public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Nick Terrell <terrelln@fb.com>,
	Kan Liang <kan.liang@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>, Leo Yan <leo.yan@linaro.org>,
	Song Liu <song@kernel.org>, Sandipan Das <sandipan.das@amd.com>,
	James Clark <james.clark@arm.com>,
	Anshuman Khandual <anshuman.khandual@arm.com>,
	Miguel Ojeda <ojeda@kernel.org>,
	Liam Howlett <liam.howlett@oracle.com>,
	Yang Jihong <yangjihong1@huawei.com>,
	Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
	Kajol Jain <kjain@linux.ibm.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Sean Christopherson <seanjc@google.com>,
	Yanteng Si <siyanteng@loongson.cn>,
	Ravi Bangoria <ravi.bangoria@amd.com>,
	German Gomez <german.gomez@arm.com>,
	Changbin Du <changbin.du@huawei.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	liuwenyu <liuwenyu7@huawei.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: [PATCH v3 18/50] tools lib api: Add io_dir an allocation free readdir alternative
Date: Tue, 24 Oct 2023 15:23:21 -0700	[thread overview]
Message-ID: <20231024222353.3024098-19-irogers@google.com> (raw)
In-Reply-To: <20231024222353.3024098-1-irogers@google.com>

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.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/lib/api/Makefile |  2 +-
 tools/lib/api/io_dir.h | 72 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 73 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..8a70c0718df5
--- /dev/null
+++ b/tools/lib/api/io_dir.h
@@ -0,0 +1,72 @@
+/* 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, const 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;
+
+		return S_ISDIR(st.st_mode);
+	}
+	return dent->d_type == DT_DIR;
+}
+
+#endif
-- 
2.42.0.758.gaed0368e0e-goog


  parent reply	other threads:[~2023-10-24 22:25 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-24 22:23 [PATCH v3 00/50] Improvements to memory use Ian Rogers
2023-10-24 22:23 ` [PATCH v3 01/50] perf rwsem: Add debug mode that uses a mutex Ian Rogers
2023-10-24 22:23 ` [PATCH v3 02/50] perf machine: Avoid out of bounds LBR memory read Ian Rogers
2023-10-24 22:23 ` [PATCH v3 03/50] libperf rc_check: Make implicit enabling work for GCC Ian Rogers
2023-10-24 22:23 ` [PATCH v3 04/50] libperf rc_check: Add RC_CHK_EQUAL Ian Rogers
2023-10-24 22:23 ` [PATCH v3 05/50] perf hist: Add missing puts to hist__account_cycles Ian Rogers
2023-10-24 22:23 ` [PATCH v3 06/50] perf threads: Remove unused dead thread list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 07/50] perf offcpu: Add missed btf_free Ian Rogers
2023-10-24 22:23 ` [PATCH v3 08/50] perf callchain: Make display use of branch_type_stat const Ian Rogers
2023-10-24 22:23 ` [PATCH v3 09/50] perf callchain: Make brtype_stat in callchain_list optional Ian Rogers
2023-10-24 22:23 ` [PATCH v3 10/50] perf callchain: Minor layout changes to callchain_list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 11/50] perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit Ian Rogers
2023-10-24 22:23 ` [PATCH v3 12/50] perf record: Lazy load kernel symbols Ian Rogers
2023-10-25 18:25   ` Namhyung Kim
2023-10-25 18:35     ` Adrian Hunter
2023-10-24 22:23 ` [PATCH v3 13/50] libperf: Lazily allocate mmap event copy Ian Rogers
2023-10-25  2:38   ` Yang Jihong
2023-10-25  3:28     ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 14/50] perf mmap: Lazily initialize zstd streams Ian Rogers
2023-10-24 22:23 ` [PATCH v3 15/50] perf machine thread: Remove exited threads by default Ian Rogers
2023-10-24 22:23 ` [PATCH v3 16/50] tools api fs: Switch filename__read_str to use io.h Ian Rogers
2023-10-24 22:23 ` [PATCH v3 17/50] tools api fs: Avoid reading whole file for a 1 byte bool Ian Rogers
2023-10-24 22:23 ` Ian Rogers [this message]
2023-10-25 18:43   ` [PATCH v3 18/50] tools lib api: Add io_dir an allocation free readdir alternative Namhyung Kim
2023-10-25 22:15     ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 19/50] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer Ian Rogers
2023-10-25  3:44   ` Yang Jihong
2023-10-25 17:00     ` Ian Rogers
2023-10-25 19:04       ` Namhyung Kim
2023-10-25 19:00   ` Namhyung Kim
2023-10-24 22:23 ` [PATCH v3 21/50] perf pmu: Switch to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 22/50] perf bpf: Don't synthesize BPF events when disabled Ian Rogers
2023-10-24 22:23 ` [PATCH v3 23/50] perf header: Switch mem topology to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 24/50] perf events: Remove scandir in thread synthesis Ian Rogers
2023-10-24 22:23 ` [PATCH v3 25/50] perf map: Simplify map_ip/unmap_ip and make map size smaller Ian Rogers
2023-10-24 22:23 ` [PATCH v3 26/50] perf maps: Move symbol maps functions to maps.c Ian Rogers
2023-10-24 22:23 ` [PATCH v3 27/50] perf thread: Add missing RC_CHK_ACCESS Ian Rogers
2023-10-24 22:23 ` [PATCH v3 28/50] perf maps: Add maps__for_each_map to call a function on each entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 29/50] perf maps: Add remove maps function to remove a map based on callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 30/50] perf debug: Expose debug file Ian Rogers
2023-10-24 22:23 ` [PATCH v3 31/50] perf maps: Refactor maps__fixup_overlappings Ian Rogers
2023-10-24 22:23 ` [PATCH v3 32/50] perf maps: Do simple merge if given map doesn't overlap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 33/50] perf maps: Rename clone to copy from Ian Rogers
2023-10-24 22:23 ` [PATCH v3 34/50] perf maps: Add maps__load_first Ian Rogers
2023-10-24 22:23 ` [PATCH v3 35/50] perf maps: Add find next entry to give entry after the given map Ian Rogers
2023-10-24 22:23 ` [PATCH v3 36/50] perf maps: Reduce scope of map_rb_node and maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 37/50] perf maps: Fix up overlaps during fixup_end Ian Rogers
2023-10-24 22:23 ` [PATCH v3 38/50] perf maps: Switch from rbtree to lazily sorted array for addresses Ian Rogers
2023-10-24 22:23 ` [PATCH v3 39/50] perf maps: Get map before returning in maps__find Ian Rogers
2023-10-24 22:23 ` [PATCH v3 40/50] perf maps: Get map before returning in maps__find_by_name Ian Rogers
2023-10-24 22:23 ` [PATCH v3 41/50] perf maps: Get map before returning in maps__find_next_entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 42/50] perf maps: Hide maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 43/50] perf maps: Locking tidy up of nr_maps Ian Rogers
2023-10-24 22:23 ` [PATCH v3 44/50] perf dso: Reorder variables to save space in struct dso Ian Rogers
2023-10-24 22:23 ` [PATCH v3 45/50] perf report: Sort child tasks by tid Ian Rogers
2023-10-24 22:23 ` [PATCH v3 46/50] perf trace: Ignore thread hashing in summary Ian Rogers
2023-10-24 22:23 ` [PATCH v3 47/50] perf machine: Move fprintf to for_each loop and a callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 48/50] perf threads: Move threads to its own files Ian Rogers
2023-10-24 22:23 ` [PATCH v3 49/50] perf threads: Switch from rbtree to hashmap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 50/50] perf threads: Reduce table size from 256 to 8 Ian Rogers
2023-10-26 17:11 ` (subset) [PATCH v3 00/50] Improvements to memory use Namhyung Kim

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=20231024222353.3024098-19-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=anshuman.khandual@arm.com \
    --cc=atrajeev@linux.vnet.ibm.com \
    --cc=changbin.du@huawei.com \
    --cc=german.gomez@arm.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=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=siyanteng@loongson.cn \
    --cc=song@kernel.org \
    --cc=terrelln@fb.com \
    --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