Commit 382619c0 authored by Jiri Olsa's avatar Jiri Olsa Committed by Arnaldo Carvalho de Melo

perf tools: Speed up report for perf compiled with linwunwind

When compiled with libunwind, perf does some preparatory work when
processing side-band events. This is not needed when report actually
don't unwind dwarf callchains, so it's disabled with
dwarf_callchain_users bool.

However we could move that check to higher level and shield more
unwanted code for normal report processing, giving us following speed up
on kernel build profile:

Before:

  $ perf record make -j40
  ...
  $ ll ../../perf.data
  -rw-------. 1 jolsa jolsa 461783932 Apr 26 09:11 perf.data
  $ perf stat -e cycles:u,instructions:u perf report -i perf.data > out

   Performance counter stats for 'perf report -i perf.data':

    78,669,920,155      cycles:u
    99,076,431,951      instructions:u            #    1.26  insn per cycle

      55.382823668 seconds time elapsed

      27.512341000 seconds user
      27.712871000 seconds sys

After:

  $ perf stat -e cycles:u,instructions:u perf report -i perf.data > out

   Performance counter stats for 'perf report -i perf.data':

    59,626,798,904      cycles:u
    88,583,575,849      instructions:u            #    1.49  insn per cycle

      21.296935559 seconds time elapsed

      20.010191000 seconds user
       1.202935000 seconds sys

The speed is higher with profile having many side-band events,
because these trigger libunwind preparatory code.

This does not apply for perf compiled with libdw for dwarf unwind,
only for build with libunwind.
Signed-off-by: default avatarJiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190426073804.17238-1-jolsa@kernel.orgSigned-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 53dbabfe
...@@ -15,6 +15,7 @@ ...@@ -15,6 +15,7 @@
#include "map.h" #include "map.h"
#include "symbol.h" #include "symbol.h"
#include "unwind.h" #include "unwind.h"
#include "callchain.h"
#include <api/fs/fs.h> #include <api/fs/fs.h>
...@@ -327,7 +328,7 @@ static int thread__prepare_access(struct thread *thread) ...@@ -327,7 +328,7 @@ static int thread__prepare_access(struct thread *thread)
{ {
int err = 0; int err = 0;
if (symbol_conf.use_callchain) if (dwarf_callchain_users)
err = __thread__prepare_access(thread); err = __thread__prepare_access(thread);
return err; return err;
......
...@@ -617,8 +617,6 @@ static unw_accessors_t accessors = { ...@@ -617,8 +617,6 @@ static unw_accessors_t accessors = {
static int _unwind__prepare_access(struct thread *thread) static int _unwind__prepare_access(struct thread *thread)
{ {
if (!dwarf_callchain_users)
return 0;
thread->addr_space = unw_create_addr_space(&accessors, 0); thread->addr_space = unw_create_addr_space(&accessors, 0);
if (!thread->addr_space) { if (!thread->addr_space) {
pr_err("unwind: Can't create unwind address space.\n"); pr_err("unwind: Can't create unwind address space.\n");
...@@ -631,15 +629,11 @@ static int _unwind__prepare_access(struct thread *thread) ...@@ -631,15 +629,11 @@ static int _unwind__prepare_access(struct thread *thread)
static void _unwind__flush_access(struct thread *thread) static void _unwind__flush_access(struct thread *thread)
{ {
if (!dwarf_callchain_users)
return;
unw_flush_cache(thread->addr_space, 0, 0); unw_flush_cache(thread->addr_space, 0, 0);
} }
static void _unwind__finish_access(struct thread *thread) static void _unwind__finish_access(struct thread *thread)
{ {
if (!dwarf_callchain_users)
return;
unw_destroy_addr_space(thread->addr_space); unw_destroy_addr_space(thread->addr_space);
} }
......
...@@ -5,6 +5,7 @@ ...@@ -5,6 +5,7 @@
#include "session.h" #include "session.h"
#include "debug.h" #include "debug.h"
#include "env.h" #include "env.h"
#include "callchain.h"
struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops; struct unwind_libunwind_ops __weak *x86_32_unwind_libunwind_ops;
...@@ -24,6 +25,9 @@ int unwind__prepare_access(struct thread *thread, struct map *map, ...@@ -24,6 +25,9 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops; struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops;
int err; int err;
if (!dwarf_callchain_users)
return 0;
if (thread->addr_space) { if (thread->addr_space) {
pr_debug("unwind: thread map already set, dso=%s\n", pr_debug("unwind: thread map already set, dso=%s\n",
map->dso->name); map->dso->name);
...@@ -65,12 +69,18 @@ int unwind__prepare_access(struct thread *thread, struct map *map, ...@@ -65,12 +69,18 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
void unwind__flush_access(struct thread *thread) void unwind__flush_access(struct thread *thread)
{ {
if (!dwarf_callchain_users)
return;
if (thread->unwind_libunwind_ops) if (thread->unwind_libunwind_ops)
thread->unwind_libunwind_ops->flush_access(thread); thread->unwind_libunwind_ops->flush_access(thread);
} }
void unwind__finish_access(struct thread *thread) void unwind__finish_access(struct thread *thread)
{ {
if (!dwarf_callchain_users)
return;
if (thread->unwind_libunwind_ops) if (thread->unwind_libunwind_ops)
thread->unwind_libunwind_ops->finish_access(thread); thread->unwind_libunwind_ops->finish_access(thread);
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment