by Alexey Budankov

[permalink] [raw]

Subject: Re: [PATCH v14 3/3]: perf record: extend trace writing to multi AIO

Hi,

On 01.11.2018 21:30, Song Liu wrote:
> On Sun, Oct 14, 2018 at 11:47 PM Alexey Budankov
> <[email protected]> wrote:
>>
<SNIP>
>>
>>
>> static int nr_cblocks_default = 1;
>>
>> static int record__aio_parse(const struct option *opt,
>> - const char *str __maybe_unused,
>> + const char *str,
>> int unset)
>> {
>> struct record_opts *opts = (struct record_opts *)opt->value;
>>
>> - if (unset)
>> + if (unset) {
>> opts->nr_cblocks = 0;
>> - else
>> - opts->nr_cblocks = nr_cblocks_default;
>> + } else {
>> + if (str)
>> + opts->nr_cblocks = strtol(str, NULL, 0);
>> + if (!opts->nr_cblocks)
>> + opts->nr_cblocks = nr_cblocks_default;
>> + }
>>
>> return 0;
>> }
>> #else /* HAVE_AIO_SUPPORT */
<SNIP>
>> @@ -1492,6 +1517,13 @@ static int perf_record_config(const char *var, const char *value, void *cb)
>> var = "call-graph.record-mode";
>> return perf_default_config(var, value, cb);
>> }
>> +#ifdef HAVE_AIO_SUPPORT
>> + if (!strcmp(var, "record.aio")) {
>> + rec->opts.nr_cblocks = strtol(value, NULL, 0);
>> + if (!rec->opts.nr_cblocks)
>> + rec->opts.nr_cblocks = nr_cblocks_default;
>> + }
>> +#endif
>>
>> return 0;
>> }
>> @@ -1884,8 +1916,8 @@ static struct option __record_options[] = {
>> OPT_BOOLEAN(0, "dry-run", &dry_run,
>> "Parse options then exit"),
>> #ifdef HAVE_AIO_SUPPORT
>> - OPT_CALLBACK_NOOPT(0, "aio", &record.opts,
>> - NULL, "Enable asynchronous trace writing mode",
>> + OPT_CALLBACK_OPTARG(0, "aio", &record.opts,
>> + &nr_cblocks_default, "n", "Use <n> control blocks in asynchronous trace writing mode (default: 1, max: 4)",
>> record__aio_parse),
>> #endif
>> OPT_END()
>> @@ -2080,6 +2112,8 @@ int cmd_record(int argc, const char **argv)
>> goto out;
>> }
>>
>> + if (rec->opts.nr_cblocks > 4)
>> + rec->opts.nr_cblocks = 4;
> nit: I feel this logic belongs to record__aio_parse(). And we should have
>
> static int nr_cblocks_max = 4;

This looks reasonable.

Thanks,
Alexey

>
> Other than this
>
> Acked-by: Song Liu <[email protected]>
>

2018-11-02 16:15:39

by Alexey Budankov

[permalink] [raw]

Subject: Re: [PATCH v14 1/3]: perf util: map data buffer for preserving collected data

Hi,

On 01.11.2018 21:47, Song Liu wrote:
> On Sun, Oct 14, 2018 at 11:44 PM Alexey Budankov
> <[email protected]> wrote:
>>
>>
>> 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 <[email protected]>
>
> Acked-by: Song Liu <[email protected]>

Thanks for review!

>
> Shall we add libaio to tools/build/Makefile.feature? It will be great to see
> whether aio is enabled in "Auto-detecting system features:".

Yes. This makes sense. There are targeted libc implementations that
currently lack Posix AIO API support required for this patch kit.

Thanks,
Alexey

>
> Thanks for implementing this!
>
> Song
>
>> ---
>> Changes in v13:
>> - grouped aio functions under single #ifdef HAVE_AIO_SUPPORT
>> Changes in v12:
>> - applied stub functions design for the whole patch kit
>> - grouped AIO related data into a struct under struct perf_mmap
>> 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 | 2 +-
>> tools/perf/util/mmap.c | 49 +++++++++++++++++++++++++++++++++++++++++++++-
>> tools/perf/util/mmap.h | 11 ++++++++++-
>> 5 files changed, 70 insertions(+), 4 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..1a83bf2c069c 100644
>> --- a/tools/perf/util/evlist.c
>> +++ b/tools/perf/util/evlist.c
>> @@ -1028,7 +1028,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
>> * Its value is decided by evsel's write_backward.
>> * So &mp should not be passed through const pointer.
>> */
>> - struct mmap_params mp;
>> + struct mmap_params mp = { .nr_cblocks = 0 };
>>
>> if (!evlist->mmap)
>> evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
>> diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
>> index cdb95b3a1213..47cdc3ad6546 100644
>> --- a/tools/perf/util/mmap.c
>> +++ b/tools/perf/util/mmap.c
>> @@ -153,8 +153,55 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
>> {
>> }
>>
>> +#ifdef HAVE_AIO_SUPPORT
>> +static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
>> +{
>> + int delta_max;
>> +
>> + if (mp->nr_cblocks) {
>> + map->aio.data = malloc(perf_mmap__mmap_len(map));
>> + if (!map->aio.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->aio.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->aio.cblock.aio_reqprio = delta_max;
>> + }
>> +
>> + return 0;
>> +}
>> +
>> +static void perf_mmap__aio_munmap(struct perf_mmap *map)
>> +{
>> + if (map->aio.data)
>> + zfree(&map->aio.data);
>> +}
>> +#else
>> +static int perf_mmap__aio_mmap(struct perf_mmap *map __maybe_unused,
>> + struct mmap_params *mp __maybe_unused)
>> +{
>> + return 0;
>> +}
>> +
>> +static void perf_mmap__aio_munmap(struct perf_mmap *map __maybe_unused)
>> +{
>> +}
>> +#endif
>> +
>> void perf_mmap__munmap(struct perf_mmap *map)
>> {
>> + perf_mmap__aio_munmap(map);
>> if (map->base != NULL) {
>> munmap(map->base, perf_mmap__mmap_len(map));
>> map->base = NULL;
>> @@ -197,7 +244,7 @@ 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;
>> + return perf_mmap__aio_mmap(map, mp);
>> }
>>
>> 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..a46dbdcdcc8a 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 +29,12 @@ struct perf_mmap {
>> bool overwrite;
>> struct auxtrace_mmap auxtrace_mmap;
>> char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
>> +#ifdef HAVE_AIO_SUPPORT
>> + struct {
>> + void *data;
>> + struct aiocb cblock;
>> + } aio;
>> +#endif
>> };
>>
>> /*
>> @@ -57,7 +66,7 @@ enum bkw_mmap_state {
>> };
>>
>> struct mmap_params {
>> - int prot, mask;
>> + int prot, mask, nr_cblocks;
>> struct auxtrace_mmap_params auxtrace_mp;
>> };
>>
>