kernel_optimize_test/tools/perf/tests/hists_cumulate.c

736 lines
20 KiB
C
Raw Normal View History

#include "perf.h"
#include "util/debug.h"
#include "util/symbol.h"
#include "util/sort.h"
#include "util/evsel.h"
#include "util/evlist.h"
#include "util/machine.h"
#include "util/thread.h"
#include "util/parse-events.h"
#include "tests/tests.h"
#include "tests/hists_common.h"
#include <linux/kernel.h>
struct sample {
u32 pid;
u64 ip;
struct thread *thread;
struct map *map;
struct symbol *sym;
};
/* For the numbers, see hists_common.c */
static struct sample fake_samples[] = {
/* perf [kernel] schedule() */
{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
/* perf [perf] main() */
{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
/* perf [perf] cmd_record() */
{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
/* perf [libc] malloc() */
{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
/* perf [libc] free() */
{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
/* perf [perf] main() */
{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
/* perf [kernel] page_fault() */
{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
/* bash [bash] main() */
{ .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_MAIN, },
/* bash [bash] xmalloc() */
{ .pid = FAKE_PID_BASH, .ip = FAKE_IP_BASH_XMALLOC, },
/* bash [kernel] page_fault() */
{ .pid = FAKE_PID_BASH, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
};
/*
* Will be casted to struct ip_callchain which has all 64 bit entries
* of nr and ips[].
*/
static u64 fake_callchains[][10] = {
/* schedule => run_command => main */
{ 3, FAKE_IP_KERNEL_SCHEDULE, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
/* main */
{ 1, FAKE_IP_PERF_MAIN, },
/* cmd_record => run_command => main */
{ 3, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
/* malloc => cmd_record => run_command => main */
{ 4, FAKE_IP_LIBC_MALLOC, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
FAKE_IP_PERF_MAIN, },
/* free => cmd_record => run_command => main */
{ 4, FAKE_IP_LIBC_FREE, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
FAKE_IP_PERF_MAIN, },
/* main */
{ 1, FAKE_IP_PERF_MAIN, },
/* page_fault => sys_perf_event_open => run_command => main */
{ 4, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN,
FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
/* main */
{ 1, FAKE_IP_BASH_MAIN, },
/* xmalloc => malloc => xmalloc => malloc => xmalloc => main */
{ 6, FAKE_IP_BASH_XMALLOC, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC,
FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC, FAKE_IP_BASH_MAIN, },
/* page_fault => malloc => main */
{ 3, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_MAIN, },
};
static int add_hist_entries(struct hists *hists, struct machine *machine)
{
struct addr_location al;
struct perf_evsel *evsel = hists_to_evsel(hists);
struct perf_sample sample = { .period = 1000, };
size_t i;
for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
struct hist_entry_iter iter = {
.evsel = evsel,
.sample = &sample,
.hide_unresolved = false,
};
if (symbol_conf.cumulate_callchain)
iter.ops = &hist_iter_cumulative;
else
iter.ops = &hist_iter_normal;
sample.cpumode = PERF_RECORD_MISC_USER;
sample.pid = fake_samples[i].pid;
sample.tid = fake_samples[i].pid;
sample.ip = fake_samples[i].ip;
sample.callchain = (struct ip_callchain *)fake_callchains[i];
if (machine__resolve(machine, &al, &sample) < 0)
goto out;
if (hist_entry_iter__add(&iter, &al, sysctl_perf_event_max_stack,
NULL) < 0) {
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
addr_location__put(&al);
goto out;
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-07 07:43:22 +08:00
}
fake_samples[i].thread = al.thread;
fake_samples[i].map = al.map;
fake_samples[i].sym = al.sym;
}
return TEST_OK;
out:
pr_debug("Not enough memory for adding a hist entry\n");
return TEST_FAIL;
}
static void del_hist_entries(struct hists *hists)
{
struct hist_entry *he;
struct rb_root *root_in;
struct rb_root *root_out;
struct rb_node *node;
if (hists__has(hists, need_collapse))
root_in = &hists->entries_collapsed;
else
root_in = hists->entries_in;
root_out = &hists->entries;
while (!RB_EMPTY_ROOT(root_out)) {
node = rb_first(root_out);
he = rb_entry(node, struct hist_entry, rb_node);
rb_erase(node, root_out);
rb_erase(&he->rb_node_in, root_in);
hist_entry__delete(he);
}
}
typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
#define COMM(he) (thread__comm_str(he->thread))
#define DSO(he) (he->ms.map->dso->short_name)
#define SYM(he) (he->ms.sym->name)
#define CPU(he) (he->cpu)
#define PID(he) (he->thread->tid)
#define DEPTH(he) (he->callchain->max_depth)
#define CDSO(cl) (cl->ms.map->dso->short_name)
#define CSYM(cl) (cl->ms.sym->name)
struct result {
u64 children;
u64 self;
const char *comm;
const char *dso;
const char *sym;
};
struct callchain_result {
u64 nr;
struct {
const char *dso;
const char *sym;
} node[10];
};
static int do_test(struct hists *hists, struct result *expected, size_t nr_expected,
struct callchain_result *expected_callchain, size_t nr_callchain)
{
char buf[32];
size_t i, c;
struct hist_entry *he;
struct rb_root *root;
struct rb_node *node;
struct callchain_node *cnode;
struct callchain_list *clist;
/*
* adding and deleting hist entries must be done outside of this
* function since TEST_ASSERT_VAL() returns in case of failure.
*/
hists__collapse_resort(hists, NULL);
perf_evsel__output_resort(hists_to_evsel(hists), NULL);
if (verbose > 2) {
pr_info("use callchain: %d, cumulate callchain: %d\n",
symbol_conf.use_callchain,
symbol_conf.cumulate_callchain);
print_hists_out(hists);
}
root = &hists->entries;
for (node = rb_first(root), i = 0;
node && (he = rb_entry(node, struct hist_entry, rb_node));
node = rb_next(node), i++) {
scnprintf(buf, sizeof(buf), "Invalid hist entry #%zd", i);
TEST_ASSERT_VAL("Incorrect number of hist entry",
i < nr_expected);
TEST_ASSERT_VAL(buf, he->stat.period == expected[i].self &&
!strcmp(COMM(he), expected[i].comm) &&
!strcmp(DSO(he), expected[i].dso) &&
!strcmp(SYM(he), expected[i].sym));
if (symbol_conf.cumulate_callchain)
TEST_ASSERT_VAL(buf, he->stat_acc->period == expected[i].children);
if (!symbol_conf.use_callchain)
continue;
/* check callchain entries */
root = &he->callchain->node.rb_root;
TEST_ASSERT_VAL("callchains expected", !RB_EMPTY_ROOT(root));
cnode = rb_entry(rb_first(root), struct callchain_node, rb_node);
c = 0;
list_for_each_entry(clist, &cnode->val, list) {
scnprintf(buf, sizeof(buf), "Invalid callchain entry #%zd/%zd", i, c);
TEST_ASSERT_VAL("Incorrect number of callchain entry",
c < expected_callchain[i].nr);
TEST_ASSERT_VAL(buf,
!strcmp(CDSO(clist), expected_callchain[i].node[c].dso) &&
!strcmp(CSYM(clist), expected_callchain[i].node[c].sym));
c++;
}
/* TODO: handle multiple child nodes properly */
TEST_ASSERT_VAL("Incorrect number of callchain entry",
c <= expected_callchain[i].nr);
}
TEST_ASSERT_VAL("Incorrect number of hist entry",
i == nr_expected);
TEST_ASSERT_VAL("Incorrect number of callchain entry",
!symbol_conf.use_callchain || nr_expected == nr_callchain);
return 0;
}
/* NO callchain + NO children */
static int test1(struct perf_evsel *evsel, struct machine *machine)
{
int err;
struct hists *hists = evsel__hists(evsel);
/*
* expected output:
*
* Overhead Command Shared Object Symbol
* ======== ======= ============= ==============
* 20.00% perf perf [.] main
* 10.00% bash [kernel] [k] page_fault
* 10.00% bash bash [.] main
* 10.00% bash bash [.] xmalloc
* 10.00% perf [kernel] [k] page_fault
* 10.00% perf [kernel] [k] schedule
* 10.00% perf libc [.] free
* 10.00% perf libc [.] malloc
* 10.00% perf perf [.] cmd_record
*/
struct result expected[] = {
{ 0, 2000, "perf", "perf", "main" },
{ 0, 1000, "bash", "[kernel]", "page_fault" },
{ 0, 1000, "bash", "bash", "main" },
{ 0, 1000, "bash", "bash", "xmalloc" },
{ 0, 1000, "perf", "[kernel]", "page_fault" },
{ 0, 1000, "perf", "[kernel]", "schedule" },
{ 0, 1000, "perf", "libc", "free" },
{ 0, 1000, "perf", "libc", "malloc" },
{ 0, 1000, "perf", "perf", "cmd_record" },
};
symbol_conf.use_callchain = false;
symbol_conf.cumulate_callchain = false;
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 18:30:48 +08:00
perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
setup_sorting(NULL);
callchain_register_param(&callchain_param);
err = add_hist_entries(hists, machine);
if (err < 0)
goto out;
err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
out:
del_hist_entries(hists);
reset_output_field();
return err;
}
/* callcain + NO children */
static int test2(struct perf_evsel *evsel, struct machine *machine)
{
int err;
struct hists *hists = evsel__hists(evsel);
/*
* expected output:
*
* Overhead Command Shared Object Symbol
* ======== ======= ============= ==============
* 20.00% perf perf [.] main
* |
* --- main
*
* 10.00% bash [kernel] [k] page_fault
* |
* --- page_fault
* malloc
* main
*
* 10.00% bash bash [.] main
* |
* --- main
*
* 10.00% bash bash [.] xmalloc
* |
* --- xmalloc
* malloc
* xmalloc <--- NOTE: there's a cycle
* malloc
* xmalloc
* main
*
* 10.00% perf [kernel] [k] page_fault
* |
* --- page_fault
* sys_perf_event_open
* run_command
* main
*
* 10.00% perf [kernel] [k] schedule
* |
* --- schedule
* run_command
* main
*
* 10.00% perf libc [.] free
* |
* --- free
* cmd_record
* run_command
* main
*
* 10.00% perf libc [.] malloc
* |
* --- malloc
* cmd_record
* run_command
* main
*
* 10.00% perf perf [.] cmd_record
* |
* --- cmd_record
* run_command
* main
*
*/
struct result expected[] = {
{ 0, 2000, "perf", "perf", "main" },
{ 0, 1000, "bash", "[kernel]", "page_fault" },
{ 0, 1000, "bash", "bash", "main" },
{ 0, 1000, "bash", "bash", "xmalloc" },
{ 0, 1000, "perf", "[kernel]", "page_fault" },
{ 0, 1000, "perf", "[kernel]", "schedule" },
{ 0, 1000, "perf", "libc", "free" },
{ 0, 1000, "perf", "libc", "malloc" },
{ 0, 1000, "perf", "perf", "cmd_record" },
};
struct callchain_result expected_callchain[] = {
{
1, { { "perf", "main" }, },
},
{
3, { { "[kernel]", "page_fault" },
{ "libc", "malloc" },
{ "bash", "main" }, },
},
{
1, { { "bash", "main" }, },
},
{
6, { { "bash", "xmalloc" },
{ "libc", "malloc" },
{ "bash", "xmalloc" },
{ "libc", "malloc" },
{ "bash", "xmalloc" },
{ "bash", "main" }, },
},
{
4, { { "[kernel]", "page_fault" },
{ "[kernel]", "sys_perf_event_open" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
3, { { "[kernel]", "schedule" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
4, { { "libc", "free" },
{ "perf", "cmd_record" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
4, { { "libc", "malloc" },
{ "perf", "cmd_record" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
3, { { "perf", "cmd_record" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
};
symbol_conf.use_callchain = true;
symbol_conf.cumulate_callchain = false;
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 18:30:48 +08:00
perf_evsel__set_sample_bit(evsel, CALLCHAIN);
setup_sorting(NULL);
callchain_register_param(&callchain_param);
err = add_hist_entries(hists, machine);
if (err < 0)
goto out;
err = do_test(hists, expected, ARRAY_SIZE(expected),
expected_callchain, ARRAY_SIZE(expected_callchain));
out:
del_hist_entries(hists);
reset_output_field();
return err;
}
/* NO callchain + children */
static int test3(struct perf_evsel *evsel, struct machine *machine)
{
int err;
struct hists *hists = evsel__hists(evsel);
/*
* expected output:
*
* Children Self Command Shared Object Symbol
* ======== ======== ======= ============= =======================
* 70.00% 20.00% perf perf [.] main
* 50.00% 0.00% perf perf [.] run_command
* 30.00% 10.00% bash bash [.] main
* 30.00% 10.00% perf perf [.] cmd_record
* 20.00% 0.00% bash libc [.] malloc
* 10.00% 10.00% bash [kernel] [k] page_fault
* 10.00% 10.00% bash bash [.] xmalloc
* 10.00% 10.00% perf [kernel] [k] page_fault
* 10.00% 10.00% perf libc [.] malloc
* 10.00% 10.00% perf [kernel] [k] schedule
* 10.00% 10.00% perf libc [.] free
* 10.00% 0.00% perf [kernel] [k] sys_perf_event_open
*/
struct result expected[] = {
{ 7000, 2000, "perf", "perf", "main" },
{ 5000, 0, "perf", "perf", "run_command" },
{ 3000, 1000, "bash", "bash", "main" },
{ 3000, 1000, "perf", "perf", "cmd_record" },
{ 2000, 0, "bash", "libc", "malloc" },
{ 1000, 1000, "bash", "[kernel]", "page_fault" },
{ 1000, 1000, "bash", "bash", "xmalloc" },
{ 1000, 1000, "perf", "[kernel]", "page_fault" },
{ 1000, 1000, "perf", "[kernel]", "schedule" },
{ 1000, 1000, "perf", "libc", "free" },
{ 1000, 1000, "perf", "libc", "malloc" },
{ 1000, 0, "perf", "[kernel]", "sys_perf_event_open" },
};
symbol_conf.use_callchain = false;
symbol_conf.cumulate_callchain = true;
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 18:30:48 +08:00
perf_evsel__reset_sample_bit(evsel, CALLCHAIN);
setup_sorting(NULL);
callchain_register_param(&callchain_param);
err = add_hist_entries(hists, machine);
if (err < 0)
goto out;
err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
out:
del_hist_entries(hists);
reset_output_field();
return err;
}
/* callchain + children */
static int test4(struct perf_evsel *evsel, struct machine *machine)
{
int err;
struct hists *hists = evsel__hists(evsel);
/*
* expected output:
*
* Children Self Command Shared Object Symbol
* ======== ======== ======= ============= =======================
* 70.00% 20.00% perf perf [.] main
* |
* --- main
*
* 50.00% 0.00% perf perf [.] run_command
* |
* --- run_command
* main
*
* 30.00% 10.00% bash bash [.] main
* |
* --- main
*
* 30.00% 10.00% perf perf [.] cmd_record
* |
* --- cmd_record
* run_command
* main
*
* 20.00% 0.00% bash libc [.] malloc
* |
* --- malloc
* |
* |--50.00%-- xmalloc
* | main
* --50.00%-- main
*
* 10.00% 10.00% bash [kernel] [k] page_fault
* |
* --- page_fault
* malloc
* main
*
* 10.00% 10.00% bash bash [.] xmalloc
* |
* --- xmalloc
* malloc
* xmalloc <--- NOTE: there's a cycle
* malloc
* xmalloc
* main
*
* 10.00% 0.00% perf [kernel] [k] sys_perf_event_open
* |
* --- sys_perf_event_open
* run_command
* main
*
* 10.00% 10.00% perf [kernel] [k] page_fault
* |
* --- page_fault
* sys_perf_event_open
* run_command
* main
*
* 10.00% 10.00% perf [kernel] [k] schedule
* |
* --- schedule
* run_command
* main
*
* 10.00% 10.00% perf libc [.] free
* |
* --- free
* cmd_record
* run_command
* main
*
* 10.00% 10.00% perf libc [.] malloc
* |
* --- malloc
* cmd_record
* run_command
* main
*
*/
struct result expected[] = {
{ 7000, 2000, "perf", "perf", "main" },
{ 5000, 0, "perf", "perf", "run_command" },
{ 3000, 1000, "bash", "bash", "main" },
{ 3000, 1000, "perf", "perf", "cmd_record" },
{ 2000, 0, "bash", "libc", "malloc" },
{ 1000, 1000, "bash", "[kernel]", "page_fault" },
{ 1000, 1000, "bash", "bash", "xmalloc" },
{ 1000, 0, "perf", "[kernel]", "sys_perf_event_open" },
{ 1000, 1000, "perf", "[kernel]", "page_fault" },
{ 1000, 1000, "perf", "[kernel]", "schedule" },
{ 1000, 1000, "perf", "libc", "free" },
{ 1000, 1000, "perf", "libc", "malloc" },
};
struct callchain_result expected_callchain[] = {
{
1, { { "perf", "main" }, },
},
{
2, { { "perf", "run_command" },
{ "perf", "main" }, },
},
{
1, { { "bash", "main" }, },
},
{
3, { { "perf", "cmd_record" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
4, { { "libc", "malloc" },
{ "bash", "xmalloc" },
{ "bash", "main" },
{ "bash", "main" }, },
},
{
3, { { "[kernel]", "page_fault" },
{ "libc", "malloc" },
{ "bash", "main" }, },
},
{
6, { { "bash", "xmalloc" },
{ "libc", "malloc" },
{ "bash", "xmalloc" },
{ "libc", "malloc" },
{ "bash", "xmalloc" },
{ "bash", "main" }, },
},
{
3, { { "[kernel]", "sys_perf_event_open" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
4, { { "[kernel]", "page_fault" },
{ "[kernel]", "sys_perf_event_open" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
3, { { "[kernel]", "schedule" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
4, { { "libc", "free" },
{ "perf", "cmd_record" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
{
4, { { "libc", "malloc" },
{ "perf", "cmd_record" },
{ "perf", "run_command" },
{ "perf", "main" }, },
},
};
symbol_conf.use_callchain = true;
symbol_conf.cumulate_callchain = true;
perf callchain: Allow disabling call graphs per event This patch introduce "call-graph=no" to disable per-event callgraph. Here is an example. perf record -e 'cpu/cpu-cycles,call-graph=fp/,cpu/instructions,call-graph=no/' sleep 1 perf report --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 6 of event 'cpu/cpu-cycles,call-graph=fp/' # Event count (approx.): 774218 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ........................................ # 61.94% 0.00% sleep [kernel.vmlinux] [k] entry_SYSCALL_64_fastpath | ---entry_SYSCALL_64_fastpath | |--97.30%-- __brk | --2.70%-- mmap64 _dl_check_map_versions _dl_check_all_versions 61.94% 0.00% sleep [kernel.vmlinux] [k] perf_event_mmap | ---perf_event_mmap | |--97.30%-- do_brk | sys_brk | entry_SYSCALL_64_fastpath | __brk | --2.70%-- mmap_region do_mmap_pgoff vm_mmap_pgoff sys_mmap_pgoff sys_mmap entry_SYSCALL_64_fastpath mmap64 _dl_check_map_versions _dl_check_all_versions ...... # Samples: 6 of event 'cpu/instructions,call-graph=no/' # Event count (approx.): 359692 # # Children Self Command Shared Object Symbol # ........ ........ ....... ................ ................................. # 89.03% 0.00% sleep [unknown] [.] 0xffff6598ffff6598 89.03% 0.00% sleep ld-2.17.so [.] _dl_resolve_conflicts 89.03% 0.00% sleep [kernel.vmlinux] [k] page_fault Signed-off-by: Kan Liang <kan.liang@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1439289050-40510-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 18:30:48 +08:00
perf_evsel__set_sample_bit(evsel, CALLCHAIN);
setup_sorting(NULL);
callchain_param = callchain_param_default;
callchain_register_param(&callchain_param);
err = add_hist_entries(hists, machine);
if (err < 0)
goto out;
err = do_test(hists, expected, ARRAY_SIZE(expected),
expected_callchain, ARRAY_SIZE(expected_callchain));
out:
del_hist_entries(hists);
reset_output_field();
return err;
}
int test__hists_cumulate(int subtest __maybe_unused)
{
int err = TEST_FAIL;
struct machines machines;
struct machine *machine;
struct perf_evsel *evsel;
struct perf_evlist *evlist = perf_evlist__new();
size_t i;
test_fn_t testcases[] = {
test1,
test2,
test3,
test4,
};
TEST_ASSERT_VAL("No memory", evlist);
perf tools: Add parse_events_error interface Adding support to return error information from parse_events function. Following struct will be populated by parse_events function on return: struct parse_events_error { int idx; char *str; char *help; }; where 'idx' is the position in the string where the parsing failed, 'str' contains dynamically allocated error string describing the error and 'help' is optional help string. The change contains reporting function, which currently does not display anything. The code changes to supply error data for specific event types are coming in next patches. However this is what the expected output is: $ sudo perf record -e 'sched:krava' ls event syntax error: 'sched:krava' \___ unknown tracepoint ... $ perf record -e 'cpu/even=0x1/' ls event syntax error: 'cpu/even=0x1/' \___ unknown term valid terms: pc,any,inv,edge,cmask,event,in_tx,ldlat,umask,in_tx_cp,offcore_rsp,config,config1,config2,name,period,branch_type ... $ perf record -e cycles,cache-mises ls event syntax error: '..es,cache-mises' \___ parser error ... The output functions cut the beginning of the event string so the error starts up to 10th character and cut the end of the string of it crosses the terminal width. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1429729824-13932-2-git-send-email-jolsa@kernel.org [ Renamed 'error' variables to 'err', not to clash with util.h error() ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-23 03:10:16 +08:00
err = parse_events(evlist, "cpu-clock", NULL);
if (err)
goto out;
err = TEST_FAIL;
machines__init(&machines);
/* setup threads/dso/map/symbols also */
machine = setup_fake_machine(&machines);
if (!machine)
goto out;
if (verbose > 1)
machine__fprintf(machine, stderr);
evsel = perf_evlist__first(evlist);
for (i = 0; i < ARRAY_SIZE(testcases); i++) {
err = testcases[i](evsel, machine);
if (err < 0)
break;
}
out:
/* tear down everything */
perf_evlist__delete(evlist);
machines__exit(&machines);
return err;
}