perf script: Support instruction latency
The instruction latency information can be recorded on some platforms, e.g., the Intel Sapphire Rapids server. With both memory latency (weight) and the new instruction latency information, users can easily locate the expensive load instructions, and also understand the time spent in different stages. The users can optimize their applications in different pipeline stages. Add a new field "ins_lat" to filter the instruction latency information, which is available with sample type PERF_SAMPLE_WEIGHT_STRUCT. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Joe Mario <jmario@redhat.com> Link: https://lore.kernel.org/r/1632929894-102778-2-git-send-email-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
57d7ecfd11
commit
6ea5d1a3e3
|
@ -130,7 +130,7 @@ OPTIONS
|
|||
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
|
||||
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
|
||||
brstackinsn, brstackoff, callindent, insn, insnlen, synth, phys_addr,
|
||||
metric, misc, srccode, ipc, data_page_size, code_page_size.
|
||||
metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat.
|
||||
Field list can be prepended with the type, trace, sw or hw,
|
||||
to indicate to which event type the field list applies.
|
||||
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
|
||||
|
|
|
@ -122,6 +122,7 @@ enum perf_output_field {
|
|||
PERF_OUTPUT_TOD = 1ULL << 32,
|
||||
PERF_OUTPUT_DATA_PAGE_SIZE = 1ULL << 33,
|
||||
PERF_OUTPUT_CODE_PAGE_SIZE = 1ULL << 34,
|
||||
PERF_OUTPUT_INS_LAT = 1ULL << 35,
|
||||
};
|
||||
|
||||
struct perf_script {
|
||||
|
@ -188,6 +189,7 @@ struct output_option {
|
|||
{.str = "tod", .field = PERF_OUTPUT_TOD},
|
||||
{.str = "data_page_size", .field = PERF_OUTPUT_DATA_PAGE_SIZE},
|
||||
{.str = "code_page_size", .field = PERF_OUTPUT_CODE_PAGE_SIZE},
|
||||
{.str = "ins_lat", .field = PERF_OUTPUT_INS_LAT},
|
||||
};
|
||||
|
||||
enum {
|
||||
|
@ -262,7 +264,8 @@ static struct {
|
|||
PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
|
||||
PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
|
||||
PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR |
|
||||
PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE,
|
||||
PERF_OUTPUT_DATA_PAGE_SIZE | PERF_OUTPUT_CODE_PAGE_SIZE |
|
||||
PERF_OUTPUT_INS_LAT,
|
||||
|
||||
.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
|
||||
},
|
||||
|
@ -522,6 +525,10 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
|
|||
evsel__check_stype(evsel, PERF_SAMPLE_CODE_PAGE_SIZE, "CODE_PAGE_SIZE", PERF_OUTPUT_CODE_PAGE_SIZE))
|
||||
return -EINVAL;
|
||||
|
||||
if (PRINT_FIELD(INS_LAT) &&
|
||||
evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_STRUCT, "WEIGHT_STRUCT", PERF_OUTPUT_INS_LAT))
|
||||
return -EINVAL;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
@ -2039,6 +2046,9 @@ static void process_event(struct perf_script *script,
|
|||
if (PRINT_FIELD(WEIGHT))
|
||||
fprintf(fp, "%16" PRIu64, sample->weight);
|
||||
|
||||
if (PRINT_FIELD(INS_LAT))
|
||||
fprintf(fp, "%16" PRIu16, sample->ins_lat);
|
||||
|
||||
if (PRINT_FIELD(IP)) {
|
||||
struct callchain_cursor *cursor = NULL;
|
||||
|
||||
|
@ -3715,7 +3725,7 @@ int cmd_script(int argc, const char **argv)
|
|||
"addr,symoff,srcline,period,iregs,uregs,brstack,"
|
||||
"brstacksym,flags,bpf-output,brstackinsn,brstackoff,"
|
||||
"callindent,insn,insnlen,synth,phys_addr,metric,misc,ipc,tod,"
|
||||
"data_page_size,code_page_size",
|
||||
"data_page_size,code_page_size,ins_lat",
|
||||
parse_output_fields),
|
||||
OPT_BOOLEAN('a', "all-cpus", &system_wide,
|
||||
"system-wide collection from all CPUs"),
|
||||
|
|
Loading…
Reference in New Issue