diff mbox series

[v3,05/11] reftable/dump: support dumping a table's block structure

Message ID c4377180ef9c92a28fa71b1cde90d80d901c8710.1715587849.git.ps@pks.im (mailing list archive)
State Accepted
Commit fcf341890ef583f519bc2746940c048bb8261d3d
Headers show
Series reftable: expose write options as config | expand

Commit Message

Patrick Steinhardt May 13, 2024, 8:18 a.m. UTC
We're about to introduce new configs that will allow users to have more
control over how exactly reftables are written. To verify that these
configs are effective we will need to take a peak into the actual blocks
written by the reftable backend.

Introduce a new mode to the dumping logic that prints out the block
structure. This logic can be invoked via `test-tool dump-reftables -b`.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 reftable/dump.c                   |   8 ++-
 reftable/reader.c                 |  63 ++++++++++++++++++
 reftable/reftable-reader.h        |   2 +
 t/t0613-reftable-write-options.sh | 102 ++++++++++++++++++++++++++++++
 4 files changed, 174 insertions(+), 1 deletion(-)
 create mode 100755 t/t0613-reftable-write-options.sh

Comments

Justin Tobler May 21, 2024, 11:35 p.m. UTC | #1
On 24/05/13 10:18AM, Patrick Steinhardt wrote:
> +int reftable_reader_print_blocks(const char *tablename)
> +{
> +	struct {
> +		const char *name;
> +		int type;
> +	} sections[] = {
> +		{
> +			.name = "ref",
> +			.type = BLOCK_TYPE_REF,
> +		},
> +		{
> +			.name = "obj",
> +			.type = BLOCK_TYPE_OBJ,
> +		},
> +		{
> +			.name = "log",
> +			.type = BLOCK_TYPE_LOG,
> +		},
> +	};

I noticed that we are not including all the block types. Would we ever
want to also be able to dump index blocks? Or would they not be useful
in this context?

-Justin
Patrick Steinhardt May 22, 2024, 7:19 a.m. UTC | #2
On Tue, May 21, 2024 at 06:35:13PM -0500, Justin Tobler wrote:
> On 24/05/13 10:18AM, Patrick Steinhardt wrote:
> > +int reftable_reader_print_blocks(const char *tablename)
> > +{
> > +	struct {
> > +		const char *name;
> > +		int type;
> > +	} sections[] = {
> > +		{
> > +			.name = "ref",
> > +			.type = BLOCK_TYPE_REF,
> > +		},
> > +		{
> > +			.name = "obj",
> > +			.type = BLOCK_TYPE_OBJ,
> > +		},
> > +		{
> > +			.name = "log",
> > +			.type = BLOCK_TYPE_LOG,
> > +		},
> > +	};
> 
> I noticed that we are not including all the block types. Would we ever
> want to also be able to dump index blocks? Or would they not be useful
> in this context?

Maybe. It wasn't really necessary to include index blocks in this
context as I was already able to extract all relevant information
without them. So I decided to skip them. We may iterate on this in the
future as required.

Patrick
diff mbox series

Patch

diff --git a/reftable/dump.c b/reftable/dump.c
index 586f3eb288..41abbb8ecf 100644
--- a/reftable/dump.c
+++ b/reftable/dump.c
@@ -48,6 +48,7 @@  static void print_help(void)
 	printf("usage: dump [-cst] arg\n\n"
 	       "options: \n"
 	       "  -c compact\n"
+	       "  -b dump blocks\n"
 	       "  -t dump table\n"
 	       "  -s dump stack\n"
 	       "  -6 sha256 hash format\n"
@@ -58,6 +59,7 @@  static void print_help(void)
 int reftable_dump_main(int argc, char *const *argv)
 {
 	int err = 0;
+	int opt_dump_blocks = 0;
 	int opt_dump_table = 0;
 	int opt_dump_stack = 0;
 	int opt_compact = 0;
@@ -67,6 +69,8 @@  int reftable_dump_main(int argc, char *const *argv)
 	for (; argc > 1; argv++, argc--)
 		if (*argv[1] != '-')
 			break;
+		else if (!strcmp("-b", argv[1]))
+			opt_dump_blocks = 1;
 		else if (!strcmp("-t", argv[1]))
 			opt_dump_table = 1;
 		else if (!strcmp("-6", argv[1]))
@@ -88,7 +92,9 @@  int reftable_dump_main(int argc, char *const *argv)
 
 	arg = argv[1];
 
-	if (opt_dump_table) {
+	if (opt_dump_blocks) {
+		err = reftable_reader_print_blocks(arg);
+	} else if (opt_dump_table) {
 		err = reftable_reader_print_file(arg);
 	} else if (opt_dump_stack) {
 		err = reftable_stack_print_directory(arg, opt_hash_id);
diff --git a/reftable/reader.c b/reftable/reader.c
index 481dff10d4..f23c8523db 100644
--- a/reftable/reader.c
+++ b/reftable/reader.c
@@ -856,3 +856,66 @@  int reftable_reader_print_file(const char *tablename)
 	reftable_reader_free(r);
 	return err;
 }
+
+int reftable_reader_print_blocks(const char *tablename)
+{
+	struct {
+		const char *name;
+		int type;
+	} sections[] = {
+		{
+			.name = "ref",
+			.type = BLOCK_TYPE_REF,
+		},
+		{
+			.name = "obj",
+			.type = BLOCK_TYPE_OBJ,
+		},
+		{
+			.name = "log",
+			.type = BLOCK_TYPE_LOG,
+		},
+	};
+	struct reftable_block_source src = { 0 };
+	struct table_iter ti = TABLE_ITER_INIT;
+	struct reftable_reader *r = NULL;
+	size_t i;
+	int err;
+
+	err = reftable_block_source_from_file(&src, tablename);
+	if (err < 0)
+		goto done;
+
+	err = reftable_new_reader(&r, &src, tablename);
+	if (err < 0)
+		goto done;
+
+	printf("header:\n");
+	printf("  block_size: %d\n", r->block_size);
+
+	for (i = 0; i < ARRAY_SIZE(sections); i++) {
+		err = reader_start(r, &ti, sections[i].type, 0);
+		if (err < 0)
+			goto done;
+		if (err > 0)
+			continue;
+
+		printf("%s:\n", sections[i].name);
+
+		while (1) {
+			printf("  - length: %u\n", ti.br.block_len);
+			printf("    restarts: %u\n", ti.br.restart_count);
+
+			err = table_iter_next_block(&ti);
+			if (err < 0)
+				goto done;
+			if (err > 0)
+				break;
+		}
+	}
+
+done:
+	reftable_reader_free(r);
+	table_iter_close(&ti);
+	return err;
+}
diff --git a/reftable/reftable-reader.h b/reftable/reftable-reader.h
index 4a4bc2fdf8..4a04857773 100644
--- a/reftable/reftable-reader.h
+++ b/reftable/reftable-reader.h
@@ -97,5 +97,7 @@  void reftable_table_from_reader(struct reftable_table *tab,
 
 /* print table onto stdout for debugging. */
 int reftable_reader_print_file(const char *tablename);
+/* print blocks onto stdout for debugging. */
+int reftable_reader_print_blocks(const char *tablename);
 
 #endif
diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh
new file mode 100755
index 0000000000..462980c37c
--- /dev/null
+++ b/t/t0613-reftable-write-options.sh
@@ -0,0 +1,102 @@ 
+#!/bin/sh
+
+test_description='reftable write options'
+
+GIT_TEST_DEFAULT_REF_FORMAT=reftable
+export GIT_TEST_DEFAULT_REF_FORMAT
+# Disable auto-compaction for all tests as we explicitly control repacking of
+# refs.
+GIT_TEST_REFTABLE_AUTOCOMPACTION=false
+export GIT_TEST_REFTABLE_AUTOCOMPACTION
+# Block sizes depend on the hash function, so we force SHA1 here.
+GIT_TEST_DEFAULT_HASH=sha1
+export GIT_TEST_DEFAULT_HASH
+# Block sizes also depend on the actual refs we write, so we force "master" to
+# be the default initial branch name.
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+
+test_expect_success 'default write options' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit initial &&
+		git pack-refs &&
+		cat >expect <<-EOF &&
+		header:
+		  block_size: 4096
+		ref:
+		  - length: 129
+		    restarts: 2
+		log:
+		  - length: 262
+		    restarts: 2
+		EOF
+		test-tool dump-reftable -b .git/reftable/*.ref >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'disabled reflog writes no log blocks' '
+	test_config_global core.logAllRefUpdates false &&
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit initial &&
+		git pack-refs &&
+		cat >expect <<-EOF &&
+		header:
+		  block_size: 4096
+		ref:
+		  - length: 129
+		    restarts: 2
+		EOF
+		test-tool dump-reftable -b .git/reftable/*.ref >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'many refs results in multiple blocks' '
+	test_when_finished "rm -rf repo" &&
+	git init repo &&
+	(
+		cd repo &&
+		test_commit initial &&
+		for i in $(test_seq 200)
+		do
+			printf "update refs/heads/branch-%d HEAD\n" "$i" ||
+			return 1
+		done >input &&
+		git update-ref --stdin <input &&
+		git pack-refs &&
+
+		cat >expect <<-EOF &&
+		header:
+		  block_size: 4096
+		ref:
+		  - length: 4049
+		    restarts: 11
+		  - length: 1136
+		    restarts: 3
+		log:
+		  - length: 4041
+		    restarts: 4
+		  - length: 4015
+		    restarts: 3
+		  - length: 4014
+		    restarts: 3
+		  - length: 4012
+		    restarts: 3
+		  - length: 3289
+		    restarts: 3
+		EOF
+		test-tool dump-reftable -b .git/reftable/*.ref >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_done