linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Nick Terrell <terrelln@fb.com>,
	Kan Liang <kan.liang@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>, Kajol Jain <kjain@linux.ibm.com>,
	Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
	Huacai Chen <chenhuacai@kernel.org>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	Vincent Whitchurch <vincent.whitchurch@axis.com>,
	"Steinar H. Gunderson" <sesse@google.com>,
	Liam Howlett <liam.howlett@oracle.com>,
	Miguel Ojeda <ojeda@kernel.org>,
	Colin Ian King <colin.i.king@gmail.com>,
	Dmitrii Dolgov <9erthalion6@gmail.com>,
	Yang Jihong <yangjihong1@huawei.com>,
	Ming Wang <wangming01@loongson.cn>,
	James Clark <james.clark@arm.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Sean Christopherson <seanjc@google.com>,
	Leo Yan <leo.yan@linaro.org>,
	Ravi Bangoria <ravi.bangoria@amd.com>,
	German Gomez <german.gomez@arm.com>,
	Changbin Du <changbin.du@huawei.com>,
	Paolo Bonzini <pbonzini@redhat.com>, Li Dong <lidong@vivo.com>,
	Sandipan Das <sandipan.das@amd.com>,
	liuwenyu <liuwenyu7@huawei.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Guilherme Amadio <amadio@gentoo.org>
Subject: Re: [PATCH v5 06/50] tools lib api: Add io_dir an allocation free readdir alternative
Date: Thu, 30 Nov 2023 14:21:47 -0300	[thread overview]
Message-ID: <ZWjEqw1cAw/eIpQH@kernel.org> (raw)
In-Reply-To: <20231127220902.1315692-7-irogers@google.com>

Em Mon, Nov 27, 2023 at 02:08:18PM -0800, Ian Rogers escreveu:
> glibc's opendir allocates a minimum of 32kb, when called recursively
> for a directory tree the memory consumption can add up - nearly 300kb
> during perf start-up when processing modules. Add a stack allocated
> variant of readdir sized a little more than 1kb.

Now, on some systems:

  CC      /tmp/build/perf/pmu-events/pmu-events.o
In file included from util/machine.c:39:
/tmp/build/perf/libapi/include/api/io_dir.h: In function ‘io_dir__readdir’:
/tmp/build/perf/libapi/include/api/io_dir.h:46:16: error: implicit declaration of function ‘getdents64’; did you mean ‘getentropy’? [-Werror=implicit-function-declaration]
   ssize_t rc = getdents64(iod->dirfd, iod->buff, sizeof(iod->buff));
                ^~~~~~~~~~
                getentropy
  CC      /tmp/build/perf/tests/workloads/brstack.o
  CC      /tmp/build/perf/tests/workloads/datasym.o
  CC      /tmp/build/perf/util/maps.o

 
> Signed-off-by: Ian Rogers <irogers@google.com>
> ---
>  tools/lib/api/Makefile |  2 +-
>  tools/lib/api/io_dir.h | 75 ++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 76 insertions(+), 1 deletion(-)
>  create mode 100644 tools/lib/api/io_dir.h
> 
> diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
> index 044860ac1ed1..186aa407de8c 100644
> --- a/tools/lib/api/Makefile
> +++ b/tools/lib/api/Makefile
> @@ -99,7 +99,7 @@ install_lib: $(LIBFILE)
>  		$(call do_install_mkdir,$(libdir_SQ)); \
>  		cp -fpR $(LIBFILE) $(DESTDIR)$(libdir_SQ)
>  
> -HDRS := cpu.h debug.h io.h
> +HDRS := cpu.h debug.h io.h io_dir.h
>  FD_HDRS := fd/array.h
>  FS_HDRS := fs/fs.h fs/tracing_path.h
>  INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/api
> diff --git a/tools/lib/api/io_dir.h b/tools/lib/api/io_dir.h
> new file mode 100644
> index 000000000000..f3479006edb6
> --- /dev/null
> +++ b/tools/lib/api/io_dir.h
> @@ -0,0 +1,75 @@
> +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
> +/*
> + * Lightweight directory reading library.
> + */
> +#ifndef __API_IO_DIR__
> +#define __API_IO_DIR__
> +
> +#include <dirent.h>
> +#include <fcntl.h>
> +#include <stdlib.h>
> +#include <unistd.h>
> +#include <sys/stat.h>
> +
> +struct io_dirent64 {
> +	ino64_t        d_ino;    /* 64-bit inode number */
> +	off64_t        d_off;    /* 64-bit offset to next structure */
> +	unsigned short d_reclen; /* Size of this dirent */
> +	unsigned char  d_type;   /* File type */
> +	char           d_name[NAME_MAX + 1]; /* Filename (null-terminated) */
> +};
> +
> +struct io_dir {
> +	int dirfd;
> +	ssize_t available_bytes;
> +	struct io_dirent64 *next;
> +	struct io_dirent64 buff[4];
> +};
> +
> +static inline void io_dir__init(struct io_dir *iod, int dirfd)
> +{
> +	iod->dirfd = dirfd;
> +	iod->available_bytes = 0;
> +}
> +
> +static inline void io_dir__rewinddir(struct io_dir *iod)
> +{
> +	lseek(iod->dirfd, 0, SEEK_SET);
> +	iod->available_bytes = 0;
> +}
> +
> +static inline struct io_dirent64 *io_dir__readdir(struct io_dir *iod)
> +{
> +	struct io_dirent64 *entry;
> +
> +	if (iod->available_bytes <= 0) {
> +		ssize_t rc = getdents64(iod->dirfd, iod->buff, sizeof(iod->buff));
> +
> +		if (rc <= 0)
> +			return NULL;
> +		iod->available_bytes = rc;
> +		iod->next = iod->buff;
> +	}
> +	entry = iod->next;
> +	iod->next = (struct io_dirent64 *)((char *)entry + entry->d_reclen);
> +	iod->available_bytes -= entry->d_reclen;
> +	return entry;
> +}
> +
> +static inline bool io_dir__is_dir(const struct io_dir *iod, struct io_dirent64 *dent)
> +{
> +	if (dent->d_type == DT_UNKNOWN) {
> +		struct stat st;
> +
> +		if (fstatat(iod->dirfd, dent->d_name, &st, /*flags=*/0))
> +			return false;
> +
> +		if (S_ISDIR(st.st_mode)) {
> +			dent->d_type = DT_DIR;
> +			return true;
> +		}
> +	}
> +	return dent->d_type == DT_DIR;
> +}
> +
> +#endif
> -- 
> 2.43.0.rc1.413.gea7ed67945-goog
> 

-- 

- Arnaldo

  parent reply	other threads:[~2023-11-30 17:21 UTC|newest]

Thread overview: 95+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-27 22:08 [PATCH v5 00/50] Improvements to memory use Ian Rogers
2023-11-27 22:08 ` [PATCH v5 01/50] perf comm: Use regular mutex Ian Rogers
2023-11-30  0:55   ` Namhyung Kim
2023-11-30 18:27     ` Ian Rogers
2023-12-02 23:54       ` Namhyung Kim
2023-12-07  0:05         ` Ian Rogers
2024-02-06  3:04           ` Ian Rogers
2023-11-27 22:08 ` [PATCH v5 02/50] libperf: Lazily allocate/size mmap event copy Ian Rogers
2023-11-30  1:25   ` Namhyung Kim
2023-11-30 13:15   ` Arnaldo Carvalho de Melo
2023-11-30 14:19     ` Arnaldo Carvalho de Melo
2023-11-30 17:17       ` Arnaldo Carvalho de Melo
2023-11-27 22:08 ` [PATCH v5 03/50] perf mmap: Lazily initialize zstd streams Ian Rogers
2023-11-30  1:28   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 04/50] tools api fs: Switch filename__read_str to use io.h Ian Rogers
2023-11-30  1:36   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 05/50] tools api fs: Avoid reading whole file for a 1 byte bool Ian Rogers
2023-11-30  1:42   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 06/50] tools lib api: Add io_dir an allocation free readdir alternative Ian Rogers
2023-11-30  1:49   ` Namhyung Kim
2023-11-30 17:21   ` Arnaldo Carvalho de Melo [this message]
2023-11-30 17:56     ` Ian Rogers
2023-11-30 21:25       ` Arnaldo Carvalho de Melo
2023-12-07  5:13         ` Ian Rogers
2023-11-27 22:08 ` [PATCH v5 07/50] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2023-11-30  1:59   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 08/50] perf record: Be lazier in allocating lost samples buffer Ian Rogers
2023-11-30  2:09   ` Namhyung Kim
2023-11-30 18:29     ` Ian Rogers
2023-12-02 23:56       ` Namhyung Kim
2023-12-05 15:54         ` Arnaldo Carvalho de Melo
2023-11-27 22:08 ` [PATCH v5 09/50] perf pmu: Switch to io_dir__readdir Ian Rogers
2023-11-30  2:16   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 10/50] perf header: Switch mem topology " Ian Rogers
2023-11-30  4:17   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 11/50] perf events: Remove scandir in thread synthesis Ian Rogers
2023-11-30  4:22   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 12/50] perf map: Simplify map_ip/unmap_ip and make map size smaller Ian Rogers
2023-12-04 23:39   ` Namhyung Kim
2023-12-06 13:49     ` Arnaldo Carvalho de Melo
2023-12-06 16:19       ` Ian Rogers
2023-11-27 22:08 ` [PATCH v5 13/50] perf maps: Move symbol maps functions to maps.c Ian Rogers
2023-12-04 23:40   ` Namhyung Kim
2023-12-06 13:50     ` Arnaldo Carvalho de Melo
2023-11-27 22:08 ` [PATCH v5 14/50] perf thread: Add missing RC_CHK_EQUAL Ian Rogers
2023-12-04 23:41   ` Namhyung Kim
2023-12-06 13:51     ` Arnaldo Carvalho de Melo
2023-11-27 22:08 ` [PATCH v5 15/50] perf maps: Add maps__for_each_map to call a function on each entry Ian Rogers
2023-12-04 23:46   ` Namhyung Kim
2023-12-06 13:53     ` Arnaldo Carvalho de Melo
2023-11-27 22:08 ` [PATCH v5 16/50] perf maps: Add remove maps function to remove a map based on callback Ian Rogers
2023-12-04 23:49   ` Namhyung Kim
2023-12-06 23:28     ` Ian Rogers
2023-11-27 22:08 ` [PATCH v5 17/50] perf debug: Expose debug file Ian Rogers
2023-12-04 23:53   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 18/50] perf maps: Refactor maps__fixup_overlappings Ian Rogers
2023-12-04 23:59   ` Namhyung Kim
2023-12-06 23:39     ` Ian Rogers
2023-11-27 22:08 ` [PATCH v5 19/50] perf maps: Do simple merge if given map doesn't overlap Ian Rogers
2023-12-05  0:06   ` Namhyung Kim
2023-12-06 23:51     ` Ian Rogers
2023-11-27 22:08 ` [PATCH v5 20/50] perf maps: Rename clone to copy from Ian Rogers
2023-12-05  0:07   ` Namhyung Kim
2023-11-27 22:08 ` [PATCH v5 21/50] perf maps: Add maps__load_first Ian Rogers
2023-11-27 22:08 ` [PATCH v5 22/50] perf maps: Add find next entry to give entry after the given map Ian Rogers
2023-11-27 22:08 ` [PATCH v5 23/50] perf maps: Reduce scope of map_rb_node and maps internals Ian Rogers
2023-11-27 22:08 ` [PATCH v5 24/50] perf maps: Fix up overlaps during fixup_end Ian Rogers
2023-11-27 22:08 ` [PATCH v5 25/50] perf maps: Switch from rbtree to lazily sorted array for addresses Ian Rogers
2023-11-27 22:08 ` [PATCH v5 26/50] perf maps: Get map before returning in maps__find Ian Rogers
2023-11-27 22:08 ` [PATCH v5 27/50] perf maps: Get map before returning in maps__find_by_name Ian Rogers
2023-11-27 22:08 ` [PATCH v5 28/50] perf maps: Get map before returning in maps__find_next_entry Ian Rogers
2023-11-27 22:08 ` [PATCH v5 29/50] perf maps: Hide maps internals Ian Rogers
2023-11-27 22:08 ` [PATCH v5 30/50] perf maps: Locking tidy up of nr_maps Ian Rogers
2023-11-27 22:08 ` [PATCH v5 31/50] perf dso: Reorder variables to save space in struct dso Ian Rogers
2023-11-27 22:08 ` [PATCH v5 32/50] perf report: Sort child tasks by tid Ian Rogers
2023-11-27 22:08 ` [PATCH v5 33/50] perf trace: Ignore thread hashing in summary Ian Rogers
2023-11-27 22:08 ` [PATCH v5 34/50] perf machine: Move fprintf to for_each loop and a callback Ian Rogers
2023-11-27 22:08 ` [PATCH v5 35/50] perf threads: Move threads to its own files Ian Rogers
2023-11-27 22:08 ` [PATCH v5 36/50] perf threads: Switch from rbtree to hashmap Ian Rogers
2023-11-27 22:08 ` [PATCH v5 37/50] perf threads: Reduce table size from 256 to 8 Ian Rogers
2023-11-27 22:08 ` [PATCH v5 38/50] perf dsos: Attempt to better abstract dsos internals Ian Rogers
2023-11-27 22:08 ` [PATCH v5 39/50] perf dsos: Tidy reference counting and locking Ian Rogers
2023-11-27 22:08 ` [PATCH v5 40/50] perf dsos: Add dsos__for_each_dso Ian Rogers
2023-11-27 22:08 ` [PATCH v5 41/50] perf dso: Move dso functions out of dsos Ian Rogers
2023-11-27 22:08 ` [PATCH v5 42/50] perf dsos: Switch more loops to dsos__for_each_dso Ian Rogers
2023-11-27 22:08 ` [PATCH v5 43/50] perf dsos: Switch backing storage to array from rbtree/list Ian Rogers
2023-11-27 22:08 ` [PATCH v5 44/50] perf dsos: Remove __dsos__addnew Ian Rogers
2023-11-27 22:08 ` [PATCH v5 45/50] perf dsos: Remove __dsos__findnew_link_by_longname_id Ian Rogers
2023-11-27 22:08 ` [PATCH v5 46/50] perf dsos: Switch hand code to bsearch Ian Rogers
2023-11-27 22:08 ` [PATCH v5 47/50] perf dso: Add reference count checking and accessor functions Ian Rogers
2023-11-27 22:09 ` [PATCH v5 48/50] perf dso: Reference counting related fixes Ian Rogers
2023-11-27 22:09 ` [PATCH v5 49/50] perf dso: Use container_of to avoid a pointer in dso_data Ian Rogers
2023-11-27 22:09 ` [PATCH v5 50/50] perf env: Avoid recursively taking env->bpf_progs.lock Ian Rogers
2023-11-30  1:16 ` [PATCH v5 00/50] Improvements to memory use Namhyung Kim
2023-12-07  0:10   ` Ian Rogers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=ZWjEqw1cAw/eIpQH@kernel.org \
    --to=acme@kernel.org \
    --cc=9erthalion6@gmail.com \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=amadio@gentoo.org \
    --cc=atrajeev@linux.vnet.ibm.com \
    --cc=changbin.du@huawei.com \
    --cc=chenhuacai@kernel.org \
    --cc=colin.i.king@gmail.com \
    --cc=german.gomez@arm.com \
    --cc=irogers@google.com \
    --cc=james.clark@arm.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=kjain@linux.ibm.com \
    --cc=kprateek.nayak@amd.com \
    --cc=leo.yan@linaro.org \
    --cc=liam.howlett@oracle.com \
    --cc=lidong@vivo.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=liuwenyu7@huawei.com \
    --cc=mark.rutland@arm.com \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=ojeda@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ravi.bangoria@amd.com \
    --cc=sandipan.das@amd.com \
    --cc=seanjc@google.com \
    --cc=sesse@google.com \
    --cc=terrelln@fb.com \
    --cc=vincent.whitchurch@axis.com \
    --cc=wangming01@loongson.cn \
    --cc=yangjihong1@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).