1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-06-02 09:26:10 +02:00
git/t/t5318-commit-graph.sh

573 lines
17 KiB
Bash
Raw Normal View History

#!/bin/sh
test_description='commit graph'
. ./test-lib.sh
test_expect_success 'setup full repo' '
mkdir full &&
cd "$TRASH_DIRECTORY/full" &&
git init &&
git config core.commitGraph true &&
objdir=".git/objects" &&
test_oid_init
'
test_expect_success 'verify graph with no graph file' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph verify
'
test_expect_success 'write graph with no packs' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write --object-dir . &&
test_path_is_file info/commit-graph
'
test_expect_success 'create commits and repack' '
cd "$TRASH_DIRECTORY/full" &&
for i in $(test_seq 3)
do
test_commit $i &&
git branch commits/$i
done &&
git repack
'
graph_git_two_modes() {
git -c core.commitGraph=true $1 >output
git -c core.commitGraph=false $1 >expect
test_cmp expect output
}
graph_git_behavior() {
MSG=$1
DIR=$2
BRANCH=$3
COMPARE=$4
test_expect_success "check normal git operations: $MSG" '
cd "$TRASH_DIRECTORY/$DIR" &&
graph_git_two_modes "log --oneline $BRANCH" &&
graph_git_two_modes "log --topo-order $BRANCH" &&
graph_git_two_modes "log --graph $COMPARE..$BRANCH" &&
graph_git_two_modes "branch -vv" &&
graph_git_two_modes "merge-base -a $BRANCH $COMPARE"
'
}
graph_git_behavior 'no graph' full commits/3 commits/1
graph_read_expect() {
OPTIONAL=""
NUM_CHUNKS=3
if test ! -z $2
then
OPTIONAL=" $2"
NUM_CHUNKS=$((3 + $(echo "$2" | wc -w)))
fi
cat >expect <<- EOF
header: 43475048 1 1 $NUM_CHUNKS 0
num_commits: $1
chunks: oid_fanout oid_lookup commit_metadata$OPTIONAL
EOF
git commit-graph read >output &&
test_cmp expect output
}
test_expect_success 'write graph' '
cd "$TRASH_DIRECTORY/full" &&
graph1=$(git commit-graph write) &&
test_path_is_file $objdir/info/commit-graph &&
graph_read_expect "3"
'
graph_git_behavior 'graph exists' full commits/3 commits/1
test_expect_success 'Add more commits' '
cd "$TRASH_DIRECTORY/full" &&
git reset --hard commits/1 &&
for i in $(test_seq 4 5)
do
test_commit $i &&
git branch commits/$i
done &&
git reset --hard commits/2 &&
for i in $(test_seq 6 7)
do
test_commit $i &&
git branch commits/$i
done &&
git reset --hard commits/2 &&
git merge commits/4 &&
git branch merge/1 &&
git reset --hard commits/4 &&
git merge commits/6 &&
git branch merge/2 &&
git reset --hard commits/3 &&
git merge commits/5 commits/7 &&
git branch merge/3 &&
git repack
'
# Current graph structure:
#
# __M3___
# / | \
# 3 M1 5 M2 7
# |/ \|/ \|
# 2 4 6
# |___/____/
# 1
test_expect_success 'write graph with merges' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "10" "extra_edges"
'
graph_git_behavior 'merge 1 vs 2' full merge/1 merge/2
graph_git_behavior 'merge 1 vs 3' full merge/1 merge/3
graph_git_behavior 'merge 2 vs 3' full merge/2 merge/3
test_expect_success 'Add one more commit' '
cd "$TRASH_DIRECTORY/full" &&
test_commit 8 &&
git branch commits/8 &&
ls $objdir/pack | grep idx >existing-idx &&
git repack &&
ls $objdir/pack| grep idx | grep -v -f existing-idx >new-idx
'
# Current graph structure:
#
# 8
# |
# __M3___
# / | \
# 3 M1 5 M2 7
# |/ \|/ \|
# 2 4 6
# |___/____/
# 1
graph_git_behavior 'mixed mode, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'mixed mode, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'write graph with new commit' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "11" "extra_edges"
'
graph_git_behavior 'full graph, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'full graph, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'write graph with nothing new' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write &&
test_path_is_file $objdir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "11" "extra_edges"
'
graph_git_behavior 'cleared graph, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'cleared graph, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'build graph from latest pack with closure' '
cd "$TRASH_DIRECTORY/full" &&
cat new-idx | git commit-graph write --stdin-packs &&
test_path_is_file $objdir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "9" "extra_edges"
'
graph_git_behavior 'graph from pack, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'graph from pack, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'build graph from commits with closure' '
cd "$TRASH_DIRECTORY/full" &&
git tag -a -m "merge" tag/merge merge/2 &&
git rev-parse tag/merge >commits-in &&
git rev-parse merge/1 >>commits-in &&
cat commits-in | git commit-graph write --stdin-commits &&
test_path_is_file $objdir/info/commit-graph &&
graph_read_expect "6"
'
graph_git_behavior 'graph from commits, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'graph from commits, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'build graph from commits with append' '
cd "$TRASH_DIRECTORY/full" &&
git rev-parse merge/3 | git commit-graph write --stdin-commits --append &&
test_path_is_file $objdir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "10" "extra_edges"
'
graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'append graph, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'build graph using --reachable' '
cd "$TRASH_DIRECTORY/full" &&
git commit-graph write --reachable &&
test_path_is_file $objdir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "11" "extra_edges"
'
graph_git_behavior 'append graph, commit 8 vs merge 1' full commits/8 merge/1
graph_git_behavior 'append graph, commit 8 vs merge 2' full commits/8 merge/2
test_expect_success 'setup bare repo' '
cd "$TRASH_DIRECTORY" &&
git clone --bare --no-local full bare &&
cd bare &&
git config core.commitGraph true &&
baredir="./objects"
'
graph_git_behavior 'bare repo, commit 8 vs merge 1' bare commits/8 merge/1
graph_git_behavior 'bare repo, commit 8 vs merge 2' bare commits/8 merge/2
test_expect_success 'write graph in bare repo' '
cd "$TRASH_DIRECTORY/bare" &&
git commit-graph write &&
test_path_is_file $baredir/info/commit-graph &&
commit-graph: rename "large edges" to "extra edges" The optional 'Large Edge List' chunk of the commit graph file stores parent information for commits with more than two parents, and the names of most of the macros, variables, struct fields, and functions related to this chunk contain the term "large edges", e.g. write_graph_chunk_large_edges(). However, it's not a really great term, as the edges to the second and subsequent parents stored in this chunk are not any larger than the edges to the first and second parents stored in the "main" 'Commit Data' chunk. It's the number of edges, IOW number of parents, that is larger compared to non-merge and "regular" two-parent merge commits. And indeed, two functions in 'commit-graph.c' have a local variable called 'num_extra_edges' that refer to the same thing, and this "extra edges" term is much better at describing these edges. So let's rename all these references to "large edges" in macro, variable, function, etc. names to "extra edges". There is a GRAPH_OCTOPUS_EDGES_NEEDED macro as well; for the sake of consistency rename it to GRAPH_EXTRA_EDGES_NEEDED. We can do so safely without causing any incompatibility issues, because the term "large edges" doesn't come up in the file format itself in any form (the chunk's magic is {'E', 'D', 'G', 'E'}, there is no 'L' in there), but only in the specification text. The string "large edges", however, does come up in the output of 'git commit-graph read' and in tests looking at its input, but that command is explicitly documented as debugging aid, so we can change its output and the affected tests safely. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-01-19 21:21:13 +01:00
graph_read_expect "11" "extra_edges"
'
graph_git_behavior 'bare repo with graph, commit 8 vs merge 1' bare commits/8 merge/1
graph_git_behavior 'bare repo with graph, commit 8 vs merge 2' bare commits/8 merge/2
test_expect_success 'perform fast-forward merge in full repo' '
cd "$TRASH_DIRECTORY/full" &&
git checkout -b merge-5-to-8 commits/5 &&
git merge commits/8 &&
git show-ref -s merge-5-to-8 >output &&
git show-ref -s commits/8 >expect &&
test_cmp expect output
'
test_expect_success 'check that gc computes commit-graph' '
cd "$TRASH_DIRECTORY/full" &&
git commit --allow-empty -m "blank" &&
git commit-graph write --reachable &&
cp $objdir/info/commit-graph commit-graph-before-gc &&
git reset --hard HEAD~1 &&
git config gc.writeCommitGraph true &&
git gc &&
cp $objdir/info/commit-graph commit-graph-after-gc &&
! test_cmp_bin commit-graph-before-gc commit-graph-after-gc &&
git commit-graph write --reachable &&
test_cmp_bin commit-graph-after-gc $objdir/info/commit-graph
'
test_expect_success 'replace-objects invalidates commit-graph' '
cd "$TRASH_DIRECTORY" &&
test_when_finished rm -rf replace &&
git clone full replace &&
(
cd replace &&
git commit-graph write --reachable &&
test_path_is_file .git/objects/info/commit-graph &&
git replace HEAD~1 HEAD~2 &&
git -c core.commitGraph=false log >expect &&
git -c core.commitGraph=true log >actual &&
test_cmp expect actual &&
git commit-graph write --reachable &&
git -c core.commitGraph=false --no-replace-objects log >expect &&
git -c core.commitGraph=true --no-replace-objects log >actual &&
test_cmp expect actual &&
rm -rf .git/objects/info/commit-graph &&
git commit-graph write --reachable &&
test_path_is_file .git/objects/info/commit-graph
)
'
test_expect_success 'commit grafts invalidate commit-graph' '
cd "$TRASH_DIRECTORY" &&
test_when_finished rm -rf graft &&
git clone full graft &&
(
cd graft &&
git commit-graph write --reachable &&
test_path_is_file .git/objects/info/commit-graph &&
H1=$(git rev-parse --verify HEAD~1) &&
H3=$(git rev-parse --verify HEAD~3) &&
echo "$H1 $H3" >.git/info/grafts &&
git -c core.commitGraph=false log >expect &&
git -c core.commitGraph=true log >actual &&
test_cmp expect actual &&
git commit-graph write --reachable &&
git -c core.commitGraph=false --no-replace-objects log >expect &&
git -c core.commitGraph=true --no-replace-objects log >actual &&
test_cmp expect actual &&
rm -rf .git/objects/info/commit-graph &&
git commit-graph write --reachable &&
test_path_is_missing .git/objects/info/commit-graph
)
'
test_expect_success 'replace-objects invalidates commit-graph' '
cd "$TRASH_DIRECTORY" &&
test_when_finished rm -rf shallow &&
git clone --depth 2 "file://$TRASH_DIRECTORY/full" shallow &&
(
cd shallow &&
git commit-graph write --reachable &&
test_path_is_missing .git/objects/info/commit-graph &&
git fetch origin --unshallow &&
git commit-graph write --reachable &&
test_path_is_file .git/objects/info/commit-graph
)
'
# the verify tests below expect the commit-graph to contain
# exactly the commits reachable from the commits/8 branch.
# If the file changes the set of commits in the list, then the
# offsets into the binary file will result in different edits
# and the tests will likely break.
test_expect_success 'git commit-graph verify' '
cd "$TRASH_DIRECTORY/full" &&
git rev-parse commits/8 | git commit-graph write --stdin-commits &&
git commit-graph verify >output
'
NUM_COMMITS=9
NUM_OCTOPUS_EDGES=2
HASH_LEN="$(test_oid rawsz)"
GRAPH_BYTE_VERSION=4
GRAPH_BYTE_HASH=5
GRAPH_BYTE_CHUNK_COUNT=6
GRAPH_CHUNK_LOOKUP_OFFSET=8
GRAPH_CHUNK_LOOKUP_WIDTH=12
GRAPH_CHUNK_LOOKUP_ROWS=5
GRAPH_BYTE_OID_FANOUT_ID=$GRAPH_CHUNK_LOOKUP_OFFSET
GRAPH_BYTE_OID_LOOKUP_ID=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
1 * $GRAPH_CHUNK_LOOKUP_WIDTH))
GRAPH_BYTE_COMMIT_DATA_ID=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
2 * $GRAPH_CHUNK_LOOKUP_WIDTH))
GRAPH_FANOUT_OFFSET=$(($GRAPH_CHUNK_LOOKUP_OFFSET + \
$GRAPH_CHUNK_LOOKUP_WIDTH * $GRAPH_CHUNK_LOOKUP_ROWS))
GRAPH_BYTE_FANOUT1=$(($GRAPH_FANOUT_OFFSET + 4 * 4))
GRAPH_BYTE_FANOUT2=$(($GRAPH_FANOUT_OFFSET + 4 * 255))
GRAPH_OID_LOOKUP_OFFSET=$(($GRAPH_FANOUT_OFFSET + 4 * 256))
GRAPH_BYTE_OID_LOOKUP_ORDER=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * 8))
GRAPH_BYTE_OID_LOOKUP_MISSING=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * 4 + 10))
GRAPH_COMMIT_DATA_OFFSET=$(($GRAPH_OID_LOOKUP_OFFSET + $HASH_LEN * $NUM_COMMITS))
GRAPH_BYTE_COMMIT_TREE=$GRAPH_COMMIT_DATA_OFFSET
GRAPH_BYTE_COMMIT_PARENT=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN))
GRAPH_BYTE_COMMIT_EXTRA_PARENT=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 4))
GRAPH_BYTE_COMMIT_WRONG_PARENT=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 3))
GRAPH_BYTE_COMMIT_GENERATION=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 11))
GRAPH_BYTE_COMMIT_DATE=$(($GRAPH_COMMIT_DATA_OFFSET + $HASH_LEN + 12))
GRAPH_COMMIT_DATA_WIDTH=$(($HASH_LEN + 16))
GRAPH_OCTOPUS_DATA_OFFSET=$(($GRAPH_COMMIT_DATA_OFFSET + \
$GRAPH_COMMIT_DATA_WIDTH * $NUM_COMMITS))
GRAPH_BYTE_OCTOPUS=$(($GRAPH_OCTOPUS_DATA_OFFSET + 4))
GRAPH_BYTE_FOOTER=$(($GRAPH_OCTOPUS_DATA_OFFSET + 4 * $NUM_OCTOPUS_EDGES))
corrupt_graph_setup() {
cd "$TRASH_DIRECTORY/full" &&
test_when_finished mv commit-graph-backup $objdir/info/commit-graph &&
cp $objdir/info/commit-graph commit-graph-backup
}
corrupt_graph_verify() {
grepstr=$1
test_must_fail git commit-graph verify 2>test_err &&
grep -v "^+" test_err >err &&
commit-graph: fix segfault on e.g. "git status" When core.commitGraph=true is set, various common commands now consult the commit graph. Because the commit-graph code is very trusting of its input data, it's possibly to construct a graph that'll cause an immediate segfault on e.g. "status" (and e.g. "log", "blame", ...). In some other cases where git immediately exits with a cryptic error about the graph being broken. The root cause of this is that while the "commit-graph verify" sub-command exhaustively verifies the graph, other users of the graph simply trust the graph, and will e.g. deference data found at certain offsets as pointers, causing segfaults. This change does the bare minimum to ensure that we don't segfault in the common fill_commit_in_graph() codepath called by e.g. setup_revisions(), to do this instrument the "commit-graph verify" tests to always check if "status" would subsequently segfault. This fixes the following tests which would previously segfault: not ok 50 - detect low chunk count not ok 51 - detect missing OID fanout chunk not ok 52 - detect missing OID lookup chunk not ok 53 - detect missing commit data chunk Those happened because with the commit-graph enabled setup_revisions() would eventually call fill_commit_in_graph(), where e.g. g->chunk_commit_data is used early as an offset (and will be 0x0). With this change we get far enough to detect that the graph is broken, and show an error instead. E.g.: $ git status; echo $? error: commit-graph is missing the Commit Data chunk 1 That also sucks, we should *warn* and not hard-fail "status" just because the commit-graph is corrupt, but fixing is left to a follow-up change. A side-effect of changing the reporting from graph_report() to error() is that we now have an "error: " prefix for these even for "commit-graph verify". Pseudo-diff before/after: $ git commit-graph verify -commit-graph is missing the Commit Data chunk +error: commit-graph is missing the Commit Data chunk Changing that is OK. Various errors it emits now early on are prefixed with "error: ", moving these over and changing the output doesn't break anything. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-25 13:08:29 +01:00
test_i18ngrep "$grepstr" err &&
commit-graph write: don't die if the existing graph is corrupt When the commit-graph is written we end up calling parse_commit(). This will in turn invoke code that'll consult the existing commit-graph about the commit, if the graph is corrupted we die. We thus get into a state where a failing "commit-graph verify" can't be followed-up with a "commit-graph write" if core.commitGraph=true is set, the graph either needs to be manually removed to proceed, or core.commitGraph needs to be set to "false". Change the "commit-graph write" codepath to use a new parse_commit_no_graph() helper instead of parse_commit() to avoid this. The latter will call repo_parse_commit_internal() with use_commit_graph=1 as seen in 177722b344 ("commit: integrate commit graph with commit parsing", 2018-04-10). Not using the old graph at all slows down the writing of the new graph by some small amount, but is a sensible way to prevent an error in the existing commit-graph from spreading. Just fixing the current issue would be likely to result in code that's inadvertently broken in the future. New code might use the commit-graph at a distance. To detect such cases introduce a "GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD" setting used when we do our corruption tests, and test that a "write/verify" combo works after every one of our current test cases where we now detect commit-graph corruption. Some of the code changes here might be strictly unnecessary, e.g. I was unable to find cases where the parse_commit() called from write_graph_chunk_data() didn't exit early due to "item->object.parsed" being true in repo_parse_commit_internal() (before the use_commit_graph=1 has any effect). But let's also convert those cases for good measure, we do not have exhaustive tests for all possible types of commit-graph corruption. This might need to be re-visited if we learn to write the commit-graph incrementally, but probably not. Hopefully we'll just start by finding out what commits we have in total, then read the old graph(s) to see what they cover, and finally write a new graph file with everything that's missing. In that case the new graph writing code just needs to continue to use e.g. a parse_commit() that doesn't consult the existing commit-graphs. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-25 13:08:33 +01:00
if test "$2" != "no-copy"
then
cp $objdir/info/commit-graph commit-graph-pre-write-test
fi &&
git status --short &&
GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD=true git commit-graph write &&
git commit-graph verify
}
# usage: corrupt_graph_and_verify <position> <data> <string> [<zero_pos>]
# Manipulates the commit-graph file at the position
# by inserting the data, optionally zeroing the file
# starting at <zero_pos>, then runs 'git commit-graph verify'
# and places the output in the file 'err'. Test 'err' for
# the given string.
corrupt_graph_and_verify() {
pos=$1
data="${2:-\0}"
grepstr=$3
corrupt_graph_setup &&
orig_size=$(wc -c < $objdir/info/commit-graph) &&
zero_pos=${4:-${orig_size}} &&
printf "$data" | dd of="$objdir/info/commit-graph" bs=1 seek="$pos" conv=notrunc &&
dd of="$objdir/info/commit-graph" bs=1 seek="$zero_pos" count=0 &&
generate_zero_bytes $(($orig_size - $zero_pos)) >>"$objdir/info/commit-graph" &&
corrupt_graph_verify "$grepstr"
}
test_expect_success POSIXPERM,SANITY 'detect permission problem' '
corrupt_graph_setup &&
chmod 000 $objdir/info/commit-graph &&
commit-graph write: don't die if the existing graph is corrupt When the commit-graph is written we end up calling parse_commit(). This will in turn invoke code that'll consult the existing commit-graph about the commit, if the graph is corrupted we die. We thus get into a state where a failing "commit-graph verify" can't be followed-up with a "commit-graph write" if core.commitGraph=true is set, the graph either needs to be manually removed to proceed, or core.commitGraph needs to be set to "false". Change the "commit-graph write" codepath to use a new parse_commit_no_graph() helper instead of parse_commit() to avoid this. The latter will call repo_parse_commit_internal() with use_commit_graph=1 as seen in 177722b344 ("commit: integrate commit graph with commit parsing", 2018-04-10). Not using the old graph at all slows down the writing of the new graph by some small amount, but is a sensible way to prevent an error in the existing commit-graph from spreading. Just fixing the current issue would be likely to result in code that's inadvertently broken in the future. New code might use the commit-graph at a distance. To detect such cases introduce a "GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD" setting used when we do our corruption tests, and test that a "write/verify" combo works after every one of our current test cases where we now detect commit-graph corruption. Some of the code changes here might be strictly unnecessary, e.g. I was unable to find cases where the parse_commit() called from write_graph_chunk_data() didn't exit early due to "item->object.parsed" being true in repo_parse_commit_internal() (before the use_commit_graph=1 has any effect). But let's also convert those cases for good measure, we do not have exhaustive tests for all possible types of commit-graph corruption. This might need to be re-visited if we learn to write the commit-graph incrementally, but probably not. Hopefully we'll just start by finding out what commits we have in total, then read the old graph(s) to see what they cover, and finally write a new graph file with everything that's missing. In that case the new graph writing code just needs to continue to use e.g. a parse_commit() that doesn't consult the existing commit-graphs. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-25 13:08:33 +01:00
corrupt_graph_verify "Could not open" "no-copy"
'
test_expect_success 'detect too small' '
corrupt_graph_setup &&
echo "a small graph" >$objdir/info/commit-graph &&
corrupt_graph_verify "too small"
'
test_expect_success 'detect bad signature' '
corrupt_graph_and_verify 0 "\0" \
"graph signature"
'
test_expect_success 'detect bad version' '
corrupt_graph_and_verify $GRAPH_BYTE_VERSION "\02" \
"graph version"
'
test_expect_success 'detect bad hash version' '
corrupt_graph_and_verify $GRAPH_BYTE_HASH "\02" \
"hash version"
'
test_expect_success 'detect low chunk count' '
corrupt_graph_and_verify $GRAPH_BYTE_CHUNK_COUNT "\02" \
"missing the .* chunk"
'
test_expect_success 'detect missing OID fanout chunk' '
corrupt_graph_and_verify $GRAPH_BYTE_OID_FANOUT_ID "\0" \
"missing the OID Fanout chunk"
'
test_expect_success 'detect missing OID lookup chunk' '
corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_ID "\0" \
"missing the OID Lookup chunk"
'
test_expect_success 'detect missing commit data chunk' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_DATA_ID "\0" \
"missing the Commit Data chunk"
'
test_expect_success 'detect incorrect fanout' '
corrupt_graph_and_verify $GRAPH_BYTE_FANOUT1 "\01" \
"fanout value"
'
test_expect_success 'detect incorrect fanout final value' '
corrupt_graph_and_verify $GRAPH_BYTE_FANOUT2 "\01" \
"fanout value"
'
test_expect_success 'detect incorrect OID order' '
corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_ORDER "\01" \
"incorrect OID order"
'
test_expect_success 'detect OID not in object database' '
corrupt_graph_and_verify $GRAPH_BYTE_OID_LOOKUP_MISSING "\01" \
"from object database"
'
test_expect_success 'detect incorrect tree OID' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_TREE "\01" \
"root tree OID for commit"
'
test_expect_success 'detect incorrect parent int-id' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_PARENT "\01" \
"invalid parent"
'
test_expect_success 'detect extra parent int-id' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_EXTRA_PARENT "\00" \
"is too long"
'
test_expect_success 'detect wrong parent' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_WRONG_PARENT "\01" \
"commit-graph parent for"
'
test_expect_success 'detect incorrect generation number' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_GENERATION "\070" \
"generation for commit"
'
test_expect_success 'detect incorrect generation number' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_GENERATION "\01" \
"non-zero generation number"
'
test_expect_success 'detect incorrect commit date' '
corrupt_graph_and_verify $GRAPH_BYTE_COMMIT_DATE "\01" \
"commit date"
'
test_expect_success 'detect incorrect parent for octopus merge' '
corrupt_graph_and_verify $GRAPH_BYTE_OCTOPUS "\01" \
"invalid parent"
'
test_expect_success 'detect invalid checksum hash' '
corrupt_graph_and_verify $GRAPH_BYTE_FOOTER "\00" \
"incorrect checksum"
'
test_expect_success 'detect incorrect chunk count' '
corrupt_graph_and_verify $GRAPH_BYTE_CHUNK_COUNT "\377" \
"chunk lookup table entry missing" $GRAPH_CHUNK_LOOKUP_OFFSET
'
test_expect_success 'git fsck (checks commit-graph)' '
cd "$TRASH_DIRECTORY/full" &&
git fsck &&
corrupt_graph_and_verify $GRAPH_BYTE_FOOTER "\00" \
"incorrect checksum" &&
commit-graph write: don't die if the existing graph is corrupt When the commit-graph is written we end up calling parse_commit(). This will in turn invoke code that'll consult the existing commit-graph about the commit, if the graph is corrupted we die. We thus get into a state where a failing "commit-graph verify" can't be followed-up with a "commit-graph write" if core.commitGraph=true is set, the graph either needs to be manually removed to proceed, or core.commitGraph needs to be set to "false". Change the "commit-graph write" codepath to use a new parse_commit_no_graph() helper instead of parse_commit() to avoid this. The latter will call repo_parse_commit_internal() with use_commit_graph=1 as seen in 177722b344 ("commit: integrate commit graph with commit parsing", 2018-04-10). Not using the old graph at all slows down the writing of the new graph by some small amount, but is a sensible way to prevent an error in the existing commit-graph from spreading. Just fixing the current issue would be likely to result in code that's inadvertently broken in the future. New code might use the commit-graph at a distance. To detect such cases introduce a "GIT_TEST_COMMIT_GRAPH_DIE_ON_LOAD" setting used when we do our corruption tests, and test that a "write/verify" combo works after every one of our current test cases where we now detect commit-graph corruption. Some of the code changes here might be strictly unnecessary, e.g. I was unable to find cases where the parse_commit() called from write_graph_chunk_data() didn't exit early due to "item->object.parsed" being true in repo_parse_commit_internal() (before the use_commit_graph=1 has any effect). But let's also convert those cases for good measure, we do not have exhaustive tests for all possible types of commit-graph corruption. This might need to be re-visited if we learn to write the commit-graph incrementally, but probably not. Hopefully we'll just start by finding out what commits we have in total, then read the old graph(s) to see what they cover, and finally write a new graph file with everything that's missing. In that case the new graph writing code just needs to continue to use e.g. a parse_commit() that doesn't consult the existing commit-graphs. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-03-25 13:08:33 +01:00
cp commit-graph-pre-write-test $objdir/info/commit-graph &&
test_must_fail git fsck
'
test_expect_success 'setup non-the_repository tests' '
rm -rf repo &&
git init repo &&
test_commit -C repo one &&
test_commit -C repo two &&
git -C repo config core.commitGraph true &&
git -C repo rev-parse two | \
git -C repo commit-graph write --stdin-commits
'
test_expect_success 'parse_commit_in_graph works for non-the_repository' '
test-tool repository parse_commit_in_graph \
repo/.git repo "$(git -C repo rev-parse two)" >actual &&
{
git -C repo log --pretty=format:"%ct " -1 &&
git -C repo rev-parse one
} >expect &&
test_cmp expect actual &&
test-tool repository parse_commit_in_graph \
repo/.git repo "$(git -C repo rev-parse one)" >actual &&
git -C repo log --pretty="%ct" -1 one >expect &&
test_cmp expect actual
'
test_expect_success 'get_commit_tree_in_graph works for non-the_repository' '
test-tool repository get_commit_tree_in_graph \
repo/.git repo "$(git -C repo rev-parse two)" >actual &&
git -C repo rev-parse two^{tree} >expect &&
test_cmp expect actual &&
test-tool repository get_commit_tree_in_graph \
repo/.git repo "$(git -C repo rev-parse one)" >actual &&
git -C repo rev-parse one^{tree} >expect &&
test_cmp expect actual
'
test_done