From: "SZEDER Gábor" <szeder.dev@gmail.com>
To: git@vger.kernel.org
Cc: "Jeff King" <peff@peff.net>, "Junio C Hamano" <gitster@pobox.com>,
"Derrick Stolee" <stolee@gmail.com>,
"Ævar Arnfjörð Bjarmason" <avarab@gmail.com>,
"Stefan Beller" <sbeller@google.com>,
"Duy Nguyen" <pclouds@gmail.com>,
"SZEDER Gábor" <szeder.dev@gmail.com>
Subject: [PATCH 1/4] Add a (very) barebones Bloom filter implementation
Date: Tue, 9 Oct 2018 21:34:42 +0200 [thread overview]
Message-ID: <20181009193445.21908-2-szeder.dev@gmail.com> (raw)
In-Reply-To: <20181009193445.21908-1-szeder.dev@gmail.com>
---
Makefile | 1 +
bloom-filter.c | 103 +++++++++++++++++++++++++++++++++++++++++++++++++
bloom-filter.h | 39 +++++++++++++++++++
3 files changed, 143 insertions(+)
create mode 100644 bloom-filter.c
create mode 100644 bloom-filter.h
diff --git a/Makefile b/Makefile
index 13e1c52478..850eafb3ee 100644
--- a/Makefile
+++ b/Makefile
@@ -827,6 +827,7 @@ LIB_OBJS += base85.o
LIB_OBJS += bisect.o
LIB_OBJS += blame.o
LIB_OBJS += blob.o
+LIB_OBJS += bloom-filter.o
LIB_OBJS += branch.o
LIB_OBJS += bulk-checkin.o
LIB_OBJS += bundle.o
diff --git a/bloom-filter.c b/bloom-filter.c
new file mode 100644
index 0000000000..7dce0e35fa
--- /dev/null
+++ b/bloom-filter.c
@@ -0,0 +1,103 @@
+#include "cache.h"
+#include "bloom-filter.h"
+
+void bloom_filter_init(struct bloom_filter *bf, uint32_t bit_size)
+{
+ if (bit_size % CHAR_BIT)
+ BUG("invalid size for bloom filter");
+
+ bf->nr_entries = 0;
+ bf->bit_size = bit_size;
+ bf->bits = xmalloc(bit_size / CHAR_BIT);
+}
+
+void bloom_filter_free(struct bloom_filter *bf)
+{
+ bf->nr_entries = 0;
+ bf->bit_size = 0;
+ FREE_AND_NULL(bf->bits);
+}
+
+
+void bloom_filter_set_bits(struct bloom_filter *bf, const uint32_t *offsets,
+ int nr_offsets, int nr_entries)
+{
+ int i;
+ for (i = 0; i < nr_offsets; i++) {
+ uint32_t byte_offset = (offsets[i] % bf->bit_size) / CHAR_BIT;
+ unsigned char mask = 1 << offsets[i] % CHAR_BIT;
+ bf->bits[byte_offset] |= mask;
+ }
+ bf->nr_entries += nr_entries;
+}
+
+int bloom_filter_check_bits(struct bloom_filter *bf, const uint32_t *offsets,
+ int nr)
+{
+ int i;
+ for (i = 0; i < nr; i++) {
+ uint32_t byte_offset = (offsets[i] % bf->bit_size) / CHAR_BIT;
+ unsigned char mask = 1 << offsets[i] % CHAR_BIT;
+ if (!(bf->bits[byte_offset] & mask))
+ return 0;
+ }
+ return 1;
+}
+
+
+void bloom_filter_add_hash(struct bloom_filter *bf, const unsigned char *hash)
+{
+ uint32_t offsets[GIT_MAX_RAWSZ / sizeof(uint32_t)];
+ hashcpy((unsigned char*)offsets, hash);
+ bloom_filter_set_bits(bf, offsets,
+ the_hash_algo->rawsz / sizeof(*offsets), 1);
+}
+
+int bloom_filter_check_hash(struct bloom_filter *bf, const unsigned char *hash)
+{
+ uint32_t offsets[GIT_MAX_RAWSZ / sizeof(uint32_t)];
+ hashcpy((unsigned char*)offsets, hash);
+ return bloom_filter_check_bits(bf, offsets,
+ the_hash_algo->rawsz / sizeof(*offsets));
+}
+
+void hashxor(const unsigned char *hash1, const unsigned char *hash2,
+ unsigned char *out)
+{
+ int i;
+ for (i = 0; i < the_hash_algo->rawsz; i++)
+ out[i] = hash1[i] ^ hash2[i];
+}
+
+/* hardcoded for now... */
+static GIT_PATH_FUNC(git_path_bloom, "objects/info/bloom")
+
+int bloom_filter_load(struct bloom_filter *bf)
+{
+ int fd = open(git_path_bloom(), O_RDONLY);
+
+ if (fd < 0)
+ return -1;
+
+ read_in_full(fd, &bf->nr_entries, sizeof(bf->nr_entries));
+ read_in_full(fd, &bf->bit_size, sizeof(bf->bit_size));
+ if (bf->bit_size % CHAR_BIT)
+ BUG("invalid size for bloom filter");
+ bf->bits = xmalloc(bf->bit_size / CHAR_BIT);
+ read_in_full(fd, bf->bits, bf->bit_size / CHAR_BIT);
+
+ close(fd);
+
+ return 0;
+}
+
+void bloom_filter_write(struct bloom_filter *bf)
+{
+ int fd = xopen(git_path_bloom(), O_WRONLY | O_CREAT | O_TRUNC, 0666);
+
+ write_in_full(fd, &bf->nr_entries, sizeof(bf->nr_entries));
+ write_in_full(fd, &bf->bit_size, sizeof(bf->bit_size));
+ write_in_full(fd, bf->bits, bf->bit_size / CHAR_BIT);
+
+ close(fd);
+}
diff --git a/bloom-filter.h b/bloom-filter.h
new file mode 100644
index 0000000000..94d0af1708
--- /dev/null
+++ b/bloom-filter.h
@@ -0,0 +1,39 @@
+#ifndef BLOOM_FILTER_H
+#define BLOOM_FILTER_H
+
+#include "git-compat-util.h"
+
+struct bloom_filter {
+ uint32_t nr_entries;
+ uint32_t bit_size;
+ unsigned char *bits;
+};
+
+
+void bloom_filter_init(struct bloom_filter *bf, uint32_t bit_size);
+void bloom_filter_free(struct bloom_filter *bf);
+
+void bloom_filter_set_bits(struct bloom_filter *bf, const uint32_t *offsets,
+ int nr_offsets, int nr_enries);
+int bloom_filter_check_bits(struct bloom_filter *bf, const uint32_t *offsets,
+ int nr);
+
+/*
+ * Turns the given (SHA1) hash into 5 unsigned ints, and sets the bits at
+ * those positions (modulo the bitmap's size) in the Bloom filter.
+ */
+void bloom_filter_add_hash(struct bloom_filter *bf, const unsigned char *hash);
+/*
+ * Turns the given (SHA1) hash into 5 unsigned ints, and checks the bits at
+ * those positions (modulo the bitmap's size) in the Bloom filter.
+ * Returns 1 if all those bits are set, 0 otherwise.
+ */
+int bloom_filter_check_hash(struct bloom_filter *bf, const unsigned char *hash);
+
+void hashxor(const unsigned char *hash1, const unsigned char *hash2,
+ unsigned char *out);
+
+int bloom_filter_load(struct bloom_filter *bf);
+void bloom_filter_write(struct bloom_filter *bf);
+
+#endif
--
2.19.1.409.g0a0ee5eb6b
next prev parent reply other threads:[~2018-10-09 19:35 UTC|newest]
Thread overview: 78+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-03 13:23 We should add a "git gc --auto" after "git clone" due to commit graph Ævar Arnfjörð Bjarmason
2018-10-03 13:36 ` SZEDER Gábor
2018-10-03 13:42 ` Derrick Stolee
2018-10-03 14:18 ` Ævar Arnfjörð Bjarmason
2018-10-03 14:01 ` Ævar Arnfjörð Bjarmason
2018-10-03 14:17 ` SZEDER Gábor
2018-10-03 14:22 ` Ævar Arnfjörð Bjarmason
2018-10-03 14:53 ` SZEDER Gábor
2018-10-03 15:19 ` Ævar Arnfjörð Bjarmason
2018-10-03 16:59 ` SZEDER Gábor
2018-10-05 6:09 ` Junio C Hamano
2018-10-10 22:07 ` SZEDER Gábor
2018-10-10 23:01 ` Ævar Arnfjörð Bjarmason
2018-10-03 19:08 ` Stefan Beller
2018-10-03 19:21 ` Jeff King
2018-10-03 20:35 ` Ævar Arnfjörð Bjarmason
2018-10-03 17:47 ` Stefan Beller
2018-10-03 18:47 ` Ævar Arnfjörð Bjarmason
2018-10-03 18:51 ` Jeff King
2018-10-03 18:59 ` Derrick Stolee
2018-10-03 19:18 ` Jeff King
2018-10-08 16:41 ` SZEDER Gábor
2018-10-08 16:57 ` Derrick Stolee
2018-10-08 18:10 ` SZEDER Gábor
2018-10-08 18:29 ` Derrick Stolee
2018-10-09 3:08 ` Jeff King
2018-10-09 13:48 ` Bloom Filters (was Re: We should add a "git gc --auto" after "git clone" due to commit graph) Derrick Stolee
2018-10-09 18:45 ` Ævar Arnfjörð Bjarmason
2018-10-09 18:46 ` Jeff King
2018-10-09 19:03 ` Derrick Stolee
2018-10-09 21:14 ` Jeff King
2018-10-09 23:12 ` Bloom Filters Jeff King
2018-10-09 23:13 ` [PoC -- do not apply 1/3] initial tree-bitmap proof of concept Jeff King
2018-10-09 23:14 ` [PoC -- do not apply 2/3] test-tree-bitmap: add "dump" mode Jeff King
2018-10-10 0:48 ` Junio C Hamano
2018-10-11 3:13 ` Jeff King
2018-10-09 23:14 ` [PoC -- do not apply 3/3] test-tree-bitmap: replace ewah with custom rle encoding Jeff King
2018-10-10 0:58 ` Junio C Hamano
2018-10-11 3:20 ` Jeff King
2018-10-11 12:33 ` Bloom Filters Derrick Stolee
2018-10-11 13:43 ` Jeff King
2018-10-09 21:30 ` We should add a "git gc --auto" after "git clone" due to commit graph SZEDER Gábor
2018-10-09 19:34 ` [PATCH 0/4] Bloom filter experiment SZEDER Gábor
2018-10-09 19:34 ` SZEDER Gábor [this message]
2018-10-09 19:34 ` [PATCH 2/4] commit-graph: write a Bloom filter containing changed paths for each commit SZEDER Gábor
2018-10-09 21:06 ` Jeff King
2018-10-09 21:37 ` SZEDER Gábor
2018-10-09 19:34 ` [PATCH 3/4] revision.c: use the Bloom filter to speed up path-limited revision walks SZEDER Gábor
2018-10-09 19:34 ` [PATCH 4/4] revision.c: add GIT_TRACE_BLOOM_FILTER for a bit of statistics SZEDER Gábor
2018-10-09 19:47 ` [PATCH 0/4] Bloom filter experiment Derrick Stolee
2018-10-11 1:21 ` [PATCH 0/2] Per-commit filter proof of concept Jonathan Tan
2018-10-11 1:21 ` [PATCH 1/2] One filter per commit Jonathan Tan
2018-10-11 12:49 ` Derrick Stolee
2018-10-11 19:11 ` [PATCH] Per-commit and per-parent filters for 2 parents Jonathan Tan
2018-10-11 1:21 ` [PATCH 2/2] Only make bloom filter for first parent Jonathan Tan
2018-10-11 7:37 ` [PATCH 0/2] Per-commit filter proof of concept Ævar Arnfjörð Bjarmason
2018-10-15 14:39 ` [PATCH 0/4] Bloom filter experiment Derrick Stolee
2018-10-16 4:45 ` Junio C Hamano
2018-10-16 11:13 ` Derrick Stolee
2018-10-16 12:57 ` Ævar Arnfjörð Bjarmason
2018-10-16 13:03 ` Derrick Stolee
2018-10-18 2:00 ` Junio C Hamano
2018-10-16 23:41 ` Jonathan Tan
2018-10-08 23:02 ` We should add a "git gc --auto" after "git clone" due to commit graph Junio C Hamano
2018-10-03 14:32 ` Duy Nguyen
2018-10-03 16:45 ` Duy Nguyen
2018-10-04 21:42 ` [RFC PATCH] " Ævar Arnfjörð Bjarmason
2018-10-05 12:05 ` Derrick Stolee
2018-10-05 13:05 ` Ævar Arnfjörð Bjarmason
2018-10-05 13:45 ` Derrick Stolee
2018-10-05 14:04 ` Ævar Arnfjörð Bjarmason
2018-10-05 19:21 ` Jeff King
2018-10-05 19:41 ` Derrick Stolee
2018-10-05 19:47 ` Jeff King
2018-10-05 20:00 ` Derrick Stolee
2018-10-05 20:02 ` Jeff King
2018-10-05 20:01 ` Ævar Arnfjörð Bjarmason
2018-10-05 20:09 ` Jeff King
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
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181009193445.21908-2-szeder.dev@gmail.com \
--to=szeder.dev@gmail.com \
--cc=avarab@gmail.com \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=pclouds@gmail.com \
--cc=peff@peff.net \
--cc=sbeller@google.com \
--cc=stolee@gmail.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.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
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 read-only IMAP folder(s) and NNTP newsgroup(s).