mirror of
https://github.com/git/git
synced 2024-07-16 10:38:05 +00:00
ed591febb4
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>
84 lines
2.2 KiB
C
84 lines
2.2 KiB
C
#ifndef BLOOM_H
|
|
#define BLOOM_H
|
|
|
|
struct commit;
|
|
struct repository;
|
|
|
|
struct bloom_filter_settings {
|
|
/*
|
|
* The version of the hashing technique being used.
|
|
* We currently only support version = 1 which is
|
|
* the seeded murmur3 hashing technique implemented
|
|
* in bloom.c.
|
|
*/
|
|
uint32_t hash_version;
|
|
|
|
/*
|
|
* The number of times a path is hashed, i.e. the
|
|
* number of bit positions tht cumulatively
|
|
* determine whether a path is present in the
|
|
* Bloom filter.
|
|
*/
|
|
uint32_t num_hashes;
|
|
|
|
/*
|
|
* The minimum number of bits per entry in the Bloom
|
|
* filter. If the filter contains 'n' entries, then
|
|
* filter size is the minimum number of 8-bit words
|
|
* that contain n*b bits.
|
|
*/
|
|
uint32_t bits_per_entry;
|
|
};
|
|
|
|
#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10 }
|
|
#define BITS_PER_WORD 8
|
|
|
|
/*
|
|
* A bloom_filter struct represents a data segment to
|
|
* use when testing hash values. The 'len' member
|
|
* dictates how many entries are stored in
|
|
* 'data'.
|
|
*/
|
|
struct bloom_filter {
|
|
unsigned char *data;
|
|
size_t len;
|
|
};
|
|
|
|
/*
|
|
* A bloom_key represents the k hash values for a
|
|
* given string. These can be precomputed and
|
|
* stored in a bloom_key for re-use when testing
|
|
* against a bloom_filter. The number of hashes is
|
|
* given by the Bloom filter settings and is the same
|
|
* for all Bloom filters and keys interacting with
|
|
* the loaded version of the commit graph file and
|
|
* the Bloom data chunks.
|
|
*/
|
|
struct bloom_key {
|
|
uint32_t *hashes;
|
|
};
|
|
|
|
/*
|
|
* 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);
|
|
|
|
void fill_bloom_key(const char *data,
|
|
size_t len,
|
|
struct bloom_key *key,
|
|
const struct bloom_filter_settings *settings);
|
|
|
|
void add_key_to_filter(const struct bloom_key *key,
|
|
struct bloom_filter *filter,
|
|
const struct bloom_filter_settings *settings);
|
|
|
|
void init_bloom_filters(void);
|
|
|
|
struct bloom_filter *get_bloom_filter(struct repository *r,
|
|
struct commit *c);
|
|
|
|
#endif |