};
-
static int event_count;
static struct perf_trace_event_type *events;
@@ -886,3 +879,58 @@ int event__process_attr(event_t *self, struct perf_session *session)
return 0;
}
+
+int event__synthesize_event_type(u64 event_id, char *name,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ event_t ev;
+ size_t size = 0;
+ int err = 0;
+
+ memset(&ev, 0, sizeof(ev));
+
+ ev.event_type.event_type.event_id = event_id;
+ memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
+ strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
+
+ ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
+ size = strlen(name);
+ size = ALIGN(size, sizeof(u64));
+ ev.event_type.header.size = sizeof(ev.event_type) -
+ (sizeof(ev.event_type.event_type.name) - size);
+
+ err = process(&ev, session);
+
+ return err;
+}
+
+int event__synthesize_event_types(event__handler_t process,
+ struct perf_session *session)
+{
+ struct perf_trace_event_type *type;
+ int i, err = 0;
+
+ for (i = 0; i < event_count; i++) {
+ type = &events[i];
+
+ err = event__synthesize_event_type(type->event_id, type->name,
+ process, session);
+ if (err) {
+ pr_debug("failed to create perf header event type\n");
+ return err;
+ }
+ }
+
+ return err;
+}
+
+int event__process_event_type(event_t *self,
+ struct perf_session *session __unused)
+{
+ if (perf_header__push_event(self->event_type.event_type.event_id,
+ self->event_type.event_type.name) < 0)
+ return -ENOMEM;
+
+ return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 79ab267..dbedaf0 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -103,4 +103,13 @@ int event__synthesize_attrs(struct perf_header *self,
struct perf_session *session);
int event__process_attr(event_t *self, struct perf_session *session);
+int event__synthesize_event_type(u64 event_id, char *name,
+ event__handler_t process,
+ struct perf_session *session);
+int event__synthesize_event_types(event__handler_t process,
+ struct perf_session *session);
+int event__process_event_type(event_t *self,
+ struct perf_session *session);
+
+
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2d977d1..7c3b355 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -212,6 +212,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->unthrottle = process_event_stub;
if (handler->attr == NULL)
handler->attr = process_event_stub;
+ if (handler->event_type == NULL)
+ handler->event_type = process_event_stub;
}
static const char *event__name[] = {
@@ -226,6 +228,7 @@ static const char *event__name[] = {
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
+ [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -312,6 +315,12 @@ static void event__attr_swap(event_t *self)
mem_bswap_64(self->attr.id, size);
}
+static void event__event_type_swap(event_t *self)
+{
+ self->event_type.event_type.event_id =
+ bswap_64(self->event_type.event_type.event_id);
+}
+
typedef void (*event__swap_op)(event_t *self);
static event__swap_op event__swap_ops[] = {
@@ -323,6 +332,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_READ] = event__read_swap,
[PERF_RECORD_SAMPLE] = event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = event__attr_swap,
+ [PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -365,6 +375,8 @@ static int perf_session__process_event(struct perf_session *self,
return ops->unthrottle(event, self);
case PERF_RECORD_HEADER_ATTR:
return ops->attr(event, self);
+ case PERF_RECORD_HEADER_EVENT_TYPE:
+ return ops->event_type(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 07ee8f2..0f0abfd 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -45,7 +45,8 @@ struct perf_event_ops {
read,
throttle,
unthrottle,
- attr;
+ attr,
+ event_type;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
--
1.6.4.GIT
Em Thu, Apr 01, 2010 at 11:59:22PM -0500, Tom Zanussi escreveu:
> Bypasses the build_id perf header code and replaces it with a
> synthesized event and processing function that accomplishes the same
> thing, used when reading/writing perf data to/from a pipe.
> static void atexit_header(void)
> {
> - session->header.data_size += bytes_written;
> + if (!pipe_output) {
> + session->header.data_size += bytes_written;
> - process_buildids();
> - perf_header__write(&session->header, output, true);
> + process_buildids();
> + perf_header__write(&session->header, output, true);
> + } else {
> + int err;
> + err = event__synthesize_build_ids(process_synthesized_event,
> + session);
> + if (err < 0)
> + pr_err("Couldn't synthesize build ids.\n");
Humm, getting everything as events looks elegant, but for the buildid
case... when processing samples we need to _first_ have the build-ids,
hence they are in the header.
We only generate them after collecting all samples because it would
disturb the system if we look at them in the ELF files when we get
PERF_RECORD_MMAP events.
In live mode we will be resolving symbols as we get samples, so I fail
to see how synthesizing the build-ids as a last step will help.
With build-ids events we can at least generate it in advance for the
kernel and modules, as it is a restriced number of DSOs and we have them
easily accessible via /sys, but for the userspace bits...
- Arnaldo
Commit-ID: 8dc58101f2c838355d44402aa77646649d10dbec
Gitweb: http://git.kernel.org/tip/8dc58101f2c838355d44402aa77646649d10dbec
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:15 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:05 +0200
perf: Add pipe-specific header read/write and event processing code
This patch makes several changes to allow the perf event stream
to be sent and received over a pipe:
- adds pipe-specific versions of the header read/write code
- adds pipe-specific version of the event processing code
- adds a range of event types to be used for header or other
pseudo events, above the range used by the kernel
- checks the return value of event handlers, which they can use
to skip over large events during event processing rather than actually
reading them into event objects.
- unifies the multiple do_read() functions and updates its
users.
Note that none of these changes affect the existing perf data
file format or processing - this code only comes into play if
perf output is sent to stdout (or is read from stdin).
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-record.c | 2 +-
tools/perf/util/event.h | 4 +
tools/perf/util/header.c | 78 +++++++++++++++++++------
tools/perf/util/header.h | 8 ++-
tools/perf/util/session.c | 135 ++++++++++++++++++++++++++++++++++++++++---
tools/perf/util/session.h | 4 +
6 files changed, 202 insertions(+), 29 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9a95136..d060fc5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -487,7 +487,7 @@ static int __cmd_record(int argc, const char **argv)
}
if (!file_new) {
- err = perf_header__read(&session->header, output);
+ err = perf_header__read(session, output);
if (err < 0)
return err;
}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7f7cf85..5c1eba6 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -83,6 +83,10 @@ struct build_id_event {
char filename[];
};
+enum perf_header_event_type { /* above any possible kernel type */
+ PERF_RECORD_HEADER_MAX = 64,
+};
+
typedef union event_union {
struct perf_event_header header;
struct ip_event ip;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6c9aa16..8d05337 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -427,6 +427,25 @@ out_free:
return err;
}
+int perf_header__write_pipe(int fd)
+{
+ struct perf_pipe_file_header f_header;
+ int err;
+
+ f_header = (struct perf_pipe_file_header){
+ .magic = PERF_MAGIC,
+ .size = sizeof(f_header),
+ };
+
+ err = do_write(fd, &f_header, sizeof(f_header));
+ if (err < 0) {
+ pr_debug("failed to write perf pipe header\n");
+ return err;
+ }
+
+ return 0;
+}
+
int perf_header__write(struct perf_header *self, int fd, bool at_exit)
{
struct perf_file_header f_header;
@@ -518,25 +537,10 @@ int perf_header__write(struct perf_header *self, int fd, bool at_exit)
return 0;
}
-static int do_read(int fd, void *buf, size_t size)
-{
- while (size) {
- int ret = read(fd, buf, size);
-
- if (ret <= 0)
- return -1;
-
- size -= ret;
- buf += ret;
- }
-
- return 0;
-}
-
static int perf_header__getbuffer64(struct perf_header *self,
int fd, void *buf, size_t size)
{
- if (do_read(fd, buf, size))
+ if (do_read(fd, buf, size) <= 0)
return -1;
if (self->needs_swap)
@@ -592,7 +596,7 @@ int perf_file_header__read(struct perf_file_header *self,
{
lseek(fd, 0, SEEK_SET);
- if (do_read(fd, self, sizeof(*self)) ||
+ if (do_read(fd, self, sizeof(*self)) <= 0 ||
memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
return -1;
@@ -662,13 +666,51 @@ static int perf_file_section__process(struct perf_file_section *self,
return 0;
}
-int perf_header__read(struct perf_header *self, int fd)
+static int perf_file_header__read_pipe(struct perf_pipe_file_header *self,
+ struct perf_header *ph, int fd)
{
+ if (do_read(fd, self, sizeof(*self)) <= 0 ||
+ memcmp(&self->magic, __perf_magic, sizeof(self->magic)))
+ return -1;
+
+ if (self->size != sizeof(*self)) {
+ u64 size = bswap_64(self->size);
+
+ if (size != sizeof(*self))
+ return -1;
+
+ ph->needs_swap = true;
+ }
+
+ return 0;
+}
+
+static int perf_header__read_pipe(struct perf_session *session, int fd)
+{
+ struct perf_header *self = &session->header;
+ struct perf_pipe_file_header f_header;
+
+ if (perf_file_header__read_pipe(&f_header, self, fd) < 0) {
+ pr_debug("incompatible file format\n");
+ return -EINVAL;
+ }
+
+ session->fd = fd;
+
+ return 0;
+}
+
+int perf_header__read(struct perf_session *session, int fd)
+{
+ struct perf_header *self = &session->header;
struct perf_file_header f_header;
struct perf_file_attr f_attr;
u64 f_id;
int nr_attrs, nr_ids, i, j;
+ if (session->fd_pipe)
+ return perf_header__read_pipe(session, fd);
+
if (perf_file_header__read(&f_header, self, fd) < 0) {
pr_debug("incompatible file format\n");
return -EINVAL;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c059f08..6562ece 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -39,6 +39,11 @@ struct perf_file_header {
DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
};
+struct perf_pipe_file_header {
+ u64 magic;
+ u64 size;
+};
+
struct perf_header;
int perf_file_header__read(struct perf_file_header *self,
@@ -60,8 +65,9 @@ struct perf_header {
int perf_header__init(struct perf_header *self);
void perf_header__exit(struct perf_header *self);
-int perf_header__read(struct perf_header *self, int fd);
+int perf_header__read(struct perf_session *session, int fd);
int perf_header__write(struct perf_header *self, int fd, bool at_exit);
+int perf_header__write_pipe(int fd);
int perf_header__add_attr(struct perf_header *self,
struct perf_header_attr *attr);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ddf288f..2c1277c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,16 @@ static int perf_session__open(struct perf_session *self, bool force)
{
struct stat input_stat;
+ if (!strcmp(self->filename, "-")) {
+ self->fd_pipe = true;
+ self->fd = STDIN_FILENO;
+
+ if (perf_header__read(self, self->fd) < 0)
+ pr_err("incompatible file format");
+
+ return 0;
+ }
+
self->fd = open(self->filename, O_RDONLY);
if (self->fd < 0) {
pr_err("failed to open file: %s", self->filename);
@@ -38,7 +48,7 @@ static int perf_session__open(struct perf_session *self, bool force)
goto out_close;
}
- if (perf_header__read(&self->header, self->fd) < 0) {
+ if (perf_header__read(self, self->fd) < 0) {
pr_err("incompatible file format");
goto out_close;
}
@@ -52,6 +62,11 @@ out_close:
return -1;
}
+void perf_session__update_sample_type(struct perf_session *self)
+{
+ self->sample_type = perf_header__sample_type(&self->header);
+}
+
struct perf_session *perf_session__new(const char *filename, int mode, bool force)
{
size_t len = filename ? strlen(filename) + 1 : 0;
@@ -85,7 +100,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
goto out_delete;
}
- self->sample_type = perf_header__sample_type(&self->header);
+ perf_session__update_sample_type(self);
out:
return self;
out_free:
@@ -200,14 +215,17 @@ static const char *event__name[] = {
[PERF_RECORD_SAMPLE] = "SAMPLE",
};
-unsigned long event__total[PERF_RECORD_MAX];
+unsigned long event__total[PERF_RECORD_HEADER_MAX];
void event__print_totals(void)
{
int i;
- for (i = 0; i < PERF_RECORD_MAX; ++i)
+ for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+ if (!event__name[i])
+ continue;
pr_info("%10s events: %10ld\n",
event__name[i], event__total[i]);
+ }
}
void mem_bswap_64(void *src, int byte_size)
@@ -271,7 +289,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_LOST] = event__all64_swap,
[PERF_RECORD_READ] = event__read_swap,
[PERF_RECORD_SAMPLE] = event__all64_swap,
- [PERF_RECORD_MAX] = NULL,
+ [PERF_RECORD_HEADER_MAX] = NULL,
};
static int perf_session__process_event(struct perf_session *self,
@@ -281,7 +299,7 @@ static int perf_session__process_event(struct perf_session *self,
{
trace_event(event);
- if (event->header.type < PERF_RECORD_MAX) {
+ if (event->header.type < PERF_RECORD_HEADER_MAX) {
dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
offset + head, event->header.size,
event__name[event->header.type]);
@@ -376,6 +394,101 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
return thread;
}
+int do_read(int fd, void *buf, size_t size)
+{
+ void *buf_start = buf;
+
+ while (size) {
+ int ret = read(fd, buf, size);
+
+ if (ret <= 0)
+ return ret;
+
+ size -= ret;
+ buf += ret;
+ }
+
+ return buf - buf_start;
+}
+
+#define session_done() (*(volatile int *)(&session_done))
+volatile int session_done;
+
+static int __perf_session__process_pipe_events(struct perf_session *self,
+ struct perf_event_ops *ops)
+{
+ event_t event;
+ uint32_t size;
+ int skip = 0;
+ u64 head;
+ int err;
+ void *p;
+
+ perf_event_ops__fill_defaults(ops);
+
+ head = 0;
+more:
+ err = do_read(self->fd, &event, sizeof(struct perf_event_header));
+ if (err <= 0) {
+ if (err == 0)
+ goto done;
+
+ pr_err("failed to read event header\n");
+ goto out_err;
+ }
+
+ if (self->header.needs_swap)
+ perf_event_header__bswap(&event.header);
+
+ size = event.header.size;
+ if (size == 0)
+ size = 8;
+
+ p = &event;
+ p += sizeof(struct perf_event_header);
+
+ err = do_read(self->fd, p, size - sizeof(struct perf_event_header));
+ if (err <= 0) {
+ if (err == 0) {
+ pr_err("unexpected end of event stream\n");
+ goto done;
+ }
+
+ pr_err("failed to read event data\n");
+ goto out_err;
+ }
+
+ if (size == 0 ||
+ (skip = perf_session__process_event(self, &event, ops,
+ 0, head)) < 0) {
+ dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
+ head, event.header.size, event.header.type);
+ /*
+ * assume we lost track of the stream, check alignment, and
+ * increment a single u64 in the hope to catch on again 'soon'.
+ */
+ if (unlikely(head & 7))
+ head &= ~7ULL;
+
+ size = 8;
+ }
+
+ head += size;
+
+ dump_printf("\n%#Lx [%#x]: event: %d\n",
+ head, event.header.size, event.header.type);
+
+ if (skip > 0)
+ head += skip;
+
+ if (!session_done())
+ goto more;
+done:
+ err = 0;
+out_err:
+ return err;
+}
+
int __perf_session__process_events(struct perf_session *self,
u64 data_offset, u64 data_size,
u64 file_size, struct perf_event_ops *ops)
@@ -499,9 +612,13 @@ out_getcwd_err:
self->cwdlen = strlen(self->cwd);
}
- err = __perf_session__process_events(self, self->header.data_offset,
- self->header.data_size,
- self->size, ops);
+ if (!self->fd_pipe)
+ err = __perf_session__process_events(self,
+ self->header.data_offset,
+ self->header.data_size,
+ self->size, ops);
+ else
+ err = __perf_session__process_pipe_events(self, ops);
out_err:
return err;
}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 27f4c2d..5f78911 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -27,6 +27,7 @@ struct perf_session {
u64 sample_type;
struct ref_reloc_sym ref_reloc_sym;
int fd;
+ bool fd_pipe;
int cwdlen;
char *cwd;
char filename[0];
@@ -92,6 +93,9 @@ static inline struct map *
return map_groups__new_module(&self->kmaps, start, filename);
}
+int do_read(int fd, void *buf, size_t size);
+void perf_session__update_sample_type(struct perf_session *self);
+
#ifdef NO_NEWT_SUPPORT
static inline int perf_session__browse_hists(struct rb_root *hists __used,
u64 nr_hists __used,
Commit-ID: 529870e37473a9fc609078f03cc5b4148cf06a87
Gitweb: http://git.kernel.org/tip/529870e37473a9fc609078f03cc5b4148cf06a87
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:16 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:06 +0200
perf record: Introduce special handling for pipe output
Adds special treatment for stdout - if the user specifies '-o -'
to perf record, the intent is that the event stream be written
to stdout rather than to a disk file.
Also, redirect stdout of forked child to stderr - in pipe mode,
stdout of the forked child interferes with the stdout perf
stream, so redirect it to stderr where it can still be seen but
won't be mixed in with the perf output.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-record.c | 18 +++++++++++++++---
1 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d060fc5..d4464f7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -35,6 +35,7 @@ static unsigned int page_size;
static unsigned int mmap_pages = 128;
static int freq = 1000;
static int output;
+static int pipe_output = 0;
static const char *output_name = "perf.data";
static int group = 0;
static unsigned int realtime_prio = 0;
@@ -449,7 +450,9 @@ static int __cmd_record(int argc, const char **argv)
exit(-1);
}
- if (!stat(output_name, &st) && st.st_size) {
+ if (!strcmp(output_name, "-"))
+ pipe_output = 1;
+ else if (!stat(output_name, &st) && st.st_size) {
if (!force) {
if (!append_file) {
pr_err("Error, output file %s exists, use -A "
@@ -474,7 +477,10 @@ static int __cmd_record(int argc, const char **argv)
else
flags |= O_TRUNC;
- output = open(output_name, flags, S_IRUSR|S_IWUSR);
+ if (pipe_output)
+ output = STDOUT_FILENO;
+ else
+ output = open(output_name, flags, S_IRUSR | S_IWUSR);
if (output < 0) {
perror("failed to create output file");
exit(-1);
@@ -513,6 +519,8 @@ static int __cmd_record(int argc, const char **argv)
}
if (!child_pid) {
+ if (pipe_output)
+ dup2(2, 1);
close(child_ready_pipe[0]);
close(go_pipe[1]);
fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -564,7 +572,11 @@ static int __cmd_record(int argc, const char **argv)
open_counters(cpumap[i]);
}
- if (file_new) {
+ if (pipe_output) {
+ err = perf_header__write_pipe(output);
+ if (err < 0)
+ return err;
+ } else if (file_new) {
err = perf_header__write(&session->header, output, false);
if (err < 0)
return err;
Commit-ID: 46656ac7fb3252f8a3db29b18638e0e8067849ba
Gitweb: http://git.kernel.org/tip/46656ac7fb3252f8a3db29b18638e0e8067849ba
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:17 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:06 +0200
perf report: Introduce special handling for pipe input
Adds special treatment for stdin - if the user specifies '-i -'
to perf report, the intent is that the event stream be written
to stdin rather than from a disk file.
The actual handling of the '-' filename is done by the session;
this just adds a signal handler to stop reporting, and turns off
interference by the pager.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-report.c | 12 +++++++++++-
1 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index daee082..00b358f 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -269,6 +269,13 @@ static struct perf_event_ops event_ops = {
.read = process_read_event,
};
+extern volatile int session_done;
+
+static void sig_handler(int sig __attribute__((__unused__)))
+{
+ session_done = 1;
+}
+
static int __cmd_report(void)
{
int ret = -EINVAL;
@@ -276,6 +283,8 @@ static int __cmd_report(void)
struct rb_node *next;
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+ signal(SIGINT, sig_handler);
+
session = perf_session__new(input_name, O_RDONLY, force);
if (session == NULL)
return -ENOMEM;
@@ -465,7 +474,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
{
argc = parse_options(argc, argv, options, report_usage, 0);
- setup_browser();
+ if (strcmp(input_name, "-") != 0)
+ setup_browser();
if (symbol__init() < 0)
return -1;
Commit-ID: c239da3b4b55dbb8f30bcb8d1a0d63fc44a567c3
Gitweb: http://git.kernel.org/tip/c239da3b4b55dbb8f30bcb8d1a0d63fc44a567c3
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:18 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:06 +0200
perf trace: Introduce special handling for pipe input
Adds special treatment for stdin - if the user specifies '-i -'
to perf trace, the intent is that the event stream be read from
stdin rather than from a disk file.
The actual handling of the '-' filename is done by the session;
this just adds a signal handler to stop reporting, and turns off
interference by the pager.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-trace.c | 12 +++++++++++-
1 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8fc50d8..c681e85 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -106,8 +106,17 @@ static struct perf_event_ops event_ops = {
.comm = event__process_comm,
};
+extern volatile int session_done;
+
+static void sig_handler(int sig __unused)
+{
+ session_done = 1;
+}
+
static int __cmd_trace(struct perf_session *session)
{
+ signal(SIGINT, sig_handler);
+
return perf_session__process_events(session, &event_ops);
}
@@ -580,7 +589,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
if (session == NULL)
return -ENOMEM;
- if (!perf_session__has_traces(session, "record -R"))
+ if (strcmp(input_name, "-") &&
+ !perf_session__has_traces(session, "record -R"))
return -EINVAL;
if (generate_script_lang) {
Commit-ID: 2c46dbb517a10b18d459e6ceffefde5bfb290cf6
Gitweb: http://git.kernel.org/tip/2c46dbb517a10b18d459e6ceffefde5bfb290cf6
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:19 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:07 +0200
perf: Convert perf header attrs into attr events
Bypasses the attr perf header code and replaces it with a
synthesized event and processing function that accomplishes the
same thing, used when reading/writing perf data to/from a pipe.
Making the attrs into events allows them to be streamed over a
pipe along with the rest of the header data (in later patches).
It also paves the way to allowing events to be added and removed
from perf sessions dynamically.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-record.c | 10 +++++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 10 +++++-
tools/perf/util/header.c | 79 +++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/header.h | 8 ++++
tools/perf/util/session.c | 26 ++++++++++++++
tools/perf/util/session.h | 3 +-
8 files changed, 136 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d4464f7..289d9cf 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -584,6 +584,16 @@ static int __cmd_record(int argc, const char **argv)
post_processing_offset = lseek(output, 0, SEEK_CUR);
+ if (pipe_output) {
+ err = event__synthesize_attrs(&session->header,
+ process_synthesized_event,
+ session);
+ if (err < 0) {
+ pr_err("Couldn't synthesize attrs.\n");
+ return err;
+ }
+ }
+
err = event__synthesize_kernel_mmap(process_synthesized_event,
session, "_text");
if (err < 0)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 00b358f..f0486ce 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -267,6 +267,7 @@ static struct perf_event_ops event_ops = {
.fork = event__process_task,
.lost = event__process_lost,
.read = process_read_event,
+ .attr = event__process_attr,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c681e85..e30eac6 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -104,6 +104,7 @@ static int process_sample_event(event_t *event, struct perf_session *session)
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
.comm = event__process_comm,
+ .attr = event__process_attr,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5c1eba6..b4fbf25 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -84,7 +84,14 @@ struct build_id_event {
};
enum perf_header_event_type { /* above any possible kernel type */
- PERF_RECORD_HEADER_MAX = 64,
+ PERF_RECORD_HEADER_ATTR = 64,
+ PERF_RECORD_HEADER_MAX
+};
+
+struct attr_event {
+ struct perf_event_header header;
+ struct perf_event_attr attr;
+ u64 id[];
};
typedef union event_union {
@@ -96,6 +103,7 @@ typedef union event_union {
struct lost_event lost;
struct read_event read;
struct sample_event sample;
+ struct attr_event attr;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 8d05337..e361739 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -807,3 +807,82 @@ perf_header__find_attr(u64 id, struct perf_header *header)
return NULL;
}
+
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ event_t *ev;
+ size_t size;
+ int err;
+
+ size = sizeof(struct perf_event_attr);
+ size = ALIGN(size, sizeof(u64));
+ size += sizeof(struct perf_event_header);
+ size += ids * sizeof(u64);
+
+ ev = malloc(size);
+
+ ev->attr.attr = *attr;
+ memcpy(ev->attr.id, id, ids * sizeof(u64));
+
+ ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
+ ev->attr.header.size = size;
+
+ err = process(ev, session);
+
+ free(ev);
+
+ return err;
+}
+
+int event__synthesize_attrs(struct perf_header *self,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ struct perf_header_attr *attr;
+ int i, err = 0;
+
+ for (i = 0; i < self->attrs; i++) {
+ attr = self->attr[i];
+
+ err = event__synthesize_attr(&attr->attr, attr->ids, attr->id,
+ process, session);
+ if (err) {
+ pr_debug("failed to create perf header attribute\n");
+ return err;
+ }
+ }
+
+ return err;
+}
+
+int event__process_attr(event_t *self, struct perf_session *session)
+{
+ struct perf_header_attr *attr;
+ unsigned int i, ids, n_ids;
+
+ attr = perf_header_attr__new(&self->attr.attr);
+ if (attr == NULL)
+ return -ENOMEM;
+
+ ids = self->header.size;
+ ids -= (void *)&self->attr.id - (void *)self;
+ n_ids = ids / sizeof(u64);
+
+ for (i = 0; i < n_ids; i++) {
+ if (perf_header_attr__add_id(attr, self->attr.id[i]) < 0) {
+ perf_header_attr__delete(attr);
+ return -ENOMEM;
+ }
+ }
+
+ if (perf_header__add_attr(&session->header, attr) < 0) {
+ perf_header_attr__delete(attr);
+ return -ENOMEM;
+ }
+
+ perf_session__update_sample_type(session);
+
+ return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 6562ece..e916ac5 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -95,4 +95,12 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
const char *name, bool is_kallsyms);
int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+int event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
+ event__handler_t process,
+ struct perf_session *session);
+int event__synthesize_attrs(struct perf_header *self,
+ event__handler_t process,
+ struct perf_session *session);
+int event__process_attr(event_t *self, struct perf_session *session);
+
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2c1277c..bc81864 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -200,6 +200,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->throttle = process_event_stub;
if (handler->unthrottle == NULL)
handler->unthrottle = process_event_stub;
+ if (handler->attr == NULL)
+ handler->attr = process_event_stub;
}
static const char *event__name[] = {
@@ -213,6 +215,7 @@ static const char *event__name[] = {
[PERF_RECORD_FORK] = "FORK",
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
+ [PERF_RECORD_HEADER_ATTR] = "ATTR",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -279,6 +282,26 @@ static void event__read_swap(event_t *self)
self->read.id = bswap_64(self->read.id);
}
+static void event__attr_swap(event_t *self)
+{
+ size_t size;
+
+ self->attr.attr.type = bswap_32(self->attr.attr.type);
+ self->attr.attr.size = bswap_32(self->attr.attr.size);
+ self->attr.attr.config = bswap_64(self->attr.attr.config);
+ self->attr.attr.sample_period = bswap_64(self->attr.attr.sample_period);
+ self->attr.attr.sample_type = bswap_64(self->attr.attr.sample_type);
+ self->attr.attr.read_format = bswap_64(self->attr.attr.read_format);
+ self->attr.attr.wakeup_events = bswap_32(self->attr.attr.wakeup_events);
+ self->attr.attr.bp_type = bswap_32(self->attr.attr.bp_type);
+ self->attr.attr.bp_addr = bswap_64(self->attr.attr.bp_addr);
+ self->attr.attr.bp_len = bswap_64(self->attr.attr.bp_len);
+
+ size = self->header.size;
+ size -= (void *)&self->attr.id - (void *)self;
+ mem_bswap_64(self->attr.id, size);
+}
+
typedef void (*event__swap_op)(event_t *self);
static event__swap_op event__swap_ops[] = {
@@ -289,6 +312,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_LOST] = event__all64_swap,
[PERF_RECORD_READ] = event__read_swap,
[PERF_RECORD_SAMPLE] = event__all64_swap,
+ [PERF_RECORD_HEADER_ATTR] = event__attr_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -329,6 +353,8 @@ static int perf_session__process_event(struct perf_session *self,
return ops->throttle(event, self);
case PERF_RECORD_UNTHROTTLE:
return ops->unthrottle(event, self);
+ case PERF_RECORD_HEADER_ATTR:
+ return ops->attr(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5f78911..45a1374 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -44,7 +44,8 @@ struct perf_event_ops {
lost,
read,
throttle,
- unthrottle;
+ unthrottle,
+ attr;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
Commit-ID: cd19a035f3b63fee6dcbdb5371c4b22276f7dc8c
Gitweb: http://git.kernel.org/tip/cd19a035f3b63fee6dcbdb5371c4b22276f7dc8c
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:20 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:07 +0200
perf: Convert perf event types into event type events
Bypasses the event type perf header code and replaces it with a
synthesized event and processing function that accomplishes the
same thing, used when reading/writing perf data to/from a pipe.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-record.c | 7 +++++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 14 +++++++++
tools/perf/util/header.c | 62 ++++++++++++++++++++++++++++++++++++++-----
tools/perf/util/header.h | 9 ++++++
tools/perf/util/session.c | 12 ++++++++
tools/perf/util/session.h | 3 +-
8 files changed, 101 insertions(+), 8 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 289d9cf..c4c1322 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -592,6 +592,13 @@ static int __cmd_record(int argc, const char **argv)
pr_err("Couldn't synthesize attrs.\n");
return err;
}
+
+ err = event__synthesize_event_types(process_synthesized_event,
+ session);
+ if (err < 0) {
+ pr_err("Couldn't synthesize event_types.\n");
+ return err;
+ }
}
err = event__synthesize_kernel_mmap(process_synthesized_event,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f0486ce..e59d012 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -268,6 +268,7 @@ static struct perf_event_ops event_ops = {
.lost = event__process_lost,
.read = process_read_event,
.attr = event__process_attr,
+ .event_type = event__process_event_type,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e30eac6..eb884a7 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -105,6 +105,7 @@ static struct perf_event_ops event_ops = {
.sample = process_sample_event,
.comm = event__process_comm,
.attr = event__process_attr,
+ .event_type = event__process_event_type,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b4fbf25..c720fe0 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@ struct build_id_event {
enum perf_header_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_ATTR = 64,
+ PERF_RECORD_HEADER_EVENT_TYPE = 65,
PERF_RECORD_HEADER_MAX
};
@@ -94,6 +95,18 @@ struct attr_event {
u64 id[];
};
+#define MAX_EVENT_NAME 64
+
+struct perf_trace_event_type {
+ u64 event_id;
+ char name[MAX_EVENT_NAME];
+};
+
+struct event_type_event {
+ struct perf_event_header header;
+ struct perf_trace_event_type event_type;
+};
+
typedef union event_union {
struct perf_event_header header;
struct ip_event ip;
@@ -104,6 +117,7 @@ typedef union event_union {
struct read_event read;
struct sample_event sample;
struct attr_event attr;
+ struct event_type_event event_type;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e361739..4463799 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -99,13 +99,6 @@ int perf_header__add_attr(struct perf_header *self,
return 0;
}
-#define MAX_EVENT_NAME 64
-
-struct perf_trace_event_type {
- u64 event_id;
- char name[MAX_EVENT_NAME];
-};
-
static int event_count;
static struct perf_trace_event_type *events;
@@ -886,3 +879,58 @@ int event__process_attr(event_t *self, struct perf_session *session)
return 0;
}
+
+int event__synthesize_event_type(u64 event_id, char *name,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ event_t ev;
+ size_t size = 0;
+ int err = 0;
+
+ memset(&ev, 0, sizeof(ev));
+
+ ev.event_type.event_type.event_id = event_id;
+ memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
+ strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
+
+ ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
+ size = strlen(name);
+ size = ALIGN(size, sizeof(u64));
+ ev.event_type.header.size = sizeof(ev.event_type) -
+ (sizeof(ev.event_type.event_type.name) - size);
+
+ err = process(&ev, session);
+
+ return err;
+}
+
+int event__synthesize_event_types(event__handler_t process,
+ struct perf_session *session)
+{
+ struct perf_trace_event_type *type;
+ int i, err = 0;
+
+ for (i = 0; i < event_count; i++) {
+ type = &events[i];
+
+ err = event__synthesize_event_type(type->event_id, type->name,
+ process, session);
+ if (err) {
+ pr_debug("failed to create perf header event type\n");
+ return err;
+ }
+ }
+
+ return err;
+}
+
+int event__process_event_type(event_t *self,
+ struct perf_session *session __unused)
+{
+ if (perf_header__push_event(self->event_type.event_type.event_id,
+ self->event_type.event_type.name) < 0)
+ return -ENOMEM;
+
+ return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e916ac5..afeb618 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -103,4 +103,13 @@ int event__synthesize_attrs(struct perf_header *self,
struct perf_session *session);
int event__process_attr(event_t *self, struct perf_session *session);
+int event__synthesize_event_type(u64 event_id, char *name,
+ event__handler_t process,
+ struct perf_session *session);
+int event__synthesize_event_types(event__handler_t process,
+ struct perf_session *session);
+int event__process_event_type(event_t *self,
+ struct perf_session *session);
+
+
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index bc81864..96c4629 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -202,6 +202,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->unthrottle = process_event_stub;
if (handler->attr == NULL)
handler->attr = process_event_stub;
+ if (handler->event_type == NULL)
+ handler->event_type = process_event_stub;
}
static const char *event__name[] = {
@@ -216,6 +218,7 @@ static const char *event__name[] = {
[PERF_RECORD_READ] = "READ",
[PERF_RECORD_SAMPLE] = "SAMPLE",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
+ [PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -302,6 +305,12 @@ static void event__attr_swap(event_t *self)
mem_bswap_64(self->attr.id, size);
}
+static void event__event_type_swap(event_t *self)
+{
+ self->event_type.event_type.event_id =
+ bswap_64(self->event_type.event_type.event_id);
+}
+
typedef void (*event__swap_op)(event_t *self);
static event__swap_op event__swap_ops[] = {
@@ -313,6 +322,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_READ] = event__read_swap,
[PERF_RECORD_SAMPLE] = event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = event__attr_swap,
+ [PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -355,6 +365,8 @@ static int perf_session__process_event(struct perf_session *self,
return ops->unthrottle(event, self);
case PERF_RECORD_HEADER_ATTR:
return ops->attr(event, self);
+ case PERF_RECORD_HEADER_EVENT_TYPE:
+ return ops->event_type(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 45a1374..0dac1f4 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -45,7 +45,8 @@ struct perf_event_ops {
read,
throttle,
unthrottle,
- attr;
+ attr,
+ event_type;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
Commit-ID: 9215545e99d8c0b27323df2de504f4294bf5e407
Gitweb: http://git.kernel.org/tip/9215545e99d8c0b27323df2de504f4294bf5e407
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:21 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:07 +0200
perf: Convert perf tracing data into a tracing_data event
Bypasses the tracing_data perf header code and replaces it with
a synthesized event and processing function that accomplishes
the same thing, used when reading/writing perf data to/from a
pipe.
The tracing data is pretty large, and this patch doesn't attempt
to break it down into component events. The tracing_data event
itself doesn't actually contain the tracing data, rather it
arranges for the event processing code to skip over it after
it's read, using the skip return value added to the event
processing loop in a previous patch.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-record.c | 16 ++++++
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 7 +++
tools/perf/util/header.c | 52 +++++++++++++++++++++
tools/perf/util/header.h | 6 ++
tools/perf/util/session.c | 13 +++++
tools/perf/util/session.h | 3 +-
tools/perf/util/trace-event-info.c | 24 ++++++++++
tools/perf/util/trace-event-read.c | 89 ++++++++++++++++++------------------
tools/perf/util/trace-event.h | 4 +-
11 files changed, 170 insertions(+), 46 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c4c1322..3775abe 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -104,6 +104,11 @@ static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
pc->data_tail = tail;
}
+static void advance_output(size_t size)
+{
+ bytes_written += size;
+}
+
static void write_output(void *buf, size_t size)
{
while (size) {
@@ -599,6 +604,17 @@ static int __cmd_record(int argc, const char **argv)
pr_err("Couldn't synthesize event_types.\n");
return err;
}
+
+ err = event__synthesize_tracing_data(output, attrs,
+ nr_counters,
+ process_synthesized_event,
+ session);
+ if (err <= 0) {
+ pr_err("Couldn't record tracing data.\n");
+ return err;
+ }
+
+ advance_output(err);
}
err = event__synthesize_kernel_mmap(process_synthesized_event,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index e59d012..76f03a7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -269,6 +269,7 @@ static struct perf_event_ops event_ops = {
.read = process_read_event,
.attr = event__process_attr,
.event_type = event__process_event_type,
+ .tracing_data = event__process_tracing_data,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index eb884a7..1509744 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -106,6 +106,7 @@ static struct perf_event_ops event_ops = {
.comm = event__process_comm,
.attr = event__process_attr,
.event_type = event__process_event_type,
+ .tracing_data = event__process_tracing_data,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c720fe0..b896a17 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -86,6 +86,7 @@ struct build_id_event {
enum perf_header_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_ATTR = 64,
PERF_RECORD_HEADER_EVENT_TYPE = 65,
+ PERF_RECORD_HEADER_TRACING_DATA = 66,
PERF_RECORD_HEADER_MAX
};
@@ -107,6 +108,11 @@ struct event_type_event {
struct perf_trace_event_type event_type;
};
+struct tracing_data_event {
+ struct perf_event_header header;
+ u32 size;
+};
+
typedef union event_union {
struct perf_event_header header;
struct ip_event ip;
@@ -118,6 +124,7 @@ typedef union event_union {
struct sample_event sample;
struct attr_event attr;
struct event_type_event event_type;
+ struct tracing_data_event tracing_data;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4463799..c6874ec 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -934,3 +934,55 @@ int event__process_event_type(event_t *self,
return 0;
}
+
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+ int nb_events,
+ event__handler_t process,
+ struct perf_session *session __unused)
+{
+ event_t ev;
+ ssize_t size = 0, aligned_size = 0, padding;
+ int err = 0;
+
+ memset(&ev, 0, sizeof(ev));
+
+ ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
+ size = read_tracing_data_size(fd, pattrs, nb_events);
+ if (size <= 0)
+ return size;
+ aligned_size = ALIGN(size, sizeof(u64));
+ padding = aligned_size - size;
+ ev.tracing_data.header.size = sizeof(ev.tracing_data);
+ ev.tracing_data.size = aligned_size;
+
+ process(&ev, session);
+
+ err = read_tracing_data(fd, pattrs, nb_events);
+ write_padded(fd, NULL, 0, padding);
+
+ return aligned_size;
+}
+
+int event__process_tracing_data(event_t *self,
+ struct perf_session *session)
+{
+ ssize_t size_read, padding, size = self->tracing_data.size;
+ off_t offset = lseek(session->fd, 0, SEEK_CUR);
+ char buf[BUFSIZ];
+
+ /* setup for reading amidst mmap */
+ lseek(session->fd, offset + sizeof(struct tracing_data_event),
+ SEEK_SET);
+
+ size_read = trace_report(session->fd);
+
+ padding = ALIGN(size_read, sizeof(u64)) - size_read;
+
+ if (read(session->fd, buf, padding) < 0)
+ die("reading input file");
+
+ if (size_read + padding != size)
+ die("tracing data size mismatch");
+
+ return size_read + padding;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index afeb618..3ed3d98 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -111,5 +111,11 @@ int event__synthesize_event_types(event__handler_t process,
int event__process_event_type(event_t *self,
struct perf_session *session);
+int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
+ int nb_events,
+ event__handler_t process,
+ struct perf_session *session);
+int event__process_tracing_data(event_t *self,
+ struct perf_session *session);
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 96c4629..1516c40 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -204,6 +204,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->attr = process_event_stub;
if (handler->event_type == NULL)
handler->event_type = process_event_stub;
+ if (handler->tracing_data == NULL)
+ handler->tracing_data = process_event_stub;
}
static const char *event__name[] = {
@@ -219,6 +221,7 @@ static const char *event__name[] = {
[PERF_RECORD_SAMPLE] = "SAMPLE",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
+ [PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -311,6 +314,11 @@ static void event__event_type_swap(event_t *self)
bswap_64(self->event_type.event_type.event_id);
}
+static void event__tracing_data_swap(event_t *self)
+{
+ self->tracing_data.size = bswap_32(self->tracing_data.size);
+}
+
typedef void (*event__swap_op)(event_t *self);
static event__swap_op event__swap_ops[] = {
@@ -323,6 +331,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_SAMPLE] = event__all64_swap,
[PERF_RECORD_HEADER_ATTR] = event__attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
+ [PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -367,6 +376,10 @@ static int perf_session__process_event(struct perf_session *self,
return ops->attr(event, self);
case PERF_RECORD_HEADER_EVENT_TYPE:
return ops->event_type(event, self);
+ case PERF_RECORD_HEADER_TRACING_DATA:
+ /* setup for reading amidst mmap */
+ lseek(self->fd, offset + head, SEEK_SET);
+ return ops->tracing_data(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0dac1f4..0739ebb 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,7 +46,8 @@ struct perf_event_ops {
throttle,
unthrottle,
attr,
- event_type;
+ event_type,
+ tracing_data;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 5ea8973..30cd9b5 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -154,10 +154,17 @@ static void put_tracing_file(char *file)
free(file);
}
+static ssize_t calc_data_size;
+
static ssize_t write_or_die(const void *buf, size_t len)
{
int ret;
+ if (calc_data_size) {
+ calc_data_size += len;
+ return len;
+ }
+
ret = write(output_fd, buf, len);
if (ret < 0)
die("writing to '%s'", output_file);
@@ -526,3 +533,20 @@ int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events)
return 0;
}
+
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+ int nb_events)
+{
+ ssize_t size;
+ int err = 0;
+
+ calc_data_size = 1;
+ err = read_tracing_data(fd, pattrs, nb_events);
+ size = calc_data_size - 1;
+ calc_data_size = 0;
+
+ if (err < 0)
+ return err;
+
+ return size;
+}
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 7cd1193..44889c9 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -50,14 +50,37 @@ static int long_size;
static unsigned long page_size;
+static ssize_t calc_data_size;
+
+static int do_read(int fd, void *buf, int size)
+{
+ int rsize = size;
+
+ while (size) {
+ int ret = read(fd, buf, size);
+
+ if (ret <= 0)
+ return -1;
+
+ size -= ret;
+ buf += ret;
+ }
+
+ return rsize;
+}
+
static int read_or_die(void *data, int size)
{
int r;
- r = read(input_fd, data, size);
- if (r != size)
+ r = do_read(input_fd, data, size);
+ if (r <= 0)
die("reading input file (size expected=%d received=%d)",
size, r);
+
+ if (calc_data_size)
+ calc_data_size += r;
+
return r;
}
@@ -82,56 +105,28 @@ static char *read_string(void)
char buf[BUFSIZ];
char *str = NULL;
int size = 0;
- int i;
off_t r;
+ char c;
for (;;) {
- r = read(input_fd, buf, BUFSIZ);
+ r = read(input_fd, &c, 1);
if (r < 0)
die("reading input file");
if (!r)
die("no data");
- for (i = 0; i < r; i++) {
- if (!buf[i])
- break;
- }
- if (i < r)
- break;
+ buf[size++] = c;
- if (str) {
- size += BUFSIZ;
- str = realloc(str, size);
- if (!str)
- die("malloc of size %d", size);
- memcpy(str + (size - BUFSIZ), buf, BUFSIZ);
- } else {
- size = BUFSIZ;
- str = malloc_or_die(size);
- memcpy(str, buf, size);
- }
+ if (!c)
+ break;
}
- /* trailing \0: */
- i++;
-
- /* move the file descriptor to the end of the string */
- r = lseek(input_fd, -(r - i), SEEK_CUR);
- if (r == (off_t)-1)
- die("lseek");
-
- if (str) {
- size += i;
- str = realloc(str, size);
- if (!str)
- die("malloc of size %d", size);
- memcpy(str + (size - i), buf, i);
- } else {
- size = i;
- str = malloc_or_die(i);
- memcpy(str, buf, i);
- }
+ if (calc_data_size)
+ calc_data_size += size;
+
+ str = malloc_or_die(size);
+ memcpy(str, buf, size);
return str;
}
@@ -459,7 +454,7 @@ struct record *trace_read_data(int cpu)
return data;
}
-void trace_report(int fd)
+ssize_t trace_report(int fd)
{
char buf[BUFSIZ];
char test[] = { 23, 8, 68 };
@@ -467,6 +462,9 @@ void trace_report(int fd)
int show_version = 0;
int show_funcs = 0;
int show_printk = 0;
+ ssize_t size;
+
+ calc_data_size = 1;
input_fd = fd;
@@ -499,14 +497,17 @@ void trace_report(int fd)
read_proc_kallsyms();
read_ftrace_printk();
+ size = calc_data_size - 1;
+ calc_data_size = 0;
+
if (show_funcs) {
print_funcs();
- return;
+ return size;
}
if (show_printk) {
print_printk();
- return;
+ return size;
}
- return;
+ return size;
}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 81f2fd2..1f45d46 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -163,7 +163,7 @@ struct record *trace_read_data(int cpu);
void parse_set_info(int nr_cpus, int long_sz);
-void trace_report(int fd);
+ssize_t trace_report(int fd);
void *malloc_or_die(unsigned int size);
@@ -259,6 +259,8 @@ void *raw_field_ptr(struct event *event, const char *name, void *data);
unsigned long long eval_flag(const char *flag);
int read_tracing_data(int fd, struct perf_event_attr *pattrs, int nb_events);
+ssize_t read_tracing_data_size(int fd, struct perf_event_attr *pattrs,
+ int nb_events);
/* taken from kernel/trace/trace.h */
enum trace_flag_type {
Commit-ID: c7929e4727e8ff2d6fc8327188820e3b1c2f1dc3
Gitweb: http://git.kernel.org/tip/c7929e4727e8ff2d6fc8327188820e3b1c2f1dc3
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:22 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:08 +0200
perf: Convert perf header build_ids into build_id events
Bypasses the build_id perf header code and replaces it with a
synthesized event and processing function that accomplishes the
same thing, used when reading/writing perf data to/from a pipe.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-record.c | 15 ++++++-
tools/perf/builtin-report.c | 1 +
tools/perf/builtin-trace.c | 1 +
tools/perf/util/event.h | 2 +
tools/perf/util/header.c | 90 +++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/header.h | 7 +++
tools/perf/util/session.c | 6 +++
tools/perf/util/session.h | 3 +-
8 files changed, 121 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3775abe..0bde31b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -426,10 +426,19 @@ static int process_buildids(void)
static void atexit_header(void)
{
- session->header.data_size += bytes_written;
+ if (!pipe_output) {
+ session->header.data_size += bytes_written;
- process_buildids();
- perf_header__write(&session->header, output, true);
+ process_buildids();
+ perf_header__write(&session->header, output, true);
+ } else {
+ int err;
+
+ err = event__synthesize_build_ids(process_synthesized_event,
+ session);
+ if (err < 0)
+ pr_err("Couldn't synthesize build ids.\n");
+ }
}
static int __cmd_record(int argc, const char **argv)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 76f03a7..7da5fb3 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -270,6 +270,7 @@ static struct perf_event_ops event_ops = {
.attr = event__process_attr,
.event_type = event__process_event_type,
.tracing_data = event__process_tracing_data,
+ .build_id = event__process_build_id,
};
extern volatile int session_done;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 1509744..1ee1e30 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -107,6 +107,7 @@ static struct perf_event_ops event_ops = {
.attr = event__process_attr,
.event_type = event__process_event_type,
.tracing_data = event__process_tracing_data,
+ .build_id = event__process_build_id,
};
extern volatile int session_done;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index b896a17..e5740ea 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -87,6 +87,7 @@ enum perf_header_event_type { /* above any possible kernel type */
PERF_RECORD_HEADER_ATTR = 64,
PERF_RECORD_HEADER_EVENT_TYPE = 65,
PERF_RECORD_HEADER_TRACING_DATA = 66,
+ PERF_RECORD_HEADER_BUILD_ID = 67,
PERF_RECORD_HEADER_MAX
};
@@ -125,6 +126,7 @@ typedef union event_union {
struct attr_event attr;
struct event_type_event event_type;
struct tracing_data_event tracing_data;
+ struct build_id_event build_id;
} event_t;
struct events_stats {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index c6874ec..628173b 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -986,3 +986,93 @@ int event__process_tracing_data(event_t *self,
return size_read + padding;
}
+
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ event_t ev;
+ size_t len;
+ int err = 0;
+
+ if (!pos->hit)
+ return err;
+
+ memset(&ev, 0, sizeof(ev));
+
+ len = pos->long_name_len + 1;
+ len = ALIGN(len, NAME_ALIGN);
+ memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
+ ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
+ ev.build_id.header.misc = misc;
+ ev.build_id.header.size = sizeof(ev.build_id) + len;
+ memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
+
+ err = process(&ev, session);
+
+ return err;
+}
+
+static int __event_synthesize_build_ids(struct list_head *head, u16 misc,
+ event__handler_t process,
+ struct perf_session *session)
+{
+ struct dso *pos;
+
+ dsos__for_each_with_build_id(pos, head) {
+ int err;
+ if (!pos->hit)
+ continue;
+
+ err = event__synthesize_build_id(pos, misc, process, session);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
+int event__synthesize_build_ids(event__handler_t process,
+ struct perf_session *session)
+{
+ int err;
+
+ if (!dsos__read_build_ids(true))
+ return 0;
+
+ err = __event_synthesize_build_ids(&dsos__kernel,
+ PERF_RECORD_MISC_KERNEL,
+ process, session);
+ if (err == 0)
+ err = __event_synthesize_build_ids(&dsos__user,
+ PERF_RECORD_MISC_USER,
+ process, session);
+
+ if (err < 0) {
+ pr_debug("failed to synthesize build ids\n");
+ return err;
+ }
+
+ dsos__cache_build_ids();
+
+ return 0;
+}
+
+int event__process_build_id(event_t *self,
+ struct perf_session *session __unused)
+{
+ struct list_head *head = &dsos__user;
+ struct dso *dso;
+
+ if (self->build_id.header.misc & PERF_RECORD_MISC_KERNEL)
+ head = &dsos__kernel;
+
+ dso = __dsos__findnew(head, self->build_id.filename);
+ if (dso != NULL) {
+ dso__set_build_id(dso, &self->build_id.build_id);
+ if (head == &dsos__kernel && self->build_id.filename[0] == '[')
+ dso->kernel = 1;
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3ed3d98..4214e23 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -118,4 +118,11 @@ int event__synthesize_tracing_data(int fd, struct perf_event_attr *pattrs,
int event__process_tracing_data(event_t *self,
struct perf_session *session);
+int event__synthesize_build_id(struct dso *pos, u16 misc,
+ event__handler_t process,
+ struct perf_session *session);
+int event__synthesize_build_ids(event__handler_t process,
+ struct perf_session *session);
+int event__process_build_id(event_t *self, struct perf_session *session);
+
#endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1516c40..0fdf3eb 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -206,6 +206,8 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->event_type = process_event_stub;
if (handler->tracing_data == NULL)
handler->tracing_data = process_event_stub;
+ if (handler->build_id == NULL)
+ handler->build_id = process_event_stub;
}
static const char *event__name[] = {
@@ -222,6 +224,7 @@ static const char *event__name[] = {
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
+ [PERF_RECORD_HEADER_BUILD_ID] = "BUILD_ID",
};
unsigned long event__total[PERF_RECORD_HEADER_MAX];
@@ -332,6 +335,7 @@ static event__swap_op event__swap_ops[] = {
[PERF_RECORD_HEADER_ATTR] = event__attr_swap,
[PERF_RECORD_HEADER_EVENT_TYPE] = event__event_type_swap,
[PERF_RECORD_HEADER_TRACING_DATA] = event__tracing_data_swap,
+ [PERF_RECORD_HEADER_BUILD_ID] = NULL,
[PERF_RECORD_HEADER_MAX] = NULL,
};
@@ -380,6 +384,8 @@ static int perf_session__process_event(struct perf_session *self,
/* setup for reading amidst mmap */
lseek(self->fd, offset + head, SEEK_SET);
return ops->tracing_data(event, self);
+ case PERF_RECORD_HEADER_BUILD_ID:
+ return ops->build_id(event, self);
default:
self->unknown_events++;
return -1;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0739ebb..0ac14d4 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -47,7 +47,8 @@ struct perf_event_ops {
unthrottle,
attr,
event_type,
- tracing_data;
+ tracing_data,
+ build_id;
};
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
Commit-ID: 47902f3611b392209e2a412bf7ec02dca95e666d
Gitweb: http://git.kernel.org/tip/47902f3611b392209e2a412bf7ec02dca95e666d
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:23 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:08 +0200
perf trace/scripting: Add rwtop and sctop scripts
A couple of scripts, one in Python and the other in Perl, that
demonstrate 'live mode' tracing. For each, the output of the
perf event stream is fed continuously to the script, which
continuously aggregates the data and reports the current results
every 3 seconds, or at the optionally specified interval. After
the current results are displayed, the aggregations are cleared
and the cycle begins anew.
To run the scripts, simply pipe the output of the 'perf trace
record' step as input to the corresponding 'perf trace report'
step, using '-' as the filename to -o and -i:
$ perf trace record sctop -o - | perf trace report sctop -i -
Also adds clear_term() utility functions to the Util.pm and
Util.py utility modules, for use by any script to clear the
screen.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
.../perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm | 6 +
tools/perf/scripts/perl/bin/rwtop-record | 2 +
tools/perf/scripts/perl/bin/rwtop-report | 23 +++
tools/perf/scripts/perl/rwtop.pl | 177 ++++++++++++++++++++
.../python/Perf-Trace-Util/lib/Perf/Trace/Util.py | 3 +
tools/perf/scripts/python/bin/sctop-record | 2 +
tools/perf/scripts/python/bin/sctop-report | 24 +++
tools/perf/scripts/python/sctop.py | 78 +++++++++
8 files changed, 315 insertions(+), 0 deletions(-)
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
index f869c48..d94b40c 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/lib/Perf/Trace/Util.pm
@@ -15,6 +15,7 @@ our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );
our @EXPORT = qw(
avg nsecs nsecs_secs nsecs_nsecs nsecs_usecs print_nsecs
+clear_term
);
our $VERSION = '0.01';
@@ -55,6 +56,11 @@ sub nsecs_str {
return $str;
}
+sub clear_term
+{
+ print "\x1b[H\x1b[2J";
+}
+
1;
__END__
=head1 NAME
diff --git a/tools/perf/scripts/perl/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
new file mode 100644
index 0000000..63976bf
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rwtop-report b/tools/perf/scripts/perl/bin/rwtop-report
new file mode 100644
index 0000000..93e698c
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -0,0 +1,23 @@
+#!/bin/bash
+# description: system-wide r/w top
+# args: [interval]
+n_args=0
+for i in "$@"
+do
+ if expr match "$i" "-" > /dev/null ; then
+ break
+ fi
+ n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 1 ] ; then
+ echo "usage: rwtop-report [interval]"
+ exit
+fi
+if [ "$n_args" -gt 0 ] ; then
+ interval=$1
+ shift
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rwtop.pl $interval
+
+
+
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
new file mode 100644
index 0000000..ec2ab49
--- /dev/null
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -0,0 +1,177 @@
+#!/usr/bin/perl -w
+# (c) 2010, Tom Zanussi <[email protected]>
+# Licensed under the terms of the GNU GPL License version 2
+
+# read/write top
+#
+# Periodically displays system-wide r/w call activity, broken down by
+# pid. If an [interval] arg is specified, the display will be
+# refreshed every [interval] seconds. The default interval is 3
+# seconds.
+
+use 5.010000;
+use strict;
+use warnings;
+
+use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+use lib "./Perf-Trace-Util/lib";
+use Perf::Trace::Core;
+use Perf::Trace::Util;
+
+my $default_interval = 3;
+my $nlines = 20;
+my $print_thread;
+
+my %reads;
+my %writes;
+
+my $interval = shift;
+if (!$interval) {
+ $interval = $default_interval;
+}
+
+sub syscalls::sys_exit_read
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $ret) = @_;
+
+ if ($ret > 0) {
+ $reads{$common_pid}{bytes_read} += $ret;
+ } else {
+ if (!defined ($reads{$common_pid}{bytes_read})) {
+ $reads{$common_pid}{bytes_read} = 0;
+ }
+ $reads{$common_pid}{errors}{$ret}++;
+ }
+}
+
+sub syscalls::sys_enter_read
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $fd, $buf, $count) = @_;
+
+ $reads{$common_pid}{bytes_requested} += $count;
+ $reads{$common_pid}{total_reads}++;
+ $reads{$common_pid}{comm} = $common_comm;
+}
+
+sub syscalls::sys_exit_write
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $ret) = @_;
+
+ if ($ret <= 0) {
+ $writes{$common_pid}{errors}{$ret}++;
+ }
+}
+
+sub syscalls::sys_enter_write
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm,
+ $nr, $fd, $buf, $count) = @_;
+
+ $writes{$common_pid}{bytes_written} += $count;
+ $writes{$common_pid}{total_writes}++;
+ $writes{$common_pid}{comm} = $common_comm;
+}
+
+sub trace_begin
+{
+ $SIG{ALRM} = \&print_totals;
+ alarm 1;
+}
+
+sub trace_end
+{
+ print_unhandled();
+ print_totals();
+}
+
+sub print_totals
+{
+ my $count;
+
+ $count = 0;
+
+ clear_term();
+
+ printf("\nread counts by pid:\n\n");
+
+ printf("%6s %20s %10s %10s %10s\n", "pid", "comm",
+ "# reads", "bytes_req", "bytes_read");
+ printf("%6s %-20s %10s %10s %10s\n", "------", "--------------------",
+ "----------", "----------", "----------");
+
+ foreach my $pid (sort {$reads{$b}{bytes_read} <=>
+ $reads{$a}{bytes_read}} keys %reads) {
+ my $comm = $reads{$pid}{comm};
+ my $total_reads = $reads{$pid}{total_reads};
+ my $bytes_requested = $reads{$pid}{bytes_requested};
+ my $bytes_read = $reads{$pid}{bytes_read};
+
+ printf("%6s %-20s %10s %10s %10s\n", $pid, $comm,
+ $total_reads, $bytes_requested, $bytes_read);
+
+ if (++$count == $nlines) {
+ last;
+ }
+ }
+
+ $count = 0;
+
+ printf("\nwrite counts by pid:\n\n");
+
+ printf("%6s %20s %10s %13s\n", "pid", "comm",
+ "# writes", "bytes_written");
+ printf("%6s %-20s %10s %13s\n", "------", "--------------------",
+ "----------", "-------------");
+
+ foreach my $pid (sort {$writes{$b}{bytes_written} <=>
+ $writes{$a}{bytes_written}} keys %writes) {
+ my $comm = $writes{$pid}{comm};
+ my $total_writes = $writes{$pid}{total_writes};
+ my $bytes_written = $writes{$pid}{bytes_written};
+
+ printf("%6s %-20s %10s %13s\n", $pid, $comm,
+ $total_writes, $bytes_written);
+
+ if (++$count == $nlines) {
+ last;
+ }
+ }
+
+ %reads = ();
+ %writes = ();
+ alarm $interval;
+}
+
+my %unhandled;
+
+sub print_unhandled
+{
+ if ((scalar keys %unhandled) == 0) {
+ return;
+ }
+
+ print "\nunhandled events:\n\n";
+
+ printf("%-40s %10s\n", "event", "count");
+ printf("%-40s %10s\n", "----------------------------------------",
+ "-----------");
+
+ foreach my $event_name (keys %unhandled) {
+ printf("%-40s %10d\n", $event_name, $unhandled{$event_name});
+ }
+}
+
+sub trace_unhandled
+{
+ my ($event_name, $context, $common_cpu, $common_secs, $common_nsecs,
+ $common_pid, $common_comm) = @_;
+
+ $unhandled{$event_name}++;
+}
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 83e9143..9689bc0 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -23,3 +23,6 @@ def nsecs_nsecs(nsecs):
def nsecs_str(nsecs):
str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)),
return str
+
+def clear_term():
+ print("\x1b[H\x1b[2J")
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
new file mode 100644
index 0000000..27ccffa
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report
new file mode 100644
index 0000000..b01c842
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -0,0 +1,24 @@
+#!/bin/bash
+# description: syscall top
+# args: [comm] [interval]
+n_args=0
+for i in "$@"
+do
+ if expr match "$i" "-" > /dev/null ; then
+ break
+ fi
+ n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 2 ] ; then
+ echo "usage: sctop-report [comm] [interval]"
+ exit
+fi
+if [ "$n_args" -gt 1 ] ; then
+ comm=$1
+ interval=$2
+ shift 2
+elif [ "$n_args" -gt 0 ] ; then
+ interval=$1
+ shift
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/sctop.py $comm $interval
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
new file mode 100644
index 0000000..6cafad4
--- /dev/null
+++ b/tools/perf/scripts/python/sctop.py
@@ -0,0 +1,78 @@
+# system call top
+# (c) 2010, Tom Zanussi <[email protected]>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# Periodically displays system-wide system call totals, broken down by
+# syscall. If a [comm] arg is specified, only syscalls called by
+# [comm] are displayed. If an [interval] arg is specified, the display
+# will be refreshed every [interval] seconds. The default interval is
+# 3 seconds.
+
+import thread
+import time
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+usage = "perf trace -s syscall-counts.py [comm] [interval]\n";
+
+for_comm = None
+default_interval = 3
+interval = default_interval
+
+if len(sys.argv) > 3:
+ sys.exit(usage)
+
+if len(sys.argv) > 2:
+ for_comm = sys.argv[1]
+ interval = int(sys.argv[2])
+elif len(sys.argv) > 1:
+ try:
+ interval = int(sys.argv[1])
+ except ValueError:
+ for_comm = sys.argv[1]
+ interval = default_interval
+
+syscalls = autodict()
+
+def trace_begin():
+ thread.start_new_thread(print_syscall_totals, (interval,))
+ pass
+
+def raw_syscalls__sys_enter(event_name, context, common_cpu,
+ common_secs, common_nsecs, common_pid, common_comm,
+ id, args):
+ if for_comm is not None:
+ if common_comm != for_comm:
+ return
+ try:
+ syscalls[id] += 1
+ except TypeError:
+ syscalls[id] = 1
+
+def print_syscall_totals(interval):
+ while 1:
+ clear_term()
+ if for_comm is not None:
+ print "\nsyscall events for %s:\n\n" % (for_comm),
+ else:
+ print "\nsyscall events:\n\n",
+
+ print "%-40s %10s\n" % ("event", "count"),
+ print "%-40s %10s\n" % ("----------------------------------------", \
+ "----------"),
+
+ for id, val in sorted(syscalls.iteritems(), key = lambda(k, v): (v, k), \
+ reverse = True):
+ try:
+ print "%-40d %10d\n" % (id, val),
+ except TypeError:
+ pass
+ syscalls.clear()
+ time.sleep(interval)
Commit-ID: 00b21a01935892a2b97613f10300434998f45093
Gitweb: http://git.kernel.org/tip/00b21a01935892a2b97613f10300434998f45093
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:24 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:08 +0200
perf trace/scripting: Enable scripting shell scripts for live mode
It should be possible to run any perf trace script in 'live
mode'. This requires being able to pass in e.g. '-i -' or other
args, which the current shell scripts aren't equipped to handle.
In a few cases, there are required or optional args that also
need special handling. This patch makes changes the current set
of shell scripts as necessary.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/scripts/perl/bin/failed-syscalls-record | 2 +-
tools/perf/scripts/perl/bin/failed-syscalls-report | 8 +++++++-
tools/perf/scripts/perl/bin/rw-by-file-record | 3 ++-
tools/perf/scripts/perl/bin/rw-by-file-report | 8 +++++++-
tools/perf/scripts/perl/bin/rw-by-pid-record | 2 +-
tools/perf/scripts/perl/bin/rw-by-pid-report | 2 +-
tools/perf/scripts/perl/bin/wakeup-latency-record | 2 +-
tools/perf/scripts/perl/bin/wakeup-latency-report | 2 +-
tools/perf/scripts/perl/bin/workqueue-stats-record | 2 +-
tools/perf/scripts/perl/bin/workqueue-stats-report | 2 +-
.../python/bin/failed-syscalls-by-pid-record | 2 +-
.../python/bin/failed-syscalls-by-pid-report | 8 +++++++-
.../python/bin/syscall-counts-by-pid-record | 2 +-
.../python/bin/syscall-counts-by-pid-report | 8 +++++++-
.../perf/scripts/python/bin/syscall-counts-record | 2 +-
.../perf/scripts/python/bin/syscall-counts-report | 8 +++++++-
16 files changed, 47 insertions(+), 16 deletions(-)
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index f8885d3..6ad9b8f 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-report b/tools/perf/scripts/perl/bin/failed-syscalls-report
index 8bfc660..f634608 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-report
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide failed syscalls
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/failed-syscalls.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-record b/tools/perf/scripts/perl/bin/rw-by-file-record
index b25056e..a828679 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-record
+++ b/tools/perf/scripts/perl/bin/rw-by-file-record
@@ -1,2 +1,3 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write
+perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_enter_write $@
+
diff --git a/tools/perf/scripts/perl/bin/rw-by-file-report b/tools/perf/scripts/perl/bin/rw-by-file-report
index eddb9cc..d83070b 100644
--- a/tools/perf/scripts/perl/bin/rw-by-file-report
+++ b/tools/perf/scripts/perl/bin/rw-by-file-report
@@ -1,7 +1,13 @@
#!/bin/bash
# description: r/w activity for a program, by file
# args: <comm>
-perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $1
+if [ $# -lt 1 ] ; then
+ echo "usage: rw-by-file <comm>"
+ exit
+fi
+comm=$1
+shift
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-file.pl $comm
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-record b/tools/perf/scripts/perl/bin/rw-by-pid-record
index 8903979..63976bf 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-record
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write
+perf record -c 1 -f -a -M -R -e syscalls:sys_enter_read -e syscalls:sys_exit_read -e syscalls:sys_enter_write -e syscalls:sys_exit_write $@
diff --git a/tools/perf/scripts/perl/bin/rw-by-pid-report b/tools/perf/scripts/perl/bin/rw-by-pid-report
index 7f44c25..7ef4698 100644
--- a/tools/perf/scripts/perl/bin/rw-by-pid-report
+++ b/tools/perf/scripts/perl/bin/rw-by-pid-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: system-wide r/w activity
-perf trace -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/rw-by-pid.pl
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-record b/tools/perf/scripts/perl/bin/wakeup-latency-record
index 6abedda..9c0cf58 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-record
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-record
@@ -1,5 +1,5 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup
+perf record -c 1 -f -a -M -R -e sched:sched_switch -e sched:sched_wakeup $@
diff --git a/tools/perf/scripts/perl/bin/wakeup-latency-report b/tools/perf/scripts/perl/bin/wakeup-latency-report
index fce3adc..a0d898f 100644
--- a/tools/perf/scripts/perl/bin/wakeup-latency-report
+++ b/tools/perf/scripts/perl/bin/wakeup-latency-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: system-wide min/max/avg wakeup latency
-perf trace -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/wakeup-latency.pl
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-record b/tools/perf/scripts/perl/bin/workqueue-stats-record
index fce6637..c2a1a94 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-record
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion
+perf record -c 1 -f -a -M -R -e workqueue:workqueue_creation -e workqueue:workqueue_destruction -e workqueue:workqueue_execution -e workqueue:workqueue_insertion $@
diff --git a/tools/perf/scripts/perl/bin/workqueue-stats-report b/tools/perf/scripts/perl/bin/workqueue-stats-report
index 71cfbd1..3508113 100644
--- a/tools/perf/scripts/perl/bin/workqueue-stats-report
+++ b/tools/perf/scripts/perl/bin/workqueue-stats-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: workqueue stats (ins/exe/create/destroy)
-perf trace -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
+perf trace $@ -s ~/libexec/perf-core/scripts/perl/workqueue-stats.pl
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index f8885d3..6ad9b8f 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_exit $@
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
index 1e0c0a8..8c128ef 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide failed syscalls, by pid
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/failed-syscalls-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 45a8c50..27ccffa 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
index f8044d1..c53362e 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide syscall counts, by pid
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts-by-pid.py $comm
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 45a8c50..27ccffa 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,2 @@
#!/bin/bash
-perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter
+perf record -c 1 -f -a -M -R -e raw_syscalls:sys_enter $@
diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report
index a366aa6..8c21552 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-report
+++ b/tools/perf/scripts/python/bin/syscall-counts-report
@@ -1,4 +1,10 @@
#!/bin/bash
# description: system-wide syscall counts
# args: [comm]
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py $1
+if [ $# -gt 0 ] ; then
+ if ! expr match "$1" "-" ; then
+ comm=$1
+ shift
+ fi
+fi
+perf trace $@ -s ~/libexec/perf-core/scripts/python/syscall-counts.py $comm
Commit-ID: a0cccc2e8e9fb16cbed3a117b30e3fbac3092ee3
Gitweb: http://git.kernel.org/tip/a0cccc2e8e9fb16cbed3a117b30e3fbac3092ee3
Author: Tom Zanussi <[email protected]>
AuthorDate: Thu, 1 Apr 2010 23:59:25 -0500
Committer: Ingo Molnar <[email protected]>
CommitDate: Wed, 14 Apr 2010 11:56:09 +0200
perf trace: Invoke live mode automatically if record/report not specified
Currently, live mode is invoked by explicitly invoking the
record and report sides and connecting them with a pipe e.g.
$ perf trace record rwtop -o - | perf trace report rwtop 5 -i -
In terms of usability, it's not that bad, but it does require
the user to type and remember more than necessary.
This patch allows the user to accomplish the same thing without
specifying the separate record/report steps or the pipe. So the
same command as above can be accomplished more simply as:
$ perf trace rwtop 5
Notice that the '-i -' and '-o -' aren't required in this case -
they're added internally, and that any extra arguments are
passed along to the report script (but not to the record
script).
The overall effect is that any of the scripts listed in 'perf
trace -l' can now be used directly in live mode, with the
expected arguments, by simply specifying the script and args to
'perf trace'.
Signed-off-by: Tom Zanussi <[email protected]>
Acked-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
LKML-Reference: <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
---
tools/perf/builtin-trace.c | 59 ++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 59 insertions(+), 0 deletions(-)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 1ee1e30..2eefb33 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -561,6 +561,65 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
suffix = REPORT_SUFFIX;
}
+ if (!suffix && argc >= 2 && strncmp(argv[1], "-", strlen("-")) != 0) {
+ char *record_script_path, *report_script_path;
+ int live_pipe[2];
+ pid_t pid;
+
+ record_script_path = get_script_path(argv[1], RECORD_SUFFIX);
+ if (!record_script_path) {
+ fprintf(stderr, "record script not found\n");
+ return -1;
+ }
+
+ report_script_path = get_script_path(argv[1], REPORT_SUFFIX);
+ if (!report_script_path) {
+ fprintf(stderr, "report script not found\n");
+ return -1;
+ }
+
+ if (pipe(live_pipe) < 0) {
+ perror("failed to create pipe");
+ exit(-1);
+ }
+
+ pid = fork();
+ if (pid < 0) {
+ perror("failed to fork");
+ exit(-1);
+ }
+
+ if (!pid) {
+ dup2(live_pipe[1], 1);
+ close(live_pipe[0]);
+
+ __argv = malloc(5 * sizeof(const char *));
+ __argv[0] = "/bin/sh";
+ __argv[1] = record_script_path;
+ __argv[2] = "-o";
+ __argv[3] = "-";
+ __argv[4] = NULL;
+
+ execvp("/bin/sh", (char **)__argv);
+ exit(-1);
+ }
+
+ dup2(live_pipe[0], 0);
+ close(live_pipe[1]);
+
+ __argv = malloc((argc + 3) * sizeof(const char *));
+ __argv[0] = "/bin/sh";
+ __argv[1] = report_script_path;
+ for (i = 2; i < argc; i++)
+ __argv[i] = argv[i];
+ __argv[i++] = "-i";
+ __argv[i++] = "-";
+ __argv[i++] = NULL;
+
+ execvp("/bin/sh", (char **)__argv);
+ exit(-1);
+ }
+
if (suffix) {
script_path = get_script_path(argv[2], suffix);
if (!script_path) {