The map->data buffer is used to preserve map->base profiling data
for writing to disk. AIO map->cblock is used to queue corresponding
map->data buffer for asynchronous writing.
Signed-off-by: Alexey Budankov <alexey.budan...@linux.intel.com>
---
Changes in v10:
- moved specific code to perf_mmap__aio_mmap(), perf_mmap__aio_munmap()
- adjusted error reporting by using %m
Changes in v9:
- implemented NO_AIO and HAVE_AIO_SUPPORT defines to cover cases of
libc implementations without Posix AIO API support
Changes in v7:
- implemented handling record.aio setting from perfconfig file
Changes in v6:
- adjusted setting of priorities for cblocks;
Changes in v5:
- reshaped layout of data structures;
- implemented --aio option;
Changes in v4:
- converted mmap()/munmap() to malloc()/free() for mmap->data buffer
management
Changes in v2:
- converted zalloc() to calloc() for allocation of mmap_aio array,
- cleared typo and adjusted fallback branch code;
---
tools/perf/Makefile.config | 5 +++++
tools/perf/Makefile.perf | 7 ++++++-
tools/perf/util/evlist.c | 4 +++-
tools/perf/util/mmap.c | 48 +++++++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/mmap.h | 11 +++++++++++
5 files changed, 72 insertions(+), 3 deletions(-)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f6d1a03c7523..2e90f4ce9214 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -355,6 +355,11 @@ endif # NO_LIBELF
ifeq ($(feature-glibc), 1)
CFLAGS += -DHAVE_GLIBC_SUPPORT
+ ifndef NO_AIO
+ ifndef BIONIC
+ CFLAGS += -DHAVE_AIO_SUPPORT
+ endif
+ endif
endif
ifdef NO_DWARF
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 92514fb3689f..7becc6a72cf2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -97,8 +97,13 @@ include ../scripts/utilities.mak
# Define LIBCLANGLLVM if you DO want builtin clang and llvm support.
# When selected, pass LLVM_CONFIG=/path/to/llvm-config to `make' if
# llvm-config is not in $PATH.
-
+#
# Define NO_CORESIGHT if you do not want support for CoreSight trace decoding.
+#
+# Define NO_AIO if you do not want support of Posix AIO based trace
+# streaming for record mode. Currently Posix AIO trace streaming is
+# supported only when linking with glibc.
+#
# As per kernel Makefile, avoid funny character set dependencies
unexport LC_ALL
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index be440df29615..af2f8c965d7a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1029,7 +1029,9 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist,
unsigned int pages,
* So &mp should not be passed through const pointer.
*/
struct mmap_params mp;
-
+#ifdef HAVE_AIO_SUPPORT
+ mp.nr_cblocks = 0;
+#endif
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
if (!evlist->mmap)
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index cdb95b3a1213..db8f16f8a363 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -153,8 +153,19 @@ void __weak auxtrace_mmap_params__set_idx(struct
auxtrace_mmap_params *mp __mayb
{
}
+#ifdef HAVE_AIO_SUPPORT
+static void perf_mmap__aio_munmap(struct perf_mmap *map)
+{
+ if (map->data)
+ zfree(&map->data);
+}
+#endif
+
void perf_mmap__munmap(struct perf_mmap *map)
{
+#ifdef HAVE_AIO_SUPPORT
+ perf_mmap__aio_munmap(map);
+#endif
if (map->base != NULL) {
munmap(map->base, perf_mmap__mmap_len(map));
map->base = NULL;
@@ -164,8 +175,40 @@ void perf_mmap__munmap(struct perf_mmap *map)
auxtrace_mmap__munmap(&map->auxtrace_mmap);
}
+#ifdef HAVE_AIO_SUPPORT
+static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
+{
+ int delta_max;
+
+ map->nr_cblocks = mp->nr_cblocks;
+ if (map->nr_cblocks) {
+ map->data = malloc(perf_mmap__mmap_len(map));
+ if (!map->data) {
+ pr_debug2("failed to allocate data buffer, error %m\n");
+ return -1;
+ }
+ /*
+ * Use cblock.aio_fildes value different from -1
+ * to denote started aio write operation on the
+ * cblock so it requires explicit record__aio_sync()
+ * call prior the cblock may be reused again.
+ */
+ map->cblock.aio_fildes = -1;
+ /*
+ * Allocate cblock with max priority delta to
+ * have faster aio write system calls.
+ */
+ delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
+ map->cblock.aio_reqprio = delta_max;
+ }
+
+ return 0;
+}
+#endif
+
int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int
cpu)
{
+ int rc = 0;
/*
* The last one will be done at perf_mmap__consume(), so that we
* make sure we don't prevent tools from consuming every last event in
@@ -197,7 +240,10 @@ int perf_mmap__mmap(struct perf_mmap *map, struct
mmap_params *mp, int fd, int c
&mp->auxtrace_mp, map->base, fd))
return -1;
- return 0;
+#ifdef HAVE_AIO_SUPPORT
+ rc = perf_mmap__aio_mmap(map, mp);
+#endif
+ return rc;
}
static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end)
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index e603314dc792..1b63b6cc7cf9 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -6,6 +6,9 @@
#include <linux/types.h>
#include <asm/barrier.h>
#include <stdbool.h>
+#ifdef HAVE_AIO_SUPPORT
+#include <aio.h>
+#endif
#include "auxtrace.h"
#include "event.h"
@@ -26,6 +29,11 @@ struct perf_mmap {
bool overwrite;
struct auxtrace_mmap auxtrace_mmap;
char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+#ifdef HAVE_AIO_SUPPORT
+ void *data;
+ struct aiocb cblock;
+ int nr_cblocks;
+#endif
};
/*
@@ -59,6 +67,9 @@ enum bkw_mmap_state {
struct mmap_params {
int prot, mask;
struct auxtrace_mmap_params auxtrace_mp;
+#ifdef HAVE_AIO_SUPPORT
+ int nr_cblocks;
+#endif
};
int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int
cpu);
