git/pack-bitmap.c

1074 строки
25 KiB
C
Исходник Обычный вид История

pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
#include "cache.h"
#include "commit.h"
#include "tag.h"
#include "diff.h"
#include "revision.h"
#include "progress.h"
#include "list-objects.h"
#include "pack.h"
#include "pack-bitmap.h"
#include "pack-revindex.h"
#include "pack-objects.h"
/*
* An entry on the bitmap index, representing the bitmap for a given
* commit.
*/
struct stored_bitmap {
unsigned char sha1[20];
struct ewah_bitmap *root;
struct stored_bitmap *xor;
int flags;
};
/*
* The currently active bitmap index. By design, repositories only have
* a single bitmap index available (the index for the biggest packfile in
* the repository), since bitmap indexes need full closure.
*
* If there is more than one bitmap index available (e.g. because of alternates),
* the active bitmap index is the largest one.
*/
static struct bitmap_index {
/* Packfile to which this bitmap index belongs to */
struct packed_git *pack;
/* reverse index for the packfile */
struct pack_revindex *reverse_index;
/*
* Mark the first `reuse_objects` in the packfile as reused:
* they will be sent as-is without using them for repacking
* calculations
*/
uint32_t reuse_objects;
/* mmapped buffer of the whole bitmap index */
unsigned char *map;
size_t map_size; /* size of the mmaped buffer */
size_t map_pos; /* current position when loading the index */
/*
* Type indexes.
*
* Each bitmap marks which objects in the packfile are of the given
* type. This provides type information when yielding the objects from
* the packfile during a walk, which allows for better delta bases.
*/
struct ewah_bitmap *commits;
struct ewah_bitmap *trees;
struct ewah_bitmap *blobs;
struct ewah_bitmap *tags;
/* Map from SHA1 -> `stored_bitmap` for all the bitmapped comits */
khash_sha1 *bitmaps;
/* Number of bitmapped commits */
uint32_t entry_count;
pack-bitmap: implement optional name_hash cache When we use pack bitmaps rather than walking the object graph, we end up with the list of objects to include in the packfile, but we do not know the path at which any tree or blob objects would be found. In a recently packed repository, this is fine. A fetch would use the paths only as a heuristic in the delta compression phase, and a fully packed repository should not need to do much delta compression. As time passes, though, we may acquire more objects on top of our large bitmapped pack. If clients fetch frequently, then they never even look at the bitmapped history, and all works as usual. However, a client who has not fetched since the last bitmap repack will have "have" tips in the bitmapped history, but "want" newer objects. The bitmaps themselves degrade gracefully in this circumstance. We manually walk the more recent bits of history, and then use bitmaps when we hit them. But we would also like to perform delta compression between the newer objects and the bitmapped objects (both to delta against what we know the user already has, but also between "new" and "old" objects that the user is fetching). The lack of pathnames makes our delta heuristics much less effective. This patch adds an optional cache of the 32-bit name_hash values to the end of the bitmap file. If present, a reader can use it to match bitmapped and non-bitmapped names during delta compression. Here are perf results for p5310: Test origin/master HEAD^ HEAD ------------------------------------------------------------------------------------------------- 5310.2: repack to disk 36.81(37.82+1.43) 47.70(48.74+1.41) +29.6% 47.75(48.70+1.51) +29.7% 5310.3: simulated clone 30.78(29.70+2.14) 1.08(0.97+0.10) -96.5% 1.07(0.94+0.12) -96.5% 5310.4: simulated fetch 3.16(6.10+0.08) 3.54(10.65+0.06) +12.0% 1.70(3.07+0.06) -46.2% 5310.6: partial bitmap 36.76(43.19+1.81) 6.71(11.25+0.76) -81.7% 4.08(6.26+0.46) -88.9% You can see that the time spent on an incremental fetch goes down, as our delta heuristics are able to do their work. And we save time on the partial bitmap clone for the same reason. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:45 +04:00
/* Name-hash cache (or NULL if not present). */
uint32_t *hashes;
pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
/*
* Extended index.
*
* When trying to perform bitmap operations with objects that are not
* packed in `pack`, these objects are added to this "fake index" and
* are assumed to appear at the end of the packfile for all operations
*/
struct eindex {
struct object **objects;
uint32_t *hashes;
uint32_t count, alloc;
khash_sha1_pos *positions;
} ext_index;
/* Bitmap result of the last performed walk */
struct bitmap *result;
/* Version of the bitmap index */
unsigned int version;
unsigned loaded : 1;
} bitmap_git;
static struct ewah_bitmap *lookup_stored_bitmap(struct stored_bitmap *st)
{
struct ewah_bitmap *parent;
struct ewah_bitmap *composed;
if (st->xor == NULL)
return st->root;
composed = ewah_pool_new();
parent = lookup_stored_bitmap(st->xor);
ewah_xor(st->root, parent, composed);
ewah_pool_free(st->root);
st->root = composed;
st->xor = NULL;
return composed;
}
/*
* Read a bitmap from the current read position on the mmaped
* index, and increase the read position accordingly
*/
static struct ewah_bitmap *read_bitmap_1(struct bitmap_index *index)
{
struct ewah_bitmap *b = ewah_pool_new();
int bitmap_size = ewah_read_mmap(b,
index->map + index->map_pos,
index->map_size - index->map_pos);
if (bitmap_size < 0) {
error("Failed to load bitmap index (corrupted?)");
ewah_pool_free(b);
return NULL;
}
index->map_pos += bitmap_size;
return b;
}
static int load_bitmap_header(struct bitmap_index *index)
{
struct bitmap_disk_header *header = (void *)index->map;
if (index->map_size < sizeof(*header) + 20)
return error("Corrupted bitmap index (missing header data)");
if (memcmp(header->magic, BITMAP_IDX_SIGNATURE, sizeof(BITMAP_IDX_SIGNATURE)) != 0)
return error("Corrupted bitmap index file (wrong header)");
index->version = ntohs(header->version);
if (index->version != 1)
return error("Unsupported version for bitmap index file (%d)", index->version);
/* Parse known bitmap format options */
{
uint32_t flags = ntohs(header->options);
if ((flags & BITMAP_OPT_FULL_DAG) == 0)
return error("Unsupported options for bitmap index file "
"(Git requires BITMAP_OPT_FULL_DAG)");
pack-bitmap: implement optional name_hash cache When we use pack bitmaps rather than walking the object graph, we end up with the list of objects to include in the packfile, but we do not know the path at which any tree or blob objects would be found. In a recently packed repository, this is fine. A fetch would use the paths only as a heuristic in the delta compression phase, and a fully packed repository should not need to do much delta compression. As time passes, though, we may acquire more objects on top of our large bitmapped pack. If clients fetch frequently, then they never even look at the bitmapped history, and all works as usual. However, a client who has not fetched since the last bitmap repack will have "have" tips in the bitmapped history, but "want" newer objects. The bitmaps themselves degrade gracefully in this circumstance. We manually walk the more recent bits of history, and then use bitmaps when we hit them. But we would also like to perform delta compression between the newer objects and the bitmapped objects (both to delta against what we know the user already has, but also between "new" and "old" objects that the user is fetching). The lack of pathnames makes our delta heuristics much less effective. This patch adds an optional cache of the 32-bit name_hash values to the end of the bitmap file. If present, a reader can use it to match bitmapped and non-bitmapped names during delta compression. Here are perf results for p5310: Test origin/master HEAD^ HEAD ------------------------------------------------------------------------------------------------- 5310.2: repack to disk 36.81(37.82+1.43) 47.70(48.74+1.41) +29.6% 47.75(48.70+1.51) +29.7% 5310.3: simulated clone 30.78(29.70+2.14) 1.08(0.97+0.10) -96.5% 1.07(0.94+0.12) -96.5% 5310.4: simulated fetch 3.16(6.10+0.08) 3.54(10.65+0.06) +12.0% 1.70(3.07+0.06) -46.2% 5310.6: partial bitmap 36.76(43.19+1.81) 6.71(11.25+0.76) -81.7% 4.08(6.26+0.46) -88.9% You can see that the time spent on an incremental fetch goes down, as our delta heuristics are able to do their work. And we save time on the partial bitmap clone for the same reason. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:45 +04:00
if (flags & BITMAP_OPT_HASH_CACHE) {
unsigned char *end = index->map + index->map_size - 20;
index->hashes = ((uint32_t *)end) - index->pack->num_objects;
}
pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
}
index->entry_count = ntohl(header->entry_count);
index->map_pos += sizeof(*header);
return 0;
}
static struct stored_bitmap *store_bitmap(struct bitmap_index *index,
struct ewah_bitmap *root,
const unsigned char *sha1,
struct stored_bitmap *xor_with,
int flags)
{
struct stored_bitmap *stored;
khiter_t hash_pos;
int ret;
stored = xmalloc(sizeof(struct stored_bitmap));
stored->root = root;
stored->xor = xor_with;
stored->flags = flags;
hashcpy(stored->sha1, sha1);
hash_pos = kh_put_sha1(index->bitmaps, stored->sha1, &ret);
/* a 0 return code means the insertion succeeded with no changes,
* because the SHA1 already existed on the map. this is bad, there
* shouldn't be duplicated commits in the index */
if (ret == 0) {
error("Duplicate entry in bitmap index: %s", sha1_to_hex(sha1));
return NULL;
}
kh_value(index->bitmaps, hash_pos) = stored;
return stored;
}
static int load_bitmap_entries_v1(struct bitmap_index *index)
{
static const size_t MAX_XOR_OFFSET = 160;
uint32_t i;
struct stored_bitmap **recent_bitmaps;
struct bitmap_disk_entry *entry;
recent_bitmaps = xcalloc(MAX_XOR_OFFSET, sizeof(struct stored_bitmap));
for (i = 0; i < index->entry_count; ++i) {
int xor_offset, flags;
struct ewah_bitmap *bitmap = NULL;
struct stored_bitmap *xor_bitmap = NULL;
uint32_t commit_idx_pos;
const unsigned char *sha1;
entry = (struct bitmap_disk_entry *)(index->map + index->map_pos);
index->map_pos += sizeof(struct bitmap_disk_entry);
commit_idx_pos = ntohl(entry->object_pos);
sha1 = nth_packed_object_sha1(index->pack, commit_idx_pos);
xor_offset = (int)entry->xor_offset;
flags = (int)entry->flags;
bitmap = read_bitmap_1(index);
if (!bitmap)
return -1;
if (xor_offset > MAX_XOR_OFFSET || xor_offset > i)
return error("Corrupted bitmap pack index");
if (xor_offset > 0) {
xor_bitmap = recent_bitmaps[(i - xor_offset) % MAX_XOR_OFFSET];
if (xor_bitmap == NULL)
return error("Invalid XOR offset in bitmap pack index");
}
recent_bitmaps[i % MAX_XOR_OFFSET] = store_bitmap(
index, bitmap, sha1, xor_bitmap, flags);
}
return 0;
}
static int open_pack_bitmap_1(struct packed_git *packfile)
{
int fd;
struct stat st;
char *idx_name;
if (open_pack_index(packfile))
return -1;
idx_name = pack_bitmap_filename(packfile);
fd = git_open_noatime(idx_name);
free(idx_name);
if (fd < 0)
return -1;
if (fstat(fd, &st)) {
close(fd);
return -1;
}
if (bitmap_git.pack) {
warning("ignoring extra bitmap file: %s", packfile->pack_name);
close(fd);
return -1;
}
bitmap_git.pack = packfile;
bitmap_git.map_size = xsize_t(st.st_size);
bitmap_git.map = xmmap(NULL, bitmap_git.map_size, PROT_READ, MAP_PRIVATE, fd, 0);
bitmap_git.map_pos = 0;
close(fd);
if (load_bitmap_header(&bitmap_git) < 0) {
munmap(bitmap_git.map, bitmap_git.map_size);
bitmap_git.map = NULL;
bitmap_git.map_size = 0;
return -1;
}
return 0;
}
static int load_pack_bitmap(void)
{
assert(bitmap_git.map && !bitmap_git.loaded);
bitmap_git.bitmaps = kh_init_sha1();
bitmap_git.ext_index.positions = kh_init_sha1_pos();
bitmap_git.reverse_index = revindex_for_pack(bitmap_git.pack);
if (!(bitmap_git.commits = read_bitmap_1(&bitmap_git)) ||
!(bitmap_git.trees = read_bitmap_1(&bitmap_git)) ||
!(bitmap_git.blobs = read_bitmap_1(&bitmap_git)) ||
!(bitmap_git.tags = read_bitmap_1(&bitmap_git)))
goto failed;
if (load_bitmap_entries_v1(&bitmap_git) < 0)
goto failed;
bitmap_git.loaded = 1;
return 0;
failed:
munmap(bitmap_git.map, bitmap_git.map_size);
bitmap_git.map = NULL;
bitmap_git.map_size = 0;
return -1;
}
char *pack_bitmap_filename(struct packed_git *p)
{
char *idx_name;
int len;
len = strlen(p->pack_name) - strlen(".pack");
idx_name = xmalloc(len + strlen(".bitmap") + 1);
memcpy(idx_name, p->pack_name, len);
memcpy(idx_name + len, ".bitmap", strlen(".bitmap") + 1);
return idx_name;
}
static int open_pack_bitmap(void)
{
struct packed_git *p;
int ret = -1;
assert(!bitmap_git.map && !bitmap_git.loaded);
prepare_packed_git();
for (p = packed_git; p; p = p->next) {
if (open_pack_bitmap_1(p) == 0)
ret = 0;
}
return ret;
}
int prepare_bitmap_git(void)
{
if (bitmap_git.loaded)
return 0;
if (!open_pack_bitmap())
return load_pack_bitmap();
return -1;
}
struct include_data {
struct bitmap *base;
struct bitmap *seen;
};
static inline int bitmap_position_extended(const unsigned char *sha1)
{
khash_sha1_pos *positions = bitmap_git.ext_index.positions;
khiter_t pos = kh_get_sha1_pos(positions, sha1);
if (pos < kh_end(positions)) {
int bitmap_pos = kh_value(positions, pos);
return bitmap_pos + bitmap_git.pack->num_objects;
}
return -1;
}
static inline int bitmap_position_packfile(const unsigned char *sha1)
{
off_t offset = find_pack_entry_one(sha1, bitmap_git.pack);
if (!offset)
return -1;
return find_revindex_position(bitmap_git.reverse_index, offset);
}
static int bitmap_position(const unsigned char *sha1)
{
int pos = bitmap_position_packfile(sha1);
return (pos >= 0) ? pos : bitmap_position_extended(sha1);
}
static int ext_index_add_object(struct object *object, const char *name)
{
struct eindex *eindex = &bitmap_git.ext_index;
khiter_t hash_pos;
int hash_ret;
int bitmap_pos;
hash_pos = kh_put_sha1_pos(eindex->positions, object->sha1, &hash_ret);
if (hash_ret > 0) {
if (eindex->count >= eindex->alloc) {
eindex->alloc = (eindex->alloc + 16) * 3 / 2;
REALLOC_ARRAY(eindex->objects, eindex->alloc);
REALLOC_ARRAY(eindex->hashes, eindex->alloc);
pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
}
bitmap_pos = eindex->count;
eindex->objects[eindex->count] = object;
eindex->hashes[eindex->count] = pack_name_hash(name);
kh_value(eindex->positions, hash_pos) = bitmap_pos;
eindex->count++;
} else {
bitmap_pos = kh_value(eindex->positions, hash_pos);
}
return bitmap_pos + bitmap_git.pack->num_objects;
}
static void show_object(struct object *object, const struct name_path *path,
const char *last, void *data)
{
struct bitmap *base = data;
int bitmap_pos;
bitmap_pos = bitmap_position(object->sha1);
if (bitmap_pos < 0) {
char *name = path_name(path, last);
bitmap_pos = ext_index_add_object(object, name);
free(name);
}
bitmap_set(base, bitmap_pos);
}
static void show_commit(struct commit *commit, void *data)
{
}
static int add_to_include_set(struct include_data *data,
const unsigned char *sha1,
int bitmap_pos)
{
khiter_t hash_pos;
if (data->seen && bitmap_get(data->seen, bitmap_pos))
return 0;
if (bitmap_get(data->base, bitmap_pos))
return 0;
hash_pos = kh_get_sha1(bitmap_git.bitmaps, sha1);
if (hash_pos < kh_end(bitmap_git.bitmaps)) {
struct stored_bitmap *st = kh_value(bitmap_git.bitmaps, hash_pos);
bitmap_or_ewah(data->base, lookup_stored_bitmap(st));
return 0;
}
bitmap_set(data->base, bitmap_pos);
return 1;
}
static int should_include(struct commit *commit, void *_data)
{
struct include_data *data = _data;
int bitmap_pos;
bitmap_pos = bitmap_position(commit->object.sha1);
if (bitmap_pos < 0)
bitmap_pos = ext_index_add_object((struct object *)commit, NULL);
if (!add_to_include_set(data, commit->object.sha1, bitmap_pos)) {
struct commit_list *parent = commit->parents;
while (parent) {
parent->item->object.flags |= SEEN;
parent = parent->next;
}
return 0;
}
return 1;
}
static struct bitmap *find_objects(struct rev_info *revs,
struct object_list *roots,
struct bitmap *seen)
{
struct bitmap *base = NULL;
int needs_walk = 0;
struct object_list *not_mapped = NULL;
/*
* Go through all the roots for the walk. The ones that have bitmaps
* on the bitmap index will be `or`ed together to form an initial
* global reachability analysis.
*
* The ones without bitmaps in the index will be stored in the
* `not_mapped_list` for further processing.
*/
while (roots) {
struct object *object = roots->item;
roots = roots->next;
if (object->type == OBJ_COMMIT) {
khiter_t pos = kh_get_sha1(bitmap_git.bitmaps, object->sha1);
if (pos < kh_end(bitmap_git.bitmaps)) {
struct stored_bitmap *st = kh_value(bitmap_git.bitmaps, pos);
struct ewah_bitmap *or_with = lookup_stored_bitmap(st);
if (base == NULL)
base = ewah_to_bitmap(or_with);
else
bitmap_or_ewah(base, or_with);
object->flags |= SEEN;
continue;
}
}
object_list_insert(object, &not_mapped);
}
/*
* Best case scenario: We found bitmaps for all the roots,
* so the resulting `or` bitmap has the full reachability analysis
*/
if (not_mapped == NULL)
return base;
roots = not_mapped;
/*
* Let's iterate through all the roots that don't have bitmaps to
* check if we can determine them to be reachable from the existing
* global bitmap.
*
* If we cannot find them in the existing global bitmap, we'll need
* to push them to an actual walk and run it until we can confirm
* they are reachable
*/
while (roots) {
struct object *object = roots->item;
int pos;
roots = roots->next;
pos = bitmap_position(object->sha1);
if (pos < 0 || base == NULL || !bitmap_get(base, pos)) {
object->flags &= ~UNINTERESTING;
add_pending_object(revs, object, "");
needs_walk = 1;
} else {
object->flags |= SEEN;
}
}
if (needs_walk) {
struct include_data incdata;
if (base == NULL)
base = bitmap_new();
incdata.base = base;
incdata.seen = seen;
revs->include_check = should_include;
revs->include_check_data = &incdata;
if (prepare_revision_walk(revs))
die("revision walk setup failed");
traverse_commit_list(revs, show_commit, show_object, base);
}
return base;
}
static void show_extended_objects(struct bitmap *objects,
show_reachable_fn show_reach)
{
struct eindex *eindex = &bitmap_git.ext_index;
uint32_t i;
for (i = 0; i < eindex->count; ++i) {
struct object *obj;
if (!bitmap_get(objects, bitmap_git.pack->num_objects + i))
continue;
obj = eindex->objects[i];
show_reach(obj->sha1, obj->type, 0, eindex->hashes[i], NULL, 0);
}
}
static void show_objects_for_type(
struct bitmap *objects,
struct ewah_bitmap *type_filter,
enum object_type object_type,
show_reachable_fn show_reach)
{
size_t pos = 0, i = 0;
uint32_t offset;
struct ewah_iterator it;
eword_t filter;
if (bitmap_git.reuse_objects == bitmap_git.pack->num_objects)
return;
ewah_iterator_init(&it, type_filter);
while (i < objects->word_alloc && ewah_iterator_next(&filter, &it)) {
eword_t word = objects->words[i] & filter;
for (offset = 0; offset < BITS_IN_WORD; ++offset) {
const unsigned char *sha1;
struct revindex_entry *entry;
uint32_t hash = 0;
if ((word >> offset) == 0)
break;
offset += ewah_bit_ctz64(word >> offset);
if (pos + offset < bitmap_git.reuse_objects)
continue;
entry = &bitmap_git.reverse_index->revindex[pos + offset];
sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr);
pack-bitmap: implement optional name_hash cache When we use pack bitmaps rather than walking the object graph, we end up with the list of objects to include in the packfile, but we do not know the path at which any tree or blob objects would be found. In a recently packed repository, this is fine. A fetch would use the paths only as a heuristic in the delta compression phase, and a fully packed repository should not need to do much delta compression. As time passes, though, we may acquire more objects on top of our large bitmapped pack. If clients fetch frequently, then they never even look at the bitmapped history, and all works as usual. However, a client who has not fetched since the last bitmap repack will have "have" tips in the bitmapped history, but "want" newer objects. The bitmaps themselves degrade gracefully in this circumstance. We manually walk the more recent bits of history, and then use bitmaps when we hit them. But we would also like to perform delta compression between the newer objects and the bitmapped objects (both to delta against what we know the user already has, but also between "new" and "old" objects that the user is fetching). The lack of pathnames makes our delta heuristics much less effective. This patch adds an optional cache of the 32-bit name_hash values to the end of the bitmap file. If present, a reader can use it to match bitmapped and non-bitmapped names during delta compression. Here are perf results for p5310: Test origin/master HEAD^ HEAD ------------------------------------------------------------------------------------------------- 5310.2: repack to disk 36.81(37.82+1.43) 47.70(48.74+1.41) +29.6% 47.75(48.70+1.51) +29.7% 5310.3: simulated clone 30.78(29.70+2.14) 1.08(0.97+0.10) -96.5% 1.07(0.94+0.12) -96.5% 5310.4: simulated fetch 3.16(6.10+0.08) 3.54(10.65+0.06) +12.0% 1.70(3.07+0.06) -46.2% 5310.6: partial bitmap 36.76(43.19+1.81) 6.71(11.25+0.76) -81.7% 4.08(6.26+0.46) -88.9% You can see that the time spent on an incremental fetch goes down, as our delta heuristics are able to do their work. And we save time on the partial bitmap clone for the same reason. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:45 +04:00
if (bitmap_git.hashes)
hash = ntohl(bitmap_git.hashes[entry->nr]);
pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
show_reach(sha1, object_type, 0, hash, bitmap_git.pack, entry->offset);
}
pos += BITS_IN_WORD;
i++;
}
}
static int in_bitmapped_pack(struct object_list *roots)
{
while (roots) {
struct object *object = roots->item;
roots = roots->next;
if (find_pack_entry_one(object->sha1, bitmap_git.pack) > 0)
return 1;
}
return 0;
}
int prepare_bitmap_walk(struct rev_info *revs)
{
unsigned int i;
unsigned int pending_nr = revs->pending.nr;
struct object_array_entry *pending_e = revs->pending.objects;
struct object_list *wants = NULL;
struct object_list *haves = NULL;
struct bitmap *wants_bitmap = NULL;
struct bitmap *haves_bitmap = NULL;
if (!bitmap_git.loaded) {
/* try to open a bitmapped pack, but don't parse it yet
* because we may not need to use it */
if (open_pack_bitmap() < 0)
return -1;
}
for (i = 0; i < pending_nr; ++i) {
struct object *object = pending_e[i].item;
if (object->type == OBJ_NONE)
parse_object_or_die(object->sha1, NULL);
while (object->type == OBJ_TAG) {
struct tag *tag = (struct tag *) object;
if (object->flags & UNINTERESTING)
object_list_insert(object, &haves);
else
object_list_insert(object, &wants);
if (!tag->tagged)
die("bad tag");
object = parse_object_or_die(tag->tagged->sha1, NULL);
}
if (object->flags & UNINTERESTING)
object_list_insert(object, &haves);
else
object_list_insert(object, &wants);
}
/*
* if we have a HAVES list, but none of those haves is contained
* in the packfile that has a bitmap, we don't have anything to
* optimize here
*/
if (haves && !in_bitmapped_pack(haves))
return -1;
/* if we don't want anything, we're done here */
if (!wants)
return -1;
/*
* now we're going to use bitmaps, so load the actual bitmap entries
* from disk. this is the point of no return; after this the rev_list
* becomes invalidated and we must perform the revwalk through bitmaps
*/
if (!bitmap_git.loaded && load_pack_bitmap() < 0)
return -1;
revs->pending.nr = 0;
revs->pending.alloc = 0;
revs->pending.objects = NULL;
if (haves) {
add `ignore_missing_links` mode to revwalk When pack-objects is computing the reachability bitmap to serve a fetch request, it can erroneously die() if some of the UNINTERESTING objects are not present. Upload-pack throws away HAVE lines from the client for objects we do not have, but we may have a tip object without all of its ancestors (e.g., if the tip is no longer reachable and was new enough to survive a `git prune`, but some of its reachable objects did get pruned). In the non-bitmap case, we do a revision walk with the HAVE objects marked as UNINTERESTING. The revision walker explicitly ignores errors in accessing UNINTERESTING commits to handle this case (and we do not bother looking at UNINTERESTING trees or blobs at all). When we have bitmaps, however, the process is quite different. The bitmap index for a pack-objects run is calculated in two separate steps: First, we perform an extensive walk from all the HAVEs to find the full set of objects reachable from them. This walk is usually optimized away because we are expected to hit an object with a bitmap during the traversal, which allows us to terminate early. Secondly, we perform an extensive walk from all the WANTs, which usually also terminates early because we hit a commit with an existing bitmap. Once we have the resulting bitmaps from the two walks, we AND-NOT them together to obtain the resulting set of objects we need to pack. When we are walking the HAVE objects, the revision walker does not know that we are walking it only to mark the results as uninteresting. We strip out the UNINTERESTING flag, because those objects _are_ interesting to us during the first walk. We want to keep going to get a complete set of reachable objects if we can. We need some way to tell the revision walker that it's OK to silently truncate the HAVE walk, just like it does for the UNINTERESTING case. This patch introduces a new `ignore_missing_links` flag to the `rev_info` struct, which we set only for the HAVE walk. It also adds tests to cover UNINTERESTING objects missing from several positions: a missing blob, a missing tree, and a missing parent commit. The missing blob already worked (as we do not care about its contents at all), but the other two cases caused us to die(). Note that there are a few cases we do not need to test: 1. We do not need to test a missing tree, with the blob still present. Without the tree that refers to it, we would not know that the blob is relevant to our walk. 2. We do not need to test a tip commit that is missing. Upload-pack omits these for us (and in fact, we complain even in the non-bitmap case if it fails to do so). Reported-by: Siddharth Agarwal <sid0@fb.com> Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-03-28 14:00:43 +04:00
revs->ignore_missing_links = 1;
pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
haves_bitmap = find_objects(revs, haves, NULL);
reset_revision_walk();
add `ignore_missing_links` mode to revwalk When pack-objects is computing the reachability bitmap to serve a fetch request, it can erroneously die() if some of the UNINTERESTING objects are not present. Upload-pack throws away HAVE lines from the client for objects we do not have, but we may have a tip object without all of its ancestors (e.g., if the tip is no longer reachable and was new enough to survive a `git prune`, but some of its reachable objects did get pruned). In the non-bitmap case, we do a revision walk with the HAVE objects marked as UNINTERESTING. The revision walker explicitly ignores errors in accessing UNINTERESTING commits to handle this case (and we do not bother looking at UNINTERESTING trees or blobs at all). When we have bitmaps, however, the process is quite different. The bitmap index for a pack-objects run is calculated in two separate steps: First, we perform an extensive walk from all the HAVEs to find the full set of objects reachable from them. This walk is usually optimized away because we are expected to hit an object with a bitmap during the traversal, which allows us to terminate early. Secondly, we perform an extensive walk from all the WANTs, which usually also terminates early because we hit a commit with an existing bitmap. Once we have the resulting bitmaps from the two walks, we AND-NOT them together to obtain the resulting set of objects we need to pack. When we are walking the HAVE objects, the revision walker does not know that we are walking it only to mark the results as uninteresting. We strip out the UNINTERESTING flag, because those objects _are_ interesting to us during the first walk. We want to keep going to get a complete set of reachable objects if we can. We need some way to tell the revision walker that it's OK to silently truncate the HAVE walk, just like it does for the UNINTERESTING case. This patch introduces a new `ignore_missing_links` flag to the `rev_info` struct, which we set only for the HAVE walk. It also adds tests to cover UNINTERESTING objects missing from several positions: a missing blob, a missing tree, and a missing parent commit. The missing blob already worked (as we do not care about its contents at all), but the other two cases caused us to die(). Note that there are a few cases we do not need to test: 1. We do not need to test a missing tree, with the blob still present. Without the tree that refers to it, we would not know that the blob is relevant to our walk. 2. We do not need to test a tip commit that is missing. Upload-pack omits these for us (and in fact, we complain even in the non-bitmap case if it fails to do so). Reported-by: Siddharth Agarwal <sid0@fb.com> Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-03-28 14:00:43 +04:00
revs->ignore_missing_links = 0;
pack-bitmap: add support for bitmap indexes A bitmap index is a `.bitmap` file that can be found inside `$GIT_DIR/objects/pack/`, next to its corresponding packfile, and contains precalculated reachability information for selected commits. The full specification of the format for these bitmap indexes can be found in `Documentation/technical/bitmap-format.txt`. For a given commit SHA1, if it happens to be available in the bitmap index, its bitmap will represent every single object that is reachable from the commit itself. The nth bit in the bitmap is the nth object in the packfile; if it's set to 1, the object is reachable. By using the bitmaps available in the index, this commit implements several new functions: - `prepare_bitmap_git` - `prepare_bitmap_walk` - `traverse_bitmap_commit_list` - `reuse_partial_packfile_from_bitmap` The `prepare_bitmap_walk` function tries to build a bitmap of all the objects that can be reached from the commit roots of a given `rev_info` struct by using the following algorithm: - If all the interesting commits for a revision walk are available in the index, the resulting reachability bitmap is the bitwise OR of all the individual bitmaps. - When the full set of WANTs is not available in the index, we perform a partial revision walk using the commits that don't have bitmaps as roots, and limiting the revision walk as soon as we reach a commit that has a corresponding bitmap. The earlier OR'ed bitmap with all the indexed commits can now be completed as this walk progresses, so the end result is the full reachability list. - For revision walks with a HAVEs set (a set of commits that are deemed uninteresting), first we perform the same method as for the WANTs, but using our HAVEs as roots, in order to obtain a full reachability bitmap of all the uninteresting commits. This bitmap then can be used to: a) limit the subsequent walk when building the WANTs bitmap b) finding the final set of interesting commits by performing an AND-NOT of the WANTs and the HAVEs. If `prepare_bitmap_walk` runs successfully, the resulting bitmap is stored and the equivalent of a `traverse_commit_list` call can be performed by using `traverse_bitmap_commit_list`; the bitmap version of this call yields the objects straight from the packfile index (without having to look them up or parse them) and hence is several orders of magnitude faster. As an extra optimization, when `prepare_bitmap_walk` succeeds, the `reuse_partial_packfile_from_bitmap` call can be attempted: it will find the amount of objects at the beginning of the on-disk packfile that can be reused as-is, and return an offset into the packfile. The source packfile can then be loaded and the bytes up to `offset` can be written directly to the result without having to consider the entires inside the packfile individually. If the `prepare_bitmap_walk` call fails (e.g. because no bitmap files are available), the `rev_info` struct is left untouched, and can be used to perform a manual rev-walk using `traverse_commit_list`. Hence, this new set of functions are a generic API that allows to perform the equivalent of git rev-list --objects [roots...] [^uninteresting...] for any set of commits, even if they don't have specific bitmaps generated for them. In further patches, we'll use this bitmap traversal optimization to speed up the `pack-objects` and `rev-list` commands. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:01 +04:00
if (haves_bitmap == NULL)
die("BUG: failed to perform bitmap walk");
}
wants_bitmap = find_objects(revs, wants, haves_bitmap);
if (!wants_bitmap)
die("BUG: failed to perform bitmap walk");
if (haves_bitmap)
bitmap_and_not(wants_bitmap, haves_bitmap);
bitmap_git.result = wants_bitmap;
bitmap_free(haves_bitmap);
return 0;
}
int reuse_partial_packfile_from_bitmap(struct packed_git **packfile,
uint32_t *entries,
off_t *up_to)
{
/*
* Reuse the packfile content if we need more than
* 90% of its objects
*/
static const double REUSE_PERCENT = 0.9;
struct bitmap *result = bitmap_git.result;
uint32_t reuse_threshold;
uint32_t i, reuse_objects = 0;
assert(result);
for (i = 0; i < result->word_alloc; ++i) {
if (result->words[i] != (eword_t)~0) {
reuse_objects += ewah_bit_ctz64(~result->words[i]);
break;
}
reuse_objects += BITS_IN_WORD;
}
#ifdef GIT_BITMAP_DEBUG
{
const unsigned char *sha1;
struct revindex_entry *entry;
entry = &bitmap_git.reverse_index->revindex[reuse_objects];
sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr);
fprintf(stderr, "Failed to reuse at %d (%016llx)\n",
reuse_objects, result->words[i]);
fprintf(stderr, " %s\n", sha1_to_hex(sha1));
}
#endif
if (!reuse_objects)
return -1;
if (reuse_objects >= bitmap_git.pack->num_objects) {
bitmap_git.reuse_objects = *entries = bitmap_git.pack->num_objects;
*up_to = -1; /* reuse the full pack */
*packfile = bitmap_git.pack;
return 0;
}
reuse_threshold = bitmap_popcount(bitmap_git.result) * REUSE_PERCENT;
if (reuse_objects < reuse_threshold)
return -1;
bitmap_git.reuse_objects = *entries = reuse_objects;
*up_to = bitmap_git.reverse_index->revindex[reuse_objects].offset;
*packfile = bitmap_git.pack;
return 0;
}
void traverse_bitmap_commit_list(show_reachable_fn show_reachable)
{
assert(bitmap_git.result);
show_objects_for_type(bitmap_git.result, bitmap_git.commits,
OBJ_COMMIT, show_reachable);
show_objects_for_type(bitmap_git.result, bitmap_git.trees,
OBJ_TREE, show_reachable);
show_objects_for_type(bitmap_git.result, bitmap_git.blobs,
OBJ_BLOB, show_reachable);
show_objects_for_type(bitmap_git.result, bitmap_git.tags,
OBJ_TAG, show_reachable);
show_extended_objects(bitmap_git.result, show_reachable);
bitmap_free(bitmap_git.result);
bitmap_git.result = NULL;
}
static uint32_t count_object_type(struct bitmap *objects,
enum object_type type)
{
struct eindex *eindex = &bitmap_git.ext_index;
uint32_t i = 0, count = 0;
struct ewah_iterator it;
eword_t filter;
switch (type) {
case OBJ_COMMIT:
ewah_iterator_init(&it, bitmap_git.commits);
break;
case OBJ_TREE:
ewah_iterator_init(&it, bitmap_git.trees);
break;
case OBJ_BLOB:
ewah_iterator_init(&it, bitmap_git.blobs);
break;
case OBJ_TAG:
ewah_iterator_init(&it, bitmap_git.tags);
break;
default:
return 0;
}
while (i < objects->word_alloc && ewah_iterator_next(&filter, &it)) {
eword_t word = objects->words[i++] & filter;
count += ewah_bit_popcount64(word);
}
for (i = 0; i < eindex->count; ++i) {
if (eindex->objects[i]->type == type &&
bitmap_get(objects, bitmap_git.pack->num_objects + i))
count++;
}
return count;
}
void count_bitmap_commit_list(uint32_t *commits, uint32_t *trees,
uint32_t *blobs, uint32_t *tags)
{
assert(bitmap_git.result);
if (commits)
*commits = count_object_type(bitmap_git.result, OBJ_COMMIT);
if (trees)
*trees = count_object_type(bitmap_git.result, OBJ_TREE);
if (blobs)
*blobs = count_object_type(bitmap_git.result, OBJ_BLOB);
if (tags)
*tags = count_object_type(bitmap_git.result, OBJ_TAG);
}
struct bitmap_test_data {
struct bitmap *base;
struct progress *prg;
size_t seen;
};
static void test_show_object(struct object *object,
const struct name_path *path,
const char *last, void *data)
{
struct bitmap_test_data *tdata = data;
int bitmap_pos;
bitmap_pos = bitmap_position(object->sha1);
if (bitmap_pos < 0)
die("Object not in bitmap: %s\n", sha1_to_hex(object->sha1));
bitmap_set(tdata->base, bitmap_pos);
display_progress(tdata->prg, ++tdata->seen);
}
static void test_show_commit(struct commit *commit, void *data)
{
struct bitmap_test_data *tdata = data;
int bitmap_pos;
bitmap_pos = bitmap_position(commit->object.sha1);
if (bitmap_pos < 0)
die("Object not in bitmap: %s\n", sha1_to_hex(commit->object.sha1));
bitmap_set(tdata->base, bitmap_pos);
display_progress(tdata->prg, ++tdata->seen);
}
void test_bitmap_walk(struct rev_info *revs)
{
struct object *root;
struct bitmap *result = NULL;
khiter_t pos;
size_t result_popcnt;
struct bitmap_test_data tdata;
if (prepare_bitmap_git())
die("failed to load bitmap indexes");
if (revs->pending.nr != 1)
die("you must specify exactly one commit to test");
fprintf(stderr, "Bitmap v%d test (%d entries loaded)\n",
bitmap_git.version, bitmap_git.entry_count);
root = revs->pending.objects[0].item;
pos = kh_get_sha1(bitmap_git.bitmaps, root->sha1);
if (pos < kh_end(bitmap_git.bitmaps)) {
struct stored_bitmap *st = kh_value(bitmap_git.bitmaps, pos);
struct ewah_bitmap *bm = lookup_stored_bitmap(st);
fprintf(stderr, "Found bitmap for %s. %d bits / %08x checksum\n",
sha1_to_hex(root->sha1), (int)bm->bit_size, ewah_checksum(bm));
result = ewah_to_bitmap(bm);
}
if (result == NULL)
die("Commit %s doesn't have an indexed bitmap", sha1_to_hex(root->sha1));
revs->tag_objects = 1;
revs->tree_objects = 1;
revs->blob_objects = 1;
result_popcnt = bitmap_popcount(result);
if (prepare_revision_walk(revs))
die("revision walk setup failed");
tdata.base = bitmap_new();
tdata.prg = start_progress("Verifying bitmap entries", result_popcnt);
tdata.seen = 0;
traverse_commit_list(revs, &test_show_commit, &test_show_object, &tdata);
stop_progress(&tdata.prg);
if (bitmap_equals(result, tdata.base))
fprintf(stderr, "OK!\n");
else
fprintf(stderr, "Mismatch!\n");
}
pack-objects: implement bitmap writing This commit extends more the functionality of `pack-objects` by allowing it to write out a `.bitmap` index next to any written packs, together with the `.idx` index that currently gets written. If bitmap writing is enabled for a given repository (either by calling `pack-objects` with the `--write-bitmap-index` flag or by having `pack.writebitmaps` set to `true` in the config) and pack-objects is writing a packfile that would normally be indexed (i.e. not piping to stdout), we will attempt to write the corresponding bitmap index for the packfile. Bitmap index writing happens after the packfile and its index has been successfully written to disk (`finish_tmp_packfile`). The process is performed in several steps: 1. `bitmap_writer_set_checksum`: this call stores the partial checksum for the packfile being written; the checksum will be written in the resulting bitmap index to verify its integrity 2. `bitmap_writer_build_type_index`: this call uses the array of `struct object_entry` that has just been sorted when writing out the actual packfile index to disk to generate 4 type-index bitmaps (one for each object type). These bitmaps have their nth bit set if the given object is of the bitmap's type. E.g. the nth bit of the Commits bitmap will be 1 if the nth object in the packfile index is a commit. This is a very cheap operation because the bitmap writing code has access to the metadata stored in the `struct object_entry` array, and hence the real type for each object in the packfile. 3. `bitmap_writer_reuse_bitmaps`: if there exists an existing bitmap index for one of the packfiles we're trying to repack, this call will efficiently rebuild the existing bitmaps so they can be reused on the new index. All the existing bitmaps will be stored in a `reuse` hash table, and the commit selection phase will prioritize these when selecting, as they can be written directly to the new index without having to perform a revision walk to fill the bitmap. This can greatly speed up the repack of a repository that already has bitmaps. 4. `bitmap_writer_select_commits`: if bitmap writing is enabled for a given `pack-objects` run, the sequence of commits generated during the Counting Objects phase will be stored in an array. We then use that array to build up the list of selected commits. Writing a bitmap in the index for each object in the repository would be cost-prohibitive, so we use a simple heuristic to pick the commits that will be indexed with bitmaps. The current heuristics are a simplified version of JGit's original implementation. We select a higher density of commits depending on their age: the 100 most recent commits are always selected, after that we pick 1 commit of each 100, and the gap increases as the commits grow older. On top of that, we make sure that every single branch that has not been merged (all the tips that would be required from a clone) gets their own bitmap, and when selecting commits between a gap, we tend to prioritize the commit with the most parents. Do note that there is no right/wrong way to perform commit selection; different selection algorithms will result in different commits being selected, but there's no such thing as "missing a commit". The bitmap walker algorithm implemented in `prepare_bitmap_walk` is able to adapt to missing bitmaps by performing manual walks that complete the bitmap: the ideal selection algorithm, however, would select the commits that are more likely to be used as roots for a walk in the future (e.g. the tips of each branch, and so on) to ensure a bitmap for them is always available. 5. `bitmap_writer_build`: this is the computationally expensive part of bitmap generation. Based on the list of commits that were selected in the previous step, we perform several incremental walks to generate the bitmap for each commit. The walks begin from the oldest commit, and are built up incrementally for each branch. E.g. consider this dag where A, B, C, D, E, F are the selected commits, and a, b, c, e are a chunk of simplified history that will not receive bitmaps. A---a---B--b--C--c--D \ E--e--F We start by building the bitmap for A, using A as the root for a revision walk and marking all the objects that are reachable until the walk is over. Once this bitmap is stored, we reuse the bitmap walker to perform the walk for B, assuming that once we reach A again, the walk will be terminated because A has already been SEEN on the previous walk. This process is repeated for C, and D, but when we try to generate the bitmaps for E, we can reuse neither the current walk nor the bitmap we have generated so far. What we do now is resetting both the walk and clearing the bitmap, and performing the walk from scratch using E as the origin. This new walk, however, does not need to be completed. Once we hit B, we can lookup the bitmap we have already stored for that commit and OR it with the existing bitmap we've composed so far, allowing us to limit the walk early. After all the bitmaps have been generated, another iteration through the list of commits is performed to find the best XOR offsets for compression before writing them to disk. Because of the incremental nature of these bitmaps, XORing one of them with its predecesor results in a minimal "bitmap delta" most of the time. We can write this delta to the on-disk bitmap index, and then re-compose the original bitmaps by XORing them again when loaded. This is a phase very similar to pack-object's `find_delta` (using bitmaps instead of objects, of course), except the heuristics have been greatly simplified: we only check the 10 bitmaps before any given one to find best compressing one. This gives good results in practice, because there is locality in the ordering of the objects (and therefore bitmaps) in the packfile. 6. `bitmap_writer_finish`: the last step in the process is serializing to disk all the bitmap data that has been generated in the two previous steps. The bitmap is written to a tmp file and then moved atomically to its final destination, using the same process as `pack-write.c:write_idx_file`. Signed-off-by: Vicent Marti <tanoku@gmail.com> Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-21 18:00:16 +04:00
static int rebuild_bitmap(uint32_t *reposition,
struct ewah_bitmap *source,
struct bitmap *dest)
{
uint32_t pos = 0;
struct ewah_iterator it;
eword_t word;
ewah_iterator_init(&it, source);
while (ewah_iterator_next(&word, &it)) {
uint32_t offset, bit_pos;
for (offset = 0; offset < BITS_IN_WORD; ++offset) {
if ((word >> offset) == 0)
break;
offset += ewah_bit_ctz64(word >> offset);
bit_pos = reposition[pos + offset];
if (bit_pos > 0)
bitmap_set(dest, bit_pos - 1);
else /* can't reuse, we don't have the object */
return -1;
}
pos += BITS_IN_WORD;
}
return 0;
}
int rebuild_existing_bitmaps(struct packing_data *mapping,
khash_sha1 *reused_bitmaps,
int show_progress)
{
uint32_t i, num_objects;
uint32_t *reposition;
struct bitmap *rebuild;
struct stored_bitmap *stored;
struct progress *progress = NULL;
khiter_t hash_pos;
int hash_ret;
if (prepare_bitmap_git() < 0)
return -1;
num_objects = bitmap_git.pack->num_objects;
reposition = xcalloc(num_objects, sizeof(uint32_t));
for (i = 0; i < num_objects; ++i) {
const unsigned char *sha1;
struct revindex_entry *entry;
struct object_entry *oe;
entry = &bitmap_git.reverse_index->revindex[i];
sha1 = nth_packed_object_sha1(bitmap_git.pack, entry->nr);
oe = packlist_find(mapping, sha1, NULL);
if (oe)
reposition[i] = oe->in_pack_pos + 1;
}
rebuild = bitmap_new();
i = 0;
if (show_progress)
progress = start_progress("Reusing bitmaps", 0);
kh_foreach_value(bitmap_git.bitmaps, stored, {
if (stored->flags & BITMAP_FLAG_REUSE) {
if (!rebuild_bitmap(reposition,
lookup_stored_bitmap(stored),
rebuild)) {
hash_pos = kh_put_sha1(reused_bitmaps,
stored->sha1,
&hash_ret);
kh_value(reused_bitmaps, hash_pos) =
bitmap_to_ewah(rebuild);
}
bitmap_reset(rebuild);
display_progress(progress, ++i);
}
});
stop_progress(&progress);
free(reposition);
bitmap_free(rebuild);
return 0;
}