git/bloom.c

303 lines
7.5 KiB
C
Raw Normal View History

#include "git-compat-util.h"
#include "bloom.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
#include "hashmap.h"
#include "commit-graph.h"
#include "commit.h"
define_commit_slab(bloom_filter_slab, struct bloom_filter);
static struct bloom_filter_slab bloom_filters;
struct pathmap_hash_entry {
struct hashmap_entry entry;
const char path[FLEX_ARRAY];
};
static uint32_t rotate_left(uint32_t value, int32_t count)
{
uint32_t mask = 8 * sizeof(uint32_t) - 1;
count &= mask;
return ((value << count) | (value >> ((-count) & mask)));
}
bloom.c: introduce core Bloom filter constructs Introduce the constructs for Bloom filters, Bloom filter keys and Bloom filter settings. For details on what Bloom filters are and how they work, refer to Dr. Derrick Stolee's blog post [1]. It provides a concise explanation of the adoption of Bloom filters as described in [2] and [3]. Implementation specifics: 1. We currently use 7 and 10 for the number of hashes and the size of each entry respectively. They served as great starting values, the mathematical details behind this choice are described in [1] and [4]. The implementation, while not completely open to it at the moment, is flexible enough to allow for tweaking these settings in the future. Note: The performance gains we have observed with these values are significant enough that we did not need to tweak these settings. The performance numbers are included in the cover letter of this series and in the commit message of the subsequent commit where we use Bloom filters to speed up `git log -- path`. 2. As described in [1] and [3], we do not need 7 independent hashing functions. We use the Murmur3 hashing scheme, seed it twice and then combine those to procure an arbitrary number of hash values. 3. The filters will be sized according to the number of changes in each commit, in multiples of 8 bit words. [1] Derrick Stolee "Supercharging the Git Commit Graph IV: Bloom Filters" https://devblogs.microsoft.com/devops/super-charging-the-git-commit-graph-iv-Bloom-filters/ [2] Flavio Bonomi, Michael Mitzenmacher, Rina Panigrahy, Sushil Singh, George Varghese "An Improved Construction for Counting Bloom Filters" http://theory.stanford.edu/~rinap/papers/esa2006b.pdf https://doi.org/10.1007/11841036_61 [3] Peter C. Dillinger and Panagiotis Manolios "Bloom Filters in Probabilistic Verification" http://www.ccs.neu.edu/home/pete/pub/Bloom-filters-verification.pdf https://doi.org/10.1007/978-3-540-30494-4_26 [4] Thomas Mueller Graf, Daniel Lemire "Xor Filters: Faster and Smaller Than Bloom and Cuckoo Filters" https://arxiv.org/abs/1912.08258 Helped-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jakub Narębski <jnareb@gmail.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-03-30 00:31:25 +00:00
static inline unsigned char get_bitmask(uint32_t pos)
{
return ((unsigned char)1) << (pos & (BITS_PER_WORD - 1));
}
static int load_bloom_filter_from_graph(struct commit_graph *g,
struct bloom_filter *filter,
struct commit *c)
{
uint32_t lex_pos, start_index, end_index;
uint32_t graph_pos = commit_graph_position(c);
while (graph_pos < g->num_commits_in_base)
g = g->base_graph;
/* The commit graph commit 'c' lives in doesn't carry bloom filters. */
if (!g->chunk_bloom_indexes)
return 0;
lex_pos = graph_pos - g->num_commits_in_base;
end_index = get_be32(g->chunk_bloom_indexes + 4 * lex_pos);
if (lex_pos > 0)
start_index = get_be32(g->chunk_bloom_indexes + 4 * (lex_pos - 1));
else
start_index = 0;
filter->len = end_index - start_index;
filter->data = (unsigned char *)(g->chunk_bloom_data +
sizeof(unsigned char) * start_index +
BLOOMDATA_CHUNK_HEADER_SIZE);
return 1;
}
/*
* Calculate the murmur3 32-bit hash value for the given data
* using the given seed.
* Produces a uniformly distributed hash value.
* Not considered to be cryptographically secure.
* Implemented as described in https://en.wikipedia.org/wiki/MurmurHash#Algorithm
*/
uint32_t murmur3_seeded(uint32_t seed, const char *data, size_t len)
{
const uint32_t c1 = 0xcc9e2d51;
const uint32_t c2 = 0x1b873593;
const uint32_t r1 = 15;
const uint32_t r2 = 13;
const uint32_t m = 5;
const uint32_t n = 0xe6546b64;
int i;
uint32_t k1 = 0;
const char *tail;
int len4 = len / sizeof(uint32_t);
uint32_t k;
for (i = 0; i < len4; i++) {
uint32_t byte1 = (uint32_t)data[4*i];
uint32_t byte2 = ((uint32_t)data[4*i + 1]) << 8;
uint32_t byte3 = ((uint32_t)data[4*i + 2]) << 16;
uint32_t byte4 = ((uint32_t)data[4*i + 3]) << 24;
k = byte1 | byte2 | byte3 | byte4;
k *= c1;
k = rotate_left(k, r1);
k *= c2;
seed ^= k;
seed = rotate_left(seed, r2) * m + n;
}
tail = (data + len4 * sizeof(uint32_t));
switch (len & (sizeof(uint32_t) - 1)) {
case 3:
k1 ^= ((uint32_t)tail[2]) << 16;
/*-fallthrough*/
case 2:
k1 ^= ((uint32_t)tail[1]) << 8;
/*-fallthrough*/
case 1:
k1 ^= ((uint32_t)tail[0]) << 0;
k1 *= c1;
k1 = rotate_left(k1, r1);
k1 *= c2;
seed ^= k1;
break;
}
seed ^= (uint32_t)len;
seed ^= (seed >> 16);
seed *= 0x85ebca6b;
seed ^= (seed >> 13);
seed *= 0xc2b2ae35;
seed ^= (seed >> 16);
return seed;
bloom.c: introduce core Bloom filter constructs Introduce the constructs for Bloom filters, Bloom filter keys and Bloom filter settings. For details on what Bloom filters are and how they work, refer to Dr. Derrick Stolee's blog post [1]. It provides a concise explanation of the adoption of Bloom filters as described in [2] and [3]. Implementation specifics: 1. We currently use 7 and 10 for the number of hashes and the size of each entry respectively. They served as great starting values, the mathematical details behind this choice are described in [1] and [4]. The implementation, while not completely open to it at the moment, is flexible enough to allow for tweaking these settings in the future. Note: The performance gains we have observed with these values are significant enough that we did not need to tweak these settings. The performance numbers are included in the cover letter of this series and in the commit message of the subsequent commit where we use Bloom filters to speed up `git log -- path`. 2. As described in [1] and [3], we do not need 7 independent hashing functions. We use the Murmur3 hashing scheme, seed it twice and then combine those to procure an arbitrary number of hash values. 3. The filters will be sized according to the number of changes in each commit, in multiples of 8 bit words. [1] Derrick Stolee "Supercharging the Git Commit Graph IV: Bloom Filters" https://devblogs.microsoft.com/devops/super-charging-the-git-commit-graph-iv-Bloom-filters/ [2] Flavio Bonomi, Michael Mitzenmacher, Rina Panigrahy, Sushil Singh, George Varghese "An Improved Construction for Counting Bloom Filters" http://theory.stanford.edu/~rinap/papers/esa2006b.pdf https://doi.org/10.1007/11841036_61 [3] Peter C. Dillinger and Panagiotis Manolios "Bloom Filters in Probabilistic Verification" http://www.ccs.neu.edu/home/pete/pub/Bloom-filters-verification.pdf https://doi.org/10.1007/978-3-540-30494-4_26 [4] Thomas Mueller Graf, Daniel Lemire "Xor Filters: Faster and Smaller Than Bloom and Cuckoo Filters" https://arxiv.org/abs/1912.08258 Helped-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jakub Narębski <jnareb@gmail.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-03-30 00:31:25 +00:00
}
void fill_bloom_key(const char *data,
size_t len,
struct bloom_key *key,
const struct bloom_filter_settings *settings)
bloom.c: introduce core Bloom filter constructs Introduce the constructs for Bloom filters, Bloom filter keys and Bloom filter settings. For details on what Bloom filters are and how they work, refer to Dr. Derrick Stolee's blog post [1]. It provides a concise explanation of the adoption of Bloom filters as described in [2] and [3]. Implementation specifics: 1. We currently use 7 and 10 for the number of hashes and the size of each entry respectively. They served as great starting values, the mathematical details behind this choice are described in [1] and [4]. The implementation, while not completely open to it at the moment, is flexible enough to allow for tweaking these settings in the future. Note: The performance gains we have observed with these values are significant enough that we did not need to tweak these settings. The performance numbers are included in the cover letter of this series and in the commit message of the subsequent commit where we use Bloom filters to speed up `git log -- path`. 2. As described in [1] and [3], we do not need 7 independent hashing functions. We use the Murmur3 hashing scheme, seed it twice and then combine those to procure an arbitrary number of hash values. 3. The filters will be sized according to the number of changes in each commit, in multiples of 8 bit words. [1] Derrick Stolee "Supercharging the Git Commit Graph IV: Bloom Filters" https://devblogs.microsoft.com/devops/super-charging-the-git-commit-graph-iv-Bloom-filters/ [2] Flavio Bonomi, Michael Mitzenmacher, Rina Panigrahy, Sushil Singh, George Varghese "An Improved Construction for Counting Bloom Filters" http://theory.stanford.edu/~rinap/papers/esa2006b.pdf https://doi.org/10.1007/11841036_61 [3] Peter C. Dillinger and Panagiotis Manolios "Bloom Filters in Probabilistic Verification" http://www.ccs.neu.edu/home/pete/pub/Bloom-filters-verification.pdf https://doi.org/10.1007/978-3-540-30494-4_26 [4] Thomas Mueller Graf, Daniel Lemire "Xor Filters: Faster and Smaller Than Bloom and Cuckoo Filters" https://arxiv.org/abs/1912.08258 Helped-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jakub Narębski <jnareb@gmail.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-03-30 00:31:25 +00:00
{
int i;
const uint32_t seed0 = 0x293ae76f;
const uint32_t seed1 = 0x7e646e2c;
const uint32_t hash0 = murmur3_seeded(seed0, data, len);
const uint32_t hash1 = murmur3_seeded(seed1, data, len);
key->hashes = (uint32_t *)xcalloc(settings->num_hashes, sizeof(uint32_t));
for (i = 0; i < settings->num_hashes; i++)
key->hashes[i] = hash0 + i * hash1;
}
line-log: integrate with changed-path Bloom filters The previous changes to the line-log machinery focused on making the first result appear faster. This was achieved by no longer walking the entire commit history before returning the early results. There is still another way to improve the performance: walk most commits much faster. Let's use the changed-path Bloom filters to reduce time spent computing diffs. Since the line-log computation requires opening blobs and checking the content-diff, there is still a lot of necessary computation that cannot be replaced with changed-path Bloom filters. The part that we can reduce is most effective when checking the history of a file that is deep in several directories and those directories are modified frequently. In this case, the computation to check if a commit is TREESAME to its first parent takes a large fraction of the time. That is ripe for improvement with changed-path Bloom filters. We must ensure that prepare_to_use_bloom_filters() is called in revision.c so that the bloom_filter_settings are loaded into the struct rev_info from the commit-graph. Of course, some cases are still forbidden, but in the line-log case the pathspec is provided in a different way than normal. Since multiple paths and segments could be requested, we compute the struct bloom_key data dynamically during the commit walk. This could likely be improved, but adds code complexity that is not valuable at this time. There are two cases to care about: merge commits and "ordinary" commits. Merge commits have multiple parents, but if we are TREESAME to our first parent in every range, then pass the blame for all ranges to the first parent. Ordinary commits have the same condition, but each is done slightly differently in the process_ranges_[merge|ordinary]_commit() methods. By checking if the changed-path Bloom filter can guarantee TREESAME, we can avoid that tree-diff cost. If the filter says "probably changed", then we need to run the tree-diff and then the blob-diff if there was a real edit. The Linux kernel repository is a good testing ground for the performance improvements claimed here. There are two different cases to test. The first is the "entire history" case, where we output the entire history to /dev/null to see how long it would take to compute the full line-log history. The second is the "first result" case, where we find how long it takes to show the first value, which is an indicator of how quickly a user would see responses when waiting at a terminal. To test, I selected the paths that were changed most frequently in the top 10,000 commits using this command (stolen from StackOverflow [1]): git log --pretty=format: --name-only -n 10000 | sort | \ uniq -c | sort -rg | head -10 which results in 121 MAINTAINERS 63 fs/namei.c 60 arch/x86/kvm/cpuid.c 59 fs/io_uring.c 58 arch/x86/kvm/vmx/vmx.c 51 arch/x86/kvm/x86.c 45 arch/x86/kvm/svm.c 42 fs/btrfs/disk-io.c 42 Documentation/scsi/index.rst (along with a bogus first result). It appears that the path arch/x86/kvm/svm.c was renamed, so we ignore that entry. This leaves the following results for the real command time: | | Entire History | First Result | | Path | Before | After | Before | After | |------------------------------|--------|--------|--------|--------| | MAINTAINERS | 4.26 s | 3.87 s | 0.41 s | 0.39 s | | fs/namei.c | 1.99 s | 0.99 s | 0.42 s | 0.21 s | | arch/x86/kvm/cpuid.c | 5.28 s | 1.12 s | 0.16 s | 0.09 s | | fs/io_uring.c | 4.34 s | 0.99 s | 0.94 s | 0.27 s | | arch/x86/kvm/vmx/vmx.c | 5.01 s | 1.34 s | 0.21 s | 0.12 s | | arch/x86/kvm/x86.c | 2.24 s | 1.18 s | 0.21 s | 0.14 s | | fs/btrfs/disk-io.c | 1.82 s | 1.01 s | 0.06 s | 0.05 s | | Documentation/scsi/index.rst | 3.30 s | 0.89 s | 1.46 s | 0.03 s | It is worth noting that the least speedup comes for the MAINTAINERS file which is * edited frequently, * low in the directory heirarchy, and * quite a large file. All of those points lead to spending more time doing the blob diff and less time doing the tree diff. Still, we see some improvement in that case and significant improvement in other cases. A 2-4x speedup is likely the more typical case as opposed to the small 5% change for that file. Signed-off-by: Derrick Stolee <dstolee@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-05-11 11:56:19 +00:00
void clear_bloom_key(struct bloom_key *key)
{
FREE_AND_NULL(key->hashes);
}
bloom.c: introduce core Bloom filter constructs Introduce the constructs for Bloom filters, Bloom filter keys and Bloom filter settings. For details on what Bloom filters are and how they work, refer to Dr. Derrick Stolee's blog post [1]. It provides a concise explanation of the adoption of Bloom filters as described in [2] and [3]. Implementation specifics: 1. We currently use 7 and 10 for the number of hashes and the size of each entry respectively. They served as great starting values, the mathematical details behind this choice are described in [1] and [4]. The implementation, while not completely open to it at the moment, is flexible enough to allow for tweaking these settings in the future. Note: The performance gains we have observed with these values are significant enough that we did not need to tweak these settings. The performance numbers are included in the cover letter of this series and in the commit message of the subsequent commit where we use Bloom filters to speed up `git log -- path`. 2. As described in [1] and [3], we do not need 7 independent hashing functions. We use the Murmur3 hashing scheme, seed it twice and then combine those to procure an arbitrary number of hash values. 3. The filters will be sized according to the number of changes in each commit, in multiples of 8 bit words. [1] Derrick Stolee "Supercharging the Git Commit Graph IV: Bloom Filters" https://devblogs.microsoft.com/devops/super-charging-the-git-commit-graph-iv-Bloom-filters/ [2] Flavio Bonomi, Michael Mitzenmacher, Rina Panigrahy, Sushil Singh, George Varghese "An Improved Construction for Counting Bloom Filters" http://theory.stanford.edu/~rinap/papers/esa2006b.pdf https://doi.org/10.1007/11841036_61 [3] Peter C. Dillinger and Panagiotis Manolios "Bloom Filters in Probabilistic Verification" http://www.ccs.neu.edu/home/pete/pub/Bloom-filters-verification.pdf https://doi.org/10.1007/978-3-540-30494-4_26 [4] Thomas Mueller Graf, Daniel Lemire "Xor Filters: Faster and Smaller Than Bloom and Cuckoo Filters" https://arxiv.org/abs/1912.08258 Helped-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jakub Narębski <jnareb@gmail.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-03-30 00:31:25 +00:00
void add_key_to_filter(const struct bloom_key *key,
struct bloom_filter *filter,
const struct bloom_filter_settings *settings)
bloom.c: introduce core Bloom filter constructs Introduce the constructs for Bloom filters, Bloom filter keys and Bloom filter settings. For details on what Bloom filters are and how they work, refer to Dr. Derrick Stolee's blog post [1]. It provides a concise explanation of the adoption of Bloom filters as described in [2] and [3]. Implementation specifics: 1. We currently use 7 and 10 for the number of hashes and the size of each entry respectively. They served as great starting values, the mathematical details behind this choice are described in [1] and [4]. The implementation, while not completely open to it at the moment, is flexible enough to allow for tweaking these settings in the future. Note: The performance gains we have observed with these values are significant enough that we did not need to tweak these settings. The performance numbers are included in the cover letter of this series and in the commit message of the subsequent commit where we use Bloom filters to speed up `git log -- path`. 2. As described in [1] and [3], we do not need 7 independent hashing functions. We use the Murmur3 hashing scheme, seed it twice and then combine those to procure an arbitrary number of hash values. 3. The filters will be sized according to the number of changes in each commit, in multiples of 8 bit words. [1] Derrick Stolee "Supercharging the Git Commit Graph IV: Bloom Filters" https://devblogs.microsoft.com/devops/super-charging-the-git-commit-graph-iv-Bloom-filters/ [2] Flavio Bonomi, Michael Mitzenmacher, Rina Panigrahy, Sushil Singh, George Varghese "An Improved Construction for Counting Bloom Filters" http://theory.stanford.edu/~rinap/papers/esa2006b.pdf https://doi.org/10.1007/11841036_61 [3] Peter C. Dillinger and Panagiotis Manolios "Bloom Filters in Probabilistic Verification" http://www.ccs.neu.edu/home/pete/pub/Bloom-filters-verification.pdf https://doi.org/10.1007/978-3-540-30494-4_26 [4] Thomas Mueller Graf, Daniel Lemire "Xor Filters: Faster and Smaller Than Bloom and Cuckoo Filters" https://arxiv.org/abs/1912.08258 Helped-by: Derrick Stolee <dstolee@microsoft.com> Reviewed-by: Jakub Narębski <jnareb@gmail.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-03-30 00:31:25 +00:00
{
int i;
uint64_t mod = filter->len * BITS_PER_WORD;
for (i = 0; i < settings->num_hashes; i++) {
uint64_t hash_mod = key->hashes[i] % mod;
uint64_t block_pos = hash_mod / BITS_PER_WORD;
filter->data[block_pos] |= get_bitmask(hash_mod);
}
}
void init_bloom_filters(void)
{
init_bloom_filter_slab(&bloom_filters);
}
static int pathmap_cmp(const void *hashmap_cmp_fn_data,
const struct hashmap_entry *eptr,
const struct hashmap_entry *entry_or_key,
const void *keydata)
{
const struct pathmap_hash_entry *e1, *e2;
e1 = container_of(eptr, const struct pathmap_hash_entry, entry);
e2 = container_of(entry_or_key, const struct pathmap_hash_entry, entry);
return strcmp(e1->path, e2->path);
}
struct bloom_filter *get_bloom_filter(struct repository *r,
struct commit *c,
int compute_if_not_present)
{
struct bloom_filter *filter;
struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
int i;
struct diff_options diffopt;
int max_changes = 512;
if (bloom_filters.slab_size == 0)
return NULL;
filter = bloom_filter_slab_at(&bloom_filters, c);
if (!filter->data) {
load_commit_graph_info(r, c);
if (commit_graph_position(c) != COMMIT_NOT_FROM_GRAPH &&
r->objects->commit_graph->chunk_bloom_indexes) {
if (load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
return filter;
else
return NULL;
}
}
if (filter->data || !compute_if_not_present)
return filter;
repo_diff_setup(r, &diffopt);
diffopt.flags.recursive = 1;
diffopt.detect_rename = 0;
diffopt.max_changes = max_changes;
diff_setup_done(&diffopt);
/* ensure commit is parsed so we have parent information */
repo_parse_commit(r, c);
if (c->parents)
diff_tree_oid(&c->parents->item->object.oid, &c->object.oid, "", &diffopt);
else
diff_tree_oid(NULL, &c->object.oid, "", &diffopt);
diffcore_std(&diffopt);
if (diffopt.num_changes <= max_changes) {
struct hashmap pathmap;
struct pathmap_hash_entry *e;
struct hashmap_iter iter;
hashmap_init(&pathmap, pathmap_cmp, NULL, 0);
for (i = 0; i < diff_queued_diff.nr; i++) {
const char *path = diff_queued_diff.queue[i]->two->path;
/*
* Add each leading directory of the changed file, i.e. for
* 'dir/subdir/file' add 'dir' and 'dir/subdir' as well, so
* the Bloom filter could be used to speed up commands like
* 'git log dir/subdir', too.
*
* Note that directories are added without the trailing '/'.
*/
do {
char *last_slash = strrchr(path, '/');
FLEX_ALLOC_STR(e, path, path);
hashmap_entry_init(&e->entry, strhash(path));
if (!hashmap_get(&pathmap, &e->entry, NULL))
hashmap_add(&pathmap, &e->entry);
else
free(e);
if (!last_slash)
last_slash = (char*)path;
*last_slash = '\0';
} while (*path);
diff_free_filepair(diff_queued_diff.queue[i]);
}
filter->len = (hashmap_get_size(&pathmap) * settings.bits_per_entry + BITS_PER_WORD - 1) / BITS_PER_WORD;
filter->data = xcalloc(filter->len, sizeof(unsigned char));
hashmap_for_each_entry(&pathmap, &iter, e, entry) {
struct bloom_key key;
fill_bloom_key(e->path, strlen(e->path), &key, &settings);
add_key_to_filter(&key, filter, &settings);
}
hashmap_free_entries(&pathmap, struct pathmap_hash_entry, entry);
} else {
for (i = 0; i < diff_queued_diff.nr; i++)
diff_free_filepair(diff_queued_diff.queue[i]);
filter->data = NULL;
filter->len = 0;
}
free(diff_queued_diff.queue);
DIFF_QUEUE_CLEAR(&diff_queued_diff);
return filter;
}
revision.c: use Bloom filters to speed up path based revision walks Revision walk will now use Bloom filters for commits to speed up revision walks for a particular path (for computing history for that path), if they are present in the commit-graph file. We load the Bloom filters during the prepare_revision_walk step, currently only when dealing with a single pathspec. Extending it to work with multiple pathspecs can be explored and built on top of this series in the future. While comparing trees in rev_compare_trees(), if the Bloom filter says that the file is not different between the two trees, we don't need to compute the expensive diff. This is where we get our performance gains. The other response of the Bloom filter is '`:maybe', in which case we fall back to the full diff calculation to determine if the path was changed in the commit. We do not try to use Bloom filters when the '--walk-reflogs' option is specified. The '--walk-reflogs' option does not walk the commit ancestry chain like the rest of the options. Incorporating the performance gains when walking reflog entries would add more complexity, and can be explored in a later series. Performance Gains: We tested the performance of `git log -- <path>` on the git repo, the linux and some internal large repos, with a variety of paths of varying depths. On the git and linux repos: - we observed a 2x to 5x speed up. On a large internal repo with files seated 6-10 levels deep in the tree: - we observed 10x to 20x speed ups, with some paths going up to 28 times faster. Helped-by: Derrick Stolee <dstolee@microsoft.com Helped-by: SZEDER Gábor <szeder.dev@gmail.com> Helped-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2020-04-06 16:59:52 +00:00
int bloom_filter_contains(const struct bloom_filter *filter,
const struct bloom_key *key,
const struct bloom_filter_settings *settings)
{
int i;
uint64_t mod = filter->len * BITS_PER_WORD;
if (!mod)
return -1;
for (i = 0; i < settings->num_hashes; i++) {
uint64_t hash_mod = key->hashes[i] % mod;
uint64_t block_pos = hash_mod / BITS_PER_WORD;
if (!(filter->data[block_pos] & get_bitmask(hash_mod)))
return 0;
}
return 1;
}