kernel_optimize_test/tools/perf/ui/stdio/hist.c

814 lines
19 KiB
C
Raw Normal View History

#include <stdio.h>
#include "../../util/util.h"
#include "../../util/hist.h"
#include "../../util/sort.h"
#include "../../util/evsel.h"
static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
{
int i;
int ret = fprintf(fp, " ");
for (i = 0; i < left_margin; i++)
ret += fprintf(fp, " ");
return ret;
}
static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
int left_margin)
{
int i;
size_t ret = callchain__fprintf_left_margin(fp, left_margin);
for (i = 0; i < depth; i++)
if (depth_mask & (1 << i))
ret += fprintf(fp, "| ");
else
ret += fprintf(fp, " ");
ret += fprintf(fp, "\n");
return ret;
}
static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
struct callchain_list *chain,
int depth, int depth_mask, int period,
u64 total_samples, int left_margin)
{
int i;
size_t ret = 0;
char bf[1024];
ret += callchain__fprintf_left_margin(fp, left_margin);
for (i = 0; i < depth; i++) {
if (depth_mask & (1 << i))
ret += fprintf(fp, "|");
else
ret += fprintf(fp, " ");
if (!period && i == depth - 1) {
ret += fprintf(fp, "--");
ret += callchain_node__fprintf_value(node, fp, total_samples);
ret += fprintf(fp, "--");
} else
ret += fprintf(fp, "%s", " ");
}
fputs(callchain_list__sym_name(chain, bf, sizeof(bf), false), fp);
fputc('\n', fp);
return ret;
}
static struct symbol *rem_sq_bracket;
static struct callchain_list rem_hits;
static void init_rem_hits(void)
{
rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
if (!rem_sq_bracket) {
fprintf(stderr, "Not enough memory to display remaining hits\n");
return;
}
strcpy(rem_sq_bracket->name, "[...]");
rem_hits.ms.sym = rem_sq_bracket;
}
static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
u64 total_samples, int depth,
int depth_mask, int left_margin)
{
struct rb_node *node, *next;
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:41 +08:00
struct callchain_node *child = NULL;
struct callchain_list *chain;
int new_depth_mask = depth_mask;
u64 remaining;
size_t ret = 0;
int i;
uint entries_printed = 0;
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:41 +08:00
int cumul_count = 0;
remaining = total_samples;
node = rb_first(root);
while (node) {
u64 new_total;
u64 cumul;
child = rb_entry(node, struct callchain_node, rb_node);
cumul = callchain_cumul_hits(child);
remaining -= cumul;
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:41 +08:00
cumul_count += callchain_cumul_counts(child);
/*
* The depth mask manages the output of pipes that show
* the depth. We don't want to keep the pipes of the current
* level for the last child of this depth.
* Except if we have remaining filtered hits. They will
* supersede the last child
*/
next = rb_next(node);
if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
new_depth_mask &= ~(1 << (depth - 1));
/*
* But we keep the older depth mask for the line separator
* to keep the level link until we reach the last child
*/
ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
left_margin);
i = 0;
list_for_each_entry(chain, &child->val, list) {
ret += ipchain__fprintf_graph(fp, child, chain, depth,
new_depth_mask, i++,
total_samples,
left_margin);
}
if (callchain_param.mode == CHAIN_GRAPH_REL)
new_total = child->children_hit;
else
new_total = total_samples;
ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
depth + 1,
new_depth_mask | (1 << depth),
left_margin);
node = next;
if (++entries_printed == callchain_param.print_limit)
break;
}
if (callchain_param.mode == CHAIN_GRAPH_REL &&
remaining && remaining != total_samples) {
struct callchain_node rem_node = {
.hit = remaining,
};
if (!rem_sq_bracket)
return ret;
perf report: Add callchain value option Now -g/--call-graph option supports how to display callchain values. Possible values are 'percent', 'period' and 'count'. The percent is same as before and it's the default behavior. The period displays the raw period value rather than the percentage. The count displays the number of occurrences. $ perf report --no-children --stdio -g percent ... 39.93% swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--28.63%-- start_secondary | --11.30%-- rest_init $ perf report --no-children --show-total-period --stdio -g period ... 39.93% 13018705 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--9334403-- start_secondary | --3684302-- rest_init $ perf report --no-children --show-nr-samples --stdio -g count ... 39.93% 80 swapper [kernel.vmlinux] [k] intel_idel | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--57-- start_secondary | --23-- rest_init Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:41 +08:00
if (callchain_param.value == CCVAL_COUNT && child && child->parent) {
rem_node.count = child->parent->children_count - cumul_count;
if (rem_node.count <= 0)
return ret;
}
new_depth_mask &= ~(1 << (depth - 1));
ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth,
new_depth_mask, 0, total_samples,
left_margin);
}
return ret;
}
perf report: Fix percent display in callchains on --stdio When there's only a single callchain, perf doesn't print its percentage in front of the symbols. This is because it assumes that the percentage is same as parents. But if a percent limit is applied, it's possible that there are actually a couple of child nodes but only one of them is shown. In this case it should display the percent to prevent misunderstanding of its percentage is same as the parent's. For example, let's see the following callchain. $ perf report -s comm --percent-limit 0.01 --stdio ... 9.95% swapper | |--7.57%--intel_idle | cpuidle_enter_state | cpuidle_enter | call_cpuidle | cpu_startup_entry | | | |--4.89%--start_secondary | | | --2.68%--rest_init | start_kernel | x86_64_start_reservations | x86_64_start_kernel | |--0.15%--__schedule | | | |--0.13%--schedule | | schedule_preempt_disable | | cpu_startup_entry | | | | | |--0.09%--start_secondary | | | | | --0.04%--rest_init | | start_kernel | | x86_64_start_reservations | | x86_64_start_kernel | | | --0.01%--schedule_preempt_disabled | cpu_startup_entry ... Current code omits the percent if 'intel_idle' becomes the only node when percent limit is set to 0.5%, its percent is not 9.95% but users will assume it incorrectly. Before: $ perf report --percent-limit 0.5 --stdio ... 9.95% swapper | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--4.89%--start_secondary | --2.68%--rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report --percent-limit 0.5 --stdio ... 9.95% swapper | --7.57%--intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--4.89%--start_secondary | --2.68%--rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1453909257-26015-7-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-01-27 23:40:53 +08:00
/*
* If have one single callchain root, don't bother printing
* its percentage (100 % in fractal mode and the same percentage
* than the hist in graph mode). This also avoid one level of column.
*
* However when percent-limit applied, it's possible that single callchain
* node have different (non-100% in fractal mode) percentage.
*/
static bool need_percent_display(struct rb_node *node, u64 parent_samples)
{
struct callchain_node *cnode;
if (rb_next(node))
return true;
cnode = rb_entry(node, struct callchain_node, rb_node);
return callchain_cumul_hits(cnode) != parent_samples;
}
static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
u64 total_samples, u64 parent_samples,
int left_margin)
{
struct callchain_node *cnode;
struct callchain_list *chain;
u32 entries_printed = 0;
bool printed = false;
struct rb_node *node;
int i = 0;
int ret = 0;
char bf[1024];
node = rb_first(root);
perf report: Fix percent display in callchains on --stdio When there's only a single callchain, perf doesn't print its percentage in front of the symbols. This is because it assumes that the percentage is same as parents. But if a percent limit is applied, it's possible that there are actually a couple of child nodes but only one of them is shown. In this case it should display the percent to prevent misunderstanding of its percentage is same as the parent's. For example, let's see the following callchain. $ perf report -s comm --percent-limit 0.01 --stdio ... 9.95% swapper | |--7.57%--intel_idle | cpuidle_enter_state | cpuidle_enter | call_cpuidle | cpu_startup_entry | | | |--4.89%--start_secondary | | | --2.68%--rest_init | start_kernel | x86_64_start_reservations | x86_64_start_kernel | |--0.15%--__schedule | | | |--0.13%--schedule | | schedule_preempt_disable | | cpu_startup_entry | | | | | |--0.09%--start_secondary | | | | | --0.04%--rest_init | | start_kernel | | x86_64_start_reservations | | x86_64_start_kernel | | | --0.01%--schedule_preempt_disabled | cpu_startup_entry ... Current code omits the percent if 'intel_idle' becomes the only node when percent limit is set to 0.5%, its percent is not 9.95% but users will assume it incorrectly. Before: $ perf report --percent-limit 0.5 --stdio ... 9.95% swapper | ---intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--4.89%--start_secondary | --2.68%--rest_init start_kernel x86_64_start_reservations x86_64_start_kernel After: $ perf report --percent-limit 0.5 --stdio ... 9.95% swapper | --7.57%--intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry | |--4.89%--start_secondary | --2.68%--rest_init start_kernel x86_64_start_reservations x86_64_start_kernel Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1453909257-26015-7-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-01-27 23:40:53 +08:00
if (node && !need_percent_display(node, parent_samples)) {
cnode = rb_entry(node, struct callchain_node, rb_node);
list_for_each_entry(chain, &cnode->val, list) {
/*
* If we sort by symbol, the first entry is the same than
* the symbol. No need to print it otherwise it appears as
* displayed twice.
*/
if (!i++ && field_order == NULL &&
sort_order && !prefixcmp(sort_order, "sym"))
continue;
if (!printed) {
ret += callchain__fprintf_left_margin(fp, left_margin);
ret += fprintf(fp, "|\n");
ret += callchain__fprintf_left_margin(fp, left_margin);
ret += fprintf(fp, "---");
left_margin += 3;
printed = true;
} else
ret += callchain__fprintf_left_margin(fp, left_margin);
ret += fprintf(fp, "%s\n", callchain_list__sym_name(chain, bf, sizeof(bf),
false));
if (++entries_printed == callchain_param.print_limit)
break;
}
root = &cnode->rb_root;
}
if (callchain_param.mode == CHAIN_GRAPH_REL)
total_samples = parent_samples;
ret += __callchain__fprintf_graph(fp, root, total_samples,
1, 1, left_margin);
if (ret) {
/* do not add a blank line if it printed nothing */
ret += fprintf(fp, "\n");
}
return ret;
}
static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node,
u64 total_samples)
{
struct callchain_list *chain;
size_t ret = 0;
char bf[1024];
if (!node)
return 0;
ret += __callchain__fprintf_flat(fp, node->parent, total_samples);
list_for_each_entry(chain, &node->val, list) {
if (chain->ip >= PERF_CONTEXT_MAX)
continue;
ret += fprintf(fp, " %s\n", callchain_list__sym_name(chain,
bf, sizeof(bf), false));
}
return ret;
}
static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree,
u64 total_samples)
{
size_t ret = 0;
u32 entries_printed = 0;
struct callchain_node *chain;
struct rb_node *rb_node = rb_first(tree);
while (rb_node) {
chain = rb_entry(rb_node, struct callchain_node, rb_node);
ret += fprintf(fp, " ");
ret += callchain_node__fprintf_value(chain, fp, total_samples);
ret += fprintf(fp, "\n");
ret += __callchain__fprintf_flat(fp, chain, total_samples);
ret += fprintf(fp, "\n");
if (++entries_printed == callchain_param.print_limit)
break;
rb_node = rb_next(rb_node);
}
return ret;
}
perf report: Support folded callchain mode on --stdio Add new call chain option (-g) 'folded' to print callchains in a line. The callchains are separated by semicolons, and preceded by (absolute) percent values and a space. For example, the following 20 lines can be printed in 3 lines with the folded output mode: $ perf report -g flat --no-children | grep -v ^# | head -20 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary 5.88% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry rest_init start_kernel x86_64_start_reservations x86_64_start_kernel $ perf report -g folded --no-children | grep -v ^# | head -3 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.88% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel This mode is supported only for --stdio now and intended to be used by some scripts like in FlameGraphs[1]. Support for other UI might be added later. [1] http://www.brendangregg.com/FlameGraphs/cpuflamegraphs.html Requested-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:37 +08:00
static size_t __callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
{
const char *sep = symbol_conf.field_sep ?: ";";
struct callchain_list *chain;
size_t ret = 0;
char bf[1024];
bool first;
if (!node)
return 0;
ret += __callchain__fprintf_folded(fp, node->parent);
first = (ret == 0);
list_for_each_entry(chain, &node->val, list) {
if (chain->ip >= PERF_CONTEXT_MAX)
continue;
ret += fprintf(fp, "%s%s", first ? "" : sep,
callchain_list__sym_name(chain,
bf, sizeof(bf), false));
first = false;
}
return ret;
}
static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree,
u64 total_samples)
{
size_t ret = 0;
u32 entries_printed = 0;
struct callchain_node *chain;
struct rb_node *rb_node = rb_first(tree);
while (rb_node) {
chain = rb_entry(rb_node, struct callchain_node, rb_node);
ret += callchain_node__fprintf_value(chain, fp, total_samples);
ret += fprintf(fp, " ");
perf report: Support folded callchain mode on --stdio Add new call chain option (-g) 'folded' to print callchains in a line. The callchains are separated by semicolons, and preceded by (absolute) percent values and a space. For example, the following 20 lines can be printed in 3 lines with the folded output mode: $ perf report -g flat --no-children | grep -v ^# | head -20 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary 5.88% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry rest_init start_kernel x86_64_start_reservations x86_64_start_kernel $ perf report -g folded --no-children | grep -v ^# | head -3 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.88% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel This mode is supported only for --stdio now and intended to be used by some scripts like in FlameGraphs[1]. Support for other UI might be added later. [1] http://www.brendangregg.com/FlameGraphs/cpuflamegraphs.html Requested-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:37 +08:00
ret += __callchain__fprintf_folded(fp, chain);
ret += fprintf(fp, "\n");
if (++entries_printed == callchain_param.print_limit)
break;
rb_node = rb_next(rb_node);
}
return ret;
}
static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
u64 total_samples, int left_margin,
FILE *fp)
{
u64 parent_samples = he->stat.period;
if (symbol_conf.cumulate_callchain)
parent_samples = he->stat_acc->period;
switch (callchain_param.mode) {
case CHAIN_GRAPH_REL:
return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
parent_samples, left_margin);
break;
case CHAIN_GRAPH_ABS:
return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
parent_samples, left_margin);
break;
case CHAIN_FLAT:
return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
break;
perf report: Support folded callchain mode on --stdio Add new call chain option (-g) 'folded' to print callchains in a line. The callchains are separated by semicolons, and preceded by (absolute) percent values and a space. For example, the following 20 lines can be printed in 3 lines with the folded output mode: $ perf report -g flat --no-children | grep -v ^# | head -20 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry start_secondary 5.88% intel_idle cpuidle_enter_state cpuidle_enter call_cpuidle cpu_startup_entry rest_init start_kernel x86_64_start_reservations x86_64_start_kernel $ perf report -g folded --no-children | grep -v ^# | head -3 60.48% swapper [kernel.vmlinux] [k] intel_idle 54.60% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary 5.88% intel_idle;cpuidle_enter_state;cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel This mode is supported only for --stdio now and intended to be used by some scripts like in FlameGraphs[1]. Support for other UI might be added later. [1] http://www.brendangregg.com/FlameGraphs/cpuflamegraphs.html Requested-and-Tested-by: Brendan Gregg <brendan.d.gregg@gmail.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1447047946-1691-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-09 13:45:37 +08:00
case CHAIN_FOLDED:
return callchain__fprintf_folded(fp, &he->sorted_chain, total_samples);
break;
case CHAIN_NONE:
break;
default:
pr_err("Bad callchain mode\n");
}
return 0;
}
static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
{
const char *sep = symbol_conf.field_sep;
struct perf_hpp_fmt *fmt;
char *start = hpp->buf;
int ret;
bool first = true;
if (symbol_conf.exclude_other && !he->parent)
return 0;
hists__for_each_format(he->hists, fmt) {
perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-23 01:07:08 +08:00
if (perf_hpp__should_skip(fmt, he->hists))
continue;
/*
* If there's no field_sep, we still need
* to display initial ' '.
*/
if (!sep || !first) {
ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " ");
advance_hpp(hpp, ret);
} else
first = false;
if (perf_hpp__use_color() && fmt->color)
ret = fmt->color(fmt, hpp, he);
else
ret = fmt->entry(fmt, hpp, he);
ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
advance_hpp(hpp, ret);
}
return hpp->buf - start;
}
static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
struct perf_hpp *hpp,
struct hists *hists,
FILE *fp)
{
const char *sep = symbol_conf.field_sep;
struct perf_hpp_fmt *fmt;
struct perf_hpp_list_node *fmt_node;
char *buf = hpp->buf;
size_t size = hpp->size;
int ret, printed = 0;
bool first = true;
if (symbol_conf.exclude_other && !he->parent)
return 0;
ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, "");
advance_hpp(hpp, ret);
/* the first hpp_list_node is for overhead columns */
fmt_node = list_first_entry(&hists->hpp_formats,
struct perf_hpp_list_node, list);
perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
/*
* If there's no field_sep, we still need
* to display initial ' '.
*/
if (!sep || !first) {
ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: " ");
advance_hpp(hpp, ret);
} else
first = false;
if (perf_hpp__use_color() && fmt->color)
ret = fmt->color(fmt, hpp, he);
else
ret = fmt->entry(fmt, hpp, he);
ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
advance_hpp(hpp, ret);
}
if (!sep)
ret = scnprintf(hpp->buf, hpp->size, "%*s",
(hists->nr_hpp_node - 2) * HIERARCHY_INDENT, "");
advance_hpp(hpp, ret);
printed += fprintf(fp, "%s", buf);
perf_hpp_list__for_each_format(he->hpp_list, fmt) {
hpp->buf = buf;
hpp->size = size;
/*
* No need to call hist_entry__snprintf_alignment() since this
* fmt is always the last column in the hierarchy mode.
*/
if (perf_hpp__use_color() && fmt->color)
fmt->color(fmt, hpp, he);
else
fmt->entry(fmt, hpp, he);
/*
* dynamic entries are right-aligned but we want left-aligned
* in the hierarchy mode
*/
printed += fprintf(fp, "%s%s", sep ?: " ", ltrim(buf));
}
printed += putc('\n', fp);
if (symbol_conf.use_callchain && he->leaf) {
u64 total = hists__total_period(hists);
printed += hist_entry_callchain__fprintf(he, total, 0, fp);
goto out;
}
out:
return printed;
}
static int hist_entry__fprintf(struct hist_entry *he, size_t size,
char *bf, size_t bfsz, FILE *fp,
bool use_callchain)
{
int ret;
struct perf_hpp hpp = {
.buf = bf,
.size = size,
};
struct hists *hists = he->hists;
u64 total_period = hists->stats.total_period;
if (size == 0 || size > bfsz)
size = hpp.size = bfsz;
if (symbol_conf.report_hierarchy)
return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
hist_entry__snprintf(he, &hpp);
ret = fprintf(fp, "%s\n", bf);
if (use_callchain)
ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
return ret;
}
static int print_hierarchy_indent(const char *sep, int indent,
const char *line, FILE *fp)
{
if (sep != NULL || indent < 2)
return 0;
return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
}
static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
const char *sep, FILE *fp)
{
bool first_node, first_col;
int indent;
int depth;
unsigned width = 0;
unsigned header_width = 0;
struct perf_hpp_fmt *fmt;
struct perf_hpp_list_node *fmt_node;
indent = hists->nr_hpp_node;
/* preserve max indent depth for column headers */
print_hierarchy_indent(sep, indent, spaces, fp);
/* the first hpp_list_node is for overhead columns */
fmt_node = list_first_entry(&hists->hpp_formats,
struct perf_hpp_list_node, list);
perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
fmt->header(fmt, hpp, hists, 0);
fprintf(fp, "%s%s", hpp->buf, sep ?: " ");
}
/* combine sort headers with ' / ' */
first_node = true;
list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
if (!first_node)
header_width += fprintf(fp, " / ");
first_node = false;
first_col = true;
perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
if (perf_hpp__should_skip(fmt, hists))
continue;
if (!first_col)
header_width += fprintf(fp, "+");
first_col = false;
fmt->header(fmt, hpp, hists, 0);
header_width += fprintf(fp, "%s", trim(hpp->buf));
}
}
fprintf(fp, "\n# ");
/* preserve max indent depth for initial dots */
print_hierarchy_indent(sep, indent, dots, fp);
/* the first hpp_list_node is for overhead columns */
fmt_node = list_first_entry(&hists->hpp_formats,
struct perf_hpp_list_node, list);
first_col = true;
perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
if (!first_col)
fprintf(fp, "%s", sep ?: "..");
first_col = false;
width = fmt->width(fmt, hpp, hists);
fprintf(fp, "%.*s", width, dots);
}
depth = 0;
list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
first_col = true;
width = depth * HIERARCHY_INDENT;
perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
if (perf_hpp__should_skip(fmt, hists))
continue;
if (!first_col)
width++; /* for '+' sign between column header */
first_col = false;
width += fmt->width(fmt, hpp, hists);
}
if (width > header_width)
header_width = width;
depth++;
}
fprintf(fp, "%s%-.*s", sep ?: " ", header_width, dots);
fprintf(fp, "\n#\n");
return 2;
}
static int
hists__fprintf_hierarchy_headers(struct hists *hists,
struct perf_hpp *hpp,
FILE *fp)
{
struct perf_hpp_list_node *fmt_node;
struct perf_hpp_fmt *fmt;
list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
perf_hpp__reset_width(fmt, hists);
}
return print_hierarchy_header(hists, hpp, symbol_conf.field_sep, fp);
}
static int
hists__fprintf_standard_headers(struct hists *hists,
struct perf_hpp *hpp,
FILE *fp)
{
struct perf_hpp_fmt *fmt;
unsigned int width;
const char *sep = symbol_conf.field_sep;
bool first = true;
hists__for_each_format(hists, fmt) {
perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-23 01:07:08 +08:00
if (perf_hpp__should_skip(fmt, hists))
continue;
if (!first)
fprintf(fp, "%s", sep ?: " ");
else
first = false;
fmt->header(fmt, hpp, hists, 0);
fprintf(fp, "%s", hpp->buf);
}
fprintf(fp, "\n");
if (sep)
return 1;
first = true;
fprintf(fp, "# ");
hists__for_each_format(hists, fmt) {
unsigned int i;
perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-23 01:07:08 +08:00
if (perf_hpp__should_skip(fmt, hists))
continue;
if (!first)
fprintf(fp, "%s", sep ?: " ");
else
first = false;
width = fmt->width(fmt, hpp, hists);
for (i = 0; i < width; i++)
fprintf(fp, ".");
}
fprintf(fp, "\n");
fprintf(fp, "#\n");
return 3;
}
static int hists__fprintf_headers(struct hists *hists, FILE *fp)
{
char bf[96];
struct perf_hpp dummy_hpp = {
.buf = bf,
.size = sizeof(bf),
};
fprintf(fp, "# ");
if (symbol_conf.report_hierarchy)
return hists__fprintf_hierarchy_headers(hists, &dummy_hpp, fp);
else
return hists__fprintf_standard_headers(hists, &dummy_hpp, fp);
}
size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
int max_cols, float min_pcnt, FILE *fp,
bool use_callchain)
{
struct perf_hpp_fmt *fmt;
struct rb_node *nd;
size_t ret = 0;
const char *sep = symbol_conf.field_sep;
int nr_rows = 0;
size_t linesz;
char *line = NULL;
unsigned indent;
init_rem_hits();
hists__for_each_format(hists, fmt)
perf_hpp__reset_width(fmt, hists);
if (symbol_conf.col_width_list_str)
perf_hpp__set_user_width(symbol_conf.col_width_list_str);
if (show_header)
nr_rows += hists__fprintf_headers(hists, fp);
if (max_rows && nr_rows >= max_rows)
goto out;
linesz = hists__sort_list_width(hists) + 3 + 1;
linesz += perf_hpp__color_overhead();
line = malloc(linesz);
if (line == NULL) {
ret = -1;
goto out;
}
perf report: Show message for percent limit on stdio When the hierarchy mode is used, some entries might be omiited due to a percent limit or filter. In this case the output hierarchy is different than other entries. Add an informative message to users about this. For example, when 4% of percent limit is applied: Before: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf Note that, gnome-shell/libc has no symbols and perf has no dso/symbols. With that patch the output will look like below: After: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so no entry >= 4.00% 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf no entry >= 4.00% Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1456488800-28124-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-26 20:13:17 +08:00
indent = hists__overhead_width(hists) + 4;
for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
float percent;
if (h->filtered)
continue;
percent = hist_entry__get_percent_limit(h);
if (percent < min_pcnt)
continue;
ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
if (max_rows && ++nr_rows >= max_rows)
break;
perf report: Show message for percent limit on stdio When the hierarchy mode is used, some entries might be omiited due to a percent limit or filter. In this case the output hierarchy is different than other entries. Add an informative message to users about this. For example, when 4% of percent limit is applied: Before: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf Note that, gnome-shell/libc has no symbols and perf has no dso/symbols. With that patch the output will look like below: After: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so no entry >= 4.00% 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf no entry >= 4.00% Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1456488800-28124-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-26 20:13:17 +08:00
/*
* If all children are filtered out or percent-limited,
* display "no entry >= x.xx%" message.
*/
if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
int depth = hists->nr_hpp_node + h->depth + 1;
perf report: Show message for percent limit on stdio When the hierarchy mode is used, some entries might be omiited due to a percent limit or filter. In this case the output hierarchy is different than other entries. Add an informative message to users about this. For example, when 4% of percent limit is applied: Before: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf Note that, gnome-shell/libc has no symbols and perf has no dso/symbols. With that patch the output will look like below: After: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so no entry >= 4.00% 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf no entry >= 4.00% Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1456488800-28124-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-26 20:13:17 +08:00
print_hierarchy_indent(sep, depth, spaces, fp);
perf report: Show message for percent limit on stdio When the hierarchy mode is used, some entries might be omiited due to a percent limit or filter. In this case the output hierarchy is different than other entries. Add an informative message to users about this. For example, when 4% of percent limit is applied: Before: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf Note that, gnome-shell/libc has no symbols and perf has no dso/symbols. With that patch the output will look like below: After: # Overhead Command / Shared Object / Symbol # .............. .......................................... # 49.09% swapper 48.67% [kernel.vmlinux] 34.42% [k] intel_idle 11.51% firefox 8.87% libpthread-2.22.so 6.60% [.] __GI___libc_recvmsg 10.49% gnome-shell 4.74% libc-2.22.so no entry >= 4.00% 10.08% Xorg 6.11% libc-2.22.so 5.27% [.] __memcpy_sse2_unaligned 6.15% perf no entry >= 4.00% Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1456488800-28124-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-26 20:13:17 +08:00
fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
if (max_rows && ++nr_rows >= max_rows)
break;
}
if (h->ms.map == NULL && verbose > 1) {
__map_groups__fprintf_maps(h->thread->mg,
MAP__FUNCTION, fp);
fprintf(fp, "%.10s end\n", graph_dotted_line);
}
}
free(line);
out:
zfree(&rem_sq_bracket);
return ret;
}
size_t events_stats__fprintf(struct events_stats *stats, FILE *fp)
{
int i;
size_t ret = 0;
for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
const char *name;
if (stats->nr_events[i] == 0)
continue;
name = perf_event__name(i);
if (!strcmp(name, "UNKNOWN"))
continue;
ret += fprintf(fp, "%16s events: %10d\n", name,
stats->nr_events[i]);
}
return ret;
}