From e9977b12fdd64a9c5d7d0aff10709e043181ca7b Mon Sep 17 00:00:00 2001 From: Abhradeep Chakraborty Date: Sun, 14 Aug 2022 16:55:06 +0000 Subject: [PATCH 1/7] Documentation/technical: describe bitmap lookup table extension When reading bitmap file, Git loads each and every bitmap one by one even if all the bitmaps are not required. A "bitmap lookup table" extension to the bitmap format can reduce the overhead of loading bitmaps which stores a list of bitmapped commit id pos (in the midx or pack, along with their offset and xor offset. This way Git can load only the necessary bitmaps without loading the previous bitmaps. Older versions of Git ignore the lookup table extension and don't throw any kind of warning or error while parsing the bitmap file. Add some information for the new "bitmap lookup table" extension in the bitmap-format documentation. Mentored-by: Taylor Blau Co-Mentored-by: Kaartic Sivaraam Co-Authored-by: Taylor Blau Signed-off-by: Abhradeep Chakraborty Reviewed-by: Taylor Blau Signed-off-by: Junio C Hamano --- Documentation/technical/bitmap-format.txt | 39 +++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/Documentation/technical/bitmap-format.txt b/Documentation/technical/bitmap-format.txt index a85f58f515..c2e652b71a 100644 --- a/Documentation/technical/bitmap-format.txt +++ b/Documentation/technical/bitmap-format.txt @@ -72,6 +72,17 @@ MIDXs, both the bit-cache and rev-cache extensions are required. pack/MIDX. The format and meaning of the name-hash is described below. + ** {empty} + BITMAP_OPT_LOOKUP_TABLE (0x10): ::: + If present, the end of the bitmap file contains a table + containing a list of `N` + triplets. The format and meaning of the table is described + below. ++ +NOTE: Unlike the xor_offset used to compress an individual bitmap, +`xor_row` stores an *absolute* index into the lookup table, not a location +relative to the current entry. + 4-byte entry count (network byte order): :: The total count of entries (bitmapped commits) in this bitmap index. @@ -216,3 +227,31 @@ Note that this hashing scheme is tied to the BITMAP_OPT_HASH_CACHE flag. If implementations want to choose a different hashing scheme, they are free to do so, but MUST allocate a new header flag (because comparing hashes made under two different schemes would be pointless). + +Commit lookup table +------------------- + +If the BITMAP_OPT_LOOKUP_TABLE flag is set, the last `N * (4 + 8 + 4)` +bytes (preceding the name-hash cache and trailing hash) of the `.bitmap` +file contains a lookup table specifying the information needed to get +the desired bitmap from the entries without parsing previous unnecessary +bitmaps. + +For a `.bitmap` containing `nr_entries` reachability bitmaps, the table +contains a list of `nr_entries` triplets +(sorted in the ascending order of `commit_pos`). The content of i'th +triplet is - + + * {empty} + commit_pos (4 byte integer, network byte order): :: + It stores the object position of a commit (in the midx or pack + index). + + * {empty} + offset (8 byte integer, network byte order): :: + The offset from which that commit's bitmap can be read. + + * {empty} + xor_row (4 byte integer, network byte order): :: + The position of the triplet whose bitmap is used to compress + this one, or `0xffffffff` if no such bitmap exists. From aa30162559ab6c5be0181853cbc07d777675d82a Mon Sep 17 00:00:00 2001 From: Abhradeep Chakraborty Date: Sun, 14 Aug 2022 16:55:07 +0000 Subject: [PATCH 2/7] bitmap: move `get commit positions` code to `bitmap_writer_finish` The `write_selected_commits_v1` function takes care of writing commit positions along with their corresponding bitmaps in the disk. It is OK because this `search commit position of a given commit` algorithm is needed only once here. But in later changes of the `lookup table extension series`, we need same commit positions which means we have to run the above mentioned algorithm one more time. Move the `search commit position of a given commit` algorithm to `bitmap_writer_finish()` and use the `commit_positions` array to get commit positions of their corresponding bitmaps. Signed-off-by: Abhradeep Chakraborty Reviewed-by: Taylor Blau Signed-off-by: Junio C Hamano --- pack-bitmap-write.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 4fcfaed428..9b1be59f6d 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -650,20 +650,15 @@ static const struct object_id *oid_access(size_t pos, const void *table) static void write_selected_commits_v1(struct hashfile *f, struct pack_idx_entry **index, - uint32_t index_nr) + uint32_t index_nr, + uint32_t *commit_positions) { int i; for (i = 0; i < writer.selected_nr; ++i) { struct bitmapped_commit *stored = &writer.selected[i]; - int commit_pos = - oid_pos(&stored->commit->object.oid, index, index_nr, oid_access); - - if (commit_pos < 0) - BUG("trying to write commit not in index"); - - hashwrite_be32(f, commit_pos); + hashwrite_be32(f, commit_positions[i]); hashwrite_u8(f, stored->xor_offset); hashwrite_u8(f, stored->flags); @@ -697,6 +692,8 @@ void bitmap_writer_finish(struct pack_idx_entry **index, static uint16_t flags = BITMAP_OPT_FULL_DAG; struct strbuf tmp_file = STRBUF_INIT; struct hashfile *f; + uint32_t *commit_positions = NULL; + uint32_t i; struct bitmap_disk_header header; @@ -715,7 +712,20 @@ void bitmap_writer_finish(struct pack_idx_entry **index, dump_bitmap(f, writer.trees); dump_bitmap(f, writer.blobs); dump_bitmap(f, writer.tags); - write_selected_commits_v1(f, index, index_nr); + + ALLOC_ARRAY(commit_positions, writer.selected_nr); + + for (i = 0; i < writer.selected_nr; i++) { + struct bitmapped_commit *stored = &writer.selected[i]; + int commit_pos = oid_pos(&stored->commit->object.oid, index, index_nr, oid_access); + + if (commit_pos < 0) + BUG(_("trying to write commit not in index")); + + commit_positions[i] = commit_pos; + } + + write_selected_commits_v1(f, index, index_nr, commit_positions); if (options & BITMAP_OPT_HASH_CACHE) write_hash_cache(f, index, index_nr); @@ -730,4 +740,5 @@ void bitmap_writer_finish(struct pack_idx_entry **index, die_errno("unable to rename temporary bitmap file to '%s'", filename); strbuf_release(&tmp_file); + free(commit_positions); } From 93eb41e2403788fa9105211956e87b6b2c22c68c Mon Sep 17 00:00:00 2001 From: Abhradeep Chakraborty Date: Sun, 14 Aug 2022 16:55:08 +0000 Subject: [PATCH 3/7] pack-bitmap-write.c: write lookup table extension The bitmap lookup table extension was documented by an earlier change, but Git does not yet know how to write that extension. Teach Git to write bitmap lookup table extension. The table contains the list of `N` ` triplets. These triplets are sorted according to their commit pos (ascending order). The meaning of each data in the i'th triplet is given below: - commit_pos stores commit position (in the pack-index or midx). It is a 4 byte network byte order unsigned integer. - offset is the position (in the bitmap file) from which that commit's bitmap can be read. - xor_row is the position of the triplet in the lookup table whose bitmap is used to compress this bitmap, or `0xffffffff` if no such bitmap exists. Mentored-by: Taylor Blau Co-mentored-by: Kaartic Sivaraam Co-authored-by: Taylor Blau Signed-off-by: Abhradeep Chakraborty Reviewed-by: Taylor Blau Signed-off-by: Junio C Hamano --- pack-bitmap-write.c | 91 ++++++++++++++++++++++++++++++++++++++++++++- pack-bitmap.h | 5 ++- 2 files changed, 92 insertions(+), 4 deletions(-) diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 9b1be59f6d..2cfc92f287 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -651,13 +651,17 @@ static const struct object_id *oid_access(size_t pos, const void *table) static void write_selected_commits_v1(struct hashfile *f, struct pack_idx_entry **index, uint32_t index_nr, - uint32_t *commit_positions) + uint32_t *commit_positions, + off_t *offsets) { int i; for (i = 0; i < writer.selected_nr; ++i) { struct bitmapped_commit *stored = &writer.selected[i]; + if (offsets) + offsets[i] = hashfile_total(f); + hashwrite_be32(f, commit_positions[i]); hashwrite_u8(f, stored->xor_offset); hashwrite_u8(f, stored->flags); @@ -666,6 +670,81 @@ static void write_selected_commits_v1(struct hashfile *f, } } +static int table_cmp(const void *_va, const void *_vb, void *_data) +{ + uint32_t *commit_positions = _data; + uint32_t a = commit_positions[*(uint32_t *)_va]; + uint32_t b = commit_positions[*(uint32_t *)_vb]; + + if (a > b) + return 1; + else if (a < b) + return -1; + + return 0; +} + +static void write_lookup_table(struct hashfile *f, + struct pack_idx_entry **index, + uint32_t index_nr, + uint32_t *commit_positions, + off_t *offsets) +{ + uint32_t i; + uint32_t *table, *table_inv; + + ALLOC_ARRAY(table, writer.selected_nr); + ALLOC_ARRAY(table_inv, writer.selected_nr); + + for (i = 0; i < writer.selected_nr; i++) + table[i] = i; + + /* + * At the end of this sort table[j] = i means that the i'th + * bitmap corresponds to j'th bitmapped commit (among the selected + * commits) in lex order of OIDs. + */ + QSORT_S(table, writer.selected_nr, table_cmp, commit_positions); + + /* table_inv helps us discover that relationship (i'th bitmap + * to j'th commit by j = table_inv[i]) + */ + for (i = 0; i < writer.selected_nr; i++) + table_inv[table[i]] = i; + + trace2_region_enter("pack-bitmap-write", "writing_lookup_table", the_repository); + for (i = 0; i < writer.selected_nr; i++) { + struct bitmapped_commit *selected = &writer.selected[table[i]]; + uint32_t xor_offset = selected->xor_offset; + uint32_t xor_row; + + if (xor_offset) { + /* + * xor_index stores the index (in the bitmap entries) + * of the corresponding xor bitmap. But we need to convert + * this index into lookup table's index. So, table_inv[xor_index] + * gives us the index position w.r.t. the lookup table. + * + * If "k = table[i] - xor_offset" then the xor base is the k'th + * bitmap. `table_inv[k]` gives us the position of that bitmap + * in the lookup table. + */ + uint32_t xor_index = table[i] - xor_offset; + xor_row = table_inv[xor_index]; + } else { + xor_row = 0xffffffff; + } + + hashwrite_be32(f, commit_positions[table[i]]); + hashwrite_be64(f, (uint64_t)offsets[table[i]]); + hashwrite_be32(f, xor_row); + } + trace2_region_leave("pack-bitmap-write", "writing_lookup_table", the_repository); + + free(table); + free(table_inv); +} + static void write_hash_cache(struct hashfile *f, struct pack_idx_entry **index, uint32_t index_nr) @@ -693,6 +772,7 @@ void bitmap_writer_finish(struct pack_idx_entry **index, struct strbuf tmp_file = STRBUF_INIT; struct hashfile *f; uint32_t *commit_positions = NULL; + off_t *offsets = NULL; uint32_t i; struct bitmap_disk_header header; @@ -713,6 +793,9 @@ void bitmap_writer_finish(struct pack_idx_entry **index, dump_bitmap(f, writer.blobs); dump_bitmap(f, writer.tags); + if (options & BITMAP_OPT_LOOKUP_TABLE) + CALLOC_ARRAY(offsets, index_nr); + ALLOC_ARRAY(commit_positions, writer.selected_nr); for (i = 0; i < writer.selected_nr; i++) { @@ -725,7 +808,10 @@ void bitmap_writer_finish(struct pack_idx_entry **index, commit_positions[i] = commit_pos; } - write_selected_commits_v1(f, index, index_nr, commit_positions); + write_selected_commits_v1(f, index, index_nr, commit_positions, offsets); + + if (options & BITMAP_OPT_LOOKUP_TABLE) + write_lookup_table(f, index, index_nr, commit_positions, offsets); if (options & BITMAP_OPT_HASH_CACHE) write_hash_cache(f, index, index_nr); @@ -741,4 +827,5 @@ void bitmap_writer_finish(struct pack_idx_entry **index, strbuf_release(&tmp_file); free(commit_positions); + free(offsets); } diff --git a/pack-bitmap.h b/pack-bitmap.h index f3a57ca065..cb065a263c 100644 --- a/pack-bitmap.h +++ b/pack-bitmap.h @@ -24,8 +24,9 @@ struct bitmap_disk_header { #define NEEDS_BITMAP (1u<<22) enum pack_bitmap_opts { - BITMAP_OPT_FULL_DAG = 1, - BITMAP_OPT_HASH_CACHE = 4, + BITMAP_OPT_FULL_DAG = 0x1, + BITMAP_OPT_HASH_CACHE = 0x4, + BITMAP_OPT_LOOKUP_TABLE = 0x10, }; enum pack_bitmap_flags { From 76f14b777c13ac8d8f6a2e5812945e725bea3d84 Mon Sep 17 00:00:00 2001 From: Abhradeep Chakraborty Date: Sun, 14 Aug 2022 16:55:09 +0000 Subject: [PATCH 4/7] pack-bitmap-write: learn pack.writeBitmapLookupTable and add tests Teach Git to provide a way for users to enable/disable bitmap lookup table extension by providing a config option named 'writeBitmapLookupTable'. Default is false. Also add test to verify writting of lookup table. Mentored-by: Taylor Blau Co-Mentored-by: Kaartic Sivaraam Co-Authored-by: Taylor Blau Signed-off-by: Abhradeep Chakraborty Reviewed-by: Taylor Blau Signed-off-by: Junio C Hamano --- Documentation/config/pack.txt | 7 + builtin/multi-pack-index.c | 7 + builtin/pack-objects.c | 8 + midx.c | 3 + midx.h | 1 + t/t5310-pack-bitmaps.sh | 788 ++++++++++++++++-------------- t/t5311-pack-bitmaps-shallow.sh | 49 +- t/t5326-multi-pack-bitmaps.sh | 507 ++++++++++--------- t/t5327-multi-pack-bitmaps-rev.sh | 24 +- 9 files changed, 772 insertions(+), 622 deletions(-) diff --git a/Documentation/config/pack.txt b/Documentation/config/pack.txt index ad7f73a1ea..b955ca572e 100644 --- a/Documentation/config/pack.txt +++ b/Documentation/config/pack.txt @@ -164,6 +164,13 @@ When writing a multi-pack reachability bitmap, no new namehashes are computed; instead, any namehashes stored in an existing bitmap are permuted into their appropriate location when writing a new bitmap. +pack.writeBitmapLookupTable:: + When true, Git will include a "lookup table" section in the + bitmap index (if one is written). This table is used to defer + loading individual bitmaps as late as possible. This can be + beneficial in repositories that have relatively large bitmap + indexes. Defaults to false. + pack.writeReverseIndex:: When true, git will write a corresponding .rev file (see: link:../technical/pack-format.html[Documentation/technical/pack-format.txt]) diff --git a/builtin/multi-pack-index.c b/builtin/multi-pack-index.c index 8f24d59a75..e7cce1d26e 100644 --- a/builtin/multi-pack-index.c +++ b/builtin/multi-pack-index.c @@ -87,6 +87,13 @@ static int git_multi_pack_index_write_config(const char *var, const char *value, opts.flags &= ~MIDX_WRITE_BITMAP_HASH_CACHE; } + if (!strcmp(var, "pack.writebitmaplookuptable")) { + if (git_config_bool(var, value)) + opts.flags |= MIDX_WRITE_BITMAP_LOOKUP_TABLE; + else + opts.flags &= ~MIDX_WRITE_BITMAP_LOOKUP_TABLE; + } + /* * We should never make a fall-back call to 'git_default_config', since * this was already called in 'cmd_multi_pack_index()'. diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 39e28cfcaf..46e2677496 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -3148,6 +3148,14 @@ static int git_pack_config(const char *k, const char *v, void *cb) else write_bitmap_options &= ~BITMAP_OPT_HASH_CACHE; } + + if (!strcmp(k, "pack.writebitmaplookuptable")) { + if (git_config_bool(k, v)) + write_bitmap_options |= BITMAP_OPT_LOOKUP_TABLE; + else + write_bitmap_options &= ~BITMAP_OPT_LOOKUP_TABLE; + } + if (!strcmp(k, "pack.usebitmaps")) { use_bitmap_index_default = git_config_bool(k, v); return 0; diff --git a/midx.c b/midx.c index 4e956cacb7..3ff6e91e6e 100644 --- a/midx.c +++ b/midx.c @@ -1070,6 +1070,9 @@ static int write_midx_bitmap(const char *midx_name, if (flags & MIDX_WRITE_BITMAP_HASH_CACHE) options |= BITMAP_OPT_HASH_CACHE; + if (flags & MIDX_WRITE_BITMAP_LOOKUP_TABLE) + options |= BITMAP_OPT_LOOKUP_TABLE; + /* * Build the MIDX-order index based on pdata.objects (which is already * in MIDX order; c.f., 'midx_pack_order_cmp()' for the definition of diff --git a/midx.h b/midx.h index 22e8e53288..5578cd7b83 100644 --- a/midx.h +++ b/midx.h @@ -47,6 +47,7 @@ struct multi_pack_index { #define MIDX_WRITE_REV_INDEX (1 << 1) #define MIDX_WRITE_BITMAP (1 << 2) #define MIDX_WRITE_BITMAP_HASH_CACHE (1 << 3) +#define MIDX_WRITE_BITMAP_LOOKUP_TABLE (1 << 4) const unsigned char *get_midx_checksum(struct multi_pack_index *m); void get_midx_filename(struct strbuf *out, const char *object_dir); diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh index f775fc1ce6..c060717282 100755 --- a/t/t5310-pack-bitmaps.sh +++ b/t/t5310-pack-bitmaps.sh @@ -26,22 +26,413 @@ has_any () { grep -Ff "$1" "$2" } -setup_bitmap_history +test_bitmap_cases () { + writeLookupTable=false + for i in "$@" + do + case "$i" in + "pack.writeBitmapLookupTable") writeLookupTable=true;; + esac + done -test_expect_success 'setup writing bitmaps during repack' ' - git config repack.writeBitmaps true -' + test_expect_success 'setup test repository' ' + rm -fr * .git && + git init && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' + ' + setup_bitmap_history -test_expect_success 'full repack creates bitmaps' ' - GIT_TRACE2_EVENT="$(pwd)/trace" \ + test_expect_success 'setup writing bitmaps during repack' ' + git config repack.writeBitmaps true + ' + + test_expect_success 'full repack creates bitmaps' ' + GIT_TRACE2_EVENT="$(pwd)/trace" \ + git repack -ad && + ls .git/objects/pack/ | grep bitmap >output && + test_line_count = 1 output && + grep "\"key\":\"num_selected_commits\",\"value\":\"106\"" trace && + grep "\"key\":\"num_maximal_commits\",\"value\":\"107\"" trace + ' + + basic_bitmap_tests + + test_expect_success 'pack-objects respects --local (non-local loose)' ' + git init --bare alt.git && + echo $(pwd)/alt.git/objects >.git/objects/info/alternates && + echo content1 >file1 && + # non-local loose object which is not present in bitmapped pack + altblob=$(GIT_DIR=alt.git git hash-object -w file1) && + # non-local loose object which is also present in bitmapped pack + git cat-file blob $blob | GIT_DIR=alt.git git hash-object -w --stdin && + git add file1 && + test_tick && + git commit -m commit_file1 && + echo HEAD | git pack-objects --local --stdout --revs >1.pack && + git index-pack 1.pack && + list_packed_objects 1.idx >1.objects && + printf "%s\n" "$altblob" "$blob" >nonlocal-loose && + ! has_any nonlocal-loose 1.objects + ' + + test_expect_success 'pack-objects respects --honor-pack-keep (local non-bitmapped pack)' ' + echo content2 >file2 && + blob2=$(git hash-object -w file2) && + git add file2 && + test_tick && + git commit -m commit_file2 && + printf "%s\n" "$blob2" "$bitmaptip" >keepobjects && + pack2=$(git pack-objects pack2 .git/objects/pack/pack2-$pack2.keep && + rm $(objpath $blob2) && + echo HEAD | git pack-objects --honor-pack-keep --stdout --revs >2a.pack && + git index-pack 2a.pack && + list_packed_objects 2a.idx >2a.objects && + ! has_any keepobjects 2a.objects + ' + + test_expect_success 'pack-objects respects --local (non-local pack)' ' + mv .git/objects/pack/pack2-$pack2.* alt.git/objects/pack/ && + echo HEAD | git pack-objects --local --stdout --revs >2b.pack && + git index-pack 2b.pack && + list_packed_objects 2b.idx >2b.objects && + ! has_any keepobjects 2b.objects + ' + + test_expect_success 'pack-objects respects --honor-pack-keep (local bitmapped pack)' ' + ls .git/objects/pack/ | grep bitmap >output && + test_line_count = 1 output && + packbitmap=$(basename $(cat output) .bitmap) && + list_packed_objects .git/objects/pack/$packbitmap.idx >packbitmap.objects && + test_when_finished "rm -f .git/objects/pack/$packbitmap.keep" && + >.git/objects/pack/$packbitmap.keep && + echo HEAD | git pack-objects --honor-pack-keep --stdout --revs >3a.pack && + git index-pack 3a.pack && + list_packed_objects 3a.idx >3a.objects && + ! has_any packbitmap.objects 3a.objects + ' + + test_expect_success 'pack-objects respects --local (non-local bitmapped pack)' ' + mv .git/objects/pack/$packbitmap.* alt.git/objects/pack/ && + rm -f .git/objects/pack/multi-pack-index && + test_when_finished "mv alt.git/objects/pack/$packbitmap.* .git/objects/pack/" && + echo HEAD | git pack-objects --local --stdout --revs >3b.pack && + git index-pack 3b.pack && + list_packed_objects 3b.idx >3b.objects && + ! has_any packbitmap.objects 3b.objects + ' + + test_expect_success 'pack-objects to file can use bitmap' ' + # make sure we still have 1 bitmap index from previous tests + ls .git/objects/pack/ | grep bitmap >output && + test_line_count = 1 output && + # verify equivalent packs are generated with/without using bitmap index + packasha1=$(git pack-objects --no-use-bitmap-index --all packa packa.objects && + list_packed_objects packb-$packbsha1.idx >packb.objects && + test_cmp packa.objects packb.objects + ' + + test_expect_success 'full repack, reusing previous bitmaps' ' git repack -ad && - ls .git/objects/pack/ | grep bitmap >output && - test_line_count = 1 output && - grep "\"key\":\"num_selected_commits\",\"value\":\"106\"" trace && - grep "\"key\":\"num_maximal_commits\",\"value\":\"107\"" trace -' + ls .git/objects/pack/ | grep bitmap >output && + test_line_count = 1 output + ' -basic_bitmap_tests + test_expect_success 'fetch (full bitmap)' ' + git --git-dir=clone.git fetch origin second:second && + git rev-parse HEAD >expect && + git --git-dir=clone.git rev-parse HEAD >actual && + test_cmp expect actual + ' + + test_expect_success 'create objects for missing-HAVE tests' ' + blob=$(echo "missing have" | git hash-object -w --stdin) && + tree=$(printf "100644 blob $blob\tfile\n" | git mktree) && + parent=$(echo parent | git commit-tree $tree) && + commit=$(echo commit | git commit-tree $tree -p $parent) && + cat >revs <<-EOF + HEAD + ^HEAD^ + ^$commit + EOF + ' + + test_expect_success 'pack-objects respects --incremental' ' + cat >revs2 <<-EOF && + HEAD + $commit + EOF + git pack-objects --incremental --stdout --revs 4.pack && + git index-pack 4.pack && + list_packed_objects 4.idx >4.objects && + test_line_count = 4 4.objects && + git rev-list --objects $commit >revlist && + cut -d" " -f1 revlist |sort >objects && + test_cmp 4.objects objects + ' + + test_expect_success 'pack with missing blob' ' + rm $(objpath $blob) && + git pack-objects --stdout --revs /dev/null + ' + + test_expect_success 'pack with missing tree' ' + rm $(objpath $tree) && + git pack-objects --stdout --revs /dev/null + ' + + test_expect_success 'pack with missing parent' ' + rm $(objpath $parent) && + git pack-objects --stdout --revs /dev/null + ' + + test_expect_success JGIT,SHA1 'we can read jgit bitmaps' ' + git clone --bare . compat-jgit.git && + ( + cd compat-jgit.git && + rm -f objects/pack/*.bitmap && + jgit gc && + git rev-list --test-bitmap HEAD + ) + ' + + test_expect_success JGIT,SHA1 'jgit can read our bitmaps' ' + git clone --bare . compat-us.git && + ( + cd compat-us.git && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + git repack -adb && + # jgit gc will barf if it does not like our bitmaps + jgit gc + ) + ' + + test_expect_success 'splitting packs does not generate bogus bitmaps' ' + test-tool genrandom foo $((1024 * 1024)) >rand && + git add rand && + git commit -m "commit with big file" && + git -c pack.packSizeLimit=500k repack -adb && + git init --bare no-bitmaps.git && + git -C no-bitmaps.git fetch .. HEAD + ' + + test_expect_success 'set up reusable pack' ' + rm -f .git/objects/pack/*.keep && + git repack -adb && + reusable_pack () { + git for-each-ref --format="%(objectname)" | + git pack-objects --delta-base-offset --revs --stdout "$@" + } + ' + + test_expect_success 'pack reuse respects --honor-pack-keep' ' + test_when_finished "rm -f .git/objects/pack/*.keep" && + for i in .git/objects/pack/*.pack + do + >${i%.pack}.keep || return 1 + done && + reusable_pack --honor-pack-keep >empty.pack && + git index-pack empty.pack && + git show-index actual && + test_must_be_empty actual + ' + + test_expect_success 'pack reuse respects --local' ' + mv .git/objects/pack/* alt.git/objects/pack/ && + test_when_finished "mv alt.git/objects/pack/* .git/objects/pack/" && + reusable_pack --local >empty.pack && + git index-pack empty.pack && + git show-index actual && + test_must_be_empty actual + ' + + test_expect_success 'pack reuse respects --incremental' ' + reusable_pack --incremental >empty.pack && + git index-pack empty.pack && + git show-index actual && + test_must_be_empty actual + ' + + test_expect_success 'truncated bitmap fails gracefully (ewah)' ' + test_config pack.writebitmaphashcache false && + git repack -ad && + git rev-list --use-bitmap-index --count --all >expect && + bitmap=$(ls .git/objects/pack/*.bitmap) && + test_when_finished "rm -f $bitmap" && + test_copy_bytes 256 <$bitmap >$bitmap.tmp && + mv -f $bitmap.tmp $bitmap && + git rev-list --use-bitmap-index --count --all >actual 2>stderr && + test_cmp expect actual && + test_i18ngrep corrupt.ewah.bitmap stderr + ' + + test_expect_success 'truncated bitmap fails gracefully (cache)' ' + git repack -ad && + git rev-list --use-bitmap-index --count --all >expect && + bitmap=$(ls .git/objects/pack/*.bitmap) && + test_when_finished "rm -f $bitmap" && + test_copy_bytes 512 <$bitmap >$bitmap.tmp && + mv -f $bitmap.tmp $bitmap && + git rev-list --use-bitmap-index --count --all >actual 2>stderr && + test_cmp expect actual && + test_i18ngrep corrupted.bitmap.index stderr + ' + + # Create a state of history with these properties: + # + # - refs that allow a client to fetch some new history, while sharing some old + # history with the server; we use branches delta-reuse-old and + # delta-reuse-new here + # + # - the new history contains an object that is stored on the server as a delta + # against a base that is in the old history + # + # - the base object is not immediately reachable from the tip of the old + # history; finding it would involve digging down through history we know the + # other side has + # + # This should result in a state where fetching from old->new would not + # traditionally reuse the on-disk delta (because we'd have to dig to realize + # that the client has it), but we will do so if bitmaps can tell us cheaply + # that the other side has it. + test_expect_success 'set up thin delta-reuse parent' ' + # This first commit contains the buried base object. + test-tool genrandom delta 16384 >file && + git add file && + git commit -m "delta base" && + base=$(git rev-parse --verify HEAD:file) && + + # These intermediate commits bury the base back in history. + # This becomes the "old" state. + for i in 1 2 3 4 5 + do + echo $i >file && + git commit -am "intermediate $i" || return 1 + done && + git branch delta-reuse-old && + + # And now our new history has a delta against the buried base. Note + # that this must be smaller than the original file, since pack-objects + # prefers to create deltas from smaller objects to larger. + test-tool genrandom delta 16300 >file && + git commit -am "delta result" && + delta=$(git rev-parse --verify HEAD:file) && + git branch delta-reuse-new && + + # Repack with bitmaps and double check that we have the expected delta + # relationship. + git repack -adb && + have_delta $delta $base + ' + + # Now we can sanity-check the non-bitmap behavior (that the server is not able + # to reuse the delta). This isn't strictly something we care about, so this + # test could be scrapped in the future. But it makes sure that the next test is + # actually triggering the feature we want. + # + # Note that our tools for working with on-the-wire "thin" packs are limited. So + # we actually perform the fetch, retain the resulting pack, and inspect the + # result. + test_expect_success 'fetch without bitmaps ignores delta against old base' ' + test_config pack.usebitmaps false && + test_when_finished "rm -rf client.git" && + git init --bare client.git && + ( + cd client.git && + git config transfer.unpackLimit 1 && + git fetch .. delta-reuse-old:delta-reuse-old && + git fetch .. delta-reuse-new:delta-reuse-new && + have_delta $delta $ZERO_OID + ) + ' + + # And do the same for the bitmap case, where we do expect to find the delta. + test_expect_success 'fetch with bitmaps can reuse old base' ' + test_config pack.usebitmaps true && + test_when_finished "rm -rf client.git" && + git init --bare client.git && + ( + cd client.git && + git config transfer.unpackLimit 1 && + git fetch .. delta-reuse-old:delta-reuse-old && + git fetch .. delta-reuse-new:delta-reuse-new && + have_delta $delta $base + ) + ' + + test_expect_success 'pack.preferBitmapTips' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + # create enough commits that not all are receive bitmap + # coverage even if they are all at the tip of some reference. + test_commit_bulk --message="%s" 103 && + + git rev-list HEAD >commits.raw && + sort commits && + + git log --format="create refs/tags/%s %H" HEAD >refs && + git update-ref --stdin bitmaps && + + # remember which commits did not receive bitmaps + comm -13 bitmaps commits >before && + test_file_not_empty before && + + # mark the commits which did not receive bitmaps as preferred, + # and generate the bitmap again + perl -pe "s{^}{create refs/tags/include/$. }" bitmaps && + comm -13 bitmaps commits >after && + + ! test_cmp before after + ) + ' + + test_expect_success 'complains about multiple pack bitmaps' ' + rm -fr repo && + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + test_commit base && + + git repack -adb && + bitmap="$(ls .git/objects/pack/pack-*.bitmap)" && + mv "$bitmap" "$bitmap.bak" && + + test_commit other && + git repack -ab && + + mv "$bitmap.bak" "$bitmap" && + + find .git/objects/pack -type f -name "*.pack" >packs && + find .git/objects/pack -type f -name "*.bitmap" >bitmaps && + test_line_count = 2 packs && + test_line_count = 2 bitmaps && + + git rev-list --use-bitmap-index HEAD 2>err && + grep "ignoring extra bitmap file" err + ) + ' +} + +test_bitmap_cases test_expect_success 'incremental repack fails when bitmaps are requested' ' test_commit more-1 && @@ -54,375 +445,12 @@ test_expect_success 'incremental repack can disable bitmaps' ' git repack -d --no-write-bitmap-index ' -test_expect_success 'pack-objects respects --local (non-local loose)' ' - git init --bare alt.git && - echo $(pwd)/alt.git/objects >.git/objects/info/alternates && - echo content1 >file1 && - # non-local loose object which is not present in bitmapped pack - altblob=$(GIT_DIR=alt.git git hash-object -w file1) && - # non-local loose object which is also present in bitmapped pack - git cat-file blob $blob | GIT_DIR=alt.git git hash-object -w --stdin && - git add file1 && - test_tick && - git commit -m commit_file1 && - echo HEAD | git pack-objects --local --stdout --revs >1.pack && - git index-pack 1.pack && - list_packed_objects 1.idx >1.objects && - printf "%s\n" "$altblob" "$blob" >nonlocal-loose && - ! has_any nonlocal-loose 1.objects -' +test_bitmap_cases "pack.writeBitmapLookupTable" -test_expect_success 'pack-objects respects --honor-pack-keep (local non-bitmapped pack)' ' - echo content2 >file2 && - blob2=$(git hash-object -w file2) && - git add file2 && - test_tick && - git commit -m commit_file2 && - printf "%s\n" "$blob2" "$bitmaptip" >keepobjects && - pack2=$(git pack-objects pack2 .git/objects/pack/pack2-$pack2.keep && - rm $(objpath $blob2) && - echo HEAD | git pack-objects --honor-pack-keep --stdout --revs >2a.pack && - git index-pack 2a.pack && - list_packed_objects 2a.idx >2a.objects && - ! has_any keepobjects 2a.objects -' - -test_expect_success 'pack-objects respects --local (non-local pack)' ' - mv .git/objects/pack/pack2-$pack2.* alt.git/objects/pack/ && - echo HEAD | git pack-objects --local --stdout --revs >2b.pack && - git index-pack 2b.pack && - list_packed_objects 2b.idx >2b.objects && - ! has_any keepobjects 2b.objects -' - -test_expect_success 'pack-objects respects --honor-pack-keep (local bitmapped pack)' ' - ls .git/objects/pack/ | grep bitmap >output && - test_line_count = 1 output && - packbitmap=$(basename $(cat output) .bitmap) && - list_packed_objects .git/objects/pack/$packbitmap.idx >packbitmap.objects && - test_when_finished "rm -f .git/objects/pack/$packbitmap.keep" && - >.git/objects/pack/$packbitmap.keep && - echo HEAD | git pack-objects --honor-pack-keep --stdout --revs >3a.pack && - git index-pack 3a.pack && - list_packed_objects 3a.idx >3a.objects && - ! has_any packbitmap.objects 3a.objects -' - -test_expect_success 'pack-objects respects --local (non-local bitmapped pack)' ' - mv .git/objects/pack/$packbitmap.* alt.git/objects/pack/ && - rm -f .git/objects/pack/multi-pack-index && - test_when_finished "mv alt.git/objects/pack/$packbitmap.* .git/objects/pack/" && - echo HEAD | git pack-objects --local --stdout --revs >3b.pack && - git index-pack 3b.pack && - list_packed_objects 3b.idx >3b.objects && - ! has_any packbitmap.objects 3b.objects -' - -test_expect_success 'pack-objects to file can use bitmap' ' - # make sure we still have 1 bitmap index from previous tests - ls .git/objects/pack/ | grep bitmap >output && - test_line_count = 1 output && - # verify equivalent packs are generated with/without using bitmap index - packasha1=$(git pack-objects --no-use-bitmap-index --all packa packa.objects && - list_packed_objects packb-$packbsha1.idx >packb.objects && - test_cmp packa.objects packb.objects -' - -test_expect_success 'full repack, reusing previous bitmaps' ' - git repack -ad && - ls .git/objects/pack/ | grep bitmap >output && - test_line_count = 1 output -' - -test_expect_success 'fetch (full bitmap)' ' - git --git-dir=clone.git fetch origin second:second && - git rev-parse HEAD >expect && - git --git-dir=clone.git rev-parse HEAD >actual && - test_cmp expect actual -' - -test_expect_success 'create objects for missing-HAVE tests' ' - blob=$(echo "missing have" | git hash-object -w --stdin) && - tree=$(printf "100644 blob $blob\tfile\n" | git mktree) && - parent=$(echo parent | git commit-tree $tree) && - commit=$(echo commit | git commit-tree $tree -p $parent) && - cat >revs <<-EOF - HEAD - ^HEAD^ - ^$commit - EOF -' - -test_expect_success 'pack-objects respects --incremental' ' - cat >revs2 <<-EOF && - HEAD - $commit - EOF - git pack-objects --incremental --stdout --revs 4.pack && - git index-pack 4.pack && - list_packed_objects 4.idx >4.objects && - test_line_count = 4 4.objects && - git rev-list --objects $commit >revlist && - cut -d" " -f1 revlist |sort >objects && - test_cmp 4.objects objects -' - -test_expect_success 'pack with missing blob' ' - rm $(objpath $blob) && - git pack-objects --stdout --revs /dev/null -' - -test_expect_success 'pack with missing tree' ' - rm $(objpath $tree) && - git pack-objects --stdout --revs /dev/null -' - -test_expect_success 'pack with missing parent' ' - rm $(objpath $parent) && - git pack-objects --stdout --revs /dev/null -' - -test_expect_success JGIT,SHA1 'we can read jgit bitmaps' ' - git clone --bare . compat-jgit.git && - ( - cd compat-jgit.git && - rm -f objects/pack/*.bitmap && - jgit gc && - git rev-list --test-bitmap HEAD - ) -' - -test_expect_success JGIT,SHA1 'jgit can read our bitmaps' ' - git clone --bare . compat-us.git && - ( - cd compat-us.git && - git repack -adb && - # jgit gc will barf if it does not like our bitmaps - jgit gc - ) -' - -test_expect_success 'splitting packs does not generate bogus bitmaps' ' - test-tool genrandom foo $((1024 * 1024)) >rand && - git add rand && - git commit -m "commit with big file" && - git -c pack.packSizeLimit=500k repack -adb && - git init --bare no-bitmaps.git && - git -C no-bitmaps.git fetch .. HEAD -' - -test_expect_success 'set up reusable pack' ' - rm -f .git/objects/pack/*.keep && - git repack -adb && - reusable_pack () { - git for-each-ref --format="%(objectname)" | - git pack-objects --delta-base-offset --revs --stdout "$@" - } -' - -test_expect_success 'pack reuse respects --honor-pack-keep' ' - test_when_finished "rm -f .git/objects/pack/*.keep" && - for i in .git/objects/pack/*.pack - do - >${i%.pack}.keep || return 1 - done && - reusable_pack --honor-pack-keep >empty.pack && - git index-pack empty.pack && - git show-index actual && - test_must_be_empty actual -' - -test_expect_success 'pack reuse respects --local' ' - mv .git/objects/pack/* alt.git/objects/pack/ && - test_when_finished "mv alt.git/objects/pack/* .git/objects/pack/" && - reusable_pack --local >empty.pack && - git index-pack empty.pack && - git show-index actual && - test_must_be_empty actual -' - -test_expect_success 'pack reuse respects --incremental' ' - reusable_pack --incremental >empty.pack && - git index-pack empty.pack && - git show-index actual && - test_must_be_empty actual -' - -test_expect_success 'truncated bitmap fails gracefully (ewah)' ' - test_config pack.writebitmaphashcache false && - git repack -ad && - git rev-list --use-bitmap-index --count --all >expect && - bitmap=$(ls .git/objects/pack/*.bitmap) && - test_when_finished "rm -f $bitmap" && - test_copy_bytes 256 <$bitmap >$bitmap.tmp && - mv -f $bitmap.tmp $bitmap && - git rev-list --use-bitmap-index --count --all >actual 2>stderr && - test_cmp expect actual && - test_i18ngrep corrupt.ewah.bitmap stderr -' - -test_expect_success 'truncated bitmap fails gracefully (cache)' ' - git repack -ad && - git rev-list --use-bitmap-index --count --all >expect && - bitmap=$(ls .git/objects/pack/*.bitmap) && - test_when_finished "rm -f $bitmap" && - test_copy_bytes 512 <$bitmap >$bitmap.tmp && - mv -f $bitmap.tmp $bitmap && - git rev-list --use-bitmap-index --count --all >actual 2>stderr && - test_cmp expect actual && - test_i18ngrep corrupted.bitmap.index stderr -' - -# Create a state of history with these properties: -# -# - refs that allow a client to fetch some new history, while sharing some old -# history with the server; we use branches delta-reuse-old and -# delta-reuse-new here -# -# - the new history contains an object that is stored on the server as a delta -# against a base that is in the old history -# -# - the base object is not immediately reachable from the tip of the old -# history; finding it would involve digging down through history we know the -# other side has -# -# This should result in a state where fetching from old->new would not -# traditionally reuse the on-disk delta (because we'd have to dig to realize -# that the client has it), but we will do so if bitmaps can tell us cheaply -# that the other side has it. -test_expect_success 'set up thin delta-reuse parent' ' - # This first commit contains the buried base object. - test-tool genrandom delta 16384 >file && - git add file && - git commit -m "delta base" && - base=$(git rev-parse --verify HEAD:file) && - - # These intermediate commits bury the base back in history. - # This becomes the "old" state. - for i in 1 2 3 4 5 - do - echo $i >file && - git commit -am "intermediate $i" || return 1 - done && - git branch delta-reuse-old && - - # And now our new history has a delta against the buried base. Note - # that this must be smaller than the original file, since pack-objects - # prefers to create deltas from smaller objects to larger. - test-tool genrandom delta 16300 >file && - git commit -am "delta result" && - delta=$(git rev-parse --verify HEAD:file) && - git branch delta-reuse-new && - - # Repack with bitmaps and double check that we have the expected delta - # relationship. - git repack -adb && - have_delta $delta $base -' - -# Now we can sanity-check the non-bitmap behavior (that the server is not able -# to reuse the delta). This isn't strictly something we care about, so this -# test could be scrapped in the future. But it makes sure that the next test is -# actually triggering the feature we want. -# -# Note that our tools for working with on-the-wire "thin" packs are limited. So -# we actually perform the fetch, retain the resulting pack, and inspect the -# result. -test_expect_success 'fetch without bitmaps ignores delta against old base' ' - test_config pack.usebitmaps false && - test_when_finished "rm -rf client.git" && - git init --bare client.git && - ( - cd client.git && - git config transfer.unpackLimit 1 && - git fetch .. delta-reuse-old:delta-reuse-old && - git fetch .. delta-reuse-new:delta-reuse-new && - have_delta $delta $ZERO_OID - ) -' - -# And do the same for the bitmap case, where we do expect to find the delta. -test_expect_success 'fetch with bitmaps can reuse old base' ' - test_config pack.usebitmaps true && - test_when_finished "rm -rf client.git" && - git init --bare client.git && - ( - cd client.git && - git config transfer.unpackLimit 1 && - git fetch .. delta-reuse-old:delta-reuse-old && - git fetch .. delta-reuse-new:delta-reuse-new && - have_delta $delta $base - ) -' - -test_expect_success 'pack.preferBitmapTips' ' - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - # create enough commits that not all are receive bitmap - # coverage even if they are all at the tip of some reference. - test_commit_bulk --message="%s" 103 && - - git rev-list HEAD >commits.raw && - sort commits && - - git log --format="create refs/tags/%s %H" HEAD >refs && - git update-ref --stdin bitmaps && - - # remember which commits did not receive bitmaps - comm -13 bitmaps commits >before && - test_file_not_empty before && - - # mark the commits which did not receive bitmaps as preferred, - # and generate the bitmap again - perl -pe "s{^}{create refs/tags/include/$. }" bitmaps && - comm -13 bitmaps commits >after && - - ! test_cmp before after - ) -' - -test_expect_success 'complains about multiple pack bitmaps' ' - rm -fr repo && - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - test_commit base && - - git repack -adb && - bitmap="$(ls .git/objects/pack/pack-*.bitmap)" && - mv "$bitmap" "$bitmap.bak" && - - test_commit other && - git repack -ab && - - mv "$bitmap.bak" "$bitmap" && - - find .git/objects/pack -type f -name "*.pack" >packs && - find .git/objects/pack -type f -name "*.bitmap" >bitmaps && - test_line_count = 2 packs && - test_line_count = 2 bitmaps && - - git rev-list --use-bitmap-index HEAD 2>err && - grep "ignoring extra bitmap file" err - ) +test_expect_success 'verify writing bitmap lookup table when enabled' ' + GIT_TRACE2_EVENT="$(pwd)/trace2" \ + git repack -ad && + grep "\"label\":\"writing_lookup_table\"" trace2 ' test_done diff --git a/t/t5311-pack-bitmaps-shallow.sh b/t/t5311-pack-bitmaps-shallow.sh index 872a95df33..9dae60f73e 100755 --- a/t/t5311-pack-bitmaps-shallow.sh +++ b/t/t5311-pack-bitmaps-shallow.sh @@ -17,23 +17,40 @@ test_description='check bitmap operation with shallow repositories' # the tree for A. But in a shallow one, we've grafted away # A, and fetching A to B requires that the other side send # us the tree for file=1. -test_expect_success 'setup shallow repo' ' - echo 1 >file && - git add file && - git commit -m orig && - echo 2 >file && - git commit -a -m update && - git clone --no-local --bare --depth=1 . shallow.git && - echo 1 >file && - git commit -a -m repeat -' +test_shallow_bitmaps () { + writeLookupTable=false -test_expect_success 'turn on bitmaps in the parent' ' - git repack -adb -' + for i in "$@" + do + case $i in + "pack.writeBitmapLookupTable") writeLookupTable=true;; + esac + done -test_expect_success 'shallow fetch from bitmapped repo' ' - (cd shallow.git && git fetch) -' + test_expect_success 'setup shallow repo' ' + rm -rf * .git && + git init && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + echo 1 >file && + git add file && + git commit -m orig && + echo 2 >file && + git commit -a -m update && + git clone --no-local --bare --depth=1 . shallow.git && + echo 1 >file && + git commit -a -m repeat + ' + + test_expect_success 'turn on bitmaps in the parent' ' + git repack -adb + ' + + test_expect_success 'shallow fetch from bitmapped repo' ' + (cd shallow.git && git fetch) + ' +} + +test_shallow_bitmaps +test_shallow_bitmaps "pack.writeBitmapLookupTable" test_done diff --git a/t/t5326-multi-pack-bitmaps.sh b/t/t5326-multi-pack-bitmaps.sh index 4fe57414c1..3b206adcee 100755 --- a/t/t5326-multi-pack-bitmaps.sh +++ b/t/t5326-multi-pack-bitmaps.sh @@ -15,17 +15,24 @@ GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 sane_unset GIT_TEST_MIDX_WRITE_REV sane_unset GIT_TEST_MIDX_READ_RIDX -midx_bitmap_core - bitmap_reuse_tests() { from=$1 to=$2 + writeLookupTable=false + + for i in $3-${$#} + do + case $i in + "pack.writeBitmapLookupTable") writeLookupTable=true;; + esac + done test_expect_success "setup pack reuse tests ($from -> $to)" ' rm -fr repo && git init repo && ( cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && test_commit_bulk 16 && git tag old-tip && @@ -43,6 +50,7 @@ bitmap_reuse_tests() { test_expect_success "build bitmap from existing ($from -> $to)" ' ( cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && test_commit_bulk --id=further 16 && git tag new-tip && @@ -59,6 +67,7 @@ bitmap_reuse_tests() { test_expect_success "verify resulting bitmaps ($from -> $to)" ' ( cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && git for-each-ref && git rev-list --test-bitmap refs/tags/old-tip && git rev-list --test-bitmap refs/tags/new-tip @@ -66,244 +75,294 @@ bitmap_reuse_tests() { ' } -bitmap_reuse_tests 'pack' 'MIDX' -bitmap_reuse_tests 'MIDX' 'pack' -bitmap_reuse_tests 'MIDX' 'MIDX' +test_midx_bitmap_cases () { + writeLookupTable=false + writeBitmapLookupTable= -test_expect_success 'missing object closure fails gracefully' ' - rm -fr repo && - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && + for i in "$@" + do + case $i in + "pack.writeBitmapLookupTable") + writeLookupTable=true + writeBitmapLookupTable="$i" + ;; + esac + done - test_commit loose && - test_commit packed && + test_expect_success 'setup test_repository' ' + rm -rf * .git && + git init && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' + ' - # Do not pass "--revs"; we want a pack without the "loose" - # commit. - git pack-objects $objdir/pack/pack <<-EOF && - $(git rev-parse packed) - EOF + midx_bitmap_core - test_must_fail git multi-pack-index write --bitmap 2>err && - grep "doesn.t have full closure" err && - test_path_is_missing $midx - ) -' - -midx_bitmap_partial_tests - -test_expect_success 'removing a MIDX clears stale bitmaps' ' - rm -fr repo && - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - test_commit base && - git repack && - git multi-pack-index write --bitmap && - - # Write a MIDX and bitmap; remove the MIDX but leave the bitmap. - stale_bitmap=$midx-$(midx_checksum $objdir).bitmap && - rm $midx && - - # Then write a new MIDX. - test_commit new && - git repack && - git multi-pack-index write --bitmap && - - test_path_is_file $midx && - test_path_is_file $midx-$(midx_checksum $objdir).bitmap && - test_path_is_missing $stale_bitmap - ) -' - -test_expect_success 'pack.preferBitmapTips' ' - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - test_commit_bulk --message="%s" 103 && - - git log --format="%H" >commits.raw && - sort commits && - - git log --format="create refs/tags/%s %H" HEAD >refs && - git update-ref --stdin bitmaps && - comm -13 bitmaps commits >before && - test_line_count = 1 before && - - perl -ne "printf(\"create refs/tags/include/%d \", $.); print" \ - bitmaps && - comm -13 bitmaps commits >after && - - ! test_cmp before after - ) -' - -test_expect_success 'writing a bitmap with --refs-snapshot' ' - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - test_commit one && - test_commit two && - - git rev-parse one >snapshot && - - git repack -ad && - - # First, write a MIDX which see both refs/tags/one and - # refs/tags/two (causing both of those commits to receive - # bitmaps). - git multi-pack-index write --bitmap && - - test_path_is_file $midx && - test_path_is_file $midx-$(midx_checksum $objdir).bitmap && - - test-tool bitmap list-commits | sort >bitmaps && - grep "$(git rev-parse one)" bitmaps && - grep "$(git rev-parse two)" bitmaps && - - rm -fr $midx-$(midx_checksum $objdir).bitmap && - rm -fr $midx && - - # Then again, but with a refs snapshot which only sees - # refs/tags/one. - git multi-pack-index write --bitmap --refs-snapshot=snapshot && - - test_path_is_file $midx && - test_path_is_file $midx-$(midx_checksum $objdir).bitmap && - - test-tool bitmap list-commits | sort >bitmaps && - grep "$(git rev-parse one)" bitmaps && - ! grep "$(git rev-parse two)" bitmaps - ) -' - -test_expect_success 'write a bitmap with --refs-snapshot (preferred tips)' ' - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - test_commit_bulk --message="%s" 103 && - - git log --format="%H" >commits.raw && - sort commits && - - git log --format="create refs/tags/%s %H" HEAD >refs && - git update-ref --stdin bitmaps && - comm -13 bitmaps commits >before && - test_line_count = 1 before && + bitmap_reuse_tests 'pack' 'MIDX' "$writeBitmapLookupTable" + bitmap_reuse_tests 'MIDX' 'pack' "$writeBitmapLookupTable" + bitmap_reuse_tests 'MIDX' 'MIDX' "$writeBitmapLookupTable" + test_expect_success 'missing object closure fails gracefully' ' + rm -fr repo && + git init repo && + test_when_finished "rm -fr repo" && ( - grep -vf before commits.raw && - # mark missing commits as preferred - sed "s/^/+/" before - ) >snapshot && + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && - rm -fr $midx-$(midx_checksum $objdir).bitmap && - rm -fr $midx && + test_commit loose && + test_commit packed && - git multi-pack-index write --bitmap --refs-snapshot=snapshot && - test-tool bitmap list-commits | sort >bitmaps && - comm -13 bitmaps commits >after && + # Do not pass "--revs"; we want a pack without the "loose" + # commit. + git pack-objects $objdir/pack/pack <<-EOF && + $(git rev-parse packed) + EOF - ! test_cmp before after - ) -' + test_must_fail git multi-pack-index write --bitmap 2>err && + grep "doesn.t have full closure" err && + test_path_is_missing $midx + ) + ' -test_expect_success 'hash-cache values are propagated from pack bitmaps' ' + midx_bitmap_partial_tests + + test_expect_success 'removing a MIDX clears stale bitmaps' ' + rm -fr repo && + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + test_commit base && + git repack && + git multi-pack-index write --bitmap && + + # Write a MIDX and bitmap; remove the MIDX but leave the bitmap. + stale_bitmap=$midx-$(midx_checksum $objdir).bitmap && + rm $midx && + + # Then write a new MIDX. + test_commit new && + git repack && + git multi-pack-index write --bitmap && + + test_path_is_file $midx && + test_path_is_file $midx-$(midx_checksum $objdir).bitmap && + test_path_is_missing $stale_bitmap + ) + ' + + test_expect_success 'pack.preferBitmapTips' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + test_commit_bulk --message="%s" 103 && + + git log --format="%H" >commits.raw && + sort commits && + + git log --format="create refs/tags/%s %H" HEAD >refs && + git update-ref --stdin bitmaps && + comm -13 bitmaps commits >before && + test_line_count = 1 before && + + perl -ne "printf(\"create refs/tags/include/%d \", $.); print" \ + bitmaps && + comm -13 bitmaps commits >after && + + ! test_cmp before after + ) + ' + + test_expect_success 'writing a bitmap with --refs-snapshot' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + test_commit one && + test_commit two && + + git rev-parse one >snapshot && + + git repack -ad && + + # First, write a MIDX which see both refs/tags/one and + # refs/tags/two (causing both of those commits to receive + # bitmaps). + git multi-pack-index write --bitmap && + + test_path_is_file $midx && + test_path_is_file $midx-$(midx_checksum $objdir).bitmap && + + test-tool bitmap list-commits | sort >bitmaps && + grep "$(git rev-parse one)" bitmaps && + grep "$(git rev-parse two)" bitmaps && + + rm -fr $midx-$(midx_checksum $objdir).bitmap && + rm -fr $midx && + + # Then again, but with a refs snapshot which only sees + # refs/tags/one. + git multi-pack-index write --bitmap --refs-snapshot=snapshot && + + test_path_is_file $midx && + test_path_is_file $midx-$(midx_checksum $objdir).bitmap && + + test-tool bitmap list-commits | sort >bitmaps && + grep "$(git rev-parse one)" bitmaps && + ! grep "$(git rev-parse two)" bitmaps + ) + ' + + test_expect_success 'write a bitmap with --refs-snapshot (preferred tips)' ' + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + test_commit_bulk --message="%s" 103 && + + git log --format="%H" >commits.raw && + sort commits && + + git log --format="create refs/tags/%s %H" HEAD >refs && + git update-ref --stdin bitmaps && + comm -13 bitmaps commits >before && + test_line_count = 1 before && + + ( + grep -vf before commits.raw && + # mark missing commits as preferred + sed "s/^/+/" before + ) >snapshot && + + rm -fr $midx-$(midx_checksum $objdir).bitmap && + rm -fr $midx && + + git multi-pack-index write --bitmap --refs-snapshot=snapshot && + test-tool bitmap list-commits | sort >bitmaps && + comm -13 bitmaps commits >after && + + ! test_cmp before after + ) + ' + + test_expect_success 'hash-cache values are propagated from pack bitmaps' ' + rm -fr repo && + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + test_commit base && + test_commit base2 && + git repack -adb && + + test-tool bitmap dump-hashes >pack.raw && + test_file_not_empty pack.raw && + sort pack.raw >pack.hashes && + + test_commit new && + git repack && + git multi-pack-index write --bitmap && + + test-tool bitmap dump-hashes >midx.raw && + sort midx.raw >midx.hashes && + + # ensure that every namehash in the pack bitmap can be found in + # the midx bitmap (i.e., that there are no oid-namehash pairs + # unique to the pack bitmap). + comm -23 pack.hashes midx.hashes >dropped.hashes && + test_must_be_empty dropped.hashes + ) + ' + + test_expect_success 'no .bitmap is written without any objects' ' + rm -fr repo && + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + empty="$(git pack-objects $objdir/pack/pack packs <<-EOF && + pack-$empty.idx + EOF + + git multi-pack-index write --bitmap --stdin-packs \ + err && + + grep "bitmap without any objects" err && + + test_path_is_file $midx && + test_path_is_missing $midx-$(midx_checksum $objdir).bitmap + ) + ' + + test_expect_success 'graceful fallback when missing reverse index' ' + rm -fr repo && + git init repo && + test_when_finished "rm -fr repo" && + ( + cd repo && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && + + test_commit base && + + # write a pack and MIDX bitmap containing base + git repack -adb && + git multi-pack-index write --bitmap && + + GIT_TEST_MIDX_READ_RIDX=0 \ + git rev-list --use-bitmap-index HEAD 2>err && + ! grep "ignoring extra bitmap file" err + ) + ' +} + +test_midx_bitmap_cases + +test_midx_bitmap_cases "pack.writeBitmapLookupTable" + +test_expect_success 'multi-pack-index write writes lookup table if enabled' ' rm -fr repo && git init repo && test_when_finished "rm -fr repo" && ( cd repo && - test_commit base && - test_commit base2 && - git repack -adb && - - test-tool bitmap dump-hashes >pack.raw && - test_file_not_empty pack.raw && - sort pack.raw >pack.hashes && - - test_commit new && - git repack && - git multi-pack-index write --bitmap && - - test-tool bitmap dump-hashes >midx.raw && - sort midx.raw >midx.hashes && - - # ensure that every namehash in the pack bitmap can be found in - # the midx bitmap (i.e., that there are no oid-namehash pairs - # unique to the pack bitmap). - comm -23 pack.hashes midx.hashes >dropped.hashes && - test_must_be_empty dropped.hashes - ) -' - -test_expect_success 'no .bitmap is written without any objects' ' - rm -fr repo && - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - empty="$(git pack-objects $objdir/pack/pack packs <<-EOF && - pack-$empty.idx - EOF - - git multi-pack-index write --bitmap --stdin-packs \ - err && - - grep "bitmap without any objects" err && - - test_path_is_file $midx && - test_path_is_missing $midx-$(midx_checksum $objdir).bitmap - ) -' - -test_expect_success 'graceful fallback when missing reverse index' ' - rm -fr repo && - git init repo && - test_when_finished "rm -fr repo" && - ( - cd repo && - - test_commit base && - - # write a pack and MIDX bitmap containing base - git repack -adb && - git multi-pack-index write --bitmap && - - GIT_TEST_MIDX_READ_RIDX=0 \ - git rev-list --use-bitmap-index HEAD 2>err && - ! grep "ignoring extra bitmap file" err + git config pack.writeBitmapLookupTable true && + git repack -ad && + GIT_TRACE2_EVENT="$(pwd)/trace" \ + git multi-pack-index write --bitmap && + grep "\"label\":\"writing_lookup_table\"" trace ) ' diff --git a/t/t5327-multi-pack-bitmaps-rev.sh b/t/t5327-multi-pack-bitmaps-rev.sh index d30ba632c8..e65e311cd7 100755 --- a/t/t5327-multi-pack-bitmaps-rev.sh +++ b/t/t5327-multi-pack-bitmaps-rev.sh @@ -17,7 +17,27 @@ GIT_TEST_MIDX_READ_RIDX=0 export GIT_TEST_MIDX_WRITE_REV export GIT_TEST_MIDX_READ_RIDX -midx_bitmap_core rev -midx_bitmap_partial_tests rev +test_midx_bitmap_rev () { + writeLookupTable=false + + for i in "$@" + do + case $i in + "pack.writeBitmapLookupTable") writeLookupTable=true;; + esac + done + + test_expect_success 'setup bitmap config' ' + rm -rf * .git && + git init && + git config pack.writeBitmapLookupTable '"$writeLookupTable"' + ' + + midx_bitmap_core rev + midx_bitmap_partial_tests rev +} + +test_midx_bitmap_rev +test_midx_bitmap_rev "pack.writeBitmapLookupTable" test_done From 28cd730680dd7d5c0e0971827315bf8ae32f47b7 Mon Sep 17 00:00:00 2001 From: Abhradeep Chakraborty Date: Sun, 14 Aug 2022 16:55:10 +0000 Subject: [PATCH 5/7] pack-bitmap: prepare to read lookup table extension Earlier change teaches Git to write bitmap lookup table. But Git does not know how to parse them. Teach Git to parse the existing bitmap lookup table. The older versions of Git are not affected by it. Those versions ignore the lookup table. Mentored-by: Taylor Blau Co-Mentored-by: Kaartic Sivaraam Signed-off-by: Abhradeep Chakraborty Reviewed-by: Taylor Blau Signed-off-by: Junio C Hamano --- pack-bitmap.c | 290 ++++++++++++++++++++++++++++++++++++++-- pack-bitmap.h | 9 ++ t/t5310-pack-bitmaps.sh | 22 +++ 3 files changed, 312 insertions(+), 9 deletions(-) diff --git a/pack-bitmap.c b/pack-bitmap.c index ef580be9e3..9a208abc1f 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -83,6 +83,12 @@ struct bitmap_index { /* The checksum of the packfile or MIDX; points into map. */ const unsigned char *checksum; + /* + * If not NULL, this point into the commit table extension + * (within the memory mapped region `map`). + */ + unsigned char *table_lookup; + /* * Extended index. * @@ -186,6 +192,16 @@ static int load_bitmap_header(struct bitmap_index *index) index->hashes = (void *)(index_end - cache_size); index_end -= cache_size; } + + if (flags & BITMAP_OPT_LOOKUP_TABLE) { + size_t table_size = st_mult(ntohl(header->entry_count), + BITMAP_LOOKUP_TABLE_TRIPLET_WIDTH); + if (table_size > index_end - index->map - header_size) + return error(_("corrupted bitmap index file (too short to fit lookup table)")); + if (git_env_bool("GIT_TEST_READ_COMMIT_TABLE", 1)) + index->table_lookup = (void *)(index_end - table_size); + index_end -= table_size; + } } index->entry_count = ntohl(header->entry_count); @@ -212,9 +228,11 @@ static struct stored_bitmap *store_bitmap(struct bitmap_index *index, hash_pos = kh_put_oid_map(index->bitmaps, stored->oid, &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 */ + /* + * 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'"), oid_to_hex(oid)); return NULL; @@ -482,7 +500,7 @@ static int load_bitmap(struct bitmap_index *bitmap_git) !(bitmap_git->tags = read_bitmap_1(bitmap_git))) goto failed; - if (load_bitmap_entries_v1(bitmap_git) < 0) + if (!bitmap_git->table_lookup && load_bitmap_entries_v1(bitmap_git) < 0) goto failed; return 0; @@ -570,13 +588,256 @@ struct include_data { struct bitmap *seen; }; +struct bitmap_lookup_table_triplet { + uint32_t commit_pos; + uint64_t offset; + uint32_t xor_row; +}; + +struct bitmap_lookup_table_xor_item { + struct object_id oid; + uint64_t offset; +}; + +/* + * Given a `triplet` struct pointer and pointer `p`, this + * function reads the triplet beginning at `p` into the struct. + * Note that this function assumes that there is enough memory + * left for filling the `triplet` struct from `p`. + */ +static int bitmap_lookup_table_get_triplet_by_pointer(struct bitmap_lookup_table_triplet *triplet, + const unsigned char *p) +{ + if (!triplet) + return -1; + + triplet->commit_pos = get_be32(p); + p += sizeof(uint32_t); + triplet->offset = get_be64(p); + p += sizeof(uint64_t); + triplet->xor_row = get_be32(p); + return 0; +} + +/* + * This function gets the raw triplet from `row`'th row in the + * lookup table and fills that data to the `triplet`. + */ +static int bitmap_lookup_table_get_triplet(struct bitmap_index *bitmap_git, + uint32_t pos, + struct bitmap_lookup_table_triplet *triplet) +{ + unsigned char *p = NULL; + if (pos >= bitmap_git->entry_count) + return error(_("corrupt bitmap lookup table: triplet position out of index")); + + p = bitmap_git->table_lookup + st_mult(pos, BITMAP_LOOKUP_TABLE_TRIPLET_WIDTH); + + return bitmap_lookup_table_get_triplet_by_pointer(triplet, p); +} + +/* + * Searches for a matching triplet. `commit_pos` is a pointer + * to the wanted commit position value. `table_entry` points to + * a triplet in lookup table. The first 4 bytes of each + * triplet (pointed by `table_entry`) are compared with `*commit_pos`. + */ +static int triplet_cmp(const void *commit_pos, const void *table_entry) +{ + + uint32_t a = *(uint32_t *)commit_pos; + uint32_t b = get_be32(table_entry); + if (a > b) + return 1; + else if (a < b) + return -1; + + return 0; +} + +static uint32_t bitmap_bsearch_pos(struct bitmap_index *bitmap_git, + struct object_id *oid, + uint32_t *result) +{ + int found; + + if (bitmap_is_midx(bitmap_git)) + found = bsearch_midx(oid, bitmap_git->midx, result); + else + found = bsearch_pack(oid, bitmap_git->pack, result); + + return found; +} + +/* + * `bsearch_triplet_by_pos` function searches for the raw triplet + * having commit position same as `commit_pos` and fills `triplet` + * object from the raw triplet. Returns 1 on success and 0 on + * failure. + */ +static int bitmap_bsearch_triplet_by_pos(uint32_t commit_pos, + struct bitmap_index *bitmap_git, + struct bitmap_lookup_table_triplet *triplet) +{ + unsigned char *p = bsearch(&commit_pos, bitmap_git->table_lookup, bitmap_git->entry_count, + BITMAP_LOOKUP_TABLE_TRIPLET_WIDTH, triplet_cmp); + + if (!p) + return -1; + + return bitmap_lookup_table_get_triplet_by_pointer(triplet, p); +} + +static struct stored_bitmap *lazy_bitmap_for_commit(struct bitmap_index *bitmap_git, + struct commit *commit) +{ + uint32_t commit_pos, xor_row; + uint64_t offset; + int flags; + struct bitmap_lookup_table_triplet triplet; + struct object_id *oid = &commit->object.oid; + struct ewah_bitmap *bitmap; + struct stored_bitmap *xor_bitmap = NULL; + const int bitmap_header_size = 6; + static struct bitmap_lookup_table_xor_item *xor_items = NULL; + static size_t xor_items_nr = 0, xor_items_alloc = 0; + static int is_corrupt = 0; + int xor_flags; + khiter_t hash_pos; + struct bitmap_lookup_table_xor_item *xor_item; + + if (is_corrupt) + return NULL; + + if (!bitmap_bsearch_pos(bitmap_git, oid, &commit_pos)) + return NULL; + + if (bitmap_bsearch_triplet_by_pos(commit_pos, bitmap_git, &triplet) < 0) + return NULL; + + xor_items_nr = 0; + offset = triplet.offset; + xor_row = triplet.xor_row; + + while (xor_row != 0xffffffff) { + ALLOC_GROW(xor_items, xor_items_nr + 1, xor_items_alloc); + + if (xor_items_nr + 1 >= bitmap_git->entry_count) { + error(_("corrupt bitmap lookup table: xor chain exceed entry count")); + goto corrupt; + } + + if (bitmap_lookup_table_get_triplet(bitmap_git, xor_row, &triplet) < 0) + goto corrupt; + + xor_item = &xor_items[xor_items_nr]; + xor_item->offset = triplet.offset; + + if (nth_bitmap_object_oid(bitmap_git, &xor_item->oid, triplet.commit_pos) < 0) { + error(_("corrupt bitmap lookup table: commit index %u out of range"), + triplet.commit_pos); + goto corrupt; + } + + hash_pos = kh_get_oid_map(bitmap_git->bitmaps, xor_item->oid); + + /* + * If desired bitmap is already stored, we don't need + * to iterate further. Because we know that bitmaps + * that are needed to be parsed to parse this bitmap + * has already been stored. So, assign this stored bitmap + * to the xor_bitmap. + */ + if (hash_pos < kh_end(bitmap_git->bitmaps) && + (xor_bitmap = kh_value(bitmap_git->bitmaps, hash_pos))) + break; + xor_items_nr++; + xor_row = triplet.xor_row; + } + + while (xor_items_nr) { + xor_item = &xor_items[xor_items_nr - 1]; + bitmap_git->map_pos = xor_item->offset; + if (bitmap_git->map_size - bitmap_git->map_pos < bitmap_header_size) { + error(_("corrupt ewah bitmap: truncated header for bitmap of commit \"%s\""), + oid_to_hex(&xor_item->oid)); + goto corrupt; + } + + bitmap_git->map_pos += sizeof(uint32_t) + sizeof(uint8_t); + xor_flags = read_u8(bitmap_git->map, &bitmap_git->map_pos); + bitmap = read_bitmap_1(bitmap_git); + + if (!bitmap) + goto corrupt; + + xor_bitmap = store_bitmap(bitmap_git, bitmap, &xor_item->oid, xor_bitmap, xor_flags); + xor_items_nr--; + } + + bitmap_git->map_pos = offset; + if (bitmap_git->map_size - bitmap_git->map_pos < bitmap_header_size) { + error(_("corrupt ewah bitmap: truncated header for bitmap of commit \"%s\""), + oid_to_hex(oid)); + goto corrupt; + } + + /* + * Don't bother reading the commit's index position or its xor + * offset: + * + * - The commit's index position is irrelevant to us, since + * load_bitmap_entries_v1 only uses it to learn the object + * id which is used to compute the hashmap's key. We already + * have an object id, so no need to look it up again. + * + * - The xor_offset is unusable for us, since it specifies how + * many entries previous to ours we should look at. This + * makes sense when reading the bitmaps sequentially (as in + * load_bitmap_entries_v1()), since we can keep track of + * each bitmap as we read them. + * + * But it can't work for us, since the bitmap's don't have a + * fixed size. So we learn the position of the xor'd bitmap + * from the commit table (and resolve it to a bitmap in the + * above if-statement). + * + * Instead, we can skip ahead and immediately read the flags and + * ewah bitmap. + */ + bitmap_git->map_pos += sizeof(uint32_t) + sizeof(uint8_t); + flags = read_u8(bitmap_git->map, &bitmap_git->map_pos); + bitmap = read_bitmap_1(bitmap_git); + + if (!bitmap) + goto corrupt; + + return store_bitmap(bitmap_git, bitmap, oid, xor_bitmap, flags); + +corrupt: + free(xor_items); + is_corrupt = 1; + return NULL; +} + struct ewah_bitmap *bitmap_for_commit(struct bitmap_index *bitmap_git, struct commit *commit) { khiter_t hash_pos = kh_get_oid_map(bitmap_git->bitmaps, commit->object.oid); - if (hash_pos >= kh_end(bitmap_git->bitmaps)) - return NULL; + if (hash_pos >= kh_end(bitmap_git->bitmaps)) { + struct stored_bitmap *bitmap = NULL; + if (!bitmap_git->table_lookup) + return NULL; + + trace2_region_enter("pack-bitmap", "reading_lookup_table", the_repository); + /* NEEDSWORK: cache misses aren't recorded */ + bitmap = lazy_bitmap_for_commit(bitmap_git, commit); + trace2_region_leave("pack-bitmap", "reading_lookup_table", the_repository); + if (!bitmap) + return NULL; + return lookup_stored_bitmap(bitmap); + } return lookup_stored_bitmap(kh_value(bitmap_git->bitmaps, hash_pos)); } @@ -1712,8 +1973,10 @@ void test_bitmap_walk(struct rev_info *revs) if (revs->pending.nr != 1) die(_("you must specify exactly one commit to test")); - fprintf_ln(stderr, "Bitmap v%d test (%d entries loaded)", - bitmap_git->version, bitmap_git->entry_count); + fprintf_ln(stderr, "Bitmap v%d test (%d entries%s)", + bitmap_git->version, + bitmap_git->entry_count, + bitmap_git->table_lookup ? "" : " loaded"); root = revs->pending.objects[0].item; bm = bitmap_for_commit(bitmap_git, (struct commit *)root); @@ -1766,13 +2029,22 @@ void test_bitmap_walk(struct rev_info *revs) int test_bitmap_commits(struct repository *r) { - struct bitmap_index *bitmap_git = prepare_bitmap_git(r); struct object_id oid; MAYBE_UNUSED void *value; + struct bitmap_index *bitmap_git = prepare_bitmap_git(r); if (!bitmap_git) die(_("failed to load bitmap indexes")); + /* + * As this function is only used to print bitmap selected + * commits, we don't have to read the commit table. + */ + if (bitmap_git->table_lookup) { + if (load_bitmap_entries_v1(bitmap_git) < 0) + die(_("failed to load bitmap indexes")); + } + kh_foreach(bitmap_git->bitmaps, oid, value, { printf_ln("%s", oid_to_hex(&oid)); }); diff --git a/pack-bitmap.h b/pack-bitmap.h index cb065a263c..f0180b5276 100644 --- a/pack-bitmap.h +++ b/pack-bitmap.h @@ -23,6 +23,15 @@ struct bitmap_disk_header { #define NEEDS_BITMAP (1u<<22) +/* + * The width in bytes of a single triplet in the lookup table + * extension: + * (commit_pos, offset, xor_row) + * + * whose fields ar 32-, 64-, 32- bits wide, respectively. + */ +#define BITMAP_LOOKUP_TABLE_TRIPLET_WIDTH (16) + enum pack_bitmap_opts { BITMAP_OPT_FULL_DAG = 0x1, BITMAP_OPT_HASH_CACHE = 0x4, diff --git a/t/t5310-pack-bitmaps.sh b/t/t5310-pack-bitmaps.sh index c060717282..7e50f8e765 100755 --- a/t/t5310-pack-bitmaps.sh +++ b/t/t5310-pack-bitmaps.sh @@ -258,6 +258,7 @@ test_bitmap_cases () { test_expect_success 'truncated bitmap fails gracefully (ewah)' ' test_config pack.writebitmaphashcache false && + test_config pack.writebitmaplookuptable false && git repack -ad && git rev-list --use-bitmap-index --count --all >expect && bitmap=$(ls .git/objects/pack/*.bitmap) && @@ -270,6 +271,7 @@ test_bitmap_cases () { ' test_expect_success 'truncated bitmap fails gracefully (cache)' ' + git config pack.writeBitmapLookupTable '"$writeLookupTable"' && git repack -ad && git rev-list --use-bitmap-index --count --all >expect && bitmap=$(ls .git/objects/pack/*.bitmap) && @@ -453,4 +455,24 @@ test_expect_success 'verify writing bitmap lookup table when enabled' ' grep "\"label\":\"writing_lookup_table\"" trace2 ' +test_expect_success 'lookup table is actually used to traverse objects' ' + git repack -adb && + GIT_TRACE2_EVENT="$(pwd)/trace3" \ + git rev-list --use-bitmap-index --count --all && + grep "\"label\":\"reading_lookup_table\"" trace3 +' + +test_expect_success 'truncated bitmap fails gracefully (lookup table)' ' + test_config pack.writebitmaphashcache false && + git repack -adb && + git rev-list --use-bitmap-index --count --all >expect && + bitmap=$(ls .git/objects/pack/*.bitmap) && + test_when_finished "rm -f $bitmap" && + test_copy_bytes 512 <$bitmap >$bitmap.tmp && + mv -f $bitmap.tmp $bitmap && + git rev-list --use-bitmap-index --count --all >actual 2>stderr && + test_cmp expect actual && + test_i18ngrep corrupted.bitmap.index stderr +' + test_done From 761416ef91d819d84a11222ec5bc3cbc66d3ddac Mon Sep 17 00:00:00 2001 From: Abhradeep Chakraborty Date: Sun, 14 Aug 2022 16:55:11 +0000 Subject: [PATCH 6/7] bitmap-lookup-table: add performance tests for lookup table Add performance tests to verify the performance of lookup table. `p5310-pack-bitmaps.sh` contain tests with and without lookup table. `p5312-pack-bitmaps-revs.sh` contain same tests with and without lookup table but with `pack.writeReverseIndex` enabled. Lookup table makes Git run faster in most of the cases. Below is the result of `t/perf/p5310-pack-bitmaps.sh`.`perf/p5326-multi-pack-bitmaps.sh` gives similar result. The repository used in the test is linux kernel. Test this tree ----------------------------------------------------------------------- 5310.4: enable lookup table: false 0.01(0.00+0.00) 5310.5: repack to disk 320.89(230.20+23.45) 5310.6: simulated clone 14.04(5.78+1.79) 5310.7: simulated fetch 1.95(3.05+0.20) 5310.8: pack to file (bitmap) 44.73(20.55+7.45) 5310.9: rev-list (commits) 0.78(0.46+0.10) 5310.10: rev-list (objects) 4.07(3.97+0.08) 5310.11: rev-list with tag negated via --not 0.06(0.02+0.03) --all (objects) 5310.12: rev-list with negative tag (objects) 0.21(0.15+0.05) 5310.13: rev-list count with blob:none 0.24(0.17+0.06) 5310.14: rev-list count with blob:limit=1k 7.07(5.92+0.48) 5310.15: rev-list count with tree:0 0.25(0.17+0.07) 5310.16: simulated partial clone 5.67(3.28+0.64) 5310.18: clone (partial bitmap) 16.05(8.34+1.86) 5310.19: pack to file (partial bitmap) 59.76(27.22+7.43) 5310.20: rev-list with tree filter (partial bitmap) 0.90(0.18+0.16) 5310.24: enable lookup table: true 0.01(0.00+0.00) 5310.25: repack to disk 319.73(229.30+23.01) 5310.26: simulated clone 13.69(5.72+1.78) 5310.27: simulated fetch 1.84(3.02+0.16) 5310.28: pack to file (bitmap) 45.63(20.67+7.50) 5310.29: rev-list (commits) 0.56(0.39+0.8) 5310.30: rev-list (objects) 3.77(3.74+0.08) 5310.31: rev-list with tag negated via --not 0.05(0.02+0.03) --all (objects) 5310.32: rev-list with negative tag (objects) 0.21(0.15+0.05) 5310.33: rev-list count with blob:none 0.23(0.17+0.05) 5310.34: rev-list count with blob:limit=1k 6.65(5.72+0.40) 5310.35: rev-list count with tree:0 0.23(0.16+0.06) 5310.36: simulated partial clone 5.57(3.26+0.59) 5310.38: clone (partial bitmap) 15.89(8.39+1.84) 5310.39: pack to file (partial bitmap) 58.32(27.55+7.47) 5310.40: rev-list with tree filter (partial bitmap) 0.73(0.18+0.15) Test 4-15 are tested without using lookup table. Same tests are repeated in 16-30 (using lookup table). Mentored-by: Taylor Blau Co-Mentored-by: Kaartic Sivaraam Signed-off-by: Abhradeep Chakraborty Reviewed-by: Taylor Blau Signed-off-by: Junio C Hamano --- t/perf/lib-bitmap.sh | 31 +++++++++++ t/perf/p5310-pack-bitmaps.sh | 66 ++++++++++-------------- t/perf/p5311-pack-bitmaps-fetch.sh | 74 ++++++++++++++------------ t/perf/p5312-pack-bitmaps-revs.sh | 35 +++++++++++++ t/perf/p5326-multi-pack-bitmaps.sh | 83 ++++++++++++++++++------------ 5 files changed, 183 insertions(+), 106 deletions(-) create mode 100755 t/perf/p5312-pack-bitmaps-revs.sh diff --git a/t/perf/lib-bitmap.sh b/t/perf/lib-bitmap.sh index 63d3bc7cec..55a8feb1dc 100644 --- a/t/perf/lib-bitmap.sh +++ b/t/perf/lib-bitmap.sh @@ -67,3 +67,34 @@ test_partial_bitmap () { --filter=tree:0 >/dev/null ' } + +test_pack_bitmap () { + test_perf "repack to disk" ' + git repack -ad + ' + + test_full_bitmap + + test_expect_success "create partial bitmap state" ' + # pick a commit to represent the repo tip in the past + cutoff=$(git rev-list HEAD~100 -1) && + orig_tip=$(git rev-parse HEAD) && + + # now kill off all of the refs and pretend we had + # just the one tip + rm -rf .git/logs .git/refs/* .git/packed-refs && + git update-ref HEAD $cutoff && + + # and then repack, which will leave us with a nice + # big bitmap pack of the "old" history, and all of + # the new history will be loose, as if it had been pushed + # up incrementally and exploded via unpack-objects + git repack -Ad && + + # and now restore our original tip, as if the pushes + # had happened + git update-ref HEAD $orig_tip + ' + + test_partial_bitmap +} diff --git a/t/perf/p5310-pack-bitmaps.sh b/t/perf/p5310-pack-bitmaps.sh index 7ad4f237bc..b1399f1007 100755 --- a/t/perf/p5310-pack-bitmaps.sh +++ b/t/perf/p5310-pack-bitmaps.sh @@ -4,51 +4,37 @@ test_description='Tests pack performance using bitmaps' . ./perf-lib.sh . "${TEST_DIRECTORY}/perf/lib-bitmap.sh" -test_perf_large_repo +test_lookup_pack_bitmap () { + test_expect_success 'start the test from scratch' ' + rm -rf * .git + ' -# note that we do everything through config, -# since we want to be able to compare bitmap-aware -# git versus non-bitmap git -# -# We intentionally use the deprecated pack.writebitmaps -# config so that we can test against older versions of git. -test_expect_success 'setup bitmap config' ' - git config pack.writebitmaps true -' + test_perf_large_repo -# we need to create the tag up front such that it is covered by the repack and -# thus by generated bitmaps. -test_expect_success 'create tags' ' - git tag --message="tag pointing to HEAD" perf-tag HEAD -' + # note that we do everything through config, + # since we want to be able to compare bitmap-aware + # git versus non-bitmap git + # + # We intentionally use the deprecated pack.writebitmaps + # config so that we can test against older versions of git. + test_expect_success 'setup bitmap config' ' + git config pack.writebitmaps true + ' -test_perf 'repack to disk' ' - git repack -ad -' + # we need to create the tag up front such that it is covered by the repack and + # thus by generated bitmaps. + test_expect_success 'create tags' ' + git tag --message="tag pointing to HEAD" perf-tag HEAD + ' -test_full_bitmap + test_perf "enable lookup table: $1" ' + git config pack.writeBitmapLookupTable '"$1"' + ' -test_expect_success 'create partial bitmap state' ' - # pick a commit to represent the repo tip in the past - cutoff=$(git rev-list HEAD~100 -1) && - orig_tip=$(git rev-parse HEAD) && + test_pack_bitmap +} - # now kill off all of the refs and pretend we had - # just the one tip - rm -rf .git/logs .git/refs/* .git/packed-refs && - git update-ref HEAD $cutoff && - - # and then repack, which will leave us with a nice - # big bitmap pack of the "old" history, and all of - # the new history will be loose, as if it had been pushed - # up incrementally and exploded via unpack-objects - git repack -Ad && - - # and now restore our original tip, as if the pushes - # had happened - git update-ref HEAD $orig_tip -' - -test_partial_bitmap +test_lookup_pack_bitmap false +test_lookup_pack_bitmap true test_done diff --git a/t/perf/p5311-pack-bitmaps-fetch.sh b/t/perf/p5311-pack-bitmaps-fetch.sh index 47c3fd7581..426fab87e3 100755 --- a/t/perf/p5311-pack-bitmaps-fetch.sh +++ b/t/perf/p5311-pack-bitmaps-fetch.sh @@ -3,42 +3,52 @@ test_description='performance of fetches from bitmapped packs' . ./perf-lib.sh -test_perf_default_repo - -test_expect_success 'create bitmapped server repo' ' - git config pack.writebitmaps true && - git repack -ad -' - -# simulate a fetch from a repository that last fetched N days ago, for -# various values of N. We do so by following the first-parent chain, -# and assume the first entry in the chain that is N days older than the current -# HEAD is where the HEAD would have been then. -for days in 1 2 4 8 16 32 64 128; do - title=$(printf '%10s' "($days days)") - test_expect_success "setup revs from $days days ago" ' - now=$(git log -1 --format=%ct HEAD) && - then=$(($now - ($days * 86400))) && - tip=$(git rev-list -1 --first-parent --until=$then HEAD) && - { - echo HEAD && - echo ^$tip - } >revs +test_fetch_bitmaps () { + test_expect_success 'setup test directory' ' + rm -fr * .git ' - test_perf "server $title" ' - git pack-objects --stdout --revs \ - --thin --delta-base-offset \ - tmp.pack + test_perf_default_repo + + test_expect_success 'create bitmapped server repo' ' + git config pack.writebitmaps true && + git config pack.writeBitmapLookupTable '"$1"' && + git repack -ad ' - test_size "size $title" ' - wc -c revs + ' - test_perf "client $title" ' - git index-pack --stdin --fix-thin tmp.pack + ' + + test_size "size $title" ' + wc -c Date: Sun, 28 Aug 2022 08:50:50 -0400 Subject: [PATCH 7/7] pack-bitmap-write: drop unused pack_idx_entry parameters Our write_selected_commits_v1() function takes an array of pack_idx_entry structs. We used to need them for computing commit positions, but since aa30162559 (bitmap: move `get commit positions` code to `bitmap_writer_finish`, 2022-08-14), the caller passes in a separate array of positions for us. We can drop the unused array (and its matching length parameter). Likewise, when we added write_lookup_table() in 93eb41e240 (pack-bitmap-write.c: write lookup table extension, 2022-08-14), it receives the same array of positions. So its "index" parameter was never used at all. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- pack-bitmap-write.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/pack-bitmap-write.c b/pack-bitmap-write.c index 2cfc92f287..a213f5eddc 100644 --- a/pack-bitmap-write.c +++ b/pack-bitmap-write.c @@ -649,8 +649,6 @@ static const struct object_id *oid_access(size_t pos, const void *table) } static void write_selected_commits_v1(struct hashfile *f, - struct pack_idx_entry **index, - uint32_t index_nr, uint32_t *commit_positions, off_t *offsets) { @@ -685,8 +683,6 @@ static int table_cmp(const void *_va, const void *_vb, void *_data) } static void write_lookup_table(struct hashfile *f, - struct pack_idx_entry **index, - uint32_t index_nr, uint32_t *commit_positions, off_t *offsets) { @@ -808,10 +804,10 @@ void bitmap_writer_finish(struct pack_idx_entry **index, commit_positions[i] = commit_pos; } - write_selected_commits_v1(f, index, index_nr, commit_positions, offsets); + write_selected_commits_v1(f, commit_positions, offsets); if (options & BITMAP_OPT_LOOKUP_TABLE) - write_lookup_table(f, index, index_nr, commit_positions, offsets); + write_lookup_table(f, commit_positions, offsets); if (options & BITMAP_OPT_HASH_CACHE) write_hash_cache(f, index, index_nr);