t4216: add end to end tests for git log with Bloom filters
These tests exercises writing commit graph with Bloom filters and exercises 'git log -- path' with all the applicable options. They check that the output is the same with and without Bloom filters, confirm Bloom filters were used by checking if trace2 statistics were logged correctly. Also confirms cases where Bloom filters are not used: 1. Multiple path specs, 2. --walk-reflogs (see patch titled 'revision.c: use Bloom filters...' for details, 3. If the latest commit graph does not have Bloom filters Signed-off-by: Garima Singh <garima.singh@microsoft.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Garima Singh committed
Apr 6, 2020 at 16:59 UTC
a759bfa9eeb2a080d7c5c0a3c4096db5438c06bf
2 files changed
+159
t/helper/test-read-graph.c
+4
@@ -45,6 +45,10 @@ int cmd__read_graph(int argc, const char **argv)
45
printf(" commit_metadata");
46
if (graph->chunk_extra_edges)
47
printf(" extra_edges");
48
+ if (graph->chunk_bloom_indexes)
49
+ printf(" bloom_indexes");
50
+ if (graph->chunk_bloom_data)
51
+ printf(" bloom_data");
52
printf("\n");
53
54
UNLEAK(graph);
t/t4216-log-bloom.sh
new
+155
@@ -0,0 +1,155 @@
1
+#!/bin/sh
2
+
3
+test_description='git log for a path with Bloom filters'
4
+. ./test-lib.sh
5
+
6
+GIT_TEST_COMMIT_GRAPH=0
7
+GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=0
8
+
9
+test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
10
+ git init &&
11
+ mkdir A A/B A/B/C &&
12
+ test_commit c1 A/file1 &&
13
+ test_commit c2 A/B/file2 &&
14
+ test_commit c3 A/B/C/file3 &&
15
+ test_commit c4 A/file1 &&
16
+ test_commit c5 A/B/file2 &&
17
+ test_commit c6 A/B/C/file3 &&
18
+ test_commit c7 A/file1 &&
19
+ test_commit c8 A/B/file2 &&
20
+ test_commit c9 A/B/C/file3 &&
21
+ test_commit c10 file_to_be_deleted &&
22
+ git checkout -b side HEAD~4 &&
23
+ test_commit side-1 file4 &&
24
+ git checkout master &&
25
+ git merge side &&
26
+ test_commit c11 file5 &&
27
+ mv file5 file5_renamed &&
28
+ git add file5_renamed &&
29
+ git commit -m "rename" &&
30
+ rm file_to_be_deleted &&
31
+ git add . &&
32
+ git commit -m "file removed" &&
33
+ git commit-graph write --reachable --changed-paths
34
+'
35
+graph_read_expect () {
36
+ NUM_CHUNKS=5
37
+ cat >expect <<- EOF
38
+ header: 43475048 1 1 $NUM_CHUNKS 0
39
+ num_commits: $1
40
+ chunks: oid_fanout oid_lookup commit_metadata bloom_indexes bloom_data
41
+ EOF
42
+ test-tool read-graph >actual &&
43
+ test_cmp expect actual
44
+}
45
+
46
+test_expect_success 'commit-graph write wrote out the bloom chunks' '
47
+ graph_read_expect 15
48
+'
49
+
50
+# Turn off any inherited trace2 settings for this test.
51
+sane_unset GIT_TRACE2 GIT_TRACE2_PERF GIT_TRACE2_EVENT
52
+sane_unset GIT_TRACE2_PERF_BRIEF
53
+sane_unset GIT_TRACE2_CONFIG_PARAMS
54
+
55
+setup () {
56
+ rm "$TRASH_DIRECTORY/trace.perf"
57
+ git -c core.commitGraph=false log --pretty="format:%s" $1 >log_wo_bloom &&
58
+ GIT_TRACE2_PERF="$TRASH_DIRECTORY/trace.perf" git -c core.commitGraph=true log --pretty="format:%s" $1 >log_w_bloom
59
+}
60
+
61
+test_bloom_filters_used () {
62
+ log_args=$1
63
+ bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"zero_length_filter\":0,\"maybe\""
64
+ setup "$log_args" &&
65
+ grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
66
+ test_cmp log_wo_bloom log_w_bloom &&
67
+ test_path_is_file "$TRASH_DIRECTORY/trace.perf"
68
+}
69
+
70
+test_bloom_filters_not_used () {
71
+ log_args=$1
72
+ setup "$log_args" &&
73
+ !(grep -q "statistics:{\"filter_not_present\":" "$TRASH_DIRECTORY/trace.perf") &&
74
+ test_cmp log_wo_bloom log_w_bloom
75
+}
76
+
77
+for path in A A/B A/B/C A/file1 A/B/file2 A/B/C/file3 file4 file5 file5_renamed file_to_be_deleted
78
+do
79
+ for option in "" \
80
+ "--all" \
81
+ "--full-history" \
82
+ "--full-history --simplify-merges" \
83
+ "--simplify-merges" \
84
+ "--simplify-by-decoration" \
85
+ "--follow" \
86
+ "--first-parent" \
87
+ "--topo-order" \
88
+ "--date-order" \
89
+ "--author-date-order" \
90
+ "--ancestry-path side..master"
91
+ do
92
+ test_expect_success "git log option: $option for path: $path" '
93
+ test_bloom_filters_used "$option -- $path"
94
+ '
95
+ done
96
+done
97
+
98
+test_expect_success 'git log -- folder works with and without the trailing slash' '
99
+ test_bloom_filters_used "-- A" &&
100
+ test_bloom_filters_used "-- A/"
101
+'
102
+
103
+test_expect_success 'git log for path that does not exist. ' '
104
+ test_bloom_filters_used "-- path_does_not_exist"
105
+'
106
+
107
+test_expect_success 'git log with --walk-reflogs does not use Bloom filters' '
108
+ test_bloom_filters_not_used "--walk-reflogs -- A"
109
+'
110
+
111
+test_expect_success 'git log -- multiple path specs does not use Bloom filters' '
112
+ test_bloom_filters_not_used "-- file4 A/file1"
113
+'
114
+
115
+test_expect_success 'git log with wildcard that resolves to a single path uses Bloom filters' '
116
+ test_bloom_filters_used "-- *4" &&
117
+ test_bloom_filters_used "-- *renamed"
118
+'
119
+
120
+test_expect_success 'git log with wildcard that resolves to a multiple paths does not uses Bloom filters' '
121
+ test_bloom_filters_not_used "-- *" &&
122
+ test_bloom_filters_not_used "-- file*"
123
+'
124
+
125
+test_expect_success 'setup - add commit-graph to the chain without Bloom filters' '
126
+ test_commit c14 A/anotherFile2 &&
127
+ test_commit c15 A/B/anotherFile2 &&
128
+ test_commit c16 A/B/C/anotherFile2 &&
129
+ GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=0 git commit-graph write --reachable --split &&
130
+ test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
131
+'
132
+
133
+test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
134
+ test_bloom_filters_not_used "-- A/B"
135
+'
136
+
137
+test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
138
+ test_commit c17 A/anotherFile3 &&
139
+ git commit-graph write --reachable --changed-paths --split &&
140
+ test_line_count = 3 .git/objects/info/commit-graphs/commit-graph-chain
141
+'
142
+
143
+test_bloom_filters_used_when_some_filters_are_missing () {
144
+ log_args=$1
145
+ bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"zero_length_filter\":0,\"maybe\":8,\"definitely_not\":6"
146
+ setup "$log_args" &&
147
+ grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
148
+ test_cmp log_wo_bloom log_w_bloom
149
+}
150
+
151
+test_expect_success 'Use Bloom filters if they exist in the latest but not all commit graphs in the chain.' '
152
+ test_bloom_filters_used_when_some_filters_are_missing "-- A/B"
153
+'
154
+
155
+test_done
\ No newline at end of file