mirror of
https://github.com/git/git
synced 2024-11-05 04:53:18 +00:00
59f0d5073f
When a changed-path Bloom filter has either zero, or more than a certain number (commonly 512) of entries, the commit-graph machinery encodes it as "missing". More specifically, it sets the indices adjacent in the BIDX chunk as equal to each other to indicate a "length 0" filter; that is, that the filter occupies zero bytes on disk. This has heretofore been fine, since the commit-graph machinery has no need to care about these filters with too few or too many changed paths. Both cases act like no filter has been generated at all, and so there is no need to store them. In a subsequent commit, however, the commit-graph machinery will learn to only compute Bloom filters for some commits in the current commit-graph layer. This is a change from the current implementation which computes Bloom filters for all commits that are in the layer being written. Critically for this patch, only computing some of the Bloom filters means adding a third state for length 0 Bloom filters: zero entries, too many entries, or "hasn't been computed". It will be important for that future patch to distinguish between "not representable" (i.e., zero or too-many changed paths), and "hasn't been computed". In particular, we don't want to waste time recomputing filters that have already been computed. To that end, change how we store Bloom filters in the "computed but not representable" category: - Bloom filters with no entries are stored as a single byte with all bits low (i.e., all queries to that Bloom filter will return "definitely not") - Bloom filters with too many entries are stored as a single byte with all bits set high (i.e., all queries to that Bloom filter will return "maybe"). These rules are sufficient to not incur a behavior change by changing the on-disk representation of these two classes. Likewise, no specification changes are necessary for the commit-graph format, either: - Filters that were previously empty will be recomputed and stored according to the new rules, and - old clients reading filters generated by new clients will interpret the filters correctly and be none the wiser to how they were generated. Clients will invoke the Bloom machinery in more cases than before, but this can be addressed by returning a NULL filter when all bits are set high. This can be addressed in a future patch. Note that this does increase the size of on-disk commit-graphs, but far less than other proposals. In particular, this is generally more efficient than storing a bitmap for which commits haven't computed their Bloom filters. Storing a bitmap incurs a penalty of one bit per commit, whereas storing explicit filters as above incurs a penalty of one byte per too-large or empty commit. In practice, these boundary commits likely occupy a small proportion of the overall number of commits, and so the size penalty is likely smaller than storing a bitmap for all commits. See, for example, these relative proportions of such boundary commits (collected by SZEDER Gábor): | Percentage of | commit-graph | | | commits modifying | file size | | ├────────┬──────────────┼───────────────────┤ pct. | | 0 path | >= 512 paths | before | after | change | ┌────────────────┼────────┼──────────────┼─────────┼─────────┼───────────┤ | android-base | 13.20% | 0.13% | 37.468M | 37.534M | +0.1741 % | | cmssw | 0.15% | 0.23% | 17.118M | 17.119M | +0.0091 % | | cpython | 3.07% | 0.01% | 7.967M | 7.971M | +0.0423 % | | elasticsearch | 0.70% | 1.00% | 8.833M | 8.835M | +0.0128 % | | gcc | 0.00% | 0.08% | 16.073M | 16.074M | +0.0030 % | | gecko-dev | 0.14% | 0.64% | 59.868M | 59.874M | +0.0105 % | | git | 0.11% | 0.02% | 3.895M | 3.895M | +0.0020 % | | glibc | 0.02% | 0.10% | 3.555M | 3.555M | +0.0021 % | | go | 0.00% | 0.07% | 3.186M | 3.186M | +0.0018 % | | homebrew-cask | 0.40% | 0.02% | 7.035M | 7.035M | +0.0065 % | | homebrew-core | 0.01% | 0.01% | 11.611M | 11.611M | +0.0002 % | | jdk | 0.26% | 5.64% | 5.537M | 5.540M | +0.0590 % | | linux | 0.01% | 0.51% | 63.735M | 63.740M | +0.0073 % | | llvm-project | 0.12% | 0.03% | 25.515M | 25.516M | +0.0050 % | | rails | 0.10% | 0.10% | 6.252M | 6.252M | +0.0027 % | | rust | 0.07% | 0.17% | 9.364M | 9.364M | +0.0033 % | | tensorflow | 0.09% | 1.02% | 7.009M | 7.010M | +0.0158 % | | webkit | 0.05% | 0.31% | 17.405M | 17.406M | +0.0047 % | (where the above increase is determined by computing a non-split commit-graph before and after this patch). Given that these projects are all "large" by commit count, the storage cost by writing these filters explicitly is negligible. In the most extreme example, android-base (which has 494,848 commits at the time of writing) would have its commit-graph increase by a modest 68.4 KB. Finally, a test to exercise filters which contain too many changed path entries will be introduced in a subsequent patch. Suggested-by: SZEDER Gábor <szeder.dev@gmail.com> Suggested-by: Jakub Narębski <jnareb@gmail.com> Helped-by: Derrick Stolee <dstolee@microsoft.com> Helped-by: SZEDER Gábor <szeder.dev@gmail.com> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
112 lines
3 KiB
C
112 lines
3 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),
|
|
BLOOM_TRUNC_EMPTY = (1 << 3),
|
|
};
|
|
|
|
struct bloom_filter *get_or_compute_bloom_filter(struct repository *r,
|
|
struct commit *c,
|
|
int compute_if_not_present,
|
|
const struct bloom_filter_settings *settings,
|
|
enum bloom_filter_computed *computed);
|
|
|
|
#define get_bloom_filter(r, c) get_or_compute_bloom_filter( \
|
|
(r), (c), 0, NULL, NULL)
|
|
|
|
int bloom_filter_contains(const struct bloom_filter *filter,
|
|
const struct bloom_key *key,
|
|
const struct bloom_filter_settings *settings);
|
|
|
|
#endif
|