git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Garima Singh via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: stolee@gmail.com, szeder.dev@gmail.com, jonathantanmy@google.com,
	Garima Singh <garima.singh@microsoft.com>,
	Garima Singh <garima.singh@microsoft.com>
Subject: [PATCH v3 15/16] t4216: add end to end tests for git log with Bloom filters
Date: Mon, 30 Mar 2020 00:31:37 +0000	[thread overview]
Message-ID: <3019ef72881289589d5b76c8c0c8177a2c464972.1585528299.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.497.v3.git.1585528298.gitgitgadget@gmail.com>

From: Garima Singh <garima.singh@microsoft.com>

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>
---
 t/helper/test-read-graph.c |   4 +
 t/t4216-log-bloom.sh       | 155 +++++++++++++++++++++++++++++++++++++
 2 files changed, 159 insertions(+)
 create mode 100755 t/t4216-log-bloom.sh

diff --git a/t/helper/test-read-graph.c b/t/helper/test-read-graph.c
index f8a461767ca..4223ff32fb6 100644
--- 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
index 00000000000..38accd272df
--- /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
-- 
gitgitgadget


  parent reply	other threads:[~2020-03-30  0:31 UTC|newest]

Thread overview: 159+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-20 22:05 [PATCH 0/9] [RFC] Changed Paths Bloom Filters Garima Singh via GitGitGadget
2019-12-20 22:05 ` [PATCH 1/9] commit-graph: add --changed-paths option to write Garima Singh via GitGitGadget
2020-01-01 20:20   ` Jakub Narebski
2019-12-20 22:05 ` [PATCH 2/9] commit-graph: write changed paths bloom filters Garima Singh via GitGitGadget
2019-12-21 16:48   ` Philip Oakley
2020-01-06 18:44   ` Jakub Narebski
2020-01-13 19:48     ` Garima Singh
2019-12-20 22:05 ` [PATCH 3/9] commit-graph: use MAX_NUM_CHUNKS Garima Singh via GitGitGadget
2020-01-07 12:19   ` Jakub Narebski
2019-12-20 22:05 ` [PATCH 4/9] commit-graph: document bloom filter format Garima Singh via GitGitGadget
2020-01-07 14:46   ` Jakub Narebski
2019-12-20 22:05 ` [PATCH 5/9] commit-graph: write changed path bloom filters to commit-graph file Garima Singh via GitGitGadget
2020-01-07 16:01   ` Jakub Narebski
2020-01-14 15:14     ` Garima Singh
2019-12-20 22:05 ` [PATCH 6/9] commit-graph: test commit-graph write --changed-paths Garima Singh via GitGitGadget
2020-01-08  0:32   ` Jakub Narebski
2019-12-20 22:05 ` [PATCH 7/9] commit-graph: reuse existing bloom filters during write Garima Singh via GitGitGadget
2020-01-09 19:12   ` Jakub Narebski
2019-12-20 22:05 ` [PATCH 8/9] revision.c: use bloom filters to speed up path based revision walks Garima Singh via GitGitGadget
2020-01-11  0:27   ` Jakub Narebski
2020-01-15  0:08     ` Garima Singh
2019-12-20 22:05 ` [PATCH 9/9] commit-graph: add GIT_TEST_COMMIT_GRAPH_BLOOM_FILTERS test flag Garima Singh via GitGitGadget
2020-01-11 19:56   ` Jakub Narebski
2020-01-15  0:55     ` Garima Singh
2019-12-20 22:14 ` [PATCH 0/9] [RFC] Changed Paths Bloom Filters Junio C Hamano
2019-12-22  9:26 ` Christian Couder
2019-12-22  9:38   ` Jeff King
2020-01-01 12:04     ` Jakub Narebski
2019-12-22  9:30 ` Jeff King
2019-12-22  9:32   ` [PATCH 1/3] commit-graph: examine changed-path objects in pack order Jeff King
2019-12-27 14:51     ` Derrick Stolee
2019-12-29  6:12       ` Jeff King
2019-12-29  6:28         ` Jeff King
2019-12-30 14:37         ` Derrick Stolee
2019-12-30 14:51           ` Derrick Stolee
2019-12-22  9:32   ` [PATCH 2/3] commit-graph: free large diffs, too Jeff King
2019-12-27 14:52     ` Derrick Stolee
2019-12-22  9:32   ` [PATCH 3/3] commit-graph: stop using full rev_info for diffs Jeff King
2019-12-27 14:53     ` Derrick Stolee
2019-12-26 14:21   ` [PATCH 0/9] [RFC] Changed Paths Bloom Filters Derrick Stolee
2019-12-29  6:03     ` Jeff King
2019-12-27 16:11   ` Derrick Stolee
2019-12-29  6:24     ` Jeff King
2019-12-30 16:04       ` Derrick Stolee
2019-12-30 17:02       ` Junio C Hamano
2019-12-31 16:45 ` Jakub Narebski
2020-01-13 16:54   ` Garima Singh
2020-01-20 13:48     ` Jakub Narebski
2020-01-21 16:14       ` Garima Singh
2020-02-02 18:43         ` Jakub Narebski
2020-01-21 23:40 ` Emily Shaffer
2020-01-27 18:24   ` Garima Singh
2020-02-01 23:32   ` Jakub Narebski
2020-02-05 22:56 ` [PATCH v2 00/11] " Garima Singh via GitGitGadget
2020-02-05 22:56   ` [PATCH v2 01/11] commit-graph: use MAX_NUM_CHUNKS Garima Singh via GitGitGadget
2020-02-09 12:39     ` Jakub Narebski
2020-02-05 22:56   ` [PATCH v2 02/11] bloom: core Bloom filter implementation for changed paths Garima Singh via GitGitGadget
2020-02-15 17:17     ` Jakub Narebski
2020-02-16 16:49     ` Jakub Narebski
2020-02-22  0:32       ` Garima Singh
2020-02-23 13:38         ` Jakub Narebski
2020-02-24 17:34           ` Garima Singh
2020-02-24 18:20             ` Jakub Narebski
2020-02-05 22:56   ` [PATCH v2 03/11] diff: halt tree-diff early after max_changes Derrick Stolee via GitGitGadget
2020-02-17  0:00     ` Jakub Narebski
2020-02-22  0:37       ` Garima Singh
2020-02-05 22:56   ` [PATCH v2 04/11] commit-graph: compute Bloom filters for changed paths Garima Singh via GitGitGadget
2020-02-17 21:56     ` Jakub Narebski
2020-02-22  0:55       ` Garima Singh
2020-02-23 17:34         ` Jakub Narebski
2020-02-05 22:56   ` [PATCH v2 05/11] commit-graph: examine changed-path objects in pack order Jeff King via GitGitGadget
2020-02-18 17:59     ` Jakub Narebski
2020-02-24 18:29       ` Garima Singh
2020-02-05 22:56   ` [PATCH v2 06/11] commit-graph: examine commits by generation number Derrick Stolee via GitGitGadget
2020-02-19  0:32     ` Jakub Narebski
2020-02-24 20:45       ` Garima Singh
2020-02-05 22:56   ` [PATCH v2 07/11] commit-graph: write Bloom filters to commit graph file Garima Singh via GitGitGadget
2020-02-19 15:13     ` Jakub Narebski
2020-02-24 21:14       ` Garima Singh
2020-02-25 11:40         ` Jakub Narebski
2020-02-25 15:58           ` Garima Singh
2020-02-05 22:56   ` [PATCH v2 08/11] commit-graph: reuse existing Bloom filters during write Garima Singh via GitGitGadget
2020-02-20 18:48     ` Jakub Narebski
2020-02-24 21:45       ` Garima Singh
2020-02-05 22:56   ` [PATCH v2 09/11] commit-graph: add --changed-paths option to write subcommand Garima Singh via GitGitGadget
2020-02-20 20:28     ` Jakub Narebski
2020-02-24 21:51       ` Garima Singh
2020-02-25 12:10         ` Jakub Narebski
2020-02-20 22:10     ` Bryan Turner
2020-02-22  1:44       ` Garima Singh
2020-02-05 22:56   ` [PATCH v2 10/11] revision.c: use Bloom filters to speed up path based revision walks Garima Singh via GitGitGadget
2020-02-21 17:31     ` Jakub Narebski
2020-02-21 22:45     ` Jakub Narebski
2020-02-05 22:56   ` [PATCH v2 11/11] commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag Garima Singh via GitGitGadget
2020-02-22  0:11     ` Jakub Narebski
2020-02-07 13:52   ` [PATCH v2 00/11] Changed Paths Bloom Filters SZEDER Gábor
2020-02-07 15:09     ` Garima Singh
2020-02-07 15:36       ` Derrick Stolee
2020-02-07 16:15         ` SZEDER Gábor
2020-02-07 16:33           ` Derrick Stolee
2020-02-11 19:08       ` Garima Singh
2020-02-08 23:04   ` Jakub Narebski
2020-02-21 17:41     ` Garima Singh
2020-03-29 18:36       ` Junio C Hamano
2020-03-30  0:31   ` [PATCH v3 00/16] " Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 01/16] commit-graph: define and use MAX_NUM_CHUNKS Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 02/16] bloom.c: add the murmur3 hash implementation Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 03/16] bloom.c: introduce core Bloom filter constructs Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 04/16] bloom.c: core Bloom filter implementation for changed paths Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 05/16] diff: halt tree-diff early after max_changes Derrick Stolee via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 06/16] commit-graph: compute Bloom filters for changed paths Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 07/16] commit-graph: examine changed-path objects in pack order Jeff King via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 08/16] commit-graph: examine commits by generation number Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 09/16] diff: skip batch object download when possible Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 10/16] commit-graph: write Bloom filters to commit graph file Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 11/16] commit-graph: reuse existing Bloom filters during write Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 12/16] commit-graph: add --changed-paths option to write subcommand Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 13/16] revision.c: use Bloom filters to speed up path based revision walks Garima Singh via GitGitGadget
2020-03-30  0:31     ` [PATCH v3 14/16] revision.c: add trace2 stats around Bloom filter usage Garima Singh via GitGitGadget
2020-03-30  0:31     ` Garima Singh via GitGitGadget [this message]
2020-03-30  0:31     ` [PATCH v3 16/16] commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag Garima Singh via GitGitGadget
2020-04-06 16:59     ` [PATCH v4 00/15] Changed Paths Bloom Filters Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 01/15] commit-graph: define and use MAX_NUM_CHUNKS Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 02/15] bloom.c: add the murmur3 hash implementation Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 03/15] bloom.c: introduce core Bloom filter constructs Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 04/15] bloom.c: core Bloom filter implementation for changed paths Garima Singh via GitGitGadget
2020-06-27 15:53         ` SZEDER Gábor
2020-04-06 16:59       ` [PATCH v4 05/15] diff: halt tree-diff early after max_changes Derrick Stolee via GitGitGadget
2020-08-04 14:47         ` SZEDER Gábor
2020-08-04 16:25           ` Derrick Stolee
2020-08-04 17:00             ` SZEDER Gábor
2020-08-04 17:31               ` Derrick Stolee
2020-08-05 17:08                 ` Derrick Stolee
2020-04-06 16:59       ` [PATCH v4 06/15] commit-graph: compute Bloom filters for changed paths Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 07/15] commit-graph: examine changed-path objects in pack order Jeff King via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 08/15] commit-graph: examine commits by generation number Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 09/15] commit-graph: write Bloom filters to commit graph file Garima Singh via GitGitGadget
2020-05-29  8:57         ` SZEDER Gábor
2020-05-29 13:35           ` Derrick Stolee
2020-05-31 17:23             ` SZEDER Gábor
2020-07-09 17:00         ` [PATCH] commit-graph: fix "Writing out commit graph" progress counter SZEDER Gábor
2020-07-09 18:01           ` Derrick Stolee
2020-07-09 18:20             ` Derrick Stolee
2020-04-06 16:59       ` [PATCH v4 10/15] commit-graph: reuse existing Bloom filters during write Garima Singh via GitGitGadget
2020-06-19 14:02         ` SZEDER Gábor
2020-06-19 19:28           ` Junio C Hamano
2020-07-27 21:33         ` SZEDER Gábor
2020-04-06 16:59       ` [PATCH v4 11/15] commit-graph: add --changed-paths option to write subcommand Garima Singh via GitGitGadget
2020-06-07 22:21         ` SZEDER Gábor
2020-04-06 16:59       ` [PATCH v4 12/15] revision.c: use Bloom filters to speed up path based revision walks Garima Singh via GitGitGadget
2020-06-26  6:34         ` SZEDER Gábor
2020-04-06 16:59       ` [PATCH v4 13/15] revision.c: add trace2 stats around Bloom filter usage Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 14/15] t4216: add end to end tests for git log with Bloom filters Garima Singh via GitGitGadget
2020-04-06 16:59       ` [PATCH v4 15/15] commit-graph: add GIT_TEST_COMMIT_GRAPH_CHANGED_PATHS test flag Garima Singh via GitGitGadget
2020-04-08 15:51       ` [PATCH v4 00/15] Changed Paths Bloom Filters Derrick Stolee
2020-04-08 19:21         ` Junio C Hamano
2020-04-08 20:05         ` Jakub Narębski
2020-04-12 20:34         ` Taylor Blau
2020-03-05 19:49 ` [PATCH 0/9] [RFC] " Garima Singh

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3019ef72881289589d5b76c8c0c8177a2c464972.1585528299.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=garima.singh@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=jonathantanmy@google.com \
    --cc=stolee@gmail.com \
    --cc=szeder.dev@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).