perf/core improvements and fixes:
. Make per-cpu mmaps the default in 'perf record', from Adrian Hunter.
. Default -t/--thread 'perf record' option to no inheritance,
from Adrian Hunter.
. Make 'perf top -g' refer to callchains, for consistency with other tools,
from David Ahern.
. Skip ignored symbols while printing callchain, from David Ahern.
. Print callchains and symbols if they exist in 'perf script',
from David Ahern.
. Remove thread summary coloring in 'perf trace', from Pekka Enberg.
. zsh completion support, from Ramkumar Ramachandra.
. 'perf timechart' improvements, including backtrace support,
from Stanislav Fomichev.
. Fix using kcore files stored in the buildid cache when doing report/annotate
in non-live sessions, from Adrian Hunter
. Minor 'timechart' cleanups.
. Fix tags/TAGS targets rebuilding, from Jiri Olsa.
. Add options to show comm, fork, exit and mmap PERF_RECORD_ events in
'perf script', from Namhyung Kim.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.15 (GNU/Linux)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=lc6f
-----END PGP SIGNATURE-----
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
* Make per-cpu mmaps the default in 'perf record', from Adrian Hunter.
* Default -t/--thread 'perf record' option to no inheritance,
from Adrian Hunter.
* Make 'perf top -g' refer to callchains, for consistency with other tools,
from David Ahern.
* Skip ignored symbols while printing callchain, from David Ahern.
* Print callchains and symbols if they exist in 'perf script',
from David Ahern.
* Remove thread summary coloring in 'perf trace', from Pekka Enberg.
* zsh completion support, from Ramkumar Ramachandra.
* 'perf timechart' improvements, including backtrace support,
from Stanislav Fomichev.
* Fix using kcore files stored in the buildid cache when doing report/annotate
in non-live sessions, from Adrian Hunter
* Minor 'timechart' cleanups.
* Fix tags/TAGS targets rebuilding, from Jiri Olsa.
* Add options to show comm, fork, exit and mmap PERF_RECORD_ events in
'perf script', from Namhyung Kim.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Ingo Molnar
commit
0ed1e0bee0
|
|
@ -4099,6 +4099,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
|
|||
unsigned long long val;
|
||||
struct func_map *func;
|
||||
const char *saveptr;
|
||||
struct trace_seq p;
|
||||
char *bprint_fmt = NULL;
|
||||
char format[32];
|
||||
int show_func;
|
||||
|
|
@ -4306,8 +4307,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
|
|||
format[len] = 0;
|
||||
if (!len_as_arg)
|
||||
len_arg = -1;
|
||||
print_str_arg(s, data, size, event,
|
||||
/* Use helper trace_seq */
|
||||
trace_seq_init(&p);
|
||||
print_str_arg(&p, data, size, event,
|
||||
format, len_arg, arg);
|
||||
trace_seq_terminate(&p);
|
||||
trace_seq_puts(s, p.buffer);
|
||||
arg = arg->next;
|
||||
break;
|
||||
default:
|
||||
|
|
|
|||
|
|
@ -57,6 +57,8 @@ OPTIONS
|
|||
-t::
|
||||
--tid=::
|
||||
Record events on existing thread ID (comma separated list).
|
||||
This option also disables inheritance by default. Enable it by adding
|
||||
--inherit.
|
||||
|
||||
-u::
|
||||
--uid=::
|
||||
|
|
@ -201,11 +203,11 @@ abort events and some memory events in precise mode on modern Intel CPUs.
|
|||
--transaction::
|
||||
Record transaction flags for transaction related events.
|
||||
|
||||
--force-per-cpu::
|
||||
Force the use of per-cpu mmaps. By default, when tasks are specified (i.e. -p,
|
||||
-t or -u options) per-thread mmaps are created. This option overrides that and
|
||||
forces per-cpu mmaps. A side-effect of that is that inheritance is
|
||||
automatically enabled. Add the -i option also to disable inheritance.
|
||||
--per-thread::
|
||||
Use per-thread mmaps. By default per-cpu mmaps are created. This option
|
||||
overrides that and uses per-thread mmaps. A side-effect of that is that
|
||||
inheritance is automatically disabled. --per-thread is ignored with a warning
|
||||
if combined with -a or -C options.
|
||||
|
||||
SEE ALSO
|
||||
--------
|
||||
|
|
|
|||
|
|
@ -203,6 +203,12 @@ OPTIONS
|
|||
--show-kernel-path::
|
||||
Try to resolve the path of [kernel.kallsyms]
|
||||
|
||||
--show-task-events
|
||||
Display task related events (e.g. FORK, COMM, EXIT).
|
||||
|
||||
--show-mmap-events
|
||||
Display mmap related events (e.g. MMAP, MMAP2).
|
||||
|
||||
SEE ALSO
|
||||
--------
|
||||
linkperf:perf-record[1], linkperf:perf-script-perl[1],
|
||||
|
|
|
|||
|
|
@ -8,8 +8,7 @@ perf-timechart - Tool to visualize total system behavior during a workload
|
|||
SYNOPSIS
|
||||
--------
|
||||
[verse]
|
||||
'perf timechart' record <command>
|
||||
'perf timechart' [<options>]
|
||||
'perf timechart' [<timechart options>] {record} [<record options>]
|
||||
|
||||
DESCRIPTION
|
||||
-----------
|
||||
|
|
@ -21,8 +20,8 @@ There are two variants of perf timechart:
|
|||
'perf timechart' to turn a trace into a Scalable Vector Graphics file,
|
||||
that can be viewed with popular SVG viewers such as 'Inkscape'.
|
||||
|
||||
OPTIONS
|
||||
-------
|
||||
TIMECHART OPTIONS
|
||||
-----------------
|
||||
-o::
|
||||
--output=::
|
||||
Select the output file (default: output.svg)
|
||||
|
|
@ -35,6 +34,9 @@ OPTIONS
|
|||
-P::
|
||||
--power-only::
|
||||
Only output the CPU power section of the diagram
|
||||
-T::
|
||||
--tasks-only::
|
||||
Don't output processor state transitions
|
||||
-p::
|
||||
--process::
|
||||
Select the processes to display, by name or PID
|
||||
|
|
@ -54,6 +56,22 @@ $ perf timechart
|
|||
|
||||
Written 10.2 seconds of trace to output.svg.
|
||||
|
||||
-n::
|
||||
--proc-num::
|
||||
Print task info for at least given number of tasks.
|
||||
|
||||
RECORD OPTIONS
|
||||
--------------
|
||||
-P::
|
||||
--power-only::
|
||||
Record only power-related events
|
||||
-T::
|
||||
--tasks-only::
|
||||
Record only tasks-related events
|
||||
-g::
|
||||
--callchain::
|
||||
Do call-graph (stack chain/backtrace) recording
|
||||
|
||||
SEE ALSO
|
||||
--------
|
||||
linkperf:perf-record[1]
|
||||
|
|
|
|||
|
|
@ -50,7 +50,6 @@ Default is to monitor all CPUS.
|
|||
--count-filter=<count>::
|
||||
Only display functions with more events than this.
|
||||
|
||||
-g::
|
||||
--group::
|
||||
Put the counters into a counter group.
|
||||
|
||||
|
|
@ -143,12 +142,12 @@ Default is to monitor all CPUS.
|
|||
--asm-raw::
|
||||
Show raw instruction encoding of assembly instructions.
|
||||
|
||||
-G::
|
||||
-g::
|
||||
Enables call-graph (stack chain/backtrace) recording.
|
||||
|
||||
--call-graph::
|
||||
Setup and enable call-graph (stack chain/backtrace) recording,
|
||||
implies -G.
|
||||
implies -g.
|
||||
|
||||
--max-stack::
|
||||
Set the stack depth limit when parsing the callchain, anything
|
||||
|
|
|
|||
|
|
@ -60,8 +60,11 @@ endef
|
|||
|
||||
#
|
||||
# Needed if no target specified:
|
||||
# (Except for tags and TAGS targets. The reason is that the
|
||||
# Makefile does not treat tags/TAGS as targets but as files
|
||||
# and thus won't rebuilt them once they are in place.)
|
||||
#
|
||||
all:
|
||||
all tags TAGS:
|
||||
$(print_msg)
|
||||
$(make)
|
||||
|
||||
|
|
@ -77,3 +80,5 @@ clean:
|
|||
%:
|
||||
$(print_msg)
|
||||
$(make)
|
||||
|
||||
.PHONY: tags TAGS
|
||||
|
|
|
|||
|
|
@ -840,9 +840,9 @@ ifndef NO_LIBPYTHON
|
|||
$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
|
||||
$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
|
||||
endif
|
||||
$(call QUIET_INSTALL, bash_completion-script) \
|
||||
$(call QUIET_INSTALL, perf_completion-script) \
|
||||
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
|
||||
$(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
|
||||
$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
|
||||
$(call QUIET_INSTALL, tests) \
|
||||
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
|
||||
$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
|
||||
|
|
|
|||
|
|
@ -800,6 +800,7 @@ static struct perf_record record = {
|
|||
.freq = 4000,
|
||||
.target = {
|
||||
.uses_mmap = true,
|
||||
.default_per_cpu = true,
|
||||
},
|
||||
},
|
||||
};
|
||||
|
|
@ -842,8 +843,9 @@ const struct option record_options[] = {
|
|||
OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
|
||||
OPT_STRING('o', "output", &record.file.path, "file",
|
||||
"output file name"),
|
||||
OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
|
||||
"child tasks do not inherit counters"),
|
||||
OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
|
||||
&record.opts.no_inherit_set,
|
||||
"child tasks do not inherit counters"),
|
||||
OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
|
||||
OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
|
||||
"number of mmap data pages",
|
||||
|
|
@ -888,8 +890,8 @@ const struct option record_options[] = {
|
|||
"sample by weight (on special events only)"),
|
||||
OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
|
||||
"sample transaction flags (special events only)"),
|
||||
OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
|
||||
"force the use of per-cpu mmaps"),
|
||||
OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
|
||||
"use per-thread mmaps"),
|
||||
OPT_END()
|
||||
};
|
||||
|
||||
|
|
@ -938,6 +940,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
|
|||
goto out_symbol_exit;
|
||||
}
|
||||
|
||||
if (rec->opts.target.tid && !rec->opts.no_inherit_set)
|
||||
rec->opts.no_inherit = true;
|
||||
|
||||
err = target__validate(&rec->opts.target);
|
||||
if (err) {
|
||||
target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
|
||||
|
|
|
|||
|
|
@ -280,6 +280,30 @@ static int perf_session__check_output_opt(struct perf_session *session)
|
|||
set_print_ip_opts(&evsel->attr);
|
||||
}
|
||||
|
||||
/*
|
||||
* set default for tracepoints to print symbols only
|
||||
* if callchains are present
|
||||
*/
|
||||
if (symbol_conf.use_callchain &&
|
||||
!output[PERF_TYPE_TRACEPOINT].user_set) {
|
||||
struct perf_event_attr *attr;
|
||||
|
||||
j = PERF_TYPE_TRACEPOINT;
|
||||
evsel = perf_session__find_first_evtype(session, j);
|
||||
if (evsel == NULL)
|
||||
goto out;
|
||||
|
||||
attr = &evsel->attr;
|
||||
|
||||
if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
|
||||
output[j].fields |= PERF_OUTPUT_IP;
|
||||
output[j].fields |= PERF_OUTPUT_SYM;
|
||||
output[j].fields |= PERF_OUTPUT_DSO;
|
||||
set_print_ip_opts(attr);
|
||||
}
|
||||
}
|
||||
|
||||
out:
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
|
@ -288,7 +312,6 @@ static void print_sample_start(struct perf_sample *sample,
|
|||
struct perf_evsel *evsel)
|
||||
{
|
||||
struct perf_event_attr *attr = &evsel->attr;
|
||||
const char *evname = NULL;
|
||||
unsigned long secs;
|
||||
unsigned long usecs;
|
||||
unsigned long long nsecs;
|
||||
|
|
@ -323,11 +346,6 @@ static void print_sample_start(struct perf_sample *sample,
|
|||
usecs = nsecs / NSECS_PER_USEC;
|
||||
printf("%5lu.%06lu: ", secs, usecs);
|
||||
}
|
||||
|
||||
if (PRINT_FIELD(EVNAME)) {
|
||||
evname = perf_evsel__name(evsel);
|
||||
printf("%s: ", evname ? evname : "[unknown]");
|
||||
}
|
||||
}
|
||||
|
||||
static bool is_bts_event(struct perf_event_attr *attr)
|
||||
|
|
@ -434,6 +452,11 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
|
|||
|
||||
print_sample_start(sample, thread, evsel);
|
||||
|
||||
if (PRINT_FIELD(EVNAME)) {
|
||||
const char *evname = perf_evsel__name(evsel);
|
||||
printf("%s: ", evname ? evname : "[unknown]");
|
||||
}
|
||||
|
||||
if (is_bts_event(attr)) {
|
||||
print_sample_bts(event, sample, evsel, machine, thread);
|
||||
return;
|
||||
|
|
@ -549,6 +572,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
|
|||
struct perf_script {
|
||||
struct perf_tool tool;
|
||||
struct perf_session *session;
|
||||
bool show_task_events;
|
||||
bool show_mmap_events;
|
||||
};
|
||||
|
||||
static int process_attr(struct perf_tool *tool, union perf_event *event,
|
||||
|
|
@ -579,6 +604,163 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
|
|||
return perf_evsel__check_attr(evsel, scr->session);
|
||||
}
|
||||
|
||||
static int process_comm_event(struct perf_tool *tool,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct thread *thread;
|
||||
struct perf_script *script = container_of(tool, struct perf_script, tool);
|
||||
struct perf_session *session = script->session;
|
||||
struct perf_evsel *evsel = perf_evlist__first(session->evlist);
|
||||
int ret = -1;
|
||||
|
||||
thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
|
||||
if (thread == NULL) {
|
||||
pr_debug("problem processing COMM event, skipping it.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (perf_event__process_comm(tool, event, sample, machine) < 0)
|
||||
goto out;
|
||||
|
||||
if (!evsel->attr.sample_id_all) {
|
||||
sample->cpu = 0;
|
||||
sample->time = 0;
|
||||
sample->tid = event->comm.tid;
|
||||
sample->pid = event->comm.pid;
|
||||
}
|
||||
print_sample_start(sample, thread, evsel);
|
||||
perf_event__fprintf(event, stdout);
|
||||
ret = 0;
|
||||
|
||||
out:
|
||||
return ret;
|
||||
}
|
||||
|
||||
static int process_fork_event(struct perf_tool *tool,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct thread *thread;
|
||||
struct perf_script *script = container_of(tool, struct perf_script, tool);
|
||||
struct perf_session *session = script->session;
|
||||
struct perf_evsel *evsel = perf_evlist__first(session->evlist);
|
||||
|
||||
if (perf_event__process_fork(tool, event, sample, machine) < 0)
|
||||
return -1;
|
||||
|
||||
thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
|
||||
if (thread == NULL) {
|
||||
pr_debug("problem processing FORK event, skipping it.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (!evsel->attr.sample_id_all) {
|
||||
sample->cpu = 0;
|
||||
sample->time = event->fork.time;
|
||||
sample->tid = event->fork.tid;
|
||||
sample->pid = event->fork.pid;
|
||||
}
|
||||
print_sample_start(sample, thread, evsel);
|
||||
perf_event__fprintf(event, stdout);
|
||||
|
||||
return 0;
|
||||
}
|
||||
static int process_exit_event(struct perf_tool *tool,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct thread *thread;
|
||||
struct perf_script *script = container_of(tool, struct perf_script, tool);
|
||||
struct perf_session *session = script->session;
|
||||
struct perf_evsel *evsel = perf_evlist__first(session->evlist);
|
||||
|
||||
thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
|
||||
if (thread == NULL) {
|
||||
pr_debug("problem processing EXIT event, skipping it.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (!evsel->attr.sample_id_all) {
|
||||
sample->cpu = 0;
|
||||
sample->time = 0;
|
||||
sample->tid = event->comm.tid;
|
||||
sample->pid = event->comm.pid;
|
||||
}
|
||||
print_sample_start(sample, thread, evsel);
|
||||
perf_event__fprintf(event, stdout);
|
||||
|
||||
if (perf_event__process_exit(tool, event, sample, machine) < 0)
|
||||
return -1;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int process_mmap_event(struct perf_tool *tool,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct thread *thread;
|
||||
struct perf_script *script = container_of(tool, struct perf_script, tool);
|
||||
struct perf_session *session = script->session;
|
||||
struct perf_evsel *evsel = perf_evlist__first(session->evlist);
|
||||
|
||||
if (perf_event__process_mmap(tool, event, sample, machine) < 0)
|
||||
return -1;
|
||||
|
||||
thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
|
||||
if (thread == NULL) {
|
||||
pr_debug("problem processing MMAP event, skipping it.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (!evsel->attr.sample_id_all) {
|
||||
sample->cpu = 0;
|
||||
sample->time = 0;
|
||||
sample->tid = event->mmap.tid;
|
||||
sample->pid = event->mmap.pid;
|
||||
}
|
||||
print_sample_start(sample, thread, evsel);
|
||||
perf_event__fprintf(event, stdout);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int process_mmap2_event(struct perf_tool *tool,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct thread *thread;
|
||||
struct perf_script *script = container_of(tool, struct perf_script, tool);
|
||||
struct perf_session *session = script->session;
|
||||
struct perf_evsel *evsel = perf_evlist__first(session->evlist);
|
||||
|
||||
if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
|
||||
return -1;
|
||||
|
||||
thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
|
||||
if (thread == NULL) {
|
||||
pr_debug("problem processing MMAP2 event, skipping it.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (!evsel->attr.sample_id_all) {
|
||||
sample->cpu = 0;
|
||||
sample->time = 0;
|
||||
sample->tid = event->mmap2.tid;
|
||||
sample->pid = event->mmap2.pid;
|
||||
}
|
||||
print_sample_start(sample, thread, evsel);
|
||||
perf_event__fprintf(event, stdout);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void sig_handler(int sig __maybe_unused)
|
||||
{
|
||||
session_done = 1;
|
||||
|
|
@ -590,6 +772,17 @@ static int __cmd_script(struct perf_script *script)
|
|||
|
||||
signal(SIGINT, sig_handler);
|
||||
|
||||
/* override event processing functions */
|
||||
if (script->show_task_events) {
|
||||
script->tool.comm = process_comm_event;
|
||||
script->tool.fork = process_fork_event;
|
||||
script->tool.exit = process_exit_event;
|
||||
}
|
||||
if (script->show_mmap_events) {
|
||||
script->tool.mmap = process_mmap_event;
|
||||
script->tool.mmap2 = process_mmap2_event;
|
||||
}
|
||||
|
||||
ret = perf_session__process_events(script->session, &script->tool);
|
||||
|
||||
if (debug_mode)
|
||||
|
|
@ -1352,6 +1545,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
|
|||
"display extended information from perf.data file"),
|
||||
OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
|
||||
"Show the path of [kernel.kallsyms]"),
|
||||
OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
|
||||
"Show the fork/comm/exit events"),
|
||||
OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
|
||||
"Show the mmap events"),
|
||||
OPT_END()
|
||||
};
|
||||
const char * const script_usage[] = {
|
||||
|
|
|
|||
|
|
@ -41,6 +41,7 @@
|
|||
#define SUPPORT_OLD_POWER_EVENTS 1
|
||||
#define PWR_EVENT_EXIT -1
|
||||
|
||||
static int proc_num = 15;
|
||||
|
||||
static unsigned int numcpus;
|
||||
static u64 min_freq; /* Lowest CPU frequency seen */
|
||||
|
|
@ -50,16 +51,12 @@ static u64 turbo_frequency;
|
|||
static u64 first_time, last_time;
|
||||
|
||||
static bool power_only;
|
||||
static bool tasks_only;
|
||||
static bool with_backtrace;
|
||||
|
||||
|
||||
struct per_pid;
|
||||
struct per_pidcomm;
|
||||
|
||||
struct cpu_sample;
|
||||
struct power_event;
|
||||
struct wake_event;
|
||||
|
||||
struct sample_wrapper;
|
||||
|
||||
/*
|
||||
* Datastructure layout:
|
||||
|
|
@ -124,6 +121,7 @@ struct cpu_sample {
|
|||
u64 end_time;
|
||||
int type;
|
||||
int cpu;
|
||||
const char *backtrace;
|
||||
};
|
||||
|
||||
static struct per_pid *all_data;
|
||||
|
|
@ -145,12 +143,12 @@ struct wake_event {
|
|||
int waker;
|
||||
int wakee;
|
||||
u64 time;
|
||||
const char *backtrace;
|
||||
};
|
||||
|
||||
static struct power_event *power_events;
|
||||
static struct wake_event *wake_events;
|
||||
|
||||
struct process_filter;
|
||||
struct process_filter {
|
||||
char *name;
|
||||
int pid;
|
||||
|
|
@ -229,7 +227,8 @@ static void pid_exit(int pid, u64 timestamp)
|
|||
}
|
||||
|
||||
static void
|
||||
pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
|
||||
pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end,
|
||||
const char *backtrace)
|
||||
{
|
||||
struct per_pid *p;
|
||||
struct per_pidcomm *c;
|
||||
|
|
@ -252,6 +251,7 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
|
|||
sample->type = type;
|
||||
sample->next = c->samples;
|
||||
sample->cpu = cpu;
|
||||
sample->backtrace = backtrace;
|
||||
c->samples = sample;
|
||||
|
||||
if (sample->type == TYPE_RUNNING && end > start && start > 0) {
|
||||
|
|
@ -299,50 +299,10 @@ static int process_exit_event(struct perf_tool *tool __maybe_unused,
|
|||
return 0;
|
||||
}
|
||||
|
||||
struct trace_entry {
|
||||
unsigned short type;
|
||||
unsigned char flags;
|
||||
unsigned char preempt_count;
|
||||
int pid;
|
||||
int lock_depth;
|
||||
};
|
||||
|
||||
#ifdef SUPPORT_OLD_POWER_EVENTS
|
||||
static int use_old_power_events;
|
||||
struct power_entry_old {
|
||||
struct trace_entry te;
|
||||
u64 type;
|
||||
u64 value;
|
||||
u64 cpu_id;
|
||||
};
|
||||
#endif
|
||||
|
||||
struct power_processor_entry {
|
||||
struct trace_entry te;
|
||||
u32 state;
|
||||
u32 cpu_id;
|
||||
};
|
||||
|
||||
#define TASK_COMM_LEN 16
|
||||
struct wakeup_entry {
|
||||
struct trace_entry te;
|
||||
char comm[TASK_COMM_LEN];
|
||||
int pid;
|
||||
int prio;
|
||||
int success;
|
||||
};
|
||||
|
||||
struct sched_switch {
|
||||
struct trace_entry te;
|
||||
char prev_comm[TASK_COMM_LEN];
|
||||
int prev_pid;
|
||||
int prev_prio;
|
||||
long prev_state; /* Arjan weeps. */
|
||||
char next_comm[TASK_COMM_LEN];
|
||||
int next_pid;
|
||||
int next_prio;
|
||||
};
|
||||
|
||||
static void c_state_start(int cpu, u64 timestamp, int state)
|
||||
{
|
||||
cpus_cstate_start_times[cpu] = timestamp;
|
||||
|
|
@ -402,23 +362,23 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
|
|||
turbo_frequency = max_freq;
|
||||
}
|
||||
|
||||
static void
|
||||
sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
|
||||
static void sched_wakeup(int cpu, u64 timestamp, int waker, int wakee,
|
||||
u8 flags, const char *backtrace)
|
||||
{
|
||||
struct per_pid *p;
|
||||
struct wakeup_entry *wake = (void *)te;
|
||||
struct wake_event *we = zalloc(sizeof(*we));
|
||||
|
||||
if (!we)
|
||||
return;
|
||||
|
||||
we->time = timestamp;
|
||||
we->waker = pid;
|
||||
we->waker = waker;
|
||||
we->backtrace = backtrace;
|
||||
|
||||
if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
|
||||
if ((flags & TRACE_FLAG_HARDIRQ) || (flags & TRACE_FLAG_SOFTIRQ))
|
||||
we->waker = -1;
|
||||
|
||||
we->wakee = wake->pid;
|
||||
we->wakee = wakee;
|
||||
we->next = wake_events;
|
||||
wake_events = we;
|
||||
p = find_create_pid(we->wakee);
|
||||
|
|
@ -428,27 +388,31 @@ sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
|
|||
p->current->state = TYPE_WAITING;
|
||||
}
|
||||
if (p && p->current && p->current->state == TYPE_BLOCKED) {
|
||||
pid_put_sample(p->pid, p->current->state, cpu, p->current->state_since, timestamp);
|
||||
pid_put_sample(p->pid, p->current->state, cpu,
|
||||
p->current->state_since, timestamp, NULL);
|
||||
p->current->state_since = timestamp;
|
||||
p->current->state = TYPE_WAITING;
|
||||
}
|
||||
}
|
||||
|
||||
static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
|
||||
static void sched_switch(int cpu, u64 timestamp, int prev_pid, int next_pid,
|
||||
u64 prev_state, const char *backtrace)
|
||||
{
|
||||
struct per_pid *p = NULL, *prev_p;
|
||||
struct sched_switch *sw = (void *)te;
|
||||
|
||||
prev_p = find_create_pid(prev_pid);
|
||||
|
||||
prev_p = find_create_pid(sw->prev_pid);
|
||||
|
||||
p = find_create_pid(sw->next_pid);
|
||||
p = find_create_pid(next_pid);
|
||||
|
||||
if (prev_p->current && prev_p->current->state != TYPE_NONE)
|
||||
pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu, prev_p->current->state_since, timestamp);
|
||||
pid_put_sample(prev_pid, TYPE_RUNNING, cpu,
|
||||
prev_p->current->state_since, timestamp,
|
||||
backtrace);
|
||||
if (p && p->current) {
|
||||
if (p->current->state != TYPE_NONE)
|
||||
pid_put_sample(sw->next_pid, p->current->state, cpu, p->current->state_since, timestamp);
|
||||
pid_put_sample(next_pid, p->current->state, cpu,
|
||||
p->current->state_since, timestamp,
|
||||
backtrace);
|
||||
|
||||
p->current->state_since = timestamp;
|
||||
p->current->state = TYPE_RUNNING;
|
||||
|
|
@ -457,18 +421,97 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
|
|||
if (prev_p->current) {
|
||||
prev_p->current->state = TYPE_NONE;
|
||||
prev_p->current->state_since = timestamp;
|
||||
if (sw->prev_state & 2)
|
||||
if (prev_state & 2)
|
||||
prev_p->current->state = TYPE_BLOCKED;
|
||||
if (sw->prev_state == 0)
|
||||
if (prev_state == 0)
|
||||
prev_p->current->state = TYPE_WAITING;
|
||||
}
|
||||
}
|
||||
|
||||
static const char *cat_backtrace(union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct addr_location al;
|
||||
unsigned int i;
|
||||
char *p = NULL;
|
||||
size_t p_len;
|
||||
u8 cpumode = PERF_RECORD_MISC_USER;
|
||||
struct addr_location tal;
|
||||
struct ip_callchain *chain = sample->callchain;
|
||||
FILE *f = open_memstream(&p, &p_len);
|
||||
|
||||
if (!f) {
|
||||
perror("open_memstream error");
|
||||
return NULL;
|
||||
}
|
||||
|
||||
if (!chain)
|
||||
goto exit;
|
||||
|
||||
if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
|
||||
fprintf(stderr, "problem processing %d event, skipping it.\n",
|
||||
event->header.type);
|
||||
goto exit;
|
||||
}
|
||||
|
||||
for (i = 0; i < chain->nr; i++) {
|
||||
u64 ip;
|
||||
|
||||
if (callchain_param.order == ORDER_CALLEE)
|
||||
ip = chain->ips[i];
|
||||
else
|
||||
ip = chain->ips[chain->nr - i - 1];
|
||||
|
||||
if (ip >= PERF_CONTEXT_MAX) {
|
||||
switch (ip) {
|
||||
case PERF_CONTEXT_HV:
|
||||
cpumode = PERF_RECORD_MISC_HYPERVISOR;
|
||||
break;
|
||||
case PERF_CONTEXT_KERNEL:
|
||||
cpumode = PERF_RECORD_MISC_KERNEL;
|
||||
break;
|
||||
case PERF_CONTEXT_USER:
|
||||
cpumode = PERF_RECORD_MISC_USER;
|
||||
break;
|
||||
default:
|
||||
pr_debug("invalid callchain context: "
|
||||
"%"PRId64"\n", (s64) ip);
|
||||
|
||||
/*
|
||||
* It seems the callchain is corrupted.
|
||||
* Discard all.
|
||||
*/
|
||||
free(p);
|
||||
p = NULL;
|
||||
goto exit;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
tal.filtered = false;
|
||||
thread__find_addr_location(al.thread, machine, cpumode,
|
||||
MAP__FUNCTION, ip, &tal);
|
||||
|
||||
if (tal.sym)
|
||||
fprintf(f, "..... %016" PRIx64 " %s\n", ip,
|
||||
tal.sym->name);
|
||||
else
|
||||
fprintf(f, "..... %016" PRIx64 "\n", ip);
|
||||
}
|
||||
|
||||
exit:
|
||||
fclose(f);
|
||||
|
||||
return p;
|
||||
}
|
||||
|
||||
typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample);
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace);
|
||||
|
||||
static int process_sample_event(struct perf_tool *tool __maybe_unused,
|
||||
union perf_event *event __maybe_unused,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct perf_evsel *evsel,
|
||||
struct machine *machine __maybe_unused)
|
||||
|
|
@ -485,81 +528,97 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
|
|||
|
||||
if (evsel->handler != NULL) {
|
||||
tracepoint_handler f = evsel->handler;
|
||||
return f(evsel, sample);
|
||||
return f(evsel, sample, cat_backtrace(event, sample, machine));
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
process_sample_cpu_idle(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace __maybe_unused)
|
||||
{
|
||||
struct power_processor_entry *ppe = sample->raw_data;
|
||||
u32 state = perf_evsel__intval(evsel, sample, "state");
|
||||
u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
|
||||
|
||||
if (ppe->state == (u32) PWR_EVENT_EXIT)
|
||||
c_state_end(ppe->cpu_id, sample->time);
|
||||
if (state == (u32)PWR_EVENT_EXIT)
|
||||
c_state_end(cpu_id, sample->time);
|
||||
else
|
||||
c_state_start(ppe->cpu_id, sample->time, ppe->state);
|
||||
c_state_start(cpu_id, sample->time, state);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
process_sample_cpu_frequency(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace __maybe_unused)
|
||||
{
|
||||
struct power_processor_entry *ppe = sample->raw_data;
|
||||
u32 state = perf_evsel__intval(evsel, sample, "state");
|
||||
u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
|
||||
|
||||
p_state_change(ppe->cpu_id, sample->time, ppe->state);
|
||||
p_state_change(cpu_id, sample->time, state);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
process_sample_sched_wakeup(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace)
|
||||
{
|
||||
struct trace_entry *te = sample->raw_data;
|
||||
u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
|
||||
int waker = perf_evsel__intval(evsel, sample, "common_pid");
|
||||
int wakee = perf_evsel__intval(evsel, sample, "pid");
|
||||
|
||||
sched_wakeup(sample->cpu, sample->time, sample->pid, te);
|
||||
sched_wakeup(sample->cpu, sample->time, waker, wakee, flags, backtrace);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
process_sample_sched_switch(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace)
|
||||
{
|
||||
struct trace_entry *te = sample->raw_data;
|
||||
int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
|
||||
int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
|
||||
u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
|
||||
|
||||
sched_switch(sample->cpu, sample->time, te);
|
||||
sched_switch(sample->cpu, sample->time, prev_pid, next_pid, prev_state,
|
||||
backtrace);
|
||||
return 0;
|
||||
}
|
||||
|
||||
#ifdef SUPPORT_OLD_POWER_EVENTS
|
||||
static int
|
||||
process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
process_sample_power_start(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace __maybe_unused)
|
||||
{
|
||||
struct power_entry_old *peo = sample->raw_data;
|
||||
u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
|
||||
u64 value = perf_evsel__intval(evsel, sample, "value");
|
||||
|
||||
c_state_start(peo->cpu_id, sample->time, peo->value);
|
||||
c_state_start(cpu_id, sample->time, value);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace __maybe_unused)
|
||||
{
|
||||
c_state_end(sample->cpu, sample->time);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
|
||||
struct perf_sample *sample)
|
||||
process_sample_power_frequency(struct perf_evsel *evsel,
|
||||
struct perf_sample *sample,
|
||||
const char *backtrace __maybe_unused)
|
||||
{
|
||||
struct power_entry_old *peo = sample->raw_data;
|
||||
u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
|
||||
u64 value = perf_evsel__intval(evsel, sample, "value");
|
||||
|
||||
p_state_change(peo->cpu_id, sample->time, peo->value);
|
||||
p_state_change(cpu_id, sample->time, value);
|
||||
return 0;
|
||||
}
|
||||
#endif /* SUPPORT_OLD_POWER_EVENTS */
|
||||
|
|
@ -739,11 +798,12 @@ static void draw_wakeups(void)
|
|||
}
|
||||
|
||||
if (we->waker == -1)
|
||||
svg_interrupt(we->time, to);
|
||||
svg_interrupt(we->time, to, we->backtrace);
|
||||
else if (from && to && abs(from - to) == 1)
|
||||
svg_wakeline(we->time, from, to);
|
||||
svg_wakeline(we->time, from, to, we->backtrace);
|
||||
else
|
||||
svg_partial_wakeline(we->time, from, task_from, to, task_to);
|
||||
svg_partial_wakeline(we->time, from, task_from, to,
|
||||
task_to, we->backtrace);
|
||||
we = we->next;
|
||||
|
||||
free(task_from);
|
||||
|
|
@ -796,11 +856,20 @@ static void draw_process_bars(void)
|
|||
sample = c->samples;
|
||||
while (sample) {
|
||||
if (sample->type == TYPE_RUNNING)
|
||||
svg_sample(Y, sample->cpu, sample->start_time, sample->end_time);
|
||||
svg_running(Y, sample->cpu,
|
||||
sample->start_time,
|
||||
sample->end_time,
|
||||
sample->backtrace);
|
||||
if (sample->type == TYPE_BLOCKED)
|
||||
svg_box(Y, sample->start_time, sample->end_time, "blocked");
|
||||
svg_blocked(Y, sample->cpu,
|
||||
sample->start_time,
|
||||
sample->end_time,
|
||||
sample->backtrace);
|
||||
if (sample->type == TYPE_WAITING)
|
||||
svg_waiting(Y, sample->start_time, sample->end_time);
|
||||
svg_waiting(Y, sample->cpu,
|
||||
sample->start_time,
|
||||
sample->end_time,
|
||||
sample->backtrace);
|
||||
sample = sample->next;
|
||||
}
|
||||
|
||||
|
|
@ -911,7 +980,7 @@ static int determine_display_tasks(u64 threshold)
|
|||
/* no exit marker, task kept running to the end */
|
||||
if (p->end_time == 0)
|
||||
p->end_time = last_time;
|
||||
if (p->total_time >= threshold && !power_only)
|
||||
if (p->total_time >= threshold)
|
||||
p->display = 1;
|
||||
|
||||
c = p->all;
|
||||
|
|
@ -922,7 +991,7 @@ static int determine_display_tasks(u64 threshold)
|
|||
if (c->start_time == 1)
|
||||
c->start_time = first_time;
|
||||
|
||||
if (c->total_time >= threshold && !power_only) {
|
||||
if (c->total_time >= threshold) {
|
||||
c->display = 1;
|
||||
count++;
|
||||
}
|
||||
|
|
@ -945,15 +1014,19 @@ static void write_svg_file(const char *filename)
|
|||
{
|
||||
u64 i;
|
||||
int count;
|
||||
int thresh = TIME_THRESH;
|
||||
|
||||
numcpus++;
|
||||
|
||||
if (power_only)
|
||||
proc_num = 0;
|
||||
|
||||
count = determine_display_tasks(TIME_THRESH);
|
||||
|
||||
/* We'd like to show at least 15 tasks; be less picky if we have fewer */
|
||||
if (count < 15)
|
||||
count = determine_display_tasks(TIME_THRESH / 10);
|
||||
/* We'd like to show at least proc_num tasks;
|
||||
* be less picky if we have fewer */
|
||||
do {
|
||||
count = determine_display_tasks(thresh);
|
||||
thresh /= 10;
|
||||
} while (!process_filter && thresh && count < proc_num);
|
||||
|
||||
open_svg(filename, numcpus, count, first_time, last_time);
|
||||
|
||||
|
|
@ -964,9 +1037,12 @@ static void write_svg_file(const char *filename)
|
|||
svg_cpu_box(i, max_freq, turbo_frequency);
|
||||
|
||||
draw_cpu_usage();
|
||||
draw_process_bars();
|
||||
draw_c_p_states();
|
||||
draw_wakeups();
|
||||
if (proc_num)
|
||||
draw_process_bars();
|
||||
if (!tasks_only)
|
||||
draw_c_p_states();
|
||||
if (proc_num)
|
||||
draw_wakeups();
|
||||
|
||||
svg_close();
|
||||
}
|
||||
|
|
@ -1031,50 +1107,92 @@ out_delete:
|
|||
|
||||
static int __cmd_record(int argc, const char **argv)
|
||||
{
|
||||
#ifdef SUPPORT_OLD_POWER_EVENTS
|
||||
const char * const record_old_args[] = {
|
||||
unsigned int rec_argc, i, j;
|
||||
const char **rec_argv;
|
||||
const char **p;
|
||||
unsigned int record_elems;
|
||||
|
||||
const char * const common_args[] = {
|
||||
"record", "-a", "-R", "-c", "1",
|
||||
};
|
||||
unsigned int common_args_nr = ARRAY_SIZE(common_args);
|
||||
|
||||
const char * const backtrace_args[] = {
|
||||
"-g",
|
||||
};
|
||||
unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
|
||||
|
||||
const char * const power_args[] = {
|
||||
"-e", "power:cpu_frequency",
|
||||
"-e", "power:cpu_idle",
|
||||
};
|
||||
unsigned int power_args_nr = ARRAY_SIZE(power_args);
|
||||
|
||||
const char * const old_power_args[] = {
|
||||
#ifdef SUPPORT_OLD_POWER_EVENTS
|
||||
"-e", "power:power_start",
|
||||
"-e", "power:power_end",
|
||||
"-e", "power:power_frequency",
|
||||
"-e", "sched:sched_wakeup",
|
||||
"-e", "sched:sched_switch",
|
||||
};
|
||||
#endif
|
||||
const char * const record_new_args[] = {
|
||||
"record", "-a", "-R", "-c", "1",
|
||||
"-e", "power:cpu_frequency",
|
||||
"-e", "power:cpu_idle",
|
||||
};
|
||||
unsigned int old_power_args_nr = ARRAY_SIZE(old_power_args);
|
||||
|
||||
const char * const tasks_args[] = {
|
||||
"-e", "sched:sched_wakeup",
|
||||
"-e", "sched:sched_switch",
|
||||
};
|
||||
unsigned int rec_argc, i, j;
|
||||
const char **rec_argv;
|
||||
const char * const *record_args = record_new_args;
|
||||
unsigned int record_elems = ARRAY_SIZE(record_new_args);
|
||||
unsigned int tasks_args_nr = ARRAY_SIZE(tasks_args);
|
||||
|
||||
#ifdef SUPPORT_OLD_POWER_EVENTS
|
||||
if (!is_valid_tracepoint("power:cpu_idle") &&
|
||||
is_valid_tracepoint("power:power_start")) {
|
||||
use_old_power_events = 1;
|
||||
record_args = record_old_args;
|
||||
record_elems = ARRAY_SIZE(record_old_args);
|
||||
power_args_nr = 0;
|
||||
} else {
|
||||
old_power_args_nr = 0;
|
||||
}
|
||||
#endif
|
||||
|
||||
rec_argc = record_elems + argc - 1;
|
||||
if (power_only)
|
||||
tasks_args_nr = 0;
|
||||
|
||||
if (tasks_only) {
|
||||
power_args_nr = 0;
|
||||
old_power_args_nr = 0;
|
||||
}
|
||||
|
||||
if (!with_backtrace)
|
||||
backtrace_args_no = 0;
|
||||
|
||||
record_elems = common_args_nr + tasks_args_nr +
|
||||
power_args_nr + old_power_args_nr + backtrace_args_no;
|
||||
|
||||
rec_argc = record_elems + argc;
|
||||
rec_argv = calloc(rec_argc + 1, sizeof(char *));
|
||||
|
||||
if (rec_argv == NULL)
|
||||
return -ENOMEM;
|
||||
|
||||
for (i = 0; i < record_elems; i++)
|
||||
rec_argv[i] = strdup(record_args[i]);
|
||||
p = rec_argv;
|
||||
for (i = 0; i < common_args_nr; i++)
|
||||
*p++ = strdup(common_args[i]);
|
||||
|
||||
for (j = 1; j < (unsigned int)argc; j++, i++)
|
||||
rec_argv[i] = argv[j];
|
||||
for (i = 0; i < backtrace_args_no; i++)
|
||||
*p++ = strdup(backtrace_args[i]);
|
||||
|
||||
return cmd_record(i, rec_argv, NULL);
|
||||
for (i = 0; i < tasks_args_nr; i++)
|
||||
*p++ = strdup(tasks_args[i]);
|
||||
|
||||
for (i = 0; i < power_args_nr; i++)
|
||||
*p++ = strdup(power_args[i]);
|
||||
|
||||
for (i = 0; i < old_power_args_nr; i++)
|
||||
*p++ = strdup(old_power_args[i]);
|
||||
|
||||
for (j = 1; j < (unsigned int)argc; j++)
|
||||
*p++ = argv[j];
|
||||
|
||||
return cmd_record(rec_argc, rec_argv, NULL);
|
||||
}
|
||||
|
||||
static int
|
||||
|
|
@ -1090,16 +1208,20 @@ int cmd_timechart(int argc, const char **argv,
|
|||
const char *prefix __maybe_unused)
|
||||
{
|
||||
const char *output_name = "output.svg";
|
||||
const struct option options[] = {
|
||||
const struct option timechart_options[] = {
|
||||
OPT_STRING('i', "input", &input_name, "file", "input file name"),
|
||||
OPT_STRING('o', "output", &output_name, "file", "output file name"),
|
||||
OPT_INTEGER('w', "width", &svg_page_width, "page width"),
|
||||
OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
|
||||
OPT_BOOLEAN('T', "tasks-only", &tasks_only,
|
||||
"output processes data only"),
|
||||
OPT_CALLBACK('p', "process", NULL, "process",
|
||||
"process selector. Pass a pid or process name.",
|
||||
parse_process),
|
||||
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
|
||||
"Look for files with symbols relative to this directory"),
|
||||
OPT_INTEGER('n', "proc-num", &proc_num,
|
||||
"min. number of tasks to print"),
|
||||
OPT_END()
|
||||
};
|
||||
const char * const timechart_usage[] = {
|
||||
|
|
@ -1107,15 +1229,39 @@ int cmd_timechart(int argc, const char **argv,
|
|||
NULL
|
||||
};
|
||||
|
||||
argc = parse_options(argc, argv, options, timechart_usage,
|
||||
const struct option record_options[] = {
|
||||
OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
|
||||
OPT_BOOLEAN('T', "tasks-only", &tasks_only,
|
||||
"output processes data only"),
|
||||
OPT_BOOLEAN('g', "callchain", &with_backtrace, "record callchain"),
|
||||
OPT_END()
|
||||
};
|
||||
const char * const record_usage[] = {
|
||||
"perf timechart record [<options>]",
|
||||
NULL
|
||||
};
|
||||
argc = parse_options(argc, argv, timechart_options, timechart_usage,
|
||||
PARSE_OPT_STOP_AT_NON_OPTION);
|
||||
|
||||
if (power_only && tasks_only) {
|
||||
pr_err("-P and -T options cannot be used at the same time.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
symbol__init();
|
||||
|
||||
if (argc && !strncmp(argv[0], "rec", 3))
|
||||
if (argc && !strncmp(argv[0], "rec", 3)) {
|
||||
argc = parse_options(argc, argv, record_options, record_usage,
|
||||
PARSE_OPT_STOP_AT_NON_OPTION);
|
||||
|
||||
if (power_only && tasks_only) {
|
||||
pr_err("-P and -T options cannot be used at the same time.\n");
|
||||
return -1;
|
||||
}
|
||||
|
||||
return __cmd_record(argc, argv);
|
||||
else if (argc)
|
||||
usage_with_options(timechart_usage, options);
|
||||
} else if (argc)
|
||||
usage_with_options(timechart_usage, timechart_options);
|
||||
|
||||
setup_pager();
|
||||
|
||||
|
|
|
|||
|
|
@ -634,26 +634,9 @@ repeat:
|
|||
return NULL;
|
||||
}
|
||||
|
||||
/* Tag samples to be skipped. */
|
||||
static const char *skip_symbols[] = {
|
||||
"intel_idle",
|
||||
"default_idle",
|
||||
"native_safe_halt",
|
||||
"cpu_idle",
|
||||
"enter_idle",
|
||||
"exit_idle",
|
||||
"mwait_idle",
|
||||
"mwait_idle_with_hints",
|
||||
"poll_idle",
|
||||
"ppc64_runlatch_off",
|
||||
"pseries_dedicated_idle_sleep",
|
||||
NULL
|
||||
};
|
||||
|
||||
static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
|
||||
{
|
||||
const char *name = sym->name;
|
||||
int i;
|
||||
|
||||
/*
|
||||
* ppc64 uses function descriptors and appends a '.' to the
|
||||
|
|
@ -671,12 +654,8 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
|
|||
strstr(name, "_text_end"))
|
||||
return 1;
|
||||
|
||||
for (i = 0; skip_symbols[i]; i++) {
|
||||
if (!strcmp(skip_symbols[i], name)) {
|
||||
sym->ignore = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (symbol__is_idle(sym))
|
||||
sym->ignore = true;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -1084,7 +1063,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
|
|||
"dump the symbol table used for profiling"),
|
||||
OPT_INTEGER('f', "count-filter", &top.count_filter,
|
||||
"only display functions with more events than this"),
|
||||
OPT_BOOLEAN('g', "group", &opts->group,
|
||||
OPT_BOOLEAN(0, "group", &opts->group,
|
||||
"put the counters into a counter group"),
|
||||
OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
|
||||
"child tasks do not inherit counters"),
|
||||
|
|
@ -1105,7 +1084,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
|
|||
" abort, in_tx, transaction"),
|
||||
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
|
||||
"Show a column with the number of samples"),
|
||||
OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
|
||||
OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
|
||||
NULL, "enables call-graph recording",
|
||||
&callchain_opt),
|
||||
OPT_CALLBACK(0, "call-graph", &top.record_opts,
|
||||
|
|
|
|||
|
|
@ -2158,7 +2158,6 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
|
|||
size_t printed = data->printed;
|
||||
struct trace *trace = data->trace;
|
||||
struct thread_trace *ttrace = thread->priv;
|
||||
const char *color;
|
||||
double ratio;
|
||||
|
||||
if (ttrace == NULL)
|
||||
|
|
@ -2166,17 +2165,9 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
|
|||
|
||||
ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
|
||||
|
||||
color = PERF_COLOR_NORMAL;
|
||||
if (ratio > 50.0)
|
||||
color = PERF_COLOR_RED;
|
||||
else if (ratio > 25.0)
|
||||
color = PERF_COLOR_GREEN;
|
||||
else if (ratio > 5.0)
|
||||
color = PERF_COLOR_YELLOW;
|
||||
|
||||
printed += color_fprintf(fp, color, " %s (%d), ", thread__comm_str(thread), thread->tid);
|
||||
printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
|
||||
printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
|
||||
printed += color_fprintf(fp, color, "%.1f%%", ratio);
|
||||
printed += fprintf(fp, "%.1f%%", ratio);
|
||||
printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
|
||||
printed += thread__dump_stats(ttrace, trace, fp);
|
||||
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
# perf completion
|
||||
# perf bash and zsh completion
|
||||
|
||||
# Taken from git.git's completion script.
|
||||
__my_reassemble_comp_words_by_ref()
|
||||
|
|
@ -89,37 +89,113 @@ __ltrim_colon_completions()
|
|||
fi
|
||||
}
|
||||
|
||||
type perf &>/dev/null &&
|
||||
_perf()
|
||||
__perfcomp ()
|
||||
{
|
||||
local cur words cword prev cmd
|
||||
COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
|
||||
}
|
||||
|
||||
COMPREPLY=()
|
||||
_get_comp_words_by_ref -n =: cur words cword prev
|
||||
__perfcomp_colon ()
|
||||
{
|
||||
__perfcomp "$1" "$2"
|
||||
__ltrim_colon_completions $cur
|
||||
}
|
||||
|
||||
__perf_main ()
|
||||
{
|
||||
local cmd
|
||||
|
||||
cmd=${words[0]}
|
||||
COMPREPLY=()
|
||||
|
||||
# List perf subcommands or long options
|
||||
if [ $cword -eq 1 ]; then
|
||||
if [[ $cur == --* ]]; then
|
||||
COMPREPLY=( $( compgen -W '--help --version \
|
||||
__perfcomp '--help --version \
|
||||
--exec-path --html-path --paginate --no-pager \
|
||||
--perf-dir --work-tree --debugfs-dir' -- "$cur" ) )
|
||||
--perf-dir --work-tree --debugfs-dir' -- "$cur"
|
||||
else
|
||||
cmds=$($cmd --list-cmds)
|
||||
COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
|
||||
__perfcomp "$cmds" "$cur"
|
||||
fi
|
||||
# List possible events for -e option
|
||||
elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
|
||||
evts=$($cmd list --raw-dump)
|
||||
COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
|
||||
__ltrim_colon_completions $cur
|
||||
__perfcomp_colon "$evts" "$cur"
|
||||
# List long option names
|
||||
elif [[ $cur == --* ]]; then
|
||||
subcmd=${words[1]}
|
||||
opts=$($cmd $subcmd --list-opts)
|
||||
COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
|
||||
__perfcomp "$opts" "$cur"
|
||||
fi
|
||||
}
|
||||
|
||||
if [[ -n ${ZSH_VERSION-} ]]; then
|
||||
autoload -U +X compinit && compinit
|
||||
|
||||
__perfcomp ()
|
||||
{
|
||||
emulate -L zsh
|
||||
|
||||
local c IFS=$' \t\n'
|
||||
local -a array
|
||||
|
||||
for c in ${=1}; do
|
||||
case $c in
|
||||
--*=*|*.) ;;
|
||||
*) c="$c " ;;
|
||||
esac
|
||||
array[${#array[@]}+1]="$c"
|
||||
done
|
||||
|
||||
compset -P '*[=:]'
|
||||
compadd -Q -S '' -a -- array && _ret=0
|
||||
}
|
||||
|
||||
__perfcomp_colon ()
|
||||
{
|
||||
emulate -L zsh
|
||||
|
||||
local cur_="${2-$cur}"
|
||||
local c IFS=$' \t\n'
|
||||
local -a array
|
||||
|
||||
if [[ "$cur_" == *:* ]]; then
|
||||
local colon_word=${cur_%"${cur_##*:}"}
|
||||
fi
|
||||
|
||||
for c in ${=1}; do
|
||||
case $c in
|
||||
--*=*|*.) ;;
|
||||
*) c="$c " ;;
|
||||
esac
|
||||
array[$#array+1]=${c#"$colon_word"}
|
||||
done
|
||||
|
||||
compset -P '*[=:]'
|
||||
compadd -Q -S '' -a -- array && _ret=0
|
||||
}
|
||||
|
||||
_perf ()
|
||||
{
|
||||
local _ret=1 cur cword prev
|
||||
cur=${words[CURRENT]}
|
||||
prev=${words[CURRENT-1]}
|
||||
let cword=CURRENT-1
|
||||
emulate ksh -c __perf_main
|
||||
let _ret && _default && _ret=0
|
||||
return _ret
|
||||
}
|
||||
|
||||
compdef _perf perf
|
||||
return
|
||||
fi
|
||||
|
||||
type perf &>/dev/null &&
|
||||
_perf()
|
||||
{
|
||||
local cur words cword prev
|
||||
_get_comp_words_by_ref -n =: cur words cword prev
|
||||
__perf_main
|
||||
} &&
|
||||
|
||||
complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
|
||||
|
|
@ -254,6 +254,7 @@ struct perf_record_opts {
|
|||
bool inherit_stat;
|
||||
bool no_delay;
|
||||
bool no_inherit;
|
||||
bool no_inherit_set;
|
||||
bool no_samples;
|
||||
bool raw_samples;
|
||||
bool sample_address;
|
||||
|
|
|
|||
|
|
@ -3,5 +3,5 @@ command = record
|
|||
args = -i kill >/dev/null 2>&1
|
||||
|
||||
[event:base-record]
|
||||
sample_type=259
|
||||
sample_type=263
|
||||
inherit=0
|
||||
|
|
|
|||
|
|
@ -732,8 +732,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
|
|||
if (thread == NULL)
|
||||
return -1;
|
||||
|
||||
if (symbol_conf.comm_list &&
|
||||
!strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread)))
|
||||
if (thread__is_filtered(thread))
|
||||
goto out_filtered;
|
||||
|
||||
dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
|
||||
|
|
|
|||
|
|
@ -819,8 +819,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
|
|||
if (evlist->threads == NULL)
|
||||
return -1;
|
||||
|
||||
if (target->force_per_cpu)
|
||||
evlist->cpus = cpu_map__new(target->cpu_list);
|
||||
if (target->default_per_cpu)
|
||||
evlist->cpus = target->per_thread ?
|
||||
cpu_map__dummy_new() :
|
||||
cpu_map__new(target->cpu_list);
|
||||
else if (target__has_task(target))
|
||||
evlist->cpus = cpu_map__dummy_new();
|
||||
else if (!target__has_cpu(target) && !target->uses_mmap)
|
||||
|
|
|
|||
|
|
@ -574,6 +574,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
|
|||
struct perf_evsel *leader = evsel->leader;
|
||||
struct perf_event_attr *attr = &evsel->attr;
|
||||
int track = !evsel->idx; /* only the first counter needs these */
|
||||
bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
|
||||
|
||||
attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
|
||||
attr->inherit = !opts->no_inherit;
|
||||
|
|
@ -647,7 +648,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
|
|||
}
|
||||
}
|
||||
|
||||
if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
|
||||
if (target__has_cpu(&opts->target))
|
||||
perf_evsel__set_sample_bit(evsel, CPU);
|
||||
|
||||
if (opts->period)
|
||||
|
|
@ -655,7 +656,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
|
|||
|
||||
if (!perf_missing_features.sample_id_all &&
|
||||
(opts->sample_time || !opts->no_inherit ||
|
||||
target__has_cpu(&opts->target) || opts->target.force_per_cpu))
|
||||
target__has_cpu(&opts->target) || per_cpu))
|
||||
perf_evsel__set_sample_bit(evsel, TIME);
|
||||
|
||||
if (opts->raw_samples) {
|
||||
|
|
|
|||
|
|
@ -78,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p,
|
|||
|
||||
case OPTION_BOOLEAN:
|
||||
*(bool *)opt->value = unset ? false : true;
|
||||
if (opt->set)
|
||||
*(bool *)opt->set = true;
|
||||
return 0;
|
||||
|
||||
case OPTION_INCR:
|
||||
|
|
@ -224,6 +226,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
|
|||
return 0;
|
||||
}
|
||||
if (!rest) {
|
||||
if (!prefixcmp(options->long_name, "no-")) {
|
||||
/*
|
||||
* The long name itself starts with "no-", so
|
||||
* accept the option without "no-" so that users
|
||||
* do not have to enter "no-no-" to get the
|
||||
* negation.
|
||||
*/
|
||||
rest = skip_prefix(arg, options->long_name + 3);
|
||||
if (rest) {
|
||||
flags |= OPT_UNSET;
|
||||
goto match;
|
||||
}
|
||||
/* Abbreviated case */
|
||||
if (!prefixcmp(options->long_name + 3, arg)) {
|
||||
flags |= OPT_UNSET;
|
||||
goto is_abbreviated;
|
||||
}
|
||||
}
|
||||
/* abbreviated? */
|
||||
if (!strncmp(options->long_name, arg, arg_end - arg)) {
|
||||
is_abbreviated:
|
||||
|
|
@ -259,6 +279,7 @@ is_abbreviated:
|
|||
if (!rest)
|
||||
continue;
|
||||
}
|
||||
match:
|
||||
if (*rest) {
|
||||
if (*rest != '=')
|
||||
continue;
|
||||
|
|
|
|||
|
|
@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
|
|||
* OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
|
||||
* the value when met.
|
||||
* CALLBACKS can use it like they want.
|
||||
*
|
||||
* `set`::
|
||||
* whether an option was set by the user
|
||||
*/
|
||||
struct option {
|
||||
enum parse_opt_type type;
|
||||
|
|
@ -94,6 +97,7 @@ struct option {
|
|||
int flags;
|
||||
parse_opt_cb *callback;
|
||||
intptr_t defval;
|
||||
bool *set;
|
||||
};
|
||||
|
||||
#define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
|
||||
|
|
@ -103,6 +107,10 @@ struct option {
|
|||
#define OPT_GROUP(h) { .type = OPTION_GROUP, .help = (h) }
|
||||
#define OPT_BIT(s, l, v, h, b) { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
|
||||
#define OPT_BOOLEAN(s, l, v, h) { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
|
||||
#define OPT_BOOLEAN_SET(s, l, v, os, h) \
|
||||
{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
|
||||
.value = check_vtype(v, bool *), .help = (h), \
|
||||
.set = check_vtype(os, bool *)}
|
||||
#define OPT_INCR(s, l, v, h) { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
|
||||
#define OPT_SET_UINT(s, l, v, h, i) { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
|
||||
#define OPT_SET_PTR(s, l, v, h, p) { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
|
||||
|
|
|
|||
|
|
@ -1522,6 +1522,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
|
|||
if (!node)
|
||||
break;
|
||||
|
||||
if (node->sym && node->sym->ignore)
|
||||
goto next;
|
||||
|
||||
if (print_ip)
|
||||
printf("%c%16" PRIx64, s, node->ip);
|
||||
|
||||
|
|
@ -1544,12 +1547,15 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
|
|||
if (!print_oneline)
|
||||
printf("\n");
|
||||
|
||||
callchain_cursor_advance(&callchain_cursor);
|
||||
|
||||
stack_depth--;
|
||||
next:
|
||||
callchain_cursor_advance(&callchain_cursor);
|
||||
}
|
||||
|
||||
} else {
|
||||
if (al.sym && al.sym->ignore)
|
||||
return;
|
||||
|
||||
if (print_ip)
|
||||
printf("%16" PRIx64, sample->ip);
|
||||
|
||||
|
|
|
|||
|
|
@ -95,6 +95,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
|
|||
|
||||
total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
|
||||
fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
|
||||
fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n");
|
||||
fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
|
||||
|
||||
fprintf(svgfile, "<defs>\n <style type=\"text/css\">\n <![CDATA[\n");
|
||||
|
|
@ -128,12 +129,33 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
|
|||
time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
|
||||
}
|
||||
|
||||
void svg_sample(int Yslot, int cpu, u64 start, u64 end)
|
||||
static char *time_to_string(u64 duration);
|
||||
void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
|
||||
{
|
||||
if (!svgfile)
|
||||
return;
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
|
||||
time_to_string(end - start));
|
||||
if (backtrace)
|
||||
fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace);
|
||||
svg_box(Yslot, start, end, "blocked");
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
|
||||
{
|
||||
double text_size;
|
||||
if (!svgfile)
|
||||
return;
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
fprintf(svgfile, "<title>#%d running %s</title>\n",
|
||||
cpu, time_to_string(end - start));
|
||||
if (backtrace)
|
||||
fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
|
||||
fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
|
||||
time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
|
||||
|
||||
|
|
@ -148,6 +170,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end)
|
|||
fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
|
||||
time2pixels(start), Yslot * SLOT_MULT + SLOT_HEIGHT - 1, text_size, cpu + 1);
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
static char *time_to_string(u64 duration)
|
||||
|
|
@ -168,7 +191,7 @@ static char *time_to_string(u64 duration)
|
|||
return text;
|
||||
}
|
||||
|
||||
void svg_waiting(int Yslot, u64 start, u64 end)
|
||||
void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
|
||||
{
|
||||
char *text;
|
||||
const char *style;
|
||||
|
|
@ -192,6 +215,9 @@ void svg_waiting(int Yslot, u64 start, u64 end)
|
|||
font_size = round_text_size(font_size);
|
||||
|
||||
fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
|
||||
fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
|
||||
if (backtrace)
|
||||
fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
|
||||
fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
|
||||
time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
|
||||
if (font_size > MIN_TEXT_SIZE)
|
||||
|
|
@ -242,6 +268,8 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
|
|||
max_freq = __max_freq;
|
||||
turbo_frequency = __turbo_freq;
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
|
||||
time2pixels(first_time),
|
||||
time2pixels(last_time)-time2pixels(first_time),
|
||||
|
|
@ -253,6 +281,8 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
|
|||
|
||||
fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
|
||||
10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
|
||||
|
|
@ -264,6 +294,7 @@ void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name
|
|||
|
||||
|
||||
fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
|
||||
fprintf(svgfile, "<title>%s %s</title>\n", name, time_to_string(end - start));
|
||||
fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
|
||||
time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
|
||||
width = time2pixels(end)-time2pixels(start);
|
||||
|
|
@ -288,6 +319,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
|
|||
return;
|
||||
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
if (type > 6)
|
||||
type = 6;
|
||||
sprintf(style, "c%i", type);
|
||||
|
|
@ -306,6 +339,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
|
|||
if (width > MIN_TEXT_SIZE)
|
||||
fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
|
||||
time2pixels(start), cpu2y(cpu)+width, width, type);
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
static char *HzToHuman(unsigned long hz)
|
||||
|
|
@ -339,6 +374,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
|
|||
if (!svgfile)
|
||||
return;
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
if (max_freq)
|
||||
height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
|
||||
height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
|
||||
|
|
@ -347,10 +384,11 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
|
|||
fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
|
||||
time2pixels(start), height+0.9, HzToHuman(freq));
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
|
||||
void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2)
|
||||
void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace)
|
||||
{
|
||||
double height;
|
||||
|
||||
|
|
@ -358,6 +396,15 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
|
|||
return;
|
||||
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
fprintf(svgfile, "<title>%s wakes up %s</title>\n",
|
||||
desc1 ? desc1 : "?",
|
||||
desc2 ? desc2 : "?");
|
||||
|
||||
if (backtrace)
|
||||
fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
|
||||
|
||||
if (row1 < row2) {
|
||||
if (row1) {
|
||||
fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
|
||||
|
|
@ -395,9 +442,11 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
|
|||
if (row1)
|
||||
fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n",
|
||||
time2pixels(start), height);
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
void svg_wakeline(u64 start, int row1, int row2)
|
||||
void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
|
||||
{
|
||||
double height;
|
||||
|
||||
|
|
@ -405,6 +454,11 @@ void svg_wakeline(u64 start, int row1, int row2)
|
|||
return;
|
||||
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
if (backtrace)
|
||||
fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
|
||||
|
||||
if (row1 < row2)
|
||||
fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
|
||||
time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT, time2pixels(start), row2 * SLOT_MULT);
|
||||
|
|
@ -417,17 +471,28 @@ void svg_wakeline(u64 start, int row1, int row2)
|
|||
height += SLOT_HEIGHT;
|
||||
fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(32,255,32)\"/>\n",
|
||||
time2pixels(start), height);
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
void svg_interrupt(u64 start, int row)
|
||||
void svg_interrupt(u64 start, int row, const char *backtrace)
|
||||
{
|
||||
if (!svgfile)
|
||||
return;
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
|
||||
fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
|
||||
|
||||
if (backtrace)
|
||||
fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
|
||||
|
||||
fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n",
|
||||
time2pixels(start), row * SLOT_MULT);
|
||||
fprintf(svgfile, "<circle cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\" style=\"fill:rgb(255,128,128)\"/>\n",
|
||||
time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
|
||||
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
void svg_text(int Yslot, u64 start, const char *text)
|
||||
|
|
@ -455,6 +520,7 @@ void svg_legenda(void)
|
|||
if (!svgfile)
|
||||
return;
|
||||
|
||||
fprintf(svgfile, "<g>\n");
|
||||
svg_legenda_box(0, "Running", "sample");
|
||||
svg_legenda_box(100, "Idle","c1");
|
||||
svg_legenda_box(200, "Deeper Idle", "c3");
|
||||
|
|
@ -462,6 +528,7 @@ void svg_legenda(void)
|
|||
svg_legenda_box(550, "Sleeping", "process2");
|
||||
svg_legenda_box(650, "Waiting for cpu", "waiting");
|
||||
svg_legenda_box(800, "Blocked on IO", "blocked");
|
||||
fprintf(svgfile, "</g>\n");
|
||||
}
|
||||
|
||||
void svg_time_grid(void)
|
||||
|
|
|
|||
|
|
@ -5,8 +5,9 @@
|
|||
|
||||
extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
|
||||
extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
|
||||
extern void svg_sample(int Yslot, int cpu, u64 start, u64 end);
|
||||
extern void svg_waiting(int Yslot, u64 start, u64 end);
|
||||
extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
|
||||
extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
|
||||
extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
|
||||
extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
|
||||
|
||||
|
||||
|
|
@ -17,9 +18,9 @@ extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
|
|||
|
||||
extern void svg_time_grid(void);
|
||||
extern void svg_legenda(void);
|
||||
extern void svg_wakeline(u64 start, int row1, int row2);
|
||||
extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2);
|
||||
extern void svg_interrupt(u64 start, int row);
|
||||
extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
|
||||
extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
|
||||
extern void svg_interrupt(u64 start, int row, const char *backtrace);
|
||||
extern void svg_text(int Yslot, u64 start, const char *text);
|
||||
extern void svg_close(void);
|
||||
|
||||
|
|
|
|||
|
|
@ -573,6 +573,36 @@ static u8 kallsyms2elf_type(char type)
|
|||
return isupper(type) ? STB_GLOBAL : STB_LOCAL;
|
||||
}
|
||||
|
||||
bool symbol__is_idle(struct symbol *sym)
|
||||
{
|
||||
const char * const idle_symbols[] = {
|
||||
"cpu_idle",
|
||||
"intel_idle",
|
||||
"default_idle",
|
||||
"native_safe_halt",
|
||||
"enter_idle",
|
||||
"exit_idle",
|
||||
"mwait_idle",
|
||||
"mwait_idle_with_hints",
|
||||
"poll_idle",
|
||||
"ppc64_runlatch_off",
|
||||
"pseries_dedicated_idle_sleep",
|
||||
NULL
|
||||
};
|
||||
|
||||
int i;
|
||||
|
||||
if (!sym)
|
||||
return false;
|
||||
|
||||
for (i = 0; idle_symbols[i]; i++) {
|
||||
if (!strcmp(idle_symbols[i], sym->name))
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
static int map__process_kallsym_symbol(void *arg, const char *name,
|
||||
char type, u64 start)
|
||||
{
|
||||
|
|
@ -1496,14 +1526,15 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
|
|||
|
||||
build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
|
||||
|
||||
scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
|
||||
sbuild_id);
|
||||
|
||||
/* Use /proc/kallsyms if possible */
|
||||
if (is_host) {
|
||||
DIR *d;
|
||||
int fd;
|
||||
|
||||
/* If no cached kcore go with /proc/kallsyms */
|
||||
scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
|
||||
buildid_dir, sbuild_id);
|
||||
d = opendir(path);
|
||||
if (!d)
|
||||
goto proc_kallsyms;
|
||||
|
|
@ -1528,6 +1559,10 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
|
|||
goto proc_kallsyms;
|
||||
}
|
||||
|
||||
/* Find kallsyms in build-id cache with kcore */
|
||||
if (!find_matching_kcore(map, path, sizeof(path)))
|
||||
return strdup(path);
|
||||
|
||||
scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
|
||||
buildid_dir, sbuild_id);
|
||||
|
||||
|
|
@ -1719,7 +1754,7 @@ out_fail:
|
|||
return -1;
|
||||
}
|
||||
|
||||
static int setup_list(struct strlist **list, const char *list_str,
|
||||
int setup_list(struct strlist **list, const char *list_str,
|
||||
const char *list_name)
|
||||
{
|
||||
if (list_str == NULL)
|
||||
|
|
|
|||
|
|
@ -240,6 +240,7 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
|
|||
bool symbol_type__is_a(char symbol_type, enum map_type map_type);
|
||||
bool symbol__restricted_filename(const char *filename,
|
||||
const char *restricted_filename);
|
||||
bool symbol__is_idle(struct symbol *sym);
|
||||
|
||||
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
|
||||
struct symsrc *runtime_ss, symbol_filter_t filter,
|
||||
|
|
@ -273,4 +274,7 @@ void kcore_extract__delete(struct kcore_extract *kce);
|
|||
int kcore_copy(const char *from_dir, const char *to_dir);
|
||||
int compare_proc_modules(const char *from, const char *to);
|
||||
|
||||
int setup_list(struct strlist **list, const char *list_str,
|
||||
const char *list_name);
|
||||
|
||||
#endif /* __PERF_SYMBOL */
|
||||
|
|
|
|||
|
|
@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
|
|||
ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
|
||||
}
|
||||
|
||||
/* THREAD and SYSTEM/CPU are mutually exclusive */
|
||||
if (target->per_thread && (target->system_wide || target->cpu_list)) {
|
||||
target->per_thread = false;
|
||||
if (ret == TARGET_ERRNO__SUCCESS)
|
||||
ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
|
@ -100,6 +107,7 @@ static const char *target__error_str[] = {
|
|||
"UID switch overriding CPU",
|
||||
"PID/TID switch overriding SYSTEM",
|
||||
"UID switch overriding SYSTEM",
|
||||
"SYSTEM/CPU switch overriding PER-THREAD",
|
||||
"Invalid User: %s",
|
||||
"Problems obtaining information for user %s",
|
||||
};
|
||||
|
|
@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
|
|||
msg = target__error_str[idx];
|
||||
|
||||
switch (errnum) {
|
||||
case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
|
||||
case TARGET_ERRNO__PID_OVERRIDE_CPU ...
|
||||
TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
|
||||
snprintf(buf, buflen, "%s", msg);
|
||||
break;
|
||||
|
||||
|
|
|
|||
|
|
@ -12,7 +12,8 @@ struct target {
|
|||
uid_t uid;
|
||||
bool system_wide;
|
||||
bool uses_mmap;
|
||||
bool force_per_cpu;
|
||||
bool default_per_cpu;
|
||||
bool per_thread;
|
||||
};
|
||||
|
||||
enum target_errno {
|
||||
|
|
@ -33,6 +34,7 @@ enum target_errno {
|
|||
TARGET_ERRNO__UID_OVERRIDE_CPU,
|
||||
TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
|
||||
TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
|
||||
TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
|
||||
|
||||
/* for target__parse_uid() */
|
||||
TARGET_ERRNO__INVALID_UID,
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@
|
|||
#include <unistd.h>
|
||||
#include <sys/types.h>
|
||||
#include "symbol.h"
|
||||
#include <strlist.h>
|
||||
|
||||
struct thread {
|
||||
union {
|
||||
|
|
@ -66,4 +67,15 @@ static inline void thread__set_priv(struct thread *thread, void *p)
|
|||
{
|
||||
thread->priv = p;
|
||||
}
|
||||
|
||||
static inline bool thread__is_filtered(struct thread *thread)
|
||||
{
|
||||
if (symbol_conf.comm_list &&
|
||||
!strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
#endif /* __PERF_THREAD_H */
|
||||
|
|
|
|||
Loading…
Reference in New Issue