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.
The 'weight' field is shared among different architectures. Reusing the
'weight' field may impacts other architectures. Add a new field to store
the instruction latency.
Like the 'weight' support, introduce a 'ins_lat' for the global
instruction latency, and a 'local_ins_lat' for the local instruction
latency version.
Add new sort functions, INSTR Latency and Local INSTR Latency,
accordingly.
Add local_ins_lat to the default_mem_sort_order[].
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-7-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
- time: Separate the samples by time stamp with the resolution specified by
--time-quantum (default 100ms). Specify with overhead and before it.
- code_page_size: the code page size of sampled code address (ip)
+ - ins_lat: Instruction latency in core cycles. This is the global instruction
+ latency
+ - local_ins_lat: Local instruction latency version
By default, comm, dso and symbol keys are used.
(i.e. --sort comm,dso,symbol)
- blocked: reason of blocked load access for the data at the time of the sample
And the default sort keys are changed to local_weight, mem, sym, dso,
- symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, see '--mem-mode'.
+ symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, local_ins_lat,
+ see '--mem-mode'.
If the data file has tracepoint event(s), following (dynamic) sort keys
are also available:
u16 insn_len;
u8 cpumode;
u16 misc;
+ u16 ins_lat;
bool no_hw_idx; /* No hw_idx collected in branch_stack */
char insn[MAX_INSN];
void *raw_data;
weight.full = *array;
if (type & PERF_SAMPLE_WEIGHT)
data->weight = weight.full;
- else
+ else {
data->weight = weight.var1_dw;
+ data->ins_lat = weight.var2_w;
+ }
array++;
}
hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
+ hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
+ hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
if (symbol_conf.nanosecs)
hists__new_col_len(hists, HISTC_TIME, 16);
else
}
static void he_stat__add_period(struct he_stat *he_stat, u64 period,
- u64 weight)
+ u64 weight, u64 ins_lat)
{
he_stat->period += period;
he_stat->weight += weight;
he_stat->nr_events += 1;
+ he_stat->ins_lat += ins_lat;
}
static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
dest->period_guest_us += src->period_guest_us;
dest->nr_events += src->nr_events;
dest->weight += src->weight;
+ dest->ins_lat += src->ins_lat;
}
static void he_stat__decay(struct he_stat *he_stat)
int64_t cmp;
u64 period = entry->stat.period;
u64 weight = entry->stat.weight;
+ u64 ins_lat = entry->stat.ins_lat;
bool leftmost = true;
p = &hists->entries_in->rb_root.rb_node;
if (!cmp) {
if (sample_self) {
- he_stat__add_period(&he->stat, period, weight);
+ he_stat__add_period(&he->stat, period, weight, ins_lat);
hist_entry__add_callchain_period(he, period);
}
if (symbol_conf.cumulate_callchain)
- he_stat__add_period(he->stat_acc, period, weight);
+ he_stat__add_period(he->stat_acc, period, weight, ins_lat);
/*
* This mem info was allocated from sample__resolve_mem
.nr_events = 1,
.period = sample->period,
.weight = sample->weight,
+ .ins_lat = sample->ins_lat,
},
.parent = sym_parent,
.filtered = symbol__parent_filter(sym_parent) | al->filtered,
HISTC_DSO_SIZE,
HISTC_SYMBOL_IPC,
HISTC_MEM_BLOCKED,
+ HISTC_LOCAL_INS_LAT,
+ HISTC_GLOBAL_INS_LAT,
HISTC_NR_COLS, /* Last entry */
};
* cycles. Use latency >> 32 to distinguish the
* different format of the mem access latency field.
*/
- if (weight > 0)
+ if (weight > 0) {
sample.weight = weight & 0xffff;
- else
+ sample.ins_lat = items->mem_access_latency & 0xffff;
+ } else
sample.weight = items->mem_access_latency;
}
if (!sample.weight && items->has_tsx_aux_info) {
if (sample_type & PERF_SAMPLE_STACK_USER)
stack_user__printf(&sample->user_stack);
- if (sample_type & PERF_SAMPLE_WEIGHT_TYPE)
- printf("... weight: %" PRIu64 "\n", sample->weight);
+ if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
+ printf("... weight: %" PRIu64 "", sample->weight);
+ if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT)
+ printf(",0x%"PRIx16"", sample->ins_lat);
+ printf("\n");
+ }
if (sample_type & PERF_SAMPLE_DATA_SRC)
printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
const char *parent_pattern = default_parent_pattern;
const char *default_sort_order = "comm,dso,symbol";
const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
-const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked";
+const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat";
const char default_top_sort_order[] = "dso,symbol";
const char default_diff_sort_order[] = "dso,symbol";
const char default_tracepoint_sort_order[] = "trace";
.se_width_idx = HISTC_GLOBAL_WEIGHT,
};
+static u64 he_ins_lat(struct hist_entry *he)
+{
+ return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0;
+}
+
+static int64_t
+sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return he_ins_lat(left) - he_ins_lat(right);
+}
+
+static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he));
+}
+
+struct sort_entry sort_local_ins_lat = {
+ .se_header = "Local INSTR Latency",
+ .se_cmp = sort__local_ins_lat_cmp,
+ .se_snprintf = hist_entry__local_ins_lat_snprintf,
+ .se_width_idx = HISTC_LOCAL_INS_LAT,
+};
+
+static int64_t
+sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return left->stat.ins_lat - right->stat.ins_lat;
+}
+
+static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat);
+}
+
+struct sort_entry sort_global_ins_lat = {
+ .se_header = "INSTR Latency",
+ .se_cmp = sort__global_ins_lat_cmp,
+ .se_snprintf = hist_entry__global_ins_lat_snprintf,
+ .se_width_idx = HISTC_GLOBAL_INS_LAT,
+};
+
struct sort_entry sort_mem_daddr_sym = {
.se_header = "Data Symbol",
.se_cmp = sort__daddr_cmp,
DIM(SORT_SYM_IPC_NULL, "ipc_null", sort_sym_ipc_null),
DIM(SORT_TIME, "time", sort_time),
DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
+ DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
+ DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
};
#undef DIM
u64 period_guest_sys;
u64 period_guest_us;
u64 weight;
+ u64 ins_lat;
u32 nr_events;
};
SORT_SYM_IPC_NULL,
SORT_TIME,
SORT_CODE_PAGE_SIZE,
+ SORT_LOCAL_INS_LAT,
+ SORT_GLOBAL_INS_LAT,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
if (type & PERF_SAMPLE_WEIGHT_TYPE) {
*array = sample->weight;
- if (type & PERF_SAMPLE_WEIGHT_STRUCT)
+ if (type & PERF_SAMPLE_WEIGHT_STRUCT) {
*array &= 0xffffffff;
+ *array |= ((u64)sample->ins_lat << 32);
+ }
array++;
}