Hi Jiri,
2014-04-17 (목), 19:39 +0200, Jiri Olsa:
> Caching registers value into an array. Got about 4% speed up
> of perf_reg_value function for report command processing
> dwarf unwind stacks.
I'm not familiar with the code base, so probably silly questions: Where
does the speed up come from? IOW I don't know what's the difference
between the regs->regs and regs->cached_regs. And does the cached_regs
contain correct values of registers for each frame?
Thanks,
Namhyung
>
> Output from report over 1.5 GB data with DWARF unwind stacks:
> (TODO fix perf diff)
>
> current code:
> 6.81% perf.old perf.old [.] perf_reg_value
>
> change:
> 2.24% perf perf [.] perf_reg_value
>
> And little bit of speed up:
>
> Performance counter stats for './perf.old report -i perf-test.data --stdio':
>
> 134,664,011,577 cycles:u # 2.472 GHz
> 189,677,227,475 instructions:u # 1.41 insns per cycle
> 54465.096050 task-clock (msec) # 0.998 CPUs utilized
>
> 54.598339009 seconds time elapsed
>
> Performance counter stats for './perf report -i perf-test.data --stdio':
>
> 124,478,681,672 cycles:u # 2.466 GHz
> 168,998,379,866 instructions:u # 1.36 insns per cycle
> 50487.110482 task-clock (msec) # 0.997 CPUs utilized
>
> 50.635824229 seconds time elapsed
>
> Cc: Corey Ashford <cjash...@linux.vnet.ibm.com>
> Cc: David Ahern <dsah...@gmail.com>
> Cc: Frederic Weisbecker <fweis...@gmail.com>
> Cc: Ingo Molnar <mi...@kernel.org>
> Cc: Namhyung Kim <namhy...@kernel.org>
> Cc: Paul Mackerras <pau...@samba.org>
> Cc: Peter Zijlstra <a.p.zijls...@chello.nl>
> Cc: Arnaldo Carvalho de Melo <a...@ghostprotocols.net>
> Cc: Jean Pihet <jean.pi...@linaro.org>
> Signed-off-by: Jiri Olsa <jo...@redhat.com>
> ---
> tools/perf/util/event.h | 5 +++++
> tools/perf/util/perf_regs.c | 10 +++++++++-
> tools/perf/util/perf_regs.h | 4 +++-
> 3 files changed, 17 insertions(+), 2 deletions(-)
>
> diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
> index 38457d4..970d4eb 100644
> --- a/tools/perf/util/event.h
> +++ b/tools/perf/util/event.h
> @@ -7,6 +7,7 @@
> #include "../perf.h"
> #include "map.h"
> #include "build-id.h"
> +#include "perf_regs.h"
>
> struct mmap_event {
> struct perf_event_header header;
> @@ -87,6 +88,10 @@ struct regs_dump {
> u64 abi;
> u64 mask;
> u64 *regs;
> +
> + /* Cached values/mask filled by first register access. */
> + u64 cache_regs[PERF_REGS_MAX];
> + u64 cache_mask;
> };
>
> struct stack_dump {
> diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
> index a3539ef..43168fb 100644
> --- a/tools/perf/util/perf_regs.c
> +++ b/tools/perf/util/perf_regs.c
> @@ -1,11 +1,15 @@
> #include <errno.h>
> #include "perf_regs.h"
> +#include "event.h"
>
> int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
> {
> int i, idx = 0;
> u64 mask = regs->mask;
>
> + if (regs->cache_mask & (1 << id))
> + goto out;
> +
> if (!(mask & (1 << id)))
> return -EINVAL;
>
> @@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int
> id)
> idx++;
> }
>
> - *valp = regs->regs[idx];
> + regs->cache_mask |= (1 << id);
> + regs->cache_regs[id] = regs->regs[idx];
> +
> +out:
> + *valp = regs->cache_regs[id];
> return 0;
> }
> diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
> index d6e8b6a..80d8ab1 100644
> --- a/tools/perf/util/perf_regs.h
> +++ b/tools/perf/util/perf_regs.h
> @@ -2,15 +2,17 @@
> #define __PERF_REGS_H
>
> #include "types.h"
> -#include "event.h"
>
> #ifdef HAVE_PERF_REGS_SUPPORT
> #include <perf_regs.h>
>
> +struct regs_dump;
> +
> int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
>
> #else
> #define PERF_REGS_MASK 0
> +#define PERF_REGS_MAX 0
>
> static inline const char *perf_reg_name(int id __maybe_unused)
> {
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
