On systems with many CPUs, recording extra context switch events can be
excessive and unnecessary. Add perf config intel-pt.all-switch-events=false
to control the behaviour.
Example:
# perf config intel-pt.all-switch-events=false
# perf record -eintel_pt//u uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.082 MB perf.data ]
# perf script -D | grep PERF_RECORD_SWITCH | awk '{print $5}' | uniq -c
5 PERF_RECORD_SWITCH
# perf config intel-pt.all-switch-events=true
# perf record -eintel_pt//u uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.102 MB perf.data ]
# perf script -D | grep PERF_RECORD_SWITCH | awk '{print $5}' | uniq -c
180 PERF_RECORD_SWITCH_CPU_WIDE
Committer testing:
While doing a make -j28 allmodconfig:
root@five:~# grep "model name" -m1 /proc/cpuinfo
model name : Intel(R) Core(TM) i7-14700K
root@five:~#
root@five:~# perf config intel-pt.all-switch-events=false
root@five:~# perf record -e intel_pt//u uname
Linux
[ perf record: Woken up 2 times to write data ]
[ perf record: Captured and wrote 0.019 MB perf.data ]
root@five:~# perf report --stats | grep SWITCH_CPU_WIDE
root@five:~#
root@five:~# perf config intel-pt.all-switch-events=true
root@five:~# perf record -e intel_pt//u uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.047 MB perf.data ]
root@five:~# perf report --stats | grep SWITCH_CPU_WIDE
SWITCH_CPU_WIDE events: 542 (96.4%)
root@five:~#
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250512093932.79854-3-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
the maximum is exceeded there will be a "Never-ending loop"
error. The default is 100000.
+ intel-pt.all-switch-events::
+ If the user has permission to do so, always record all context
+ switch events on all CPUs.
+
auxtrace.*::
auxtrace.dumpdir::
#include "../../../util/evlist.h"
#include "../../../util/evsel.h"
#include "../../../util/evsel_config.h"
+#include "../../../util/config.h"
#include "../../../util/cpumap.h"
#include "../../../util/mmap.h"
#include <subcmd/parse-options.h>
struct perf_pmu *intel_pt_pmu;
int have_sched_switch;
struct evlist *evlist;
+ bool all_switch_events;
bool snapshot_mode;
bool snapshot_init_done;
size_t snapshot_size;
bool cpu_wide = !target__none(&opts->target) &&
!target__has_task(&opts->target);
- if (!cpu_wide && perf_can_record_cpu_wide()) {
+ if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) {
struct evsel *switch_evsel;
switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
return rdtsc();
}
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+ struct intel_pt_recording *ptr = data;
+
+ if (!strcmp(var, "intel-pt.all-switch-events"))
+ ptr->all_switch_events = perf_config_bool(var, value);
+
+ return 0;
+}
+
struct auxtrace_record *intel_pt_recording_init(int *err)
{
struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
return NULL;
}
+ perf_config(intel_pt_perf_config, ptr);
+
ptr->intel_pt_pmu = intel_pt_pmu;
ptr->itr.recording_options = intel_pt_recording_options;
ptr->itr.info_priv_size = intel_pt_info_priv_size;