linux/tools/perf/util/sort.c

1271 lines
30 KiB
C
Raw Normal View History

#include "sort.h"
#include "hist.h"
#include "comm.h"
#include "symbol.h"
#include "evsel.h"
regex_t parent_regex;
const char default_parent_pattern[] = "^sys_|^do_page_fault";
const char *parent_pattern = default_parent_pattern;
const char default_sort_order[] = "comm,dso,symbol";
const char *sort_order = default_sort_order;
perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price <price@mit.edu> Tested-by: Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.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/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu <fengguang.wu@intel.com> [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-07 05:48:05 +00:00
regex_t ignore_callees_regex;
int have_ignore_callees = 0;
int sort__need_collapse = 0;
int sort__has_parent = 0;
int sort__has_sym = 0;
int sort__has_dso = 0;
enum sort_mode sort__mode = SORT_MODE__NORMAL;
perf tools: Bind callchains to the first sort dimension column Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 21:23:23 +00:00
enum sort_type sort__first_dimension;
LIST_HEAD(hist_entry__sort_list);
static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
{
int n;
va_list ap;
va_start(ap, fmt);
n = vsnprintf(bf, size, fmt, ap);
if (symbol_conf.field_sep && n > 0) {
char *sep = bf;
while (1) {
sep = strchr(sep, *symbol_conf.field_sep);
if (sep == NULL)
break;
*sep = '.';
}
}
va_end(ap);
perf tools: Incorrect use of snprintf results in SEGV I have a workload where perf top scribbles over the stack and we SEGV. What makes it interesting is that an snprintf is causing this. The workload is a c++ gem that has method names over 3000 characters long, but snprintf is designed to avoid overrunning buffers. So what went wrong? The problem is we assume snprintf returns the number of characters written: ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); ... ret += repsep_snprintf(bf + ret, size - ret, "%s", self->ms.sym->name); Unfortunately this is not how snprintf works. snprintf returns the number of characters that would have been written if there was enough space. In the above case, if the first snprintf returns a value larger than size, we pass a negative size into the second snprintf and happily scribble over the stack. If you have 3000 character c++ methods thats a lot of stack to trample. This patch fixes repsep_snprintf by clamping the value at size - 1 which is the maximum snprintf can write before adding the NULL terminator. I get the sinking feeling that there are a lot of other uses of snprintf that have this same bug, we should audit them all. Cc: David Ahern <dsahern@gmail.com> Cc: Eric B Munson <emunson@mgebm.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Yanmin Zhang <yanmin_zhang@linux.intel.com> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/20120307114249.44275ca3@kryten Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-07 00:42:49 +00:00
if (n >= (int)size)
return size - 1;
return n;
}
static int64_t cmp_null(const void *l, const void *r)
{
if (!l && !r)
return 0;
else if (!l)
return -1;
else
return 1;
}
/* --sort pid */
static int64_t
sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->thread->tid - left->thread->tid;
}
static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
const char *comm = thread__comm_str(he->thread);
return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
comm ?: "", he->thread->tid);
}
struct sort_entry sort_thread = {
.se_header = "Command: Pid",
.se_cmp = sort__thread_cmp,
.se_snprintf = hist_entry__thread_snprintf,
.se_width_idx = HISTC_THREAD,
};
/* --sort comm */
static int64_t
sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
{
/* Compare the addr that should be unique among comm */
return comm__str(right->comm) - comm__str(left->comm);
}
static int64_t
sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
{
/* Compare the addr that should be unique among comm */
return comm__str(right->comm) - comm__str(left->comm);
}
static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
}
struct sort_entry sort_comm = {
.se_header = "Command",
.se_cmp = sort__comm_cmp,
.se_collapse = sort__comm_collapse,
.se_snprintf = hist_entry__comm_snprintf,
.se_width_idx = HISTC_COMM,
};
/* --sort dso */
static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
{
struct dso *dso_l = map_l ? map_l->dso : NULL;
struct dso *dso_r = map_r ? map_r->dso : NULL;
const char *dso_name_l, *dso_name_r;
if (!dso_l || !dso_r)
return cmp_null(dso_l, dso_r);
if (verbose) {
dso_name_l = dso_l->long_name;
dso_name_r = dso_r->long_name;
} else {
dso_name_l = dso_l->short_name;
dso_name_r = dso_r->short_name;
}
return strcmp(dso_name_l, dso_name_r);
}
static int64_t
sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->ms.map, right->ms.map);
}
static int _hist_entry__dso_snprintf(struct map *map, char *bf,
size_t size, unsigned int width)
{
if (map && map->dso) {
const char *dso_name = !verbose ? map->dso->short_name :
map->dso->long_name;
return repsep_snprintf(bf, size, "%-*s", width, dso_name);
}
return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
}
static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
}
struct sort_entry sort_dso = {
.se_header = "Shared Object",
.se_cmp = sort__dso_cmp,
.se_snprintf = hist_entry__dso_snprintf,
.se_width_idx = HISTC_DSO,
};
/* --sort symbol */
static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
{
return (int64_t)(right_ip - left_ip);
}
static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
{
u64 ip_l, ip_r;
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
if (sym_l == sym_r)
return 0;
ip_l = sym_l->start;
ip_r = sym_r->start;
return (int64_t)(ip_r - ip_l);
}
static int64_t
sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
{
int64_t ret;
if (!left->ms.sym && !right->ms.sym)
return _sort__addr_cmp(left->ip, right->ip);
/*
* comparing symbol address alone is not enough since it's a
* relative address within a dso.
*/
if (!sort__has_dso) {
ret = sort__dso_cmp(left, right);
if (ret != 0)
return ret;
}
return _sort__sym_cmp(left->ms.sym, right->ms.sym);
}
static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
u64 ip, char level, char *bf, size_t size,
unsigned int width)
{
size_t ret = 0;
if (verbose) {
char o = map ? dso__symtab_origin(map->dso) : '!';
ret += repsep_snprintf(bf, size, "%-#*llx %c ",
BITS_PER_LONG / 4 + 2, ip, o);
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
}
ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
if (sym && map) {
if (map->type == MAP__VARIABLE) {
ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
ip - map->unmap_ip(map, sym->start));
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret, "");
} else {
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret,
sym->name);
}
} else {
size_t len = BITS_PER_LONG / 4;
ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
len, ip);
ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
width - ret, "");
}
return ret;
}
static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__sym_snprintf(he->ms.map, he->ms.sym, he->ip,
he->level, bf, size, width);
}
struct sort_entry sort_sym = {
.se_header = "Symbol",
.se_cmp = sort__sym_cmp,
.se_snprintf = hist_entry__sym_snprintf,
.se_width_idx = HISTC_SYMBOL,
};
perf tools: Add sort by src line/number Using addr2line for now, requires debuginfo, needs more work to support detached debuginfo, aka foo-debuginfo packages. Example: [root@sandy ~]# perf record -a sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.555 MB perf.data (~24236 samples) ] [root@sandy ~]# perf report -s dso,srcline 2>&1 | grep -v ^# | head -5 22.41% [kernel.kallsyms] /home/git/linux/drivers/idle/intel_idle.c:280 4.79% [kernel.kallsyms] /home/git/linux/drivers/cpuidle/cpuidle.c:148 4.78% [kernel.kallsyms] /home/git/linux/arch/x86/include/asm/atomic64_64.h:121 4.49% [kernel.kallsyms] /home/git/linux/kernel/sched/core.c:1690 4.30% [kernel.kallsyms] /home/git/linux/include/linux/seqlock.h:90 [root@sandy ~]# [root@sandy ~]# perf top -U -s dso,symbol,srcline Samples: 1K of event 'cycles', Event count (approx.): 589617389 18.66% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:143 7.83% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:39 6.59% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:38 3.66% [kernel] [k] page_fault /home/git/linux/arch/x86/kernel/entry_64.S:1379 3.25% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:40 3.12% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:37 2.74% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:36 2.39% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:43 2.12% [kernel] [k] ioread32 /home/git/linux/lib/iomap.c:90 1.51% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:144 1.19% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:154 Suggested-by: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pdmqbng9twz06jzkbgtuwbp8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 13:33:24 +00:00
/* --sort srcline */
static int64_t
sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
{
if (!left->srcline) {
if (!left->ms.map)
left->srcline = SRCLINE_UNKNOWN;
else {
struct map *map = left->ms.map;
left->srcline = get_srcline(map->dso,
map__rip_2objdump(map, left->ip));
}
}
if (!right->srcline) {
if (!right->ms.map)
right->srcline = SRCLINE_UNKNOWN;
else {
struct map *map = right->ms.map;
right->srcline = get_srcline(map->dso,
map__rip_2objdump(map, right->ip));
}
}
return strcmp(left->srcline, right->srcline);
perf tools: Add sort by src line/number Using addr2line for now, requires debuginfo, needs more work to support detached debuginfo, aka foo-debuginfo packages. Example: [root@sandy ~]# perf record -a sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.555 MB perf.data (~24236 samples) ] [root@sandy ~]# perf report -s dso,srcline 2>&1 | grep -v ^# | head -5 22.41% [kernel.kallsyms] /home/git/linux/drivers/idle/intel_idle.c:280 4.79% [kernel.kallsyms] /home/git/linux/drivers/cpuidle/cpuidle.c:148 4.78% [kernel.kallsyms] /home/git/linux/arch/x86/include/asm/atomic64_64.h:121 4.49% [kernel.kallsyms] /home/git/linux/kernel/sched/core.c:1690 4.30% [kernel.kallsyms] /home/git/linux/include/linux/seqlock.h:90 [root@sandy ~]# [root@sandy ~]# perf top -U -s dso,symbol,srcline Samples: 1K of event 'cycles', Event count (approx.): 589617389 18.66% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:143 7.83% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:39 6.59% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:38 3.66% [kernel] [k] page_fault /home/git/linux/arch/x86/kernel/entry_64.S:1379 3.25% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:40 3.12% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:37 2.74% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:36 2.39% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:43 2.12% [kernel] [k] ioread32 /home/git/linux/lib/iomap.c:90 1.51% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:144 1.19% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:154 Suggested-by: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pdmqbng9twz06jzkbgtuwbp8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 13:33:24 +00:00
}
static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-10 22:15:03 +00:00
size_t size,
unsigned int width __maybe_unused)
perf tools: Add sort by src line/number Using addr2line for now, requires debuginfo, needs more work to support detached debuginfo, aka foo-debuginfo packages. Example: [root@sandy ~]# perf record -a sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.555 MB perf.data (~24236 samples) ] [root@sandy ~]# perf report -s dso,srcline 2>&1 | grep -v ^# | head -5 22.41% [kernel.kallsyms] /home/git/linux/drivers/idle/intel_idle.c:280 4.79% [kernel.kallsyms] /home/git/linux/drivers/cpuidle/cpuidle.c:148 4.78% [kernel.kallsyms] /home/git/linux/arch/x86/include/asm/atomic64_64.h:121 4.49% [kernel.kallsyms] /home/git/linux/kernel/sched/core.c:1690 4.30% [kernel.kallsyms] /home/git/linux/include/linux/seqlock.h:90 [root@sandy ~]# [root@sandy ~]# perf top -U -s dso,symbol,srcline Samples: 1K of event 'cycles', Event count (approx.): 589617389 18.66% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:143 7.83% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:39 6.59% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:38 3.66% [kernel] [k] page_fault /home/git/linux/arch/x86/kernel/entry_64.S:1379 3.25% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:40 3.12% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:37 2.74% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:36 2.39% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:43 2.12% [kernel] [k] ioread32 /home/git/linux/lib/iomap.c:90 1.51% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:144 1.19% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:154 Suggested-by: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pdmqbng9twz06jzkbgtuwbp8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 13:33:24 +00:00
{
return repsep_snprintf(bf, size, "%s", he->srcline);
perf tools: Add sort by src line/number Using addr2line for now, requires debuginfo, needs more work to support detached debuginfo, aka foo-debuginfo packages. Example: [root@sandy ~]# perf record -a sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.555 MB perf.data (~24236 samples) ] [root@sandy ~]# perf report -s dso,srcline 2>&1 | grep -v ^# | head -5 22.41% [kernel.kallsyms] /home/git/linux/drivers/idle/intel_idle.c:280 4.79% [kernel.kallsyms] /home/git/linux/drivers/cpuidle/cpuidle.c:148 4.78% [kernel.kallsyms] /home/git/linux/arch/x86/include/asm/atomic64_64.h:121 4.49% [kernel.kallsyms] /home/git/linux/kernel/sched/core.c:1690 4.30% [kernel.kallsyms] /home/git/linux/include/linux/seqlock.h:90 [root@sandy ~]# [root@sandy ~]# perf top -U -s dso,symbol,srcline Samples: 1K of event 'cycles', Event count (approx.): 589617389 18.66% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:143 7.83% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:39 6.59% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:38 3.66% [kernel] [k] page_fault /home/git/linux/arch/x86/kernel/entry_64.S:1379 3.25% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:40 3.12% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:37 2.74% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:36 2.39% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:43 2.12% [kernel] [k] ioread32 /home/git/linux/lib/iomap.c:90 1.51% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:144 1.19% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:154 Suggested-by: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pdmqbng9twz06jzkbgtuwbp8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 13:33:24 +00:00
}
struct sort_entry sort_srcline = {
.se_header = "Source:Line",
.se_cmp = sort__srcline_cmp,
.se_snprintf = hist_entry__srcline_snprintf,
.se_width_idx = HISTC_SRCLINE,
};
/* --sort parent */
static int64_t
sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct symbol *sym_l = left->parent;
struct symbol *sym_r = right->parent;
if (!sym_l || !sym_r)
return cmp_null(sym_l, sym_r);
return strcmp(sym_l->name, sym_r->name);
}
static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*s", width,
he->parent ? he->parent->name : "[other]");
}
struct sort_entry sort_parent = {
.se_header = "Parent symbol",
.se_cmp = sort__parent_cmp,
.se_snprintf = hist_entry__parent_snprintf,
.se_width_idx = HISTC_PARENT,
};
/* --sort cpu */
static int64_t
sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
{
return right->cpu - left->cpu;
}
static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%*d", width, he->cpu);
}
struct sort_entry sort_cpu = {
.se_header = "CPU",
.se_cmp = sort__cpu_cmp,
.se_snprintf = hist_entry__cpu_snprintf,
.se_width_idx = HISTC_CPU,
};
/* sort keys for branch stacks */
static int64_t
sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->branch_info->from.map,
right->branch_info->from.map);
}
static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(he->branch_info->from.map,
bf, size, width);
}
static int64_t
sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
{
return _sort__dso_cmp(left->branch_info->to.map,
right->branch_info->to.map);
}
static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return _hist_entry__dso_snprintf(he->branch_info->to.map,
bf, size, width);
}
static int64_t
sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct addr_map_symbol *from_l = &left->branch_info->from;
struct addr_map_symbol *from_r = &right->branch_info->from;
if (!from_l->sym && !from_r->sym)
return _sort__addr_cmp(from_l->addr, from_r->addr);
return _sort__sym_cmp(from_l->sym, from_r->sym);
}
static int64_t
sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct addr_map_symbol *to_l = &left->branch_info->to;
struct addr_map_symbol *to_r = &right->branch_info->to;
if (!to_l->sym && !to_r->sym)
return _sort__addr_cmp(to_l->addr, to_r->addr);
return _sort__sym_cmp(to_l->sym, to_r->sym);
}
static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
struct addr_map_symbol *from = &he->branch_info->from;
return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
he->level, bf, size, width);
}
static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
struct addr_map_symbol *to = &he->branch_info->to;
return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
he->level, bf, size, width);
}
struct sort_entry sort_dso_from = {
.se_header = "Source Shared Object",
.se_cmp = sort__dso_from_cmp,
.se_snprintf = hist_entry__dso_from_snprintf,
.se_width_idx = HISTC_DSO_FROM,
};
struct sort_entry sort_dso_to = {
.se_header = "Target Shared Object",
.se_cmp = sort__dso_to_cmp,
.se_snprintf = hist_entry__dso_to_snprintf,
.se_width_idx = HISTC_DSO_TO,
};
struct sort_entry sort_sym_from = {
.se_header = "Source Symbol",
.se_cmp = sort__sym_from_cmp,
.se_snprintf = hist_entry__sym_from_snprintf,
.se_width_idx = HISTC_SYMBOL_FROM,
};
struct sort_entry sort_sym_to = {
.se_header = "Target Symbol",
.se_cmp = sort__sym_to_cmp,
.se_snprintf = hist_entry__sym_to_snprintf,
.se_width_idx = HISTC_SYMBOL_TO,
};
static int64_t
sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
{
const unsigned char mp = left->branch_info->flags.mispred !=
right->branch_info->flags.mispred;
const unsigned char p = left->branch_info->flags.predicted !=
right->branch_info->flags.predicted;
return mp || p;
}
static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width){
static const char *out = "N/A";
if (he->branch_info->flags.predicted)
out = "N";
else if (he->branch_info->flags.mispred)
out = "Y";
return repsep_snprintf(bf, size, "%-*s", width, out);
}
/* --sort daddr_sym */
static int64_t
sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
{
uint64_t l = 0, r = 0;
if (left->mem_info)
l = left->mem_info->daddr.addr;
if (right->mem_info)
r = right->mem_info->daddr.addr;
return (int64_t)(r - l);
}
static int hist_entry__daddr_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
uint64_t addr = 0;
struct map *map = NULL;
struct symbol *sym = NULL;
if (he->mem_info) {
addr = he->mem_info->daddr.addr;
map = he->mem_info->daddr.map;
sym = he->mem_info->daddr.sym;
}
return _hist_entry__sym_snprintf(map, sym, addr, he->level, bf, size,
width);
}
static int64_t
sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
{
struct map *map_l = NULL;
struct map *map_r = NULL;
if (left->mem_info)
map_l = left->mem_info->daddr.map;
if (right->mem_info)
map_r = right->mem_info->daddr.map;
return _sort__dso_cmp(map_l, map_r);
}
static int hist_entry__dso_daddr_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
struct map *map = NULL;
if (he->mem_info)
map = he->mem_info->daddr.map;
return _hist_entry__dso_snprintf(map, bf, size, width);
}
static int64_t
sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
{
union perf_mem_data_src data_src_l;
union perf_mem_data_src data_src_r;
if (left->mem_info)
data_src_l = left->mem_info->data_src;
else
data_src_l.mem_lock = PERF_MEM_LOCK_NA;
if (right->mem_info)
data_src_r = right->mem_info->data_src;
else
data_src_r.mem_lock = PERF_MEM_LOCK_NA;
return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock);
}
static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
const char *out;
u64 mask = PERF_MEM_LOCK_NA;
if (he->mem_info)
mask = he->mem_info->data_src.mem_lock;
if (mask & PERF_MEM_LOCK_NA)
out = "N/A";
else if (mask & PERF_MEM_LOCK_LOCKED)
out = "Yes";
else
out = "No";
return repsep_snprintf(bf, size, "%-*s", width, out);
}
static int64_t
sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
{
union perf_mem_data_src data_src_l;
union perf_mem_data_src data_src_r;
if (left->mem_info)
data_src_l = left->mem_info->data_src;
else
data_src_l.mem_dtlb = PERF_MEM_TLB_NA;
if (right->mem_info)
data_src_r = right->mem_info->data_src;
else
data_src_r.mem_dtlb = PERF_MEM_TLB_NA;
return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
}
static const char * const tlb_access[] = {
"N/A",
"HIT",
"MISS",
"L1",
"L2",
"Walker",
"Fault",
};
#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
char out[64];
size_t sz = sizeof(out) - 1; /* -1 for null termination */
size_t l = 0, i;
u64 m = PERF_MEM_TLB_NA;
u64 hit, miss;
out[0] = '\0';
if (he->mem_info)
m = he->mem_info->data_src.mem_dtlb;
hit = m & PERF_MEM_TLB_HIT;
miss = m & PERF_MEM_TLB_MISS;
/* already taken care of */
m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
if (!(m & 0x1))
continue;
if (l) {
strcat(out, " or ");
l += 4;
}
strncat(out, tlb_access[i], sz - l);
l += strlen(tlb_access[i]);
}
if (*out == '\0')
strcpy(out, "N/A");
if (hit)
strncat(out, " hit", sz - l);
if (miss)
strncat(out, " miss", sz - l);
return repsep_snprintf(bf, size, "%-*s", width, out);
}
static int64_t
sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
{
union perf_mem_data_src data_src_l;
union perf_mem_data_src data_src_r;
if (left->mem_info)
data_src_l = left->mem_info->data_src;
else
data_src_l.mem_lvl = PERF_MEM_LVL_NA;
if (right->mem_info)
data_src_r = right->mem_info->data_src;
else
data_src_r.mem_lvl = PERF_MEM_LVL_NA;
return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
}
static const char * const mem_lvl[] = {
"N/A",
"HIT",
"MISS",
"L1",
"LFB",
"L2",
"L3",
"Local RAM",
"Remote RAM (1 hop)",
"Remote RAM (2 hops)",
"Remote Cache (1 hop)",
"Remote Cache (2 hops)",
"I/O",
"Uncached",
};
#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
char out[64];
size_t sz = sizeof(out) - 1; /* -1 for null termination */
size_t i, l = 0;
u64 m = PERF_MEM_LVL_NA;
u64 hit, miss;
if (he->mem_info)
m = he->mem_info->data_src.mem_lvl;
out[0] = '\0';
hit = m & PERF_MEM_LVL_HIT;
miss = m & PERF_MEM_LVL_MISS;
/* already taken care of */
m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
if (!(m & 0x1))
continue;
if (l) {
strcat(out, " or ");
l += 4;
}
strncat(out, mem_lvl[i], sz - l);
l += strlen(mem_lvl[i]);
}
if (*out == '\0')
strcpy(out, "N/A");
if (hit)
strncat(out, " hit", sz - l);
if (miss)
strncat(out, " miss", sz - l);
return repsep_snprintf(bf, size, "%-*s", width, out);
}
static int64_t
sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
{
union perf_mem_data_src data_src_l;
union perf_mem_data_src data_src_r;
if (left->mem_info)
data_src_l = left->mem_info->data_src;
else
data_src_l.mem_snoop = PERF_MEM_SNOOP_NA;
if (right->mem_info)
data_src_r = right->mem_info->data_src;
else
data_src_r.mem_snoop = PERF_MEM_SNOOP_NA;
return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
}
static const char * const snoop_access[] = {
"N/A",
"None",
"Miss",
"Hit",
"HitM",
};
#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
char out[64];
size_t sz = sizeof(out) - 1; /* -1 for null termination */
size_t i, l = 0;
u64 m = PERF_MEM_SNOOP_NA;
out[0] = '\0';
if (he->mem_info)
m = he->mem_info->data_src.mem_snoop;
for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
if (!(m & 0x1))
continue;
if (l) {
strcat(out, " or ");
l += 4;
}
strncat(out, snoop_access[i], sz - l);
l += strlen(snoop_access[i]);
}
if (*out == '\0')
strcpy(out, "N/A");
return repsep_snprintf(bf, size, "%-*s", width, out);
}
struct sort_entry sort_mispredict = {
.se_header = "Branch Mispredicted",
.se_cmp = sort__mispredict_cmp,
.se_snprintf = hist_entry__mispredict_snprintf,
.se_width_idx = HISTC_MISPREDICT,
};
static u64 he_weight(struct hist_entry *he)
{
return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
}
static int64_t
sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
{
return he_weight(left) - he_weight(right);
}
static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
}
struct sort_entry sort_local_weight = {
.se_header = "Local Weight",
.se_cmp = sort__local_weight_cmp,
.se_snprintf = hist_entry__local_weight_snprintf,
.se_width_idx = HISTC_LOCAL_WEIGHT,
};
static int64_t
sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
{
return left->stat.weight - right->stat.weight;
}
static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
}
struct sort_entry sort_global_weight = {
.se_header = "Weight",
.se_cmp = sort__global_weight_cmp,
.se_snprintf = hist_entry__global_weight_snprintf,
.se_width_idx = HISTC_GLOBAL_WEIGHT,
};
struct sort_entry sort_mem_daddr_sym = {
.se_header = "Data Symbol",
.se_cmp = sort__daddr_cmp,
.se_snprintf = hist_entry__daddr_snprintf,
.se_width_idx = HISTC_MEM_DADDR_SYMBOL,
};
struct sort_entry sort_mem_daddr_dso = {
.se_header = "Data Object",
.se_cmp = sort__dso_daddr_cmp,
.se_snprintf = hist_entry__dso_daddr_snprintf,
.se_width_idx = HISTC_MEM_DADDR_SYMBOL,
};
struct sort_entry sort_mem_locked = {
.se_header = "Locked",
.se_cmp = sort__locked_cmp,
.se_snprintf = hist_entry__locked_snprintf,
.se_width_idx = HISTC_MEM_LOCKED,
};
struct sort_entry sort_mem_tlb = {
.se_header = "TLB access",
.se_cmp = sort__tlb_cmp,
.se_snprintf = hist_entry__tlb_snprintf,
.se_width_idx = HISTC_MEM_TLB,
};
struct sort_entry sort_mem_lvl = {
.se_header = "Memory access",
.se_cmp = sort__lvl_cmp,
.se_snprintf = hist_entry__lvl_snprintf,
.se_width_idx = HISTC_MEM_LVL,
};
struct sort_entry sort_mem_snoop = {
.se_header = "Snoop",
.se_cmp = sort__snoop_cmp,
.se_snprintf = hist_entry__snoop_snprintf,
.se_width_idx = HISTC_MEM_SNOOP,
};
static int64_t
sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
{
return left->branch_info->flags.abort !=
right->branch_info->flags.abort;
}
static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
static const char *out = ".";
if (he->branch_info->flags.abort)
out = "A";
return repsep_snprintf(bf, size, "%-*s", width, out);
}
struct sort_entry sort_abort = {
.se_header = "Transaction abort",
.se_cmp = sort__abort_cmp,
.se_snprintf = hist_entry__abort_snprintf,
.se_width_idx = HISTC_ABORT,
};
static int64_t
sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
{
return left->branch_info->flags.in_tx !=
right->branch_info->flags.in_tx;
}
static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
static const char *out = ".";
if (he->branch_info->flags.in_tx)
out = "T";
return repsep_snprintf(bf, size, "%-*s", width, out);
}
struct sort_entry sort_in_tx = {
.se_header = "Branch in transaction",
.se_cmp = sort__in_tx_cmp,
.se_snprintf = hist_entry__in_tx_snprintf,
.se_width_idx = HISTC_IN_TX,
};
static int64_t
sort__transaction_cmp(struct hist_entry *left, struct hist_entry *right)
{
return left->transaction - right->transaction;
}
static inline char *add_str(char *p, const char *str)
{
strcpy(p, str);
return p + strlen(str);
}
static struct txbit {
unsigned flag;
const char *name;
int skip_for_len;
} txbits[] = {
{ PERF_TXN_ELISION, "EL ", 0 },
{ PERF_TXN_TRANSACTION, "TX ", 1 },
{ PERF_TXN_SYNC, "SYNC ", 1 },
{ PERF_TXN_ASYNC, "ASYNC ", 0 },
{ PERF_TXN_RETRY, "RETRY ", 0 },
{ PERF_TXN_CONFLICT, "CON ", 0 },
{ PERF_TXN_CAPACITY_WRITE, "CAP-WRITE ", 1 },
{ PERF_TXN_CAPACITY_READ, "CAP-READ ", 0 },
{ 0, NULL, 0 }
};
int hist_entry__transaction_len(void)
{
int i;
int len = 0;
for (i = 0; txbits[i].name; i++) {
if (!txbits[i].skip_for_len)
len += strlen(txbits[i].name);
}
len += 4; /* :XX<space> */
return len;
}
static int hist_entry__transaction_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
u64 t = he->transaction;
char buf[128];
char *p = buf;
int i;
buf[0] = 0;
for (i = 0; txbits[i].name; i++)
if (txbits[i].flag & t)
p = add_str(p, txbits[i].name);
if (t && !(t & (PERF_TXN_SYNC|PERF_TXN_ASYNC)))
p = add_str(p, "NEITHER ");
if (t & PERF_TXN_ABORT_MASK) {
sprintf(p, ":%" PRIx64,
(t & PERF_TXN_ABORT_MASK) >>
PERF_TXN_ABORT_SHIFT);
p += strlen(p);
}
return repsep_snprintf(bf, size, "%-*s", width, buf);
}
struct sort_entry sort_transaction = {
.se_header = "Transaction ",
.se_cmp = sort__transaction_cmp,
.se_snprintf = hist_entry__transaction_snprintf,
.se_width_idx = HISTC_TRANSACTION,
};
struct sort_dimension {
const char *name;
struct sort_entry *entry;
int taken;
};
#define DIM(d, n, func) [d] = { .name = n, .entry = &(func) }
static struct sort_dimension common_sort_dimensions[] = {
DIM(SORT_PID, "pid", sort_thread),
DIM(SORT_COMM, "comm", sort_comm),
DIM(SORT_DSO, "dso", sort_dso),
DIM(SORT_SYM, "symbol", sort_sym),
DIM(SORT_PARENT, "parent", sort_parent),
DIM(SORT_CPU, "cpu", sort_cpu),
perf tools: Add sort by src line/number Using addr2line for now, requires debuginfo, needs more work to support detached debuginfo, aka foo-debuginfo packages. Example: [root@sandy ~]# perf record -a sleep 3 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.555 MB perf.data (~24236 samples) ] [root@sandy ~]# perf report -s dso,srcline 2>&1 | grep -v ^# | head -5 22.41% [kernel.kallsyms] /home/git/linux/drivers/idle/intel_idle.c:280 4.79% [kernel.kallsyms] /home/git/linux/drivers/cpuidle/cpuidle.c:148 4.78% [kernel.kallsyms] /home/git/linux/arch/x86/include/asm/atomic64_64.h:121 4.49% [kernel.kallsyms] /home/git/linux/kernel/sched/core.c:1690 4.30% [kernel.kallsyms] /home/git/linux/include/linux/seqlock.h:90 [root@sandy ~]# [root@sandy ~]# perf top -U -s dso,symbol,srcline Samples: 1K of event 'cycles', Event count (approx.): 589617389 18.66% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:143 7.83% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:39 6.59% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:38 3.66% [kernel] [k] page_fault /home/git/linux/arch/x86/kernel/entry_64.S:1379 3.25% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:40 3.12% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:37 2.74% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:36 2.39% [kernel] [k] clear_page /home/git/linux/arch/x86/lib/clear_page_64.S:43 2.12% [kernel] [k] ioread32 /home/git/linux/lib/iomap.c:90 1.51% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:144 1.19% [kernel] [k] copy_user_generic_unrolled /home/git/linux/arch/x86/lib/copy_user_64.S:154 Suggested-by: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pdmqbng9twz06jzkbgtuwbp8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-05-30 13:33:24 +00:00
DIM(SORT_SRCLINE, "srcline", sort_srcline),
DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
DIM(SORT_TRANSACTION, "transaction", sort_transaction),
};
#undef DIM
#define DIM(d, n, func) [d - __SORT_BRANCH_STACK] = { .name = n, .entry = &(func) }
static struct sort_dimension bstack_sort_dimensions[] = {
DIM(SORT_DSO_FROM, "dso_from", sort_dso_from),
DIM(SORT_DSO_TO, "dso_to", sort_dso_to),
DIM(SORT_SYM_FROM, "symbol_from", sort_sym_from),
DIM(SORT_SYM_TO, "symbol_to", sort_sym_to),
DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
DIM(SORT_IN_TX, "in_tx", sort_in_tx),
DIM(SORT_ABORT, "abort", sort_abort),
};
#undef DIM
#define DIM(d, n, func) [d - __SORT_MEMORY_MODE] = { .name = n, .entry = &(func) }
static struct sort_dimension memory_sort_dimensions[] = {
DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
};
#undef DIM
struct hpp_sort_entry {
struct perf_hpp_fmt hpp;
struct sort_entry *se;
};
static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct perf_evsel *evsel)
{
struct hpp_sort_entry *hse;
size_t len;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
}
static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
struct perf_hpp *hpp __maybe_unused,
struct perf_evsel *evsel)
{
struct hpp_sort_entry *hse;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
return hists__col_len(&evsel->hists, hse->se->se_width_idx);
}
static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
struct hist_entry *he)
{
struct hpp_sort_entry *hse;
size_t len;
hse = container_of(fmt, struct hpp_sort_entry, hpp);
len = hists__col_len(he->hists, hse->se->se_width_idx);
return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
}
static int __sort_dimension__add_hpp(struct sort_dimension *sd)
{
struct hpp_sort_entry *hse;
hse = malloc(sizeof(*hse));
if (hse == NULL) {
pr_err("Memory allocation failed\n");
return -1;
}
hse->se = sd->entry;
hse->hpp.header = __sort__hpp_header;
hse->hpp.width = __sort__hpp_width;
hse->hpp.entry = __sort__hpp_entry;
hse->hpp.color = NULL;
hse->hpp.cmp = sd->entry->se_cmp;
hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp;
hse->hpp.sort = hse->hpp.collapse;
INIT_LIST_HEAD(&hse->hpp.list);
INIT_LIST_HEAD(&hse->hpp.sort_list);
perf_hpp__register_sort_field(&hse->hpp);
return 0;
}
static int __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
{
if (sd->taken)
return 0;
if (__sort_dimension__add_hpp(sd) < 0)
return -1;
if (sd->entry->se_collapse)
sort__need_collapse = 1;
if (list_empty(&hist_entry__sort_list))
sort__first_dimension = idx;
list_add_tail(&sd->entry->list, &hist_entry__sort_list);
sd->taken = 1;
return 0;
}
int sort_dimension__add(const char *tok)
{
unsigned int i;
for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
struct sort_dimension *sd = &common_sort_dimensions[i];
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
if (sd->entry == &sort_parent) {
int ret = regcomp(&parent_regex, parent_pattern, REG_EXTENDED);
if (ret) {
char err[BUFSIZ];
regerror(ret, &parent_regex, err, sizeof(err));
pr_err("Invalid regex: %s\n%s", parent_pattern, err);
return -EINVAL;
}
sort__has_parent = 1;
} else if (sd->entry == &sort_sym) {
sort__has_sym = 1;
} else if (sd->entry == &sort_dso) {
sort__has_dso = 1;
}
return __sort_dimension__add(sd, i);
}
for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
struct sort_dimension *sd = &bstack_sort_dimensions[i];
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
if (sort__mode != SORT_MODE__BRANCH)
return -EINVAL;
if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
sort__has_sym = 1;
__sort_dimension__add(sd, i + __SORT_BRANCH_STACK);
return 0;
}
for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
struct sort_dimension *sd = &memory_sort_dimensions[i];
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
if (sort__mode != SORT_MODE__MEMORY)
return -EINVAL;
if (sd->entry == &sort_mem_daddr_sym)
sort__has_sym = 1;
__sort_dimension__add(sd, i + __SORT_MEMORY_MODE);
return 0;
}
return -ESRCH;
}
int setup_sorting(void)
{
char *tmp, *tok, *str = strdup(sort_order);
int ret = 0;
if (str == NULL) {
error("Not enough memory to setup sort keys");
return -ENOMEM;
}
for (tok = strtok_r(str, ", ", &tmp);
tok; tok = strtok_r(NULL, ", ", &tmp)) {
ret = sort_dimension__add(tok);
if (ret == -EINVAL) {
error("Invalid --sort key: `%s'", tok);
break;
} else if (ret == -ESRCH) {
error("Unknown --sort key: `%s'", tok);
break;
}
}
free(str);
return ret;
}
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 15:49:27 +00:00
static void sort_entry__setup_elide(struct sort_entry *se,
struct strlist *list,
const char *list_name, FILE *fp)
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 15:49:27 +00:00
{
if (list && strlist__nr_entries(list) == 1) {
if (fp != NULL)
fprintf(fp, "# %s: %s\n", list_name,
strlist__entry(list, 0)->s);
se->elide = true;
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 15:49:27 +00:00
}
}
void sort__setup_elide(FILE *output)
{
struct sort_entry *se;
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"dso", output);
sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
"comm", output);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
"symbol", output);
if (sort__mode == SORT_MODE__BRANCH) {
sort_entry__setup_elide(&sort_dso_from,
symbol_conf.dso_from_list,
"dso_from", output);
sort_entry__setup_elide(&sort_dso_to,
symbol_conf.dso_to_list,
"dso_to", output);
sort_entry__setup_elide(&sort_sym_from,
symbol_conf.sym_from_list,
"sym_from", output);
sort_entry__setup_elide(&sort_sym_to,
symbol_conf.sym_to_list,
"sym_to", output);
} else if (sort__mode == SORT_MODE__MEMORY) {
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"symbol_daddr", output);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"dso_daddr", output);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"mem", output);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"local_weight", output);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"tlb", output);
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
"snoop", output);
}
/*
* It makes no sense to elide all of sort entries.
* Just revert them to show up again.
*/
list_for_each_entry(se, &hist_entry__sort_list, list) {
if (!se->elide)
return;
}
list_for_each_entry(se, &hist_entry__sort_list, list)
se->elide = false;
}