mirror of
https://github.com/git/git
synced 2024-10-05 16:19:28 +00:00
312cff5207
'get_bloom_filter' takes a flag to control whether it will compute a Bloom filter if the requested one is missing. In the next patch, we'll add yet another parameter to this method, which would force all but one caller to specify an extra 'NULL' parameter at the end. Instead of doing this, split 'get_bloom_filter' into two functions: 'get_bloom_filter' and 'get_or_compute_bloom_filter'. The former only looks up a Bloom filter (and does not compute one if it's missing, thus dropping the 'compute_if_not_present' flag). The latter does compute missing Bloom filters, with an additional parameter to store whether or not it needed to do so. This simplifies many call-sites, since the majority of existing callers to 'get_bloom_filter' do not want missing Bloom filters to be computed (so they can drop the parameter entirely and use the simpler version of the function). While we're at it, instrument the new 'get_or_compute_bloom_filter()' with counters in the 'write_commit_graph_context' struct which store the number of filters that we did and didn't compute, as well as filters that were truncated. It would be nice to drop the 'compute_if_not_present' flag entirely, since all remaining callers of 'get_or_compute_bloom_filter' pass it as '1', but this will change in a future patch and hence cannot be removed. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
111 lines
2.9 KiB
C
111 lines
2.9 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;
|
|
|
|
/*
|
|
* The maximum number of changed paths per commit
|
|
* before declaring a Bloom filter to be too-large.
|
|
*
|
|
* Not written to the commit-graph file.
|
|
*/
|
|
uint32_t max_changed_paths;
|
|
};
|
|
|
|
#define DEFAULT_BLOOM_MAX_CHANGES 512
|
|
#define DEFAULT_BLOOM_FILTER_SETTINGS { 1, 7, 10, DEFAULT_BLOOM_MAX_CHANGES }
|
|
#define BITS_PER_WORD 8
|
|
#define BLOOMDATA_CHUNK_HEADER_SIZE 3 * sizeof(uint32_t)
|
|
|
|
/*
|
|
* 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 clear_bloom_key(struct bloom_key *key);
|
|
|
|
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);
|
|
|
|
enum bloom_filter_computed {
|
|
BLOOM_NOT_COMPUTED = (1 << 0),
|
|
BLOOM_COMPUTED = (1 << 1),
|
|
BLOOM_TRUNC_LARGE = (1 << 2),
|
|
};
|
|
|
|
struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
|
|
struct commit *c,
|
|
int compute_if_not_present,
|
|
enum bloom_filter_computed *computed);
|
|
|
|
#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
|
|
(r), (c), 0, NULL)
|
|
|
|
int bloom_filter_contains(const struct bloom_filter *filter,
|
|
const struct bloom_key *key,
|
|
const struct bloom_filter_settings *settings);
|
|
|
|
#endif
|