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>

diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index f8a461767ca44571193005e3c3d2fb74d775f9de..4223ff32fb69a1c8e498d0543a737dff44946640 100644 (file)
--- a/t/helper/test-read-graph.c
+++ b/t/helper/test-read-graph.c
@@ -45,6 +45,10 @@ int cmd__read_graph(int argc, const char **argv)
                printf(" commit_metadata");
        if (graph->chunk_extra_edges)
                printf(" extra_edges");
+       if (graph->chunk_bloom_indexes)
+               printf(" bloom_indexes");
+       if (graph->chunk_bloom_data)
+               printf(" bloom_data");
        printf("\n");
 
        UNLEAK(graph);

diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
new file mode 100755 (executable)
index 0000000..c7011f3
--- /dev/null
+++ b/t/t4216-log-bloom.sh
@@ -0,0 +1,155 @@
+#!/bin/sh
+
+test_description='git log for a path with Bloom filters'
+. ./test-lib.sh
+
+GIT_TEST_COMMIT_GRAPH=0
+GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=0
+
+test_expect_success 'setup test - repo, commits, commit graph, log outputs' '
+       git init &&
+       mkdir A A/B A/B/C &&
+       test_commit c1 A/file1 &&
+       test_commit c2 A/B/file2 &&
+       test_commit c3 A/B/C/file3 &&
+       test_commit c4 A/file1 &&
+       test_commit c5 A/B/file2 &&
+       test_commit c6 A/B/C/file3 &&
+       test_commit c7 A/file1 &&
+       test_commit c8 A/B/file2 &&
+       test_commit c9 A/B/C/file3 &&
+       test_commit c10 file_to_be_deleted &&
+       git checkout -b side HEAD~4 &&
+       test_commit side-1 file4 &&
+       git checkout master &&
+       git merge side &&
+       test_commit c11 file5 &&
+       mv file5 file5_renamed &&
+       git add file5_renamed &&
+       git commit -m "rename" &&
+       rm file_to_be_deleted &&
+       git add . &&
+       git commit -m "file removed" &&
+       git commit-graph write --reachable --changed-paths
+'
+graph_read_expect () {
+       NUM_CHUNKS=5
+       cat >expect <<- EOF
+       header: 43475048 1 1 $NUM_CHUNKS 0
+       num_commits: $1
+       chunks: oid_fanout oid_lookup commit_metadata bloom_indexes bloom_data
+       EOF
+       test-tool read-graph >actual &&
+       test_cmp expect actual
+}
+
+test_expect_success 'commit-graph write wrote out the bloom chunks' '
+       graph_read_expect 15
+'
+
+# Turn off any inherited trace2 settings for this test.
+sane_unset GIT_TRACE2 GIT_TRACE2_PERF GIT_TRACE2_EVENT
+sane_unset GIT_TRACE2_PERF_BRIEF
+sane_unset GIT_TRACE2_CONFIG_PARAMS
+
+setup () {
+       rm "$TRASH_DIRECTORY/trace.perf"
+       git -c core.commitGraph=false log --pretty="format:%s" $1 >log_wo_bloom &&
+       GIT_TRACE2_PERF="$TRASH_DIRECTORY/trace.perf" git -c core.commitGraph=true log --pretty="format:%s" $1 >log_w_bloom
+}
+
+test_bloom_filters_used () {
+       log_args=$1
+       bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"zero_length_filter\":0,\"maybe\""
+       setup "$log_args" &&
+       grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
+       test_cmp log_wo_bloom log_w_bloom &&
+    test_path_is_file "$TRASH_DIRECTORY/trace.perf"
+}
+
+test_bloom_filters_not_used () {
+       log_args=$1
+       setup "$log_args" &&
+       !(grep -q "statistics:{\"filter_not_present\":" "$TRASH_DIRECTORY/trace.perf") &&
+       test_cmp log_wo_bloom log_w_bloom
+}
+
+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
+do
+       for option in "" \
+             "--all" \
+                     "--full-history" \
+                     "--full-history --simplify-merges" \
+                     "--simplify-merges" \
+                     "--simplify-by-decoration" \
+                     "--follow" \
+                     "--first-parent" \
+                     "--topo-order" \
+                     "--date-order" \
+                     "--author-date-order" \
+                     "--ancestry-path side..master"
+       do
+               test_expect_success "git log option: $option for path: $path" '
+                       test_bloom_filters_used "$option -- $path"
+               '
+       done
+done
+
+test_expect_success 'git log -- folder works with and without the trailing slash' '
+       test_bloom_filters_used "-- A" &&
+       test_bloom_filters_used "-- A/"
+'
+
+test_expect_success 'git log for path that does not exist. ' '
+       test_bloom_filters_used "-- path_does_not_exist"
+'
+
+test_expect_success 'git log with --walk-reflogs does not use Bloom filters' '
+       test_bloom_filters_not_used "--walk-reflogs -- A"
+'
+
+test_expect_success 'git log -- multiple path specs does not use Bloom filters' '
+       test_bloom_filters_not_used "-- file4 A/file1"
+'
+
+test_expect_success 'git log with wildcard that resolves to a single path uses Bloom filters' '
+       test_bloom_filters_used "-- *4" &&
+       test_bloom_filters_used "-- *renamed"
+'
+
+test_expect_success 'git log with wildcard that resolves to a multiple paths does not uses Bloom filters' '
+       test_bloom_filters_not_used "-- *" &&
+       test_bloom_filters_not_used "-- file*"
+'
+
+test_expect_success 'setup - add commit-graph to the chain without Bloom filters' '
+       test_commit c14 A/anotherFile2 &&
+       test_commit c15 A/B/anotherFile2 &&
+       test_commit c16 A/B/C/anotherFile2 &&
+       GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS=0 git commit-graph write --reachable --split &&
+       test_line_count = 2 .git/objects/info/commit-graphs/commit-graph-chain
+'
+
+test_expect_success 'Do not use Bloom filters if the latest graph does not have Bloom filters.' '
+       test_bloom_filters_not_used "-- A/B"
+'
+
+test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
+       test_commit c17 A/anotherFile3 &&
+       git commit-graph write --reachable --changed-paths --split &&
+       test_line_count = 3 .git/objects/info/commit-graphs/commit-graph-chain
+'
+
+test_bloom_filters_used_when_some_filters_are_missing () {
+       log_args=$1
+       bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"zero_length_filter\":0,\"maybe\":8,\"definitely_not\":6"
+       setup "$log_args" &&
+       grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
+       test_cmp log_wo_bloom log_w_bloom
+}
+
+test_expect_success 'Use Bloom filters if they exist in the latest but not all commit graphs in the chain.' '
+       test_bloom_filters_used_when_some_filters_are_missing "-- A/B"
+'
+
+test_done
\ No newline at end of file