* [RFC PATCH 0/7] perf: 'live mode'
@ 2010-03-03 7:05 Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 1/7] perf: introduce special handling for pipe input/output Tom Zanussi
` (8 more replies)
0 siblings, 9 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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.
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: 120234
#
# Overhead Command Shared Object Symbol
# ........ ............... ......................... ......
#
98.65% perf libpthread-2.8.90.so [.] __read
0.46% perf libpthread-2.8.90.so [.] __write_nocancel
0.32% perf libpthread-2.8.90.so [.] __open_nocancel
0.29% perf libpthread-2.8.90.so [.] __libc_close
0.07% perf libc-2.8.90.so [.] 0x000000000a4b15
0.03% perf libc-2.8.90.so [.] __fxstat64
0.03% perf libc-2.8.90.so [.] __open
0.03% perf libc-2.8.90.so [.] close
0.02% Xorg libc-2.8.90.so [.] __select
0.01% Xorg libpthread-2.8.90.so [.] __read
0.01% perf libpthread-2.8.90.so [.] __libc_lseek
0.01% Xorg libc-2.8.90.so [.] setitimer
0.01% perf libc-2.8.90.so [.] __xstat64
0.01% firefox libpthread-2.8.90.so [.] __read
0.00% perf libc-2.8.90.so [.] llseek
0.00% Xorg libpthread-2.8.90.so [.] __restore_rt
0.00% Xorg libc-2.8.90.so [.] sigprocmask
0.00% Xorg libc-2.8.90.so [.] __poll
0.00% wterm libc-2.8.90.so [.] __read
0.00% gnome-screensav libpthread-2.8.90.so [.] __read
0.00% firefox libc-2.8.90.so [.] __poll
0.00% Xorg libc-2.8.90.so [.] writev
0.00% gnome-settings- libpthread-2.8.90.so [.] __read
0.00% wterm libc-2.8.90.so [.] __select
0.00% perf libc-2.8.90.so [.] statfs
0.00% mysqld libc-2.8.90.so [.] __select
0.00% firefox libpthread-2.8.90.so [.] __pthread_cond_timedwait
0.00% firefox libpthread-2.8.90.so [.] __lll_unlock_wake
0.00% firefox libpthread-2.8.90.so [.] 0x0000000000decb
0.00% firefox libc-2.8.90.so [.] __select
0.00% perf libc-2.8.90.so [.] getcwd
0.00% perf libc-2.8.90.so [.] mmap64
0.00% gnome-settings- libc-2.8.90.so [.] __poll
0.00% gnome-screensav libc-2.8.90.so [.] __poll
0.00% firefox libc-2.8.90.so [.] writev
0.00% apache2 libpthread-2.8.90.so [.] __waitpid
0.00% apache2 libc-2.8.90.so [.] __select
#
# (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.
Basically the original scripts were modified to add a 5 second timer.
In the handler for the timer, 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 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] syscall top
syscall-counts [comm] system-wide syscall counts
And here's a few iterations of the output of the 'sctop' Python
script:
root@tropicana:~# perf trace record sctop | perf trace report sctop
perf trace started with Python script /root/libexec/perf-core/scripts/python/sctop.py
syscall events:
event count
---------------------------------------- -----------
2 179
3 158
0 79
78 24
5 13
1 3
16 2
298 1
137 1
79 1
72 1
8 1
syscall events:
event count
---------------------------------------- -----------
0 659287
202 1995
1 812
2 246
3 224
78 56
12 51
5 23
23 22
8 18
7 18
4 9
38 6
61 5
254 4
20 2
16 2
137 1
15 1
14 1
9 1
syscall events:
event count
---------------------------------------- -----------
0 647178
202 1209
1 324
12 52
7 29
14 6
16 4
23 3
3 3
72 2
21 1
11 1
9 1
5 1
4 1
2 1
.
.
.
Obviously, it would be better to have a real top-like display for
these rather than a continuously scrolling mode like this, and of
course it will be much more useful once we get the syscall name
injection events going (the column on the left shows syscall numbers
only).
Last, but not least, here's an example that uses netcat to run the
'rwtop' Perl script over the network:
On the system being traced:
root@tropicana:~# perf trace record rwtop | nc localhost 7777
^C
On the system collecting the data and printing the output every 5
seconds:
root@tropicana:~# nc -l -p 7777 | perf trace report rwtop
perf trace started with Perl script /root/libexec/perf-core/scripts/perl/rwtop.pl
read counts by pid:
pid comm # reads bytes_requested bytes_read
------ -------------------- ----------- ---------- ----------
6672 perf 156016 6238975 6238980
6670 nc 741 6070272 6054460
6675 perf 3235 9445712 4589634
6674 nc 1376 11272192 1586892
6342 gvfsd-trash 2 4096 194
5856 Xorg 5 8264 76
6335 trashapplet 5 16384 48
6378 gnome-power-man 3 12288 32
6298 gnome-panel 1 4096 0
write counts by pid:
pid comm # writes bytes_written
------ -------------------- ----------- ----------
6675 perf 15651 16412612
6670 nc 741 6054460
6674 nc 1376 1586892
6342 gvfsd-trash 2 93
6676 gvfsd-trash 1 35
read counts by pid:
pid comm # reads bytes_requested bytes_read
------ -------------------- ----------- ---------- ----------
6672 perf 166458 6657104 6656232
6670 nc 787 6447104 6447104
6342 gvfsd-trash 2 4096 194
6335 trashapplet 5 16384 48
write counts by pid:
pid comm # writes bytes_written
------ -------------------- ----------- ----------
6675 perf 13734 15206704
6670 nc 787 6447104
6342 gvfsd-trash 2 93
6677 gvfsd-trash 1 35
read counts by pid:
pid comm # reads bytes_requested bytes_read
------ -------------------- ----------- ---------- ----------
6672 perf 167645 6704272 6704048
6670 nc 793 6496256 6529024
6298 gnome-panel 1 4096 0
write counts by pid:
pid comm # writes bytes_written
------ -------------------- ----------- ----------
6675 perf 13473 15011968
6670 nc 797 6529024
failed to read event payload
read counts by pid:
pid comm # reads bytes_requested bytes_read
------ -------------------- ----------- ---------- ----------
6670 nc 217 1777664 1875968
6672 perf 45782 1830816 1830560
6451 wterm 3 19873 607
5856 Xorg 3 72 72
6480 wterm 3 12288 32
6263 gnome-settings- 3 12288 32
6326 gnome-screensav 4 16384 32
write counts by pid:
pid comm # writes bytes_written
------ -------------------- ----------- ----------
6675 perf 3821 4635048
6670 nc 229 1875968
6672 perf 11 592
perf trace Perl script stopped
There are some rough edges and inefficiencies, and I guess 'event
injection' may be a better way to do this in the end, but it seems to
work pretty well already, and I think it shows how useful such a
capability can be.
Tom Zanussi (7):
perf: introduce special handling for pipe input/output
perf: add pipe-specific header read/write and event processing code
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
tools/perf/builtin-record.c | 66 +++++-
tools/perf/builtin-report.c | 13 +-
tools/perf/builtin-trace.c | 11 +
tools/perf/scripts/perl/bin/rwtop-record | 2 +
tools/perf/scripts/perl/bin/rwtop-report | 6 +
tools/perf/scripts/perl/rwtop.pl | 165 +++++++++++++
tools/perf/scripts/python/bin/sctop-record | 2 +
tools/perf/scripts/python/bin/sctop-report | 4 +
tools/perf/scripts/python/sctop.py | 64 +++++
tools/perf/util/event.h | 35 +++
tools/perf/util/header.c | 348 +++++++++++++++++++++++++++-
tools/perf/util/header.h | 38 +++-
tools/perf/util/session.c | 214 ++++++++++++++++-
tools/perf/util/session.h | 23 ++-
tools/perf/util/trace-event-info.c | 24 ++
tools/perf/util/trace-event-read.c | 89 ++++----
tools/perf/util/trace-event.h | 4 +-
17 files changed, 1035 insertions(+), 73 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
^ permalink raw reply [flat|nested] 17+ messages in thread
* [RFC PATCH 1/7] perf: introduce special handling for pipe input/output
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code Tom Zanussi
` (7 subsequent siblings)
8 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
Adds special treatment for stdin/stdout - if the user specifies '-o -'
to perf record or '-i -' to perf report et al, the intent is that the
event stream be written to stdout or read from stdin rather than a
disk file.
This initial patch just handles parsing the cmdline for those modes
and setting a couple variables to be used by the code in later
patches.
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
---
tools/perf/builtin-record.c | 10 ++++++++--
tools/perf/builtin-report.c | 3 ++-
tools/perf/util/session.c | 10 ++++++++++
tools/perf/util/session.h | 1 +
4 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 771533c..4fe87e3 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;
@@ -431,7 +432,9 @@ 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 "
@@ -456,7 +459,10 @@ 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);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cfc655d..ca12efa 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -359,7 +359,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __used)
{
argc = parse_options(argc, argv, options, report_usage, 0);
- setup_pager();
+ if (strcmp(input_name, "-") != 0)
+ setup_pager();
if (symbol__init() < 0)
return -1;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0de7258..dd1e923 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->header, 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);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 31950fc..dbfb74a 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -26,6 +26,7 @@ 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];
--
1.6.4.GIT
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 1/7] perf: introduce special handling for pipe input/output Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-27 3:14 ` Frederic Weisbecker
2010-03-03 7:05 ` [RFC PATCH 3/7] perf: convert perf header attrs into attr events Tom Zanussi
` (6 subsequent siblings)
8 siblings, 1 reply; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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
- adds code to interpret return values >0 from event processing
functions as 'actions'. The first action defined is for stopping
the event-processing loop at the first non-header event. So
initially there's still a restriction that header events come first
in the event stream.
Note that none of this affects 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 <tzanussi@gmail.com>
---
tools/perf/builtin-record.c | 8 ++-
tools/perf/builtin-report.c | 10 +++
tools/perf/builtin-trace.c | 11 +++
tools/perf/util/event.h | 4 +
| 62 ++++++++++++++++++-
| 8 ++-
tools/perf/util/session.c | 145 +++++++++++++++++++++++++++++++++++++++---
tools/perf/util/session.h | 16 +++++
8 files changed, 249 insertions(+), 15 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4fe87e3..b676689 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -475,7 +475,7 @@ 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;
}
@@ -554,7 +554,11 @@ static int __cmd_record(int argc, const char **argv)
open_counters(i, target_pid);
}
- if (file_new) {
+ if (pipe_output) {
+ err = perf_header__write_pipe(&session->header, output);
+ if (err < 0)
+ return err;
+ } else if (file_new) {
err = perf_header__write(&session->header, output, false);
if (err < 0)
return err;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ca12efa..603f705 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -193,11 +193,21 @@ static struct perf_event_ops event_ops = {
.read = process_read_event,
};
+extern volatile int done;
+
+static void sig_handler(int sig __attribute__((__unused__)))
+{
+ done = 1;
+}
+
static int __cmd_report(void)
{
int ret = -EINVAL;
struct perf_session *session;
+ signal(SIGCHLD, sig_handler);
+ signal(SIGINT, sig_handler);
+
session = perf_session__new(input_name, O_RDONLY, force);
if (session == NULL)
return -ENOMEM;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 407041d..2a56dda 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -106,8 +106,18 @@ static struct perf_event_ops event_ops = {
.comm = event__process_comm,
};
+extern volatile int done;
+
+static void sig_handler(int sig __unused)
+{
+ done = 1;
+}
+
static int __cmd_trace(struct perf_session *session)
{
+ signal(SIGCHLD, sig_handler);
+ signal(SIGINT, sig_handler);
+
return perf_session__process_events(session, &event_ops);
}
@@ -609,6 +619,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
return -1;
}
+ perf_header__read(session, input);
err = scripting_ops->generate_script("perf-trace");
goto out;
}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 50a7132..cec3067 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;
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6c9aa16..75b8a4c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -427,6 +427,26 @@ out_free:
return err;
}
+int perf_header__write_pipe(struct perf_header *self, int fd)
+{
+ struct perf_file_header_pipe f_header;
+ int err;
+
+ f_header = (struct perf_file_header_pipe){
+ .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;
+ }
+
+ self->frozen = 1;
+ return 0;
+}
+
int perf_header__write(struct perf_header *self, int fd, bool at_exit)
{
struct perf_file_header f_header;
@@ -662,13 +682,53 @@ 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_file_header_pipe *self,
+ struct perf_header *ph, int fd)
+{
+ if (do_read(fd, self, sizeof(*self)) ||
+ 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_file_header_pipe f_header;
+ struct perf_event_ops header_ops;
+
+ if (perf_file_header__read_pipe(&f_header, self, fd) < 0) {
+ pr_debug("incompatible file format\n");
+ return -EINVAL;
+ }
+
+ perf_event_ops__fill_stop(&header_ops);
+ session->fd = fd;
+
+ return perf_session__process_events(session, &header_ops);
+}
+
+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;
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 82a6af7..714b1d5 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_file_header_pipe {
+ 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(struct perf_header *self, 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 dd1e923..3a3db33 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -18,7 +18,7 @@ static int perf_session__open(struct perf_session *self, bool force)
self->fd_pipe = true;
self->fd = STDIN_FILENO;
- if (perf_header__read(&self->header, self->fd) < 0)
+ if (perf_header__read(self, self->fd) < 0)
pr_err("incompatible file format");
return 0;
@@ -48,12 +48,13 @@ static int perf_session__open(struct perf_session *self, bool force)
goto out_close;
}
- if (perf_header__read(&self->header, self->fd) < 0) {
+ self->size = input_stat.st_size;
+
+ if (perf_header__read(self, self->fd) < 0) {
pr_err("incompatible file format");
goto out_close;
}
- self->size = input_stat.st_size;
return 0;
out_close:
@@ -67,6 +68,11 @@ 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;
@@ -99,7 +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:
@@ -205,6 +211,26 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
handler->unthrottle = process_event_stub;
}
+static int process_event_stop(event_t *event __used,
+ struct perf_session *session __used)
+{
+ dump_printf(": stop!\n");
+ return PERF_PROCESS_EVENT_STOP;
+}
+
+void perf_event_ops__fill_stop(struct perf_event_ops *handler)
+{
+ handler->sample = process_event_stop;
+ handler->mmap = process_event_stop;
+ handler->comm = process_event_stop;
+ handler->fork = process_event_stop;
+ handler->exit = process_event_stop;
+ handler->lost = process_event_stop;
+ handler->read = process_event_stop;
+ handler->throttle = process_event_stop;
+ handler->unthrottle = process_event_stop;
+}
+
static const char *event__name[] = {
[0] = "TOTAL",
[PERF_RECORD_MMAP] = "MMAP",
@@ -218,14 +244,17 @@ 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)
@@ -289,7 +318,7 @@ 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,
@@ -299,7 +328,7 @@ 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]);
@@ -394,6 +423,96 @@ static struct thread *perf_session__register_idle_thread(struct perf_session *se
return thread;
}
+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;
+}
+
+#define is_done() (*(volatile int *)(&done))
+volatile int done;
+
+static int __perf_session__process_events_pipe(struct perf_session *self,
+ struct perf_event_ops *ops)
+{
+ int action = 0;
+ event_t event;
+ uint32_t size;
+ 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) {
+ 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) {
+ pr_err("failed to read event payload\n");
+ goto out_err;
+ }
+
+ if (size == 0 ||
+ (action = 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 (action == PERF_PROCESS_EVENT_STOP) {
+ self->header.data_offset = head;
+ goto done;
+ }
+
+ if (action >= PERF_PROCESS_EVENT_MAX)
+ head += action;
+
+ if (!is_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)
@@ -511,9 +630,13 @@ 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_events_pipe(self, ops);
out_err:
return err;
}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index dbfb74a..ab1fcbf 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,6 +46,18 @@ struct perf_event_ops {
unthrottle;
};
+/*
+ * interpret process_event return values as actions.
+ * PERF_PROCESS_EVENT_MAX or greater is interpreted as 'skip ahead
+ * that many bytes'. Since that can never be less than
+ * sizeof(perf_event_header), 1 through sizeof(perf_event_header) can
+ * be interpreted as 'actions'.
+*/
+enum perf_process_event_action {
+ PERF_PROCESS_EVENT_STOP = 1,
+ PERF_PROCESS_EVENT_MAX
+};
+
struct perf_session *perf_session__new(const char *filename, int mode, bool force);
void perf_session__delete(struct perf_session *self);
@@ -86,4 +98,8 @@ static inline struct map *
{
return map_groups__new_module(&self->kmaps, start, filename);
}
+
+void perf_session__update_sample_type(struct perf_session *self);
+void perf_event_ops__fill_stop(struct perf_event_ops *handler);
+
#endif /* __PERF_SESSION_H */
--
1.6.4.GIT
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [RFC PATCH 3/7] perf: convert perf header attrs into attr events
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 1/7] perf: introduce special handling for pipe input/output Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 4/7] perf: convert perf event types into event type events Tom Zanussi
` (5 subsequent siblings)
8 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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 <tzanussi@gmail.com>
---
tools/perf/builtin-record.c | 10 +++++
tools/perf/util/event.h | 10 +++++-
| 80 +++++++++++++++++++++++++++++++++++++++++++
| 8 ++++
tools/perf/util/session.c | 27 ++++++++++++++
tools/perf/util/session.h | 3 +-
6 files changed, 136 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b676689..3ba466f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -566,6 +566,16 @@ 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/util/event.h b/tools/perf/util/event.h
index cec3067..83e5d08 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 {
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 75b8a4c..6397ad9 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -713,6 +713,7 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
}
perf_event_ops__fill_stop(&header_ops);
+ header_ops.attr = event__process_attr;
session->fd = fd;
return perf_session__process_events(session, &header_ops);
@@ -825,3 +826,82 @@ 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;
+}
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 714b1d5..f5fd82c 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 3a3db33..ff51105 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -209,6 +209,8 @@ 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 int process_event_stop(event_t *event __used,
@@ -229,6 +231,7 @@ void perf_event_ops__fill_stop(struct perf_event_ops *handler)
handler->read = process_event_stop;
handler->throttle = process_event_stop;
handler->unthrottle = process_event_stop;
+ handler->attr = process_event_stop;
}
static const char *event__name[] = {
@@ -242,6 +245,7 @@ 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];
@@ -308,6 +312,26 @@ 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[] = {
@@ -318,6 +342,7 @@ 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,
};
@@ -358,6 +383,8 @@ 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 ab1fcbf..7365a24 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -43,7 +43,8 @@ struct perf_event_ops {
lost,
read,
throttle,
- unthrottle;
+ unthrottle,
+ attr;
};
/*
--
1.6.4.GIT
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [RFC PATCH 4/7] perf: convert perf event types into event type events
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
` (2 preceding siblings ...)
2010-03-03 7:05 ` [RFC PATCH 3/7] perf: convert perf header attrs into attr events Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 5/7] perf: convert perf tracing data into a tracing_data event Tom Zanussi
` (4 subsequent siblings)
8 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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 <tzanussi@gmail.com>
---
tools/perf/builtin-record.c | 7 +++++
tools/perf/util/event.h | 14 +++++++++
| 63 ++++++++++++++++++++++++++++++++++++++-----
| 9 ++++++
tools/perf/util/session.c | 13 +++++++++
tools/perf/util/session.h | 3 +-
6 files changed, 101 insertions(+), 8 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3ba466f..0e3d4cd 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -574,6 +574,13 @@ 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/util/event.h b/tools/perf/util/event.h
index 83e5d08..dc6d27b 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 {
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6397ad9..cb75e66 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;
@@ -714,6 +707,7 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
perf_event_ops__fill_stop(&header_ops);
header_ops.attr = event__process_attr;
+ header_ops.event_type = event__process_event_type;
session->fd = fd;
return perf_session__process_events(session, &header_ops);
@@ -905,3 +899,58 @@ 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;
+}
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index f5fd82c..9d18c9b 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 ff51105..d704bdf 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -211,6 +211,8 @@ 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 int process_event_stop(event_t *event __used,
@@ -232,6 +234,7 @@ void perf_event_ops__fill_stop(struct perf_event_ops *handler)
handler->throttle = process_event_stop;
handler->unthrottle = process_event_stop;
handler->attr = process_event_stop;
+ handler->event_type = process_event_stop;
}
static const char *event__name[] = {
@@ -246,6 +249,7 @@ 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];
@@ -332,6 +336,12 @@ 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[] = {
@@ -343,6 +353,7 @@ 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,
};
@@ -385,6 +396,8 @@ 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 7365a24..ea9eb4a 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -44,7 +44,8 @@ struct perf_event_ops {
read,
throttle,
unthrottle,
- attr;
+ attr,
+ event_type;
};
/*
--
1.6.4.GIT
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [RFC PATCH 5/7] perf: convert perf tracing data into a tracing_data event
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
` (3 preceding siblings ...)
2010-03-03 7:05 ` [RFC PATCH 4/7] perf: convert perf event types into event type events Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 6/7] perf: convert perf header build_ids into build_id events Tom Zanussi
` (3 subsequent siblings)
8 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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
'action' added in a previous patch; in this case the action is 'skip'.
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
---
tools/perf/builtin-record.c | 16 ++++++
tools/perf/util/event.h | 7 +++
| 53 +++++++++++++++++++++
| 6 ++
tools/perf/util/session.c | 14 ++++++
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 +-
9 files changed, 170 insertions(+), 46 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0e3d4cd..95bccdc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -101,6 +101,11 @@ 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) {
@@ -581,6 +586,17 @@ 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/util/event.h b/tools/perf/util/event.h
index dc6d27b..c111358 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 {
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index cb75e66..5910aee 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -708,6 +708,7 @@ static int perf_header__read_pipe(struct perf_session *session, int fd)
perf_event_ops__fill_stop(&header_ops);
header_ops.attr = event__process_attr;
header_ops.event_type = event__process_event_type;
+ header_ops.tracing_data = event__process_tracing_data;
session->fd = fd;
return perf_session__process_events(session, &header_ops);
@@ -954,3 +955,55 @@ 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;
+}
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 9d18c9b..a83f375 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 d704bdf..74e9646 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -213,6 +213,8 @@ 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 int process_event_stop(event_t *event __used,
@@ -235,6 +237,7 @@ void perf_event_ops__fill_stop(struct perf_event_ops *handler)
handler->unthrottle = process_event_stop;
handler->attr = process_event_stop;
handler->event_type = process_event_stop;
+ handler->tracing_data = process_event_stop;
}
static const char *event__name[] = {
@@ -250,6 +253,7 @@ 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];
@@ -342,6 +346,11 @@ 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[] = {
@@ -354,6 +363,7 @@ 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,
};
@@ -398,6 +408,10 @@ 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 ea9eb4a..a648af0 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -45,7 +45,8 @@ struct perf_event_ops {
throttle,
unthrottle,
attr,
- event_type;
+ event_type,
+ tracing_data;
};
/*
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
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [RFC PATCH 6/7] perf: convert perf header build_ids into build_id events
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
` (4 preceding siblings ...)
2010-03-03 7:05 ` [RFC PATCH 5/7] perf: convert perf tracing data into a tracing_data event Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 7/7] perf trace/scripting: rwtop and sctop scripts Tom Zanussi
` (2 subsequent siblings)
8 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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 <tzanussi@gmail.com>
---
tools/perf/builtin-record.c | 15 ++++++-
tools/perf/util/event.h | 2 +
| 90 +++++++++++++++++++++++++++++++++++++++++++
| 7 +++
tools/perf/util/session.c | 7 +++
tools/perf/util/session.h | 3 +-
6 files changed, 120 insertions(+), 4 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 95bccdc..0ab9ffa 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -405,10 +405,19 @@ 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/util/event.h b/tools/perf/util/event.h
index c111358..0705e75 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 {
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 5910aee..c380264 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1007,3 +1007,93 @@ 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;
+}
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index a83f375..cfb807f 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 74e9646..679274d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -215,6 +215,8 @@ 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 int process_event_stop(event_t *event __used,
@@ -238,6 +240,7 @@ void perf_event_ops__fill_stop(struct perf_event_ops *handler)
handler->attr = process_event_stop;
handler->event_type = process_event_stop;
handler->tracing_data = process_event_stop;
+ handler->build_id = process_event_stop;
}
static const char *event__name[] = {
@@ -254,6 +257,7 @@ 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];
@@ -364,6 +368,7 @@ 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,
};
@@ -412,6 +417,8 @@ 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 a648af0..87821a9 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -46,7 +46,8 @@ struct perf_event_ops {
unthrottle,
attr,
event_type,
- tracing_data;
+ tracing_data,
+ build_id;
};
/*
--
1.6.4.GIT
^ permalink raw reply related [flat|nested] 17+ messages in thread
* [RFC PATCH 7/7] perf trace/scripting: rwtop and sctop scripts
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
` (5 preceding siblings ...)
2010-03-03 7:05 ` [RFC PATCH 6/7] perf: convert perf header build_ids into build_id events Tom Zanussi
@ 2010-03-03 7:05 ` Tom Zanussi
2010-03-04 11:18 ` [RFC PATCH 0/7] perf: 'live mode' Ingo Molnar
2010-03-27 0:57 ` Frederic Weisbecker
8 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-03 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: mingo, fweisbec, rostedt, k-keiichi
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 5 seconds.
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:
$ perf trace record sctop | perf trace report sctop
A future patch should probably automatically do this i.e. the user
should be able to just run 'perf trace sctop' and get the same thing,
and the output should do better than just continuously scroll, but
these are just demo scripts for now...
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
---
tools/perf/scripts/perl/bin/rwtop-record | 2 +
tools/perf/scripts/perl/bin/rwtop-report | 6 +
tools/perf/scripts/perl/rwtop.pl | 165 ++++++++++++++++++++++++++++
tools/perf/scripts/python/bin/sctop-record | 2 +
tools/perf/scripts/python/bin/sctop-report | 4 +
tools/perf/scripts/python/sctop.py | 64 +++++++++++
6 files changed, 243 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/bin/rwtop-record b/tools/perf/scripts/perl/bin/rwtop-record
new file mode 100644
index 0000000..0993193
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -o - -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..3d06c98
--- /dev/null
+++ b/tools/perf/scripts/perl/bin/rwtop-report
@@ -0,0 +1,6 @@
+#!/bin/bash
+# description: system-wide r/w top
+perf trace -i - -s ~/libexec/perf-core/scripts/perl/rwtop.pl
+
+
+
diff --git a/tools/perf/scripts/perl/rwtop.pl b/tools/perf/scripts/perl/rwtop.pl
new file mode 100644
index 0000000..4e0d1fd
--- /dev/null
+++ b/tools/perf/scripts/perl/rwtop.pl
@@ -0,0 +1,165 @@
+#!/usr/bin/perl -w
+# (c) 2009, Tom Zanussi <tzanussi@gmail.com>
+# Licensed under the terms of the GNU GPL License version 2
+
+# Display r/w activity for all processes
+
+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 $interval = 5;
+my $nlines = 10;
+my $print_thread;
+
+my %reads;
+my %writes;
+
+sub syscalls::sys_exit_read
+{
+ my ($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 5;
+}
+
+sub trace_end
+{
+ print_unhandled();
+ print_totals();
+}
+
+sub print_totals
+{
+ my $count;
+
+ $count = 0;
+
+ printf("\nread counts by pid:\n\n");
+
+ printf("%6s %20s %10s %10s %10s\n", "pid", "comm",
+ "# reads", "bytes_requested", "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 %10s\n", "pid", "comm",
+ "# writes", "bytes_written");
+ printf("%6s %-20s %10s %10s\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 %10s\n", $pid, $comm,
+ $total_writes, $bytes_written);
+
+ if (++$count == $nlines) {
+ last;
+ }
+ }
+
+ %reads = ();
+ %writes = ();
+ alarm 5;
+}
+
+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/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
new file mode 100644
index 0000000..1a46fb6
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -o - -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..4ca46c0
--- /dev/null
+++ b/tools/perf/scripts/python/bin/sctop-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: syscall top
+# args: [comm]
+perf trace -i - -s ~/libexec/perf-core/scripts/python/sctop.py $1
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
new file mode 100644
index 0000000..a44de25
--- /dev/null
+++ b/tools/perf/scripts/python/sctop.py
@@ -0,0 +1,64 @@
+# system call top
+# (c) 2010, Tom Zanussi <tzanussi@gmail.com>
+# 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.
+
+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]\n";
+
+for_comm = None
+interval = 5
+
+if len(sys.argv) > 2:
+ sys.exit(usage)
+
+if len(sys.argv) > 1:
+ for_comm = sys.argv[1]
+
+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:
+ 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):
+ print "%-40d %10d\n" % (id, val),
+ syscalls.clear()
+ time.sleep(interval)
--
1.6.4.GIT
^ permalink raw reply related [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 0/7] perf: 'live mode'
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
` (6 preceding siblings ...)
2010-03-03 7:05 ` [RFC PATCH 7/7] perf trace/scripting: rwtop and sctop scripts Tom Zanussi
@ 2010-03-04 11:18 ` Ingo Molnar
2010-03-27 23:00 ` Arnaldo Carvalho de Melo
2010-03-27 0:57 ` Frederic Weisbecker
8 siblings, 1 reply; 17+ messages in thread
From: Ingo Molnar @ 2010-03-04 11:18 UTC (permalink / raw)
To: Tom Zanussi; +Cc: linux-kernel, fweisbec, rostedt, k-keiichi
* Tom Zanussi <tzanussi@gmail.com> wrote:
> 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.
Very nice!
> Obviously, it would be better to have a real top-like display for these
> rather than a continuously scrolling mode like this, and of course it will
> be much more useful once we get the syscall name injection events going (the
> column on the left shows syscall numbers only).
It's still useful for ad-hoc tracing!
Side-note, it might make sense to expose the 'clear' escape sequence somehow
in an easy fashion:
^[[H^[[2J
to make it non-scrolling ;-) via a pre-provided method.
> There are some rough edges and inefficiencies, and I guess 'event injection'
> may be a better way to do this in the end, but it seems to work pretty well
> already, and I think it shows how useful such a capability can be.
I'm all for it. Frederic, Steve, what do you think?
Ingo
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 0/7] perf: 'live mode'
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
` (7 preceding siblings ...)
2010-03-04 11:18 ` [RFC PATCH 0/7] perf: 'live mode' Ingo Molnar
@ 2010-03-27 0:57 ` Frederic Weisbecker
8 siblings, 0 replies; 17+ messages in thread
From: Frederic Weisbecker @ 2010-03-27 0:57 UTC (permalink / raw)
To: Tom Zanussi
Cc: linux-kernel, mingo, rostedt, k-keiichi, Arnaldo Carvalho de Melo,
Peter Zijlstra, Paul Mackerras
On Wed, Mar 03, 2010 at 01:05:22AM -0600, Tom Zanussi wrote:
> 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.
>
> 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: 120234
> #
> # Overhead Command Shared Object Symbol
> # ........ ............... ......................... ......
> #
> 98.65% perf libpthread-2.8.90.so [.] __read
> 0.46% perf libpthread-2.8.90.so [.] __write_nocancel
> 0.32% perf libpthread-2.8.90.so [.] __open_nocancel
> 0.29% perf libpthread-2.8.90.so [.] __libc_close
> 0.07% perf libc-2.8.90.so [.] 0x000000000a4b15
> 0.03% perf libc-2.8.90.so [.] __fxstat64
> 0.03% perf libc-2.8.90.so [.] __open
> 0.03% perf libc-2.8.90.so [.] close
> 0.02% Xorg libc-2.8.90.so [.] __select
> 0.01% Xorg libpthread-2.8.90.so [.] __read
> 0.01% perf libpthread-2.8.90.so [.] __libc_lseek
> 0.01% Xorg libc-2.8.90.so [.] setitimer
> 0.01% perf libc-2.8.90.so [.] __xstat64
> 0.01% firefox libpthread-2.8.90.so [.] __read
> 0.00% perf libc-2.8.90.so [.] llseek
> 0.00% Xorg libpthread-2.8.90.so [.] __restore_rt
> 0.00% Xorg libc-2.8.90.so [.] sigprocmask
> 0.00% Xorg libc-2.8.90.so [.] __poll
> 0.00% wterm libc-2.8.90.so [.] __read
> 0.00% gnome-screensav libpthread-2.8.90.so [.] __read
> 0.00% firefox libc-2.8.90.so [.] __poll
> 0.00% Xorg libc-2.8.90.so [.] writev
> 0.00% gnome-settings- libpthread-2.8.90.so [.] __read
> 0.00% wterm libc-2.8.90.so [.] __select
> 0.00% perf libc-2.8.90.so [.] statfs
> 0.00% mysqld libc-2.8.90.so [.] __select
> 0.00% firefox libpthread-2.8.90.so [.] __pthread_cond_timedwait
> 0.00% firefox libpthread-2.8.90.so [.] __lll_unlock_wake
> 0.00% firefox libpthread-2.8.90.so [.] 0x0000000000decb
> 0.00% firefox libc-2.8.90.so [.] __select
> 0.00% perf libc-2.8.90.so [.] getcwd
> 0.00% perf libc-2.8.90.so [.] mmap64
> 0.00% gnome-settings- libc-2.8.90.so [.] __poll
> 0.00% gnome-screensav libc-2.8.90.so [.] __poll
> 0.00% firefox libc-2.8.90.so [.] writev
> 0.00% apache2 libpthread-2.8.90.so [.] __waitpid
> 0.00% apache2 libc-2.8.90.so [.] __select
> #
> # (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.
> Basically the original scripts were modified to add a 5 second timer.
> In the handler for the timer, 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 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] syscall top
> syscall-counts [comm] system-wide syscall counts
>
>
> And here's a few iterations of the output of the 'sctop' Python
> script:
>
> root@tropicana:~# perf trace record sctop | perf trace report sctop
> perf trace started with Python script /root/libexec/perf-core/scripts/python/sctop.py
>
> syscall events:
>
> event count
> ---------------------------------------- -----------
> 2 179
> 3 158
> 0 79
> 78 24
> 5 13
> 1 3
> 16 2
> 298 1
> 137 1
> 79 1
> 72 1
> 8 1
>
> syscall events:
>
> event count
> ---------------------------------------- -----------
> 0 659287
> 202 1995
> 1 812
> 2 246
> 3 224
> 78 56
> 12 51
> 5 23
> 23 22
> 8 18
> 7 18
> 4 9
> 38 6
> 61 5
> 254 4
> 20 2
> 16 2
> 137 1
> 15 1
> 14 1
> 9 1
>
> syscall events:
>
> event count
> ---------------------------------------- -----------
> 0 647178
> 202 1209
> 1 324
> 12 52
> 7 29
> 14 6
> 16 4
> 23 3
> 3 3
> 72 2
> 21 1
> 11 1
> 9 1
> 5 1
> 4 1
> 2 1
>
> .
> .
> .
>
> Obviously, it would be better to have a real top-like display for
> these rather than a continuously scrolling mode like this, and of
> course it will be much more useful once we get the syscall name
> injection events going (the column on the left shows syscall numbers
> only).
>
That's a very nice thing. I guess that we could make
the scripting API to provide something to write such top
like things.
Providing a simple dict must be enough, something organized like
this:
topdict = {
"colname" : [val1, val2, val3],
"col2name" : [val4, val5, val6]
}
Or may be a callback that returns a dict.
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code
2010-03-03 7:05 ` [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code Tom Zanussi
@ 2010-03-27 3:14 ` Frederic Weisbecker
2010-03-27 22:57 ` Arnaldo Carvalho de Melo
0 siblings, 1 reply; 17+ messages in thread
From: Frederic Weisbecker @ 2010-03-27 3:14 UTC (permalink / raw)
To: Tom Zanussi; +Cc: linux-kernel, mingo, rostedt, k-keiichi
On Wed, Mar 03, 2010 at 01:05:24AM -0600, Tom Zanussi wrote:
>
> +int perf_header__write_pipe(struct perf_header *self, int fd)
> +{
> + struct perf_file_header_pipe f_header;
> + int err;
> +
> + f_header = (struct perf_file_header_pipe){
> + .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;
> + }
> +
> + self->frozen = 1;
> + return 0;
> +}
I actually wonder why you bother with a header in the pipe mode,
since it only contains MAGIC and its size.
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code
2010-03-27 3:14 ` Frederic Weisbecker
@ 2010-03-27 22:57 ` Arnaldo Carvalho de Melo
2010-03-27 23:05 ` Arnaldo Carvalho de Melo
0 siblings, 1 reply; 17+ messages in thread
From: Arnaldo Carvalho de Melo @ 2010-03-27 22:57 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: Tom Zanussi, linux-kernel, mingo, rostedt, k-keiichi
Em Sat, Mar 27, 2010 at 04:14:57AM +0100, Frederic Weisbecker escreveu:
> On Wed, Mar 03, 2010 at 01:05:24AM -0600, Tom Zanussi wrote:
> >
> > +int perf_header__write_pipe(struct perf_header *self, int fd)
> > +{
> > + struct perf_file_header_pipe f_header;
> > + int err;
> > +
> > + f_header = (struct perf_file_header_pipe){
> > + .magic = PERF_MAGIC,
> > + .size = sizeof(f_header),
> > + };
> I actually wonder why you bother with a header in the pipe mode,
> since it only contains MAGIC and its size.
Because he wants to detect endianness :-)
- ARnaldo
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 0/7] perf: 'live mode'
2010-03-04 11:18 ` [RFC PATCH 0/7] perf: 'live mode' Ingo Molnar
@ 2010-03-27 23:00 ` Arnaldo Carvalho de Melo
2010-03-28 5:04 ` Tom Zanussi
0 siblings, 1 reply; 17+ messages in thread
From: Arnaldo Carvalho de Melo @ 2010-03-27 23:00 UTC (permalink / raw)
To: Ingo Molnar; +Cc: Tom Zanussi, linux-kernel, fweisbec, rostedt, k-keiichi
Em Thu, Mar 04, 2010 at 12:18:56PM +0100, Ingo Molnar escreveu:
> * Tom Zanussi <tzanussi@gmail.com> wrote:
>
> > 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.
>
> Very nice!
>
> > Obviously, it would be better to have a real top-like display for these
> > rather than a continuously scrolling mode like this, and of course it will
> > be much more useful once we get the syscall name injection events going (the
> > column on the left shows syscall numbers only).
>
> It's still useful for ad-hoc tracing!
>
> Side-note, it might make sense to expose the 'clear' escape sequence somehow
> in an easy fashion:
>
> ^[[H^[[2J
>
> to make it non-scrolling ;-) via a pre-provided method.
>
> > There are some rough edges and inefficiencies, and I guess 'event injection'
> > may be a better way to do this in the end, but it seems to work pretty well
> > already, and I think it shows how useful such a capability can be.
>
> I'm all for it. Frederic, Steve, what do you think?
ITs really nice indeed, I'm reviewing the patches and will test them
after weekend, it fits nicely with the idea of unifying top and report,
i.e. the refresh thing he mentions could do the decay as well if a
parameter is set.
Thnaks Frederic for pointing this patchset to me.
Great work!
- Arnaldo
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code
2010-03-27 22:57 ` Arnaldo Carvalho de Melo
@ 2010-03-27 23:05 ` Arnaldo Carvalho de Melo
2010-03-27 23:12 ` Frederic Weisbecker
0 siblings, 1 reply; 17+ messages in thread
From: Arnaldo Carvalho de Melo @ 2010-03-27 23:05 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: Tom Zanussi, linux-kernel, mingo, rostedt, k-keiichi
Em Sat, Mar 27, 2010 at 07:57:47PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Sat, Mar 27, 2010 at 04:14:57AM +0100, Frederic Weisbecker escreveu:
> > On Wed, Mar 03, 2010 at 01:05:24AM -0600, Tom Zanussi wrote:
> > >
> > > +int perf_header__write_pipe(struct perf_header *self, int fd)
> > > +{
> > > + struct perf_file_header_pipe f_header;
> > > + int err;
> > > +
> > > + f_header = (struct perf_file_header_pipe){
> > > + .magic = PERF_MAGIC,
> > > + .size = sizeof(f_header),
> > > + };
>
> > I actually wonder why you bother with a header in the pipe mode,
> > since it only contains MAGIC and its size.
>
> Because he wants to detect endianness :-)
Elaborating: piping over netcat from a big endian to a little endian
machine works because he used the ->needs_swap logic I implemented to
allow cross platform analysis.
Its just a matter of having the DSOS with matching build-ids in the
cache of the machine running 'perf report'.
- Arnaldo
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code
2010-03-27 23:05 ` Arnaldo Carvalho de Melo
@ 2010-03-27 23:12 ` Frederic Weisbecker
2010-03-28 0:15 ` Arnaldo Carvalho de Melo
0 siblings, 1 reply; 17+ messages in thread
From: Frederic Weisbecker @ 2010-03-27 23:12 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Tom Zanussi, linux-kernel, mingo, rostedt, k-keiichi
On Sat, Mar 27, 2010 at 08:05:05PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Sat, Mar 27, 2010 at 07:57:47PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Sat, Mar 27, 2010 at 04:14:57AM +0100, Frederic Weisbecker escreveu:
> > > On Wed, Mar 03, 2010 at 01:05:24AM -0600, Tom Zanussi wrote:
> > > >
> > > > +int perf_header__write_pipe(struct perf_header *self, int fd)
> > > > +{
> > > > + struct perf_file_header_pipe f_header;
> > > > + int err;
> > > > +
> > > > + f_header = (struct perf_file_header_pipe){
> > > > + .magic = PERF_MAGIC,
> > > > + .size = sizeof(f_header),
> > > > + };
> >
> > > I actually wonder why you bother with a header in the pipe mode,
> > > since it only contains MAGIC and its size.
> >
> > Because he wants to detect endianness :-)
>
> Elaborating: piping over netcat from a big endian to a little endian
> machine works because he used the ->needs_swap logic I implemented to
> allow cross platform analysis.
>
> Its just a matter of having the DSOS with matching build-ids in the
> cache of the machine running 'perf report'.
>
> - Arnaldo
Ok, thanks for the explanations :-)
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code
2010-03-27 23:12 ` Frederic Weisbecker
@ 2010-03-28 0:15 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 17+ messages in thread
From: Arnaldo Carvalho de Melo @ 2010-03-28 0:15 UTC (permalink / raw)
To: Frederic Weisbecker; +Cc: Tom Zanussi, linux-kernel, mingo, rostedt, k-keiichi
Em Sun, Mar 28, 2010 at 12:12:05AM +0100, Frederic Weisbecker escreveu:
> On Sat, Mar 27, 2010 at 08:05:05PM -0300, Arnaldo Carvalho de Melo wrote:
> > Em Sat, Mar 27, 2010 at 07:57:47PM -0300, Arnaldo Carvalho de Melo escreveu:
> > > Em Sat, Mar 27, 2010 at 04:14:57AM +0100, Frederic Weisbecker escreveu:
> > > > I actually wonder why you bother with a header in the pipe mode,
> > > > since it only contains MAGIC and its size.
> > >
> > > Because he wants to detect endianness :-)
> >
> > Elaborating: piping over netcat from a big endian to a little endian
> > machine works because he used the ->needs_swap logic I implemented to
> > allow cross platform analysis.
> >
> > Its just a matter of having the DSOS with matching build-ids in the
> > cache of the machine running 'perf report'.
> Ok, thanks for the explanations :-)
Humm, now that I read this again, the build-ids now are in the headers,
which will not be pushed as it is the last step in 'perf record', after
we stop recording events, so only if we make sure that the binaries are
the same is that we will be able to make sense of it over the network.
One more reason for the loader of DSOs to read the pre calculated
build-id ELF session to tell the kernel the 20 bytes build id that in
turn will inject it in the PERF_RECORD_MMAP event.
- Arnaldo
^ permalink raw reply [flat|nested] 17+ messages in thread
* Re: [RFC PATCH 0/7] perf: 'live mode'
2010-03-27 23:00 ` Arnaldo Carvalho de Melo
@ 2010-03-28 5:04 ` Tom Zanussi
0 siblings, 0 replies; 17+ messages in thread
From: Tom Zanussi @ 2010-03-28 5:04 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Ingo Molnar, linux-kernel, fweisbec, rostedt, k-keiichi
On Sat, 2010-03-27 at 20:00 -0300, Arnaldo Carvalho de Melo wrote:
> Em Thu, Mar 04, 2010 at 12:18:56PM +0100, Ingo Molnar escreveu:
> > * Tom Zanussi <tzanussi@gmail.com> wrote:
> >
> > > 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.
> >
> > Very nice!
> >
> > > Obviously, it would be better to have a real top-like display for these
> > > rather than a continuously scrolling mode like this, and of course it will
> > > be much more useful once we get the syscall name injection events going (the
> > > column on the left shows syscall numbers only).
> >
> > It's still useful for ad-hoc tracing!
> >
> > Side-note, it might make sense to expose the 'clear' escape sequence somehow
> > in an easy fashion:
> >
> > ^[[H^[[2J
> >
> > to make it non-scrolling ;-) via a pre-provided method.
> >
> > > There are some rough edges and inefficiencies, and I guess 'event injection'
> > > may be a better way to do this in the end, but it seems to work pretty well
> > > already, and I think it shows how useful such a capability can be.
> >
> > I'm all for it. Frederic, Steve, what do you think?
>
> ITs really nice indeed, I'm reviewing the patches and will test them
> after weekend, it fits nicely with the idea of unifying top and report,
> i.e. the refresh thing he mentions could do the decay as well if a
> parameter is set.
>
> Thnaks Frederic for pointing this patchset to me.
>
> Great work!
Thanks! Just FYI, I have a new version of this patchset that I'm hoping
to post in the next couple of days. It adds the refresh sequence and a
specifiable delay, among other things (like bugfixes)...
Tom
>
> - Arnaldo
^ permalink raw reply [flat|nested] 17+ messages in thread
end of thread, other threads:[~2010-03-28 5:04 UTC | newest]
Thread overview: 17+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-03-03 7:05 [RFC PATCH 0/7] perf: 'live mode' Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 1/7] perf: introduce special handling for pipe input/output Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 2/7] perf: add pipe-specific header read/write and event processing code Tom Zanussi
2010-03-27 3:14 ` Frederic Weisbecker
2010-03-27 22:57 ` Arnaldo Carvalho de Melo
2010-03-27 23:05 ` Arnaldo Carvalho de Melo
2010-03-27 23:12 ` Frederic Weisbecker
2010-03-28 0:15 ` Arnaldo Carvalho de Melo
2010-03-03 7:05 ` [RFC PATCH 3/7] perf: convert perf header attrs into attr events Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 4/7] perf: convert perf event types into event type events Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 5/7] perf: convert perf tracing data into a tracing_data event Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 6/7] perf: convert perf header build_ids into build_id events Tom Zanussi
2010-03-03 7:05 ` [RFC PATCH 7/7] perf trace/scripting: rwtop and sctop scripts Tom Zanussi
2010-03-04 11:18 ` [RFC PATCH 0/7] perf: 'live mode' Ingo Molnar
2010-03-27 23:00 ` Arnaldo Carvalho de Melo
2010-03-28 5:04 ` Tom Zanussi
2010-03-27 0:57 ` Frederic Weisbecker
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox