提交 1e181b92 编写于 作者: J Jiri Olsa 提交者: Arnaldo Carvalho de Melo

perf c2c report: Add 'node' sort key

It is to be displayed in the single cacheline output:

  node

It displays nodes hits related to cacheline accesses.

The node filed comes in 3 flavors:
  - node IDs separated by ','
  - node IDs with stats for each ID, in following format:
      Node{cpus %hitms %stores}
  - node IDs with list of affected CPUs in following format:
      Node{cpu list}

User can switch the flavor with -N option (-NN,-NNN).
It will be available in TUI to switch this with 'n' key.
Signed-off-by: NJiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-6742e6g0r7n63y5wc4rrgxx5@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
上级 51dedaa4
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/stringify.h>
#include <asm/bug.h>
#include "util.h"
#include "debug.h"
#include "builtin.h"
......@@ -22,6 +23,8 @@ struct c2c_hists {
struct c2c_hist_entry {
struct c2c_hists *hists;
struct c2c_stats stats;
unsigned long *cpuset;
struct c2c_stats *node_stats;
/*
* must be at the end,
* because of its callchain dynamic entry
......@@ -32,6 +35,12 @@ struct c2c_hist_entry {
struct perf_c2c {
struct perf_tool tool;
struct c2c_hists hists;
unsigned long **nodes;
int nodes_cnt;
int cpus_cnt;
int *cpu2node;
int node_info;
};
static struct perf_c2c c2c;
......@@ -44,6 +53,14 @@ static void *c2c_he_zalloc(size_t size)
if (!c2c_he)
return NULL;
c2c_he->cpuset = bitmap_alloc(c2c.cpus_cnt);
if (!c2c_he->cpuset)
return NULL;
c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));
if (!c2c_he->node_stats)
return NULL;
return &c2c_he->he;
}
......@@ -57,6 +74,8 @@ static void c2c_he_free(void *he)
free(c2c_he->hists);
}
free(c2c_he->cpuset);
free(c2c_he->node_stats);
free(c2c_he);
}
......@@ -93,6 +112,16 @@ he__get_c2c_hists(struct hist_entry *he,
return hists;
}
static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he,
struct perf_sample *sample)
{
if (WARN_ONCE(sample->cpu == (unsigned int) -1,
"WARNING: no sample cpu value"))
return;
set_bit(sample->cpu, c2c_he->cpuset);
}
static int process_sample_event(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
......@@ -133,10 +162,23 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
c2c_add_stats(&c2c_he->stats, &stats);
c2c_add_stats(&c2c_hists->stats, &stats);
c2c_he__set_cpu(c2c_he, sample);
hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
ret = hist_entry__append_callchain(he, sample);
if (!ret) {
/*
* There's already been warning about missing
* sample's cpu value. Let's account all to
* node 0 in this case, without any further
* warning.
*
* Doing node stats only for single callchain data.
*/
int cpu = sample->cpu == (unsigned int) -1 ? 0 : sample->cpu;
int node = c2c.cpu2node[cpu];
mi = mi_dup;
mi_dup = memdup(mi, sizeof(*mi));
......@@ -156,6 +198,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
c2c_he = container_of(he, struct c2c_hist_entry, he);
c2c_add_stats(&c2c_he->stats, &stats);
c2c_add_stats(&c2c_hists->stats, &stats);
c2c_add_stats(&c2c_he->node_stats[node], &stats);
c2c_he__set_cpu(c2c_he, sample);
hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
ret = hist_entry__append_callchain(he, sample);
......@@ -826,6 +871,97 @@ pid_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
return left->thread->pid_ - right->thread->pid_;
}
static int64_t
empty_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
struct hist_entry *left __maybe_unused,
struct hist_entry *right __maybe_unused)
{
return 0;
}
static int
node_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
struct hist_entry *he)
{
struct c2c_hist_entry *c2c_he;
bool first = true;
int node;
int ret = 0;
c2c_he = container_of(he, struct c2c_hist_entry, he);
for (node = 0; node < c2c.nodes_cnt; node++) {
DECLARE_BITMAP(set, c2c.cpus_cnt);
bitmap_zero(set, c2c.cpus_cnt);
bitmap_and(set, c2c_he->cpuset, c2c.nodes[node], c2c.cpus_cnt);
if (!bitmap_weight(set, c2c.cpus_cnt)) {
if (c2c.node_info == 1) {
ret = scnprintf(hpp->buf, hpp->size, "%21s", " ");
advance_hpp(hpp, ret);
}
continue;
}
if (!first) {
ret = scnprintf(hpp->buf, hpp->size, " ");
advance_hpp(hpp, ret);
}
switch (c2c.node_info) {
case 0:
ret = scnprintf(hpp->buf, hpp->size, "%2d", node);
advance_hpp(hpp, ret);
break;
case 1:
{
int num = bitmap_weight(c2c_he->cpuset, c2c.cpus_cnt);
struct c2c_stats *stats = &c2c_he->node_stats[node];
ret = scnprintf(hpp->buf, hpp->size, "%2d{%2d ", node, num);
advance_hpp(hpp, ret);
if (c2c_he->stats.rmt_hitm > 0) {
ret = scnprintf(hpp->buf, hpp->size, "%5.1f%% ",
percent(stats->rmt_hitm, c2c_he->stats.rmt_hitm));
} else {
ret = scnprintf(hpp->buf, hpp->size, "%6s ", "n/a");
}
advance_hpp(hpp, ret);
if (c2c_he->stats.store > 0) {
ret = scnprintf(hpp->buf, hpp->size, "%5.1f%%}",
percent(stats->store, c2c_he->stats.store));
} else {
ret = scnprintf(hpp->buf, hpp->size, "%6s}", "n/a");
}
advance_hpp(hpp, ret);
break;
}
case 2:
ret = scnprintf(hpp->buf, hpp->size, "%2d{", node);
advance_hpp(hpp, ret);
ret = bitmap_scnprintf(set, c2c.cpus_cnt, hpp->buf, hpp->size);
advance_hpp(hpp, ret);
ret = scnprintf(hpp->buf, hpp->size, "}");
advance_hpp(hpp, ret);
break;
default:
break;
}
first = false;
}
return 0;
}
#define HEADER_LOW(__h) \
{ \
.line[1] = { \
......@@ -1115,6 +1251,19 @@ static struct c2c_dimension dim_dso = {
.se = &sort_dso,
};
static struct c2c_header header_node[3] = {
HEADER_LOW("Node"),
HEADER_LOW("Node{cpus %hitms %stores}"),
HEADER_LOW("Node{cpu list}"),
};
static struct c2c_dimension dim_node = {
.name = "node",
.cmp = empty_cmp,
.entry = node_entry,
.width = 4,
};
static struct c2c_dimension *dimensions[] = {
&dim_dcacheline,
&dim_offset,
......@@ -1148,6 +1297,7 @@ static struct c2c_dimension *dimensions[] = {
&dim_tid,
&dim_symbol,
&dim_dso,
&dim_node,
NULL,
};
......@@ -1374,6 +1524,68 @@ static int resort_cl_cb(struct hist_entry *he)
return 0;
}
static void setup_nodes_header(void)
{
dim_node.header = header_node[c2c.node_info];
}
static int setup_nodes(struct perf_session *session)
{
struct numa_node *n;
unsigned long **nodes;
int node, cpu;
int *cpu2node;
if (c2c.node_info > 2)
c2c.node_info = 2;
c2c.nodes_cnt = session->header.env.nr_numa_nodes;
c2c.cpus_cnt = session->header.env.nr_cpus_online;
n = session->header.env.numa_nodes;
if (!n)
return -EINVAL;
nodes = zalloc(sizeof(unsigned long *) * c2c.nodes_cnt);
if (!nodes)
return -ENOMEM;
c2c.nodes = nodes;
cpu2node = zalloc(sizeof(int) * c2c.cpus_cnt);
if (!cpu2node)
return -ENOMEM;
for (cpu = 0; cpu < c2c.cpus_cnt; cpu++)
cpu2node[cpu] = -1;
c2c.cpu2node = cpu2node;
for (node = 0; node < c2c.nodes_cnt; node++) {
struct cpu_map *map = n[node].map;
unsigned long *set;
set = bitmap_alloc(c2c.cpus_cnt);
if (!set)
return -ENOMEM;
for (cpu = 0; cpu < map->nr; cpu++) {
set_bit(map->map[cpu], set);
if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug"))
return -EINVAL;
cpu2node[map->map[cpu]] = node;
}
nodes[node] = set;
}
setup_nodes_header();
return 0;
}
static int perf_c2c__report(int argc, const char **argv)
{
struct perf_session *session;
......@@ -1388,6 +1600,8 @@ static int perf_c2c__report(int argc, const char **argv)
"be more verbose (show counter open errors, etc)"),
OPT_STRING('i', "input", &input_name, "file",
"the input file to process"),
OPT_INCR('N', "node-info", &c2c.node_info,
"show extra node info in report (repeat for more info)"),
OPT_END()
};
int err = 0;
......@@ -1413,6 +1627,11 @@ static int perf_c2c__report(int argc, const char **argv)
pr_debug("No memory for session\n");
goto out;
}
err = setup_nodes(session);
if (err) {
pr_err("Failed setup nodes\n");
goto out;
}
if (symbol__init(&session->header.env) < 0)
goto out_session;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册