bloom.c: core Bloom filter implementation for changed paths.

Add the core implementation for computing Bloom filters for
the paths changed between a commit and it's first parent.

We fill the Bloom filters as (const char *data, int len) pairs
as `struct bloom_filters" within a commit slab.

Filters for commits with no changes and more than 512 changes,
is represented with a filter of length zero. There is no gain
in distinguishing between a computed filter of length zero for
a commit with no changes, and an uncomputed filter for new commits
or for commits with more than 512 changes. The effect on
`git log -- path` is the same in both cases. We will fall back to
the normal diffing algorithm when we can't benefit from the
existence of Bloom filters.

Helped-by: Jeff King <peff@peff.net>
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>
This commit is contained in:
Garima Singh
2020-03-30 00:31:26 +00:00
committed by Junio C Hamano
parent f1294eaf7f
commit ed591febb4
4 changed files with 172 additions and 0 deletions

97
bloom.c
View File

@@ -1,5 +1,18 @@
#include "git-compat-util.h"
#include "bloom.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
#include "hashmap.h"
define_commit_slab(bloom_filter_slab, struct bloom_filter);
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)
{
@@ -107,3 +120,87 @@ void add_key_to_filter(const struct bloom_key *key,
filter->data[block_pos] |= get_bitmask(hash_mod);
}
}
void init_bloom_filters(void)
{
init_bloom_filter_slab(&bloom_filters);
}
struct bloom_filter *get_bloom_filter(struct repository *r,
struct commit *c)
{
struct bloom_filter *filter;
struct bloom_filter_settings settings = DEFAULT_BLOOM_FILTER_SETTINGS;
int i;
struct diff_options diffopt;
if (bloom_filters.slab_size == 0)
return NULL;
filter = bloom_filter_slab_at(&bloom_filters, c);
repo_diff_setup(r, &diffopt);
diffopt.flags.recursive = 1;
diff_setup_done(&diffopt);
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 (diff_queued_diff.nr <= 512) {
struct hashmap pathmap;
struct pathmap_hash_entry *e;
struct hashmap_iter iter;
hashmap_init(&pathmap, NULL, 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));
hashmap_add(&pathmap, &e->entry);
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;
}