User space tasks can migrate between CPUs, we need to track side-band
events for all CPUs.
The specific scenarios are as follows:
CPU0 CPU1
perf record -C 0 start
taskA starts to be created and executed
-> PERF_RECORD_COMM and PERF_RECORD_MMAP
events only deliver to CPU1
......
|
migrate to CPU0
|
Running on CPU0 <----------/
...
perf record -C 0 stop
Now perf samples the PC of taskA. However, perf does not record the
PERF_RECORD_COMM and PERF_RECORD_MMAP events of taskA.
Therefore, the comm and symbols of taskA cannot be parsed.
The solution is to record sideband events for all CPUs when tracing
selected CPUs. Because this modifies the default behavior, add related
comments to the perf record man page.
The sys_perf_event_open invoked is as follows:
# perf --debug verbose=3 record -e cpu-clock -C 1 true
<SNIP>
Opening: cpu-clock
------------------------------------------------------------
perf_event_attr:
type 1 (PERF_TYPE_SOFTWARE)
size 136
config 0 (PERF_COUNT_SW_CPU_CLOCK)
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|CPU|PERIOD|IDENTIFIER
read_format ID|LOST
disabled 1
inherit 1
freq 1
sample_id_all 1
exclude_guest 1
------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8 = 5
Opening: dummy:u
------------------------------------------------------------
perf_event_attr:
type 1 (PERF_TYPE_SOFTWARE)
size 136
config 0x9 (PERF_COUNT_SW_DUMMY)
{ sample_period, sample_freq } 1
sample_type IP|TID|TIME|CPU|IDENTIFIER
read_format ID|LOST
inherit 1
exclude_kernel 1
exclude_hv 1
mmap 1
comm 1
task 1
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 6
sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8 = 7
sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8 = 9
sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8 = 10
sys_perf_event_open: pid -1 cpu 4 group_fd -1 flags 0x8 = 11
sys_perf_event_open: pid -1 cpu 5 group_fd -1 flags 0x8 = 12
sys_perf_event_open: pid -1 cpu 6 group_fd -1 flags 0x8 = 13
sys_perf_event_open: pid -1 cpu 7 group_fd -1 flags 0x8 = 14
<SNIP>
Signed-off-by: Yang Jihong <[email protected]>
---
tools/perf/Documentation/perf-record.txt | 3 +++
tools/perf/builtin-record.c | 30 +++++++++++++++++++++++-
2 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d5217be012d7..1889f66addf2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -374,6 +374,9 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-
In per-thread mode with inheritance mode on (default), samples are captured only when
the thread executes on the designated CPUs. Default is to monitor all CPUs.
+User space tasks can migrate between CPUs, so when tracing selected CPUs,
+a dummy event is created to track sideband for all CPUs.
+
-B::
--no-buildid::
Do not save the build ids of binaries in the perf.data files. This skips
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 83bd1f117191..dcf288a4fb9a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -906,10 +906,30 @@ static int record__config_off_cpu(struct record *rec)
return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts);
}
+static bool record__tracking_system_wide(struct record *rec)
+{
+ struct evlist *evlist = rec->evlist;
+ struct evsel *evsel;
+
+ /*
+ * If non-dummy evsel exists, system_wide sideband is need to
+ * help parse sample information.
+ * For example, PERF_EVENT_MMAP event to help parse symbol,
+ * and PERF_EVENT_COMM event to help parse task executable name.
+ */
+ evlist__for_each_entry(evlist, evsel) {
+ if (!evsel__is_dummy_event(evsel))
+ return true;
+ }
+
+ return false;
+}
+
static int record__config_tracking_events(struct record *rec)
{
struct record_opts *opts = &rec->opts;
struct evlist *evlist = rec->evlist;
+ bool system_wide = false;
struct evsel *evsel;
/*
@@ -919,7 +939,15 @@ static int record__config_tracking_events(struct record *rec)
*/
if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
perf_pmus__num_core_pmus() > 1) {
- evsel = evlist__findnew_tracking_event(evlist, false);
+
+ /*
+ * User space tasks can migrate between CPUs, so when tracing
+ * selected CPUs, sideband for all CPUs is still needed.
+ */
+ if (!!opts->target.cpu_list && record__tracking_system_wide(rec))
+ system_wide = true;
+
+ evsel = evlist__findnew_tracking_event(evlist, system_wide);
if (!evsel)
return -ENOMEM;
--
2.30.GIT