* [PATCH GSoC v14 13/13] cat-file: make remote-object-info allow-list dynamic
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
The static allow-list in expand_atom() is hardcoded to only allow
"objectname" and "objectsize" for remote queries. This works because
up to this point all servers will either support object-info with name
and size or they do not support them at all, but we cannot expect that
in a future different servers with different git versions to have the
same object-info capabilities. Therefore, the allow_list needs to be
dynamic depending on what the server advertises.
The client will now:
1. Request the protocol option that the placeholder refers to (i.e.
"size" when "%(objectsize)").
2. Filters the request in fetch_object_info() dropping any option that
the server does not advertise.
3. After the fetching, the options that haven't been dropped are the ones
fetched and supported by the server, these supported options are
mapped and remote_allowed_atoms is populated with the placeholders.
4. expand_atom() checks remote_allowed_atoms with the same behaviour as
the static allow_list had.
Move object_info_options out of get_remote_info so the caller which has
data can select what options will be requested instead of requesting
always size.
Move batch_object_write() out so there will always be an output even if
all the placeholders are not supported by the server (returns an empty
line).
Include "type" in the object_info_options so once the server supports
it, the clients know already how to request it.
Mentored-by: Karthik Nayak <karthik.188@gmail.com>
Mentored-by: Chandra Pratap <chandrapratap3519@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
builtin/cat-file.c | 97 +++++++++++++++++++++++++++++++++++------------------
fetch-object-info.c | 20 +++++++++++
2 files changed, 84 insertions(+), 33 deletions(-)
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index ea3869f3ed..86e4f78eb6 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -338,13 +338,11 @@ struct expand_data {
* Flags about when an object info is being fetched from remote.
*/
unsigned is_remote:1;
-};
-#define EXPAND_DATA_INIT { .mode = S_IFINVALID, .type = OBJ_BAD }
-static const char *remote_object_info_atoms[] = {
- "objectname",
- "objectsize",
+ struct string_list remote_allowed_atoms;
};
+#define EXPAND_DATA_INIT { .mode = S_IFINVALID, .type = OBJ_BAD, \
+ .remote_allowed_atoms = STRING_LIST_INIT_NODUP }
static int is_atom(const char *atom, const char *s, int slen)
{
@@ -356,17 +354,11 @@ static int expand_atom(struct strbuf *sb, const char *atom, int len,
struct expand_data *data)
{
if (data->is_remote) {
- size_t i, allowed_nr = ARRAY_SIZE(remote_object_info_atoms);
- for (i = 0; i < allowed_nr; i++)
- if (is_atom(remote_object_info_atoms[i], atom, len))
+ size_t i;
+ for (i = 0; i < data->remote_allowed_atoms.nr; i++)
+ if (is_atom(data->remote_allowed_atoms.items[i].string, atom, len))
break;
-
- /*
- * On remote, skip unsupported atoms returning an empty sb,
- * honoring how for-each-ref handles known but inapplicable
- * atoms (e.g. %(tagger)).
- */
- if (i == allowed_nr)
+ if (i == data->remote_allowed_atoms.nr)
return 1;
}
@@ -680,12 +672,12 @@ static int get_remote_info(struct batch_options *opt,
int argc,
const char **argv,
struct object_info **remote_object_info,
- struct oid_array *object_info_oids)
+ struct oid_array *object_info_oids,
+ struct string_list *object_info_options)
{
int retval = 0;
struct remote *remote = NULL;
struct object_id oid;
- struct string_list object_info_options = STRING_LIST_INIT_NODUP;
struct transport *gtransport;
/*
@@ -734,15 +726,12 @@ static int get_remote_info(struct batch_options *opt,
gtransport->smart_options->object_info = 1;
gtransport->smart_options->object_info_oids = object_info_oids;
- string_list_append(&object_info_options, "size");
-
- if (object_info_options.nr > 0) {
- gtransport->smart_options->object_info_options = &object_info_options;
+ if (object_info_options->nr > 0) {
+ gtransport->smart_options->object_info_options = object_info_options;
gtransport->smart_options->object_info_data = *remote_object_info;
retval = transport_fetch_refs(gtransport, NULL);
}
cleanup:
- string_list_clear(&object_info_options, 0);
transport_disconnect(gtransport);
return retval;
}
@@ -828,6 +817,21 @@ static void parse_cmd_mailmap(struct batch_options *opt UNUSED,
load_mailmap();
}
+struct protocol_placeholder_entry {
+ const char *option;
+ const char *atom;
+};
+
+static const struct protocol_placeholder_entry remote_atom_map[] = {
+ {"size", "objectsize"},
+ {"type", "objecttype"},
+ /*
+ * Add new protocol options here. Even if the server doesn't support
+ * them the allow_list will drop them if the server doesn't advertise
+ * them.
+ */
+};
+
static void parse_cmd_remote_object_info(struct batch_options *opt,
const char *line, struct strbuf *output,
struct expand_data *data)
@@ -837,6 +841,7 @@ static void parse_cmd_remote_object_info(struct batch_options *opt,
char *line_to_split;
struct object_info *remote_object_info = NULL;
struct oid_array object_info_oids = OID_ARRAY_INIT;
+ struct string_list object_info_options = STRING_LIST_INIT_NODUP;
if (strlen(line) >= MAX_REMOTE_OBJ_INFO_LINE)
die(_("remote-object-info command too long"));
@@ -849,32 +854,57 @@ static void parse_cmd_remote_object_info(struct batch_options *opt,
die(_("remote-object-info supports at most %d objects"),
MAX_ALLOWED_OBJ_LIMIT);
+ if (data->info.sizep)
+ string_list_append(&object_info_options, "size");
+ if (data->info.typep)
+ string_list_append(&object_info_options, "type");
+
if (get_remote_info(opt, count, argv, &remote_object_info,
- &object_info_oids))
+ &object_info_oids, &object_info_options))
goto cleanup;
+ string_list_clear(&data->remote_allowed_atoms, 0);
+ string_list_append(&data->remote_allowed_atoms, "objectname");
+ for (size_t i = 0; i < ARRAY_SIZE(remote_atom_map); i++)
+ if (unsorted_string_list_has_string(&object_info_options, remote_atom_map[i].option))
+ string_list_append(&data->remote_allowed_atoms,
+ remote_atom_map[i].atom);
+
data->skip_object_info = 1;
for (size_t i = 0; i < object_info_oids.nr; i++) {
+ int found = 0;
data->oid = object_info_oids.oid[i];
+ /*
+ * When reaching here, it means remote-object-info can retrieve
+ * information from server without downloading them.
+ */
if (remote_object_info[i].sizep) {
- /*
- * When reaching here, it means remote-object-info can retrieve
- * information from server without downloading them.
- */
data->size = *remote_object_info[i].sizep;
- opt->batch_mode = BATCH_MODE_INFO;
- data->is_remote = 1;
- batch_object_write(argv[i + 1], output, opt, data, NULL, 0);
- data->is_remote = 0;
- } else {
- report_object_status(opt, oid_to_hex(&data->oid), &data->oid, "missing");
+ found = 1;
}
+
+ if (remote_object_info[i].typep) {
+ data->type = *remote_object_info[i].typep;
+ found = 1;
+ }
+
+ if (!found && object_info_options.nr > 0) {
+ report_object_status(opt, oid_to_hex(&data->oid),
+ &data->oid, "missing");
+ continue;
+ }
+
+ opt->batch_mode = BATCH_MODE_INFO;
+ data->is_remote = 1;
+ batch_object_write(argv[i + 1], output, opt, data, NULL, 0);
+ data->is_remote = 0;
}
data->skip_object_info = 0;
cleanup:
for (size_t i = 0; i < object_info_oids.nr; i++)
free_object_info_contents(&remote_object_info[i]);
+ string_list_clear(&object_info_options, 0);
free(line_to_split);
free(argv);
free(remote_object_info);
@@ -1190,6 +1220,7 @@ static int batch_objects(struct batch_options *opt)
cleanup:
strbuf_release(&input);
strbuf_release(&output);
+ string_list_clear(&data.remote_allowed_atoms, 0);
cfg->warn_on_object_refname_ambiguity = save_warning;
return retval;
}
diff --git a/fetch-object-info.c b/fetch-object-info.c
index 9c4ae9bd11..c6954bde5d 100644
--- a/fetch-object-info.c
+++ b/fetch-object-info.c
@@ -39,6 +39,26 @@ int fetch_object_info(const enum protocol_version version, struct object_info_ar
case protocol_v2:
if (!server_supports_v2("object-info"))
die(_("object-info capability is not enabled on the server"));
+ /*
+ * When removing an element from the list it gets swapped by the
+ * last element, iterate backwards to prevent elements skipping
+ * evaluation.
+ *
+ * object_info_options->nr can be safely casted without overflow
+ * beacuse the number of options is a small known number (the
+ * supported placeholders which currently are size and type).
+ */
+ for (int i = (int)args->object_info_options->nr - 1; i >= 0; i--)
+ if (!server_supports_feature("object-info",
+ args->object_info_options->items[i].string, 0))
+ unsorted_string_list_delete_item(args->object_info_options, i, 0);
+ /*
+ * If no options are left after the filtering, avoid unnecessary
+ * request to the server.
+ */
+ if (!args->object_info_options->nr)
+ return 0;
+
send_object_info_request(fd_out, args);
break;
case protocol_v1:
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 12/13] cat-file: validate remote atoms with allow_list
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
strstr() is not enough to validate the format placeholders in
remote-object-info causing two errors:
- Atoms recognized by expand_atom() but the remote doesn't returns 1, but
data->type contains garbage causing segfault.
- expand_atom() returns 0 for unknown atoms, calling
strbuf_expand_bad_format() which ends in die() blocking local queries
if the same format is shared.
Add an allow_list with the supported atoms at the top of expand_atom().
In remote mode, unsupported atoms return 1 leaving the sb empty,
honoring how for-each-ref handles known but inapplicable atoms.
As extra safety, initialize data->type to OBJ_BAD and add a NULL check
for type_name() so uninitialized data doesn't cause segfault.
Update tests that expect previous die() behaviour to expect an empty
string and add an explicit test for empty string return on unknown
placeholder.
Update caveat behaviour documentation.
Mentored-by: Karthik Nayak <karthik.188@gmail.com>
Mentored-by: Chandra Pratap <chandrapratap3519@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
Documentation/git-cat-file.adoc | 5 +++--
builtin/cat-file.c | 41 +++++++++++++++++++++++++++-------
t/t1017-cat-file-remote-object-info.sh | 27 ++++++++++++++++++----
3 files changed, 59 insertions(+), 14 deletions(-)
diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc
index aba20eb770..3b7a85b383 100644
--- a/Documentation/git-cat-file.adoc
+++ b/Documentation/git-cat-file.adoc
@@ -451,8 +451,9 @@ CAVEATS
-------
Note that since %(objecttype), %(objectsize:disk) and %(deltabase) are
-currently not supported by the `remote-object-info` command, we will raise
-an error and exit when they appear in the format string.
+currently not supported by the `remote-object-info` command, they will
+return an empty string for remote queries, matching how `for-each-ref`
+behaves for known but inapplicable placeholders.
Note that the sizes of objects on disk are reported accurately, but care
should be taken in drawing conclusions about which refs or objects are
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 49bd62ba3f..ea3869f3ed 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -333,8 +333,18 @@ struct expand_data {
* optimized out.
*/
unsigned skip_object_info : 1;
+
+ /*
+ * Flags about when an object info is being fetched from remote.
+ */
+ unsigned is_remote:1;
+};
+#define EXPAND_DATA_INIT { .mode = S_IFINVALID, .type = OBJ_BAD }
+
+static const char *remote_object_info_atoms[] = {
+ "objectname",
+ "objectsize",
};
-#define EXPAND_DATA_INIT { .mode = S_IFINVALID }
static int is_atom(const char *atom, const char *s, int slen)
{
@@ -345,14 +355,31 @@ static int is_atom(const char *atom, const char *s, int slen)
static int expand_atom(struct strbuf *sb, const char *atom, int len,
struct expand_data *data)
{
+ if (data->is_remote) {
+ size_t i, allowed_nr = ARRAY_SIZE(remote_object_info_atoms);
+ for (i = 0; i < allowed_nr; i++)
+ if (is_atom(remote_object_info_atoms[i], atom, len))
+ break;
+
+ /*
+ * On remote, skip unsupported atoms returning an empty sb,
+ * honoring how for-each-ref handles known but inapplicable
+ * atoms (e.g. %(tagger)).
+ */
+ if (i == allowed_nr)
+ return 1;
+ }
+
if (is_atom("objectname", atom, len)) {
if (!data->mark_query)
strbuf_add_oid_hex(sb, &data->oid);
} else if (is_atom("objecttype", atom, len)) {
- if (data->mark_query)
+ if (data->mark_query) {
data->info.typep = &data->type;
- else
- strbuf_addstr(sb, type_name(data->type));
+ } else {
+ const char *t = type_name(data->type);
+ strbuf_addstr(sb, t ? t : "");
+ }
} else if (is_atom("objectsize", atom, len)) {
if (data->mark_query)
data->info.sizep = &data->size;
@@ -707,10 +734,6 @@ static int get_remote_info(struct batch_options *opt,
gtransport->smart_options->object_info = 1;
gtransport->smart_options->object_info_oids = object_info_oids;
- /* 'objectsize' is the only option currently supported */
- if (!strstr(opt->format, "%(objectsize)"))
- die(_("%s is currently not supported with remote-object-info"), opt->format);
-
string_list_append(&object_info_options, "size");
if (object_info_options.nr > 0) {
@@ -840,7 +863,9 @@ static void parse_cmd_remote_object_info(struct batch_options *opt,
*/
data->size = *remote_object_info[i].sizep;
opt->batch_mode = BATCH_MODE_INFO;
+ data->is_remote = 1;
batch_object_write(argv[i + 1], output, opt, data, NULL, 0);
+ data->is_remote = 0;
} else {
report_object_status(opt, oid_to_hex(&data->oid), &data->oid, "missing");
}
diff --git a/t/t1017-cat-file-remote-object-info.sh b/t/t1017-cat-file-remote-object-info.sh
index b744e81701..9d8f114b72 100755
--- a/t/t1017-cat-file-remote-object-info.sh
+++ b/t/t1017-cat-file-remote-object-info.sh
@@ -236,6 +236,21 @@ test_expect_success 'remote-object-info does not die on missing oid like info' '
)
'
+# This tests depends on %(objecttype) not being supported yet, once supported
+# it needs to be updated.
+test_expect_success 'unsupported placeholder on remote returns empty string' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ echo "" >expect &&
+ git cat-file --batch-command="%(objecttype)" >actual <<-EOF &&
+ remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
# Test --batch-command remote-object-info with 'git://' and
# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability
test_expect_success 'batch-command remote-object-info git:// fails when transfer.advertiseobjectinfo=false' '
@@ -575,10 +590,12 @@ test_expect_success 'remote-object-info fails on unsupported filter option (obje
set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
- test_must_fail git cat-file --batch-command="%(objectsize:disk)" 2>err <<-EOF &&
+ echo "$hello_oid " >expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize:disk)" >actual <<-EOF &&
remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
EOF
- test_grep "%(objectsize:disk) is currently not supported with remote-object-info" err
+ test_cmp expect actual
)
'
@@ -587,10 +604,12 @@ test_expect_success 'remote-object-info fails on unsupported filter option (delt
set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
- test_must_fail git cat-file --batch-command="%(deltabase)" 2>err <<-EOF &&
+ echo "" >expect &&
+
+ git cat-file --batch-command="%(deltabase)" >actual <<-EOF &&
remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
EOF
- test_grep "%(deltabase) is currently not supported with remote-object-info" err
+ test_cmp expect actual
)
'
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 11/13] cat-file: add remote-object-info to batch-command
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Jonathan Tan,
Calvin Wan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Eric Ju <eric.peijian@gmail.com>
Since the `info` command in `cat-file --batch-command` prints object
info for a given object, it is natural to add another command in
`cat-file --batch-command` to print object info for a given object
from a remote.
Add `remote-object-info` to `cat-file --batch-command`.
While `info` takes object ids one at a time, this creates
overhead when making requests to a server. So `remote-object-info`
instead can take multiple object ids at once.
The `cat-file --batch-command` command is generally implemented in
the following manner:
- Receive and parse input from user
- Call respective function attached to command
- Get object info, print object info
In --buffer mode, this changes to:
- Receive and parse input from user
- Store respective function attached to command in a queue
- After flush, loop through commands in queue
- Call respective function attached to command
- Get object info, print object info
Notice how the getting and printing of object info is accomplished one
at a time. As described above, this creates a problem for making
requests to a server. Therefore, `remote-object-info` is implemented in
the following manner:
- Receive and parse input from user
If command is `remote-object-info`:
- Get object info from remote
- Loop through and print each object info
Else:
- Call respective function attached to command
- Parse input, get object info, print object info
And finally for --buffer mode `remote-object-info`:
- Receive and parse input from user
- Store respective function attached to command in a queue
- After flush, loop through commands in queue:
If command is `remote-object-info`:
- Get object info from remote
- Loop through and print each object info
Else:
- Call respective function attached to command
- Get object info, print object info
To summarize, `remote-object-info` gets object info from the remote and
then loops through the object info passed in, printing the info.
In order for `remote-object-info` to avoid remote communication
overhead in the non-buffer mode, the objects are passed in as such:
remote-object-info <remote> <oid> <oid> ... <oid>
rather than
remote-object-info <remote> <oid>
remote-object-info <remote> <oid>
...
remote-object-info <remote> <oid>
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
Documentation/git-cat-file.adoc | 24 +-
builtin/cat-file.c | 145 ++++++-
object-file.c | 10 +
odb.h | 3 +
t/meson.build | 1 +
t/t1017-cat-file-remote-object-info.sh | 680 +++++++++++++++++++++++++++++++++
transport.c | 4 +-
7 files changed, 860 insertions(+), 7 deletions(-)
diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc
index 86b9181599..aba20eb770 100644
--- a/Documentation/git-cat-file.adoc
+++ b/Documentation/git-cat-file.adoc
@@ -169,6 +169,13 @@ info <object>::
Print object info for object reference `<object>`. This corresponds to the
output of `--batch-check`.
+remote-object-info <remote> <object>...::
+ Print object info for object references `<object>` at specified
+ `<remote>` without downloading objects from the remote.
+ Raise an error when the `object-info` capability is not supported by the remote.
+ Raise an error when no object references are provided.
+ This command may be combined with `--buffer`.
+
flush::
Used with `--buffer` to execute all preceding commands that were issued
since the beginning or since the last flush was issued. When `--buffer`
@@ -312,7 +319,8 @@ newline. The available atoms are:
The full hex representation of the object name.
`objecttype`::
- The type of the object (the same as `cat-file -t` reports).
+ The type of the object (the same as `cat-file -t` reports). See
+ `CAVEATS` below. Not supported by `remote-object-info`.
`objectmode`::
If the specified object has mode information (such as a tree or
@@ -325,13 +333,14 @@ newline. The available atoms are:
`objectsize:disk`::
The size, in bytes, that the object takes up on disk. See the
- note about on-disk sizes in the `CAVEATS` section below.
+ note about on-disk sizes in the `CAVEATS` section below. Not
+ supported by `remote-object-info`.
`deltabase`::
If the object is stored as a delta on-disk, this expands to the
full hex representation of the delta base object name.
Otherwise, expands to the null OID (all zeroes). See `CAVEATS`
- below.
+ below. Not supported by `remote-object-info`.
`rest`::
If this atom is used in the output string, input lines are split
@@ -341,7 +350,10 @@ newline. The available atoms are:
line) are output in place of the `%(rest)` atom.
If no format is specified, the default format is `%(objectname)
-%(objecttype) %(objectsize)`.
+%(objecttype) %(objectsize)`, except for `remote-object-info` commands which use
+`%(objectname) %(objectsize)` for now because "%(objecttype)" is not supported yet.
+WARNING: When "%(objecttype)" is supported, the default format WILL be unified, so
+DO NOT RELY on the current default format to stay the same!!!
If `--batch` is specified, or if `--batch-command` is used with the `contents`
command, the object information is followed by the object contents (consisting
@@ -438,6 +450,10 @@ scripting purposes.
CAVEATS
-------
+Note that since %(objecttype), %(objectsize:disk) and %(deltabase) are
+currently not supported by the `remote-object-info` command, we will raise
+an error and exit when they appear in the format string.
+
Note that the sizes of objects on disk are reported accurately, but care
should be taken in drawing conclusions about which refs or objects are
responsible for disk usage. The size of a packed non-delta object may be
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 1e5473ab70..49bd62ba3f 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -29,6 +29,22 @@
#include "promisor-remote.h"
#include "mailmap.h"
#include "write-or-die.h"
+#include "alias.h"
+#include "remote.h"
+#include "transport.h"
+
+/*
+ * Maximum length for a remote URL. While no universal standard exists,
+ * 8K is assumed to be a reasonable limit.
+ */
+#define MAX_REMOTE_URL_LEN (8 * 1024)
+
+/* Maximum number of objects allowed in a single remote-object-info request. */
+#define MAX_ALLOWED_OBJ_LIMIT 10000
+
+/* Maximum input size permitted for the remote-object-info command. */
+#define MAX_REMOTE_OBJ_INFO_LINE \
+ (MAX_REMOTE_URL_LEN + MAX_ALLOWED_OBJ_LIMIT * (GIT_MAX_HEXSZ + 1))
enum batch_mode {
BATCH_MODE_CONTENTS,
@@ -633,6 +649,81 @@ static void batch_one_object(const char *obj_name,
object_context_release(&ctx);
}
+static int get_remote_info(struct batch_options *opt,
+ int argc,
+ const char **argv,
+ struct object_info **remote_object_info,
+ struct oid_array *object_info_oids)
+{
+ int retval = 0;
+ struct remote *remote = NULL;
+ struct object_id oid;
+ struct string_list object_info_options = STRING_LIST_INIT_NODUP;
+ struct transport *gtransport;
+
+ /*
+ * Change the format to "%(objectname) %(objectsize)" when
+ * remote-object-info command is used. Once we start supporting objecttype
+ * the default format should change to DEFAULT_FORMAT.
+ */
+ if (!opt->format)
+ opt->format = "%(objectname) %(objectsize)";
+
+ remote = remote_get(argv[0]);
+ if (!remote)
+ die(_("must supply valid remote when using remote-object-info"));
+
+ oid_array_clear(object_info_oids);
+ for (size_t i = 1; i < argc; i++) {
+ if (get_oid_hex(argv[i], &oid)) {
+ size_t len = strlen(argv[i]);
+
+ if (len < the_hash_algo->hexsz && len >= 4) {
+ size_t j;
+ for (j = 0; j < len; j++)
+ if (!isxdigit(argv[i][j]))
+ break;
+ if (j == len)
+ die(_("remote-object-info does not support "
+ "short oids, %d characters required"),
+ (int)the_hash_algo->hexsz);
+ }
+ die(_("not a valid object name '%s'"), argv[i]);
+ }
+ oid_array_append(object_info_oids, &oid);
+ }
+
+ if (!object_info_oids->nr)
+ die(_("remote-object-info requires objects"));
+
+ gtransport = transport_get(remote, NULL);
+
+ if (!gtransport->smart_options) {
+ retval = -1;
+ goto cleanup;
+ }
+
+ CALLOC_ARRAY(*remote_object_info, object_info_oids->nr);
+ gtransport->smart_options->object_info = 1;
+ gtransport->smart_options->object_info_oids = object_info_oids;
+
+ /* 'objectsize' is the only option currently supported */
+ if (!strstr(opt->format, "%(objectsize)"))
+ die(_("%s is currently not supported with remote-object-info"), opt->format);
+
+ string_list_append(&object_info_options, "size");
+
+ if (object_info_options.nr > 0) {
+ gtransport->smart_options->object_info_options = &object_info_options;
+ gtransport->smart_options->object_info_data = *remote_object_info;
+ retval = transport_fetch_refs(gtransport, NULL);
+ }
+cleanup:
+ string_list_clear(&object_info_options, 0);
+ transport_disconnect(gtransport);
+ return retval;
+}
+
struct object_cb_data {
struct batch_options *opt;
struct expand_data *expand;
@@ -714,6 +805,57 @@ static void parse_cmd_mailmap(struct batch_options *opt UNUSED,
load_mailmap();
}
+static void parse_cmd_remote_object_info(struct batch_options *opt,
+ const char *line, struct strbuf *output,
+ struct expand_data *data)
+{
+ int count;
+ const char **argv;
+ char *line_to_split;
+ struct object_info *remote_object_info = NULL;
+ struct oid_array object_info_oids = OID_ARRAY_INIT;
+
+ if (strlen(line) >= MAX_REMOTE_OBJ_INFO_LINE)
+ die(_("remote-object-info command too long"));
+
+ line_to_split = xstrdup(line);
+ count = split_cmdline(line_to_split, &argv);
+ if (count < 0)
+ die(_("split remote-object-info command"));
+ if (count - 1 > MAX_ALLOWED_OBJ_LIMIT)
+ die(_("remote-object-info supports at most %d objects"),
+ MAX_ALLOWED_OBJ_LIMIT);
+
+ if (get_remote_info(opt, count, argv, &remote_object_info,
+ &object_info_oids))
+ goto cleanup;
+
+ data->skip_object_info = 1;
+ for (size_t i = 0; i < object_info_oids.nr; i++) {
+ data->oid = object_info_oids.oid[i];
+ if (remote_object_info[i].sizep) {
+ /*
+ * When reaching here, it means remote-object-info can retrieve
+ * information from server without downloading them.
+ */
+ data->size = *remote_object_info[i].sizep;
+ opt->batch_mode = BATCH_MODE_INFO;
+ batch_object_write(argv[i + 1], output, opt, data, NULL, 0);
+ } else {
+ report_object_status(opt, oid_to_hex(&data->oid), &data->oid, "missing");
+ }
+ }
+ data->skip_object_info = 0;
+
+cleanup:
+ for (size_t i = 0; i < object_info_oids.nr; i++)
+ free_object_info_contents(&remote_object_info[i]);
+ free(line_to_split);
+ free(argv);
+ free(remote_object_info);
+ oid_array_clear(&object_info_oids);
+}
+
static void dispatch_calls(struct batch_options *opt,
struct strbuf *output,
struct expand_data *data,
@@ -745,8 +887,9 @@ static const struct parse_cmd {
} commands[] = {
{ "contents", parse_cmd_contents, 1 },
{ "info", parse_cmd_info, 1 },
- { "flush", NULL, 0 },
{ "mailmap", parse_cmd_mailmap, 1 },
+ { "remote-object-info", parse_cmd_remote_object_info, 1 },
+ { "flush", NULL, 0 },
};
static void batch_objects_command(struct batch_options *opt,
diff --git a/object-file.c b/object-file.c
index e3d92bbda2..9928e82e0b 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1694,3 +1694,13 @@ struct odb_transaction *odb_transaction_files_begin(struct odb_source *source)
return &transaction->base;
}
+
+void free_object_info_contents(struct object_info *object_info)
+{
+ if (!object_info)
+ return;
+ free(object_info->typep);
+ free(object_info->sizep);
+ free(object_info->disk_sizep);
+ free(object_info->delta_base_oid);
+}
diff --git a/odb.h b/odb.h
index 3834a0dcbf..42e3934035 100644
--- a/odb.h
+++ b/odb.h
@@ -573,4 +573,7 @@ void parse_alternates(const char *string,
const char *relative_base,
struct strvec *out);
+/* Free pointers inside of object_info, but not object_info itself */
+void free_object_info_contents(struct object_info *object_info);
+
#endif /* ODB_H */
diff --git a/t/meson.build b/t/meson.build
index 3219264fe7..54d21111a3 100644
--- a/t/meson.build
+++ b/t/meson.build
@@ -170,6 +170,7 @@ integration_tests = [
't1014-read-tree-confusing.sh',
't1015-read-index-unmerged.sh',
't1016-compatObjectFormat.sh',
+ 't1017-cat-file-remote-object-info.sh',
't1020-subdirectory.sh',
't1022-read-tree-partial-clone.sh',
't1050-large.sh',
diff --git a/t/t1017-cat-file-remote-object-info.sh b/t/t1017-cat-file-remote-object-info.sh
new file mode 100755
index 0000000000..b744e81701
--- /dev/null
+++ b/t/t1017-cat-file-remote-object-info.sh
@@ -0,0 +1,680 @@
+#!/bin/sh
+
+test_description='git cat-file --batch-command with remote-object-info command'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-cat-file.sh
+
+hello_content="Hello World"
+hello_size=$(strlen "$hello_content")
+hello_oid=$(echo_without_newline "$hello_content" | git hash-object --stdin)
+hello_short_oid=$(git rev-parse --short "$hello_oid")
+
+unstored_content="Hello Git"
+unstored_oid=$(echo_without_newline "$unstored_content" | git hash-object --stdin)
+
+# This is how we get 13:
+# 13 = <file mode> + <a_space> + <file name> + <a_null>, where
+# file mode is 100644, which is 6 characters;
+# file name is hello, which is 5 characters
+# a space is 1 character and a null is 1 character
+tree_size=$(($(test_oid rawsz) + 13))
+
+commit_message="Initial commit"
+
+# This is how we get 137:
+# 137 = <tree header> + <a_space> + <a newline> +
+# <Author line> + <a newline> +
+# <Committer line> + <a newline> +
+# <a newline> +
+# <commit message length>
+# An easier way to calculate is: 1. use `git cat-file commit <commit hash> | wc -c`,
+# to get 177, 2. then deduct 40 hex characters to get 137
+commit_size=$(($(test_oid hexsz) + 137))
+
+tag_header_without_oid="type blob
+tag hellotag
+tagger $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL>"
+tag_header_without_timestamp="object $hello_oid
+$tag_header_without_oid"
+tag_description="This is a tag"
+tag_content="$tag_header_without_timestamp 0 +0000
+
+$tag_description"
+
+tag_oid=$(echo_without_newline "$tag_content" | git hash-object -t tag --stdin -w)
+tag_size=$(strlen "$tag_content")
+
+set_transport_variables () {
+ hello_oid=$(echo_without_newline "$hello_content" | git hash-object --stdin)
+ tree_oid=$(git -C "$1" write-tree)
+ commit_oid=$(echo_without_newline "$commit_message" | git -C "$1" commit-tree $tree_oid)
+ tag_oid=$(echo_without_newline "$tag_content" | git -C "$1" hash-object -t tag --stdin -w)
+ tag_size=$(strlen "$tag_content")
+}
+
+# This section tests --batch-command with remote-object-info command
+# Since "%(objecttype)" is currently not supported by the command remote-object-info ,
+# the filters are set to "%(objectname) %(objectsize)" in some test cases.
+
+# Test --batch-command remote-object-info with 'git://' transport with
+# transfer.advertiseobjectinfo set to true, i.e. server has object-info capability
+. "$TEST_DIRECTORY"/lib-git-daemon.sh
+start_git_daemon --export-all --enable=receive-pack
+daemon_parent=$GIT_DAEMON_DOCUMENT_ROOT_PATH/parent
+
+test_expect_success 'create repo to be served by git-daemon' '
+ git init "$daemon_parent" &&
+ echo_without_newline "$hello_content" > $daemon_parent/hello &&
+ git -C "$daemon_parent" update-index --add hello &&
+ git -C "$daemon_parent" config transfer.advertiseobjectinfo true &&
+ git clone "$GIT_DAEMON_URL/parent" -n "$daemon_parent/daemon_client_empty"
+'
+
+test_expect_success 'batch-command remote-object-info git://' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF &&
+ remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid
+ remote-object-info "$GIT_DAEMON_URL/parent" $tree_oid
+ remote-object-info "$GIT_DAEMON_URL/parent" $commit_oid
+ remote-object-info "$GIT_DAEMON_URL/parent" $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command remote-object-info git:// multiple sha1 per line' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF &&
+ remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid $tree_oid $commit_oid $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command remote-object-info git:// default filter' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+ GIT_TRACE_PACKET=1 git cat-file --batch-command >actual <<-EOF &&
+ remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid $tree_oid
+ remote-object-info "$GIT_DAEMON_URL/parent" $commit_oid $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command --buffer remote-object-info git://' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" --buffer >actual <<-EOF &&
+ remote-object-info "$GIT_DAEMON_URL/parent" $hello_oid $tree_oid
+ remote-object-info "$GIT_DAEMON_URL/parent" $commit_oid $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ flush
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command -Z remote-object-info git:// default filter' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ printf "%s\0" "$hello_oid $hello_size" >expect &&
+ printf "%s\0" "$tree_oid $tree_size" >>expect &&
+ printf "%s\0" "$commit_oid $commit_size" >>expect &&
+ printf "%s\0" "$tag_oid $tag_size" >>expect &&
+
+ printf "%s\0" "$hello_oid missing" >>expect &&
+ printf "%s\0" "$tree_oid missing" >>expect &&
+ printf "%s\0" "$commit_oid missing" >>expect &&
+ printf "%s\0" "$tag_oid missing" >>expect &&
+
+ batch_input="remote-object-info $GIT_DAEMON_URL/parent $hello_oid $tree_oid
+remote-object-info $GIT_DAEMON_URL/parent $commit_oid $tag_oid
+info $hello_oid
+info $tree_oid
+info $commit_oid
+info $tag_oid
+" &&
+ echo_without_newline_nul "$batch_input" >commands_null_delimited &&
+
+ git cat-file --batch-command -Z < commands_null_delimited >actual &&
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'remote-object-info does not support short oids' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ test_must_fail git cat-file --batch-command 2>err <<-EOF &&
+ remote-object-info $GIT_DAEMON_URL/parent $hello_short_oid
+ EOF
+ test_grep "does not support short oids" err
+ )
+'
+
+test_expect_success 'remote-object-info does not die on missing oid like info' '
+ (
+ set_transport_variables "$daemon_parent" &&
+ cd "$daemon_parent/daemon_client_empty" &&
+
+ git cat-file --batch-command >local <<-EOF &&
+ info $unstored_oid
+ EOF
+ git cat-file --batch-command >remote <<-EOF &&
+ remote-object-info $GIT_DAEMON_URL/parent $unstored_oid
+ EOF
+ test_cmp local remote
+ )
+'
+
+# Test --batch-command remote-object-info with 'git://' and
+# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability
+test_expect_success 'batch-command remote-object-info git:// fails when transfer.advertiseobjectinfo=false' '
+ (
+ git -C "$daemon_parent" config transfer.advertiseobjectinfo false &&
+ set_transport_variables "$daemon_parent" &&
+
+ test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF &&
+ remote-object-info $GIT_DAEMON_URL/parent $hello_oid $tree_oid $commit_oid $tag_oid
+ EOF
+ test_grep "object-info capability is not enabled on the server" err &&
+
+ # revert server state back
+ git -C "$daemon_parent" config transfer.advertiseobjectinfo true
+
+ )
+'
+
+stop_git_daemon
+
+# Test --batch-command remote-object-info with 'file://' transport with
+# transfer.advertiseobjectinfo set to true, i.e. server has object-info capability
+# shellcheck disable=SC2016
+test_expect_success 'create repo to be served by file:// transport' '
+ git init server &&
+ git -C server config protocol.version 2 &&
+ git -C server config transfer.advertiseobjectinfo true &&
+ echo_without_newline "$hello_content" > server/hello &&
+ git -C server update-index --add hello &&
+ git clone -n "file://$(pwd)/server" file_client_empty
+'
+
+test_expect_success 'batch-command remote-object-info file://' '
+ (
+ set_transport_variables "server" &&
+ server_path="$(pwd)/server" &&
+ cd file_client_empty &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF &&
+ remote-object-info "file://${server_path}" $hello_oid
+ remote-object-info "file://${server_path}" $tree_oid
+ remote-object-info "file://${server_path}" $commit_oid
+ remote-object-info "file://${server_path}" $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command remote-object-info file:// multiple sha1 per line' '
+ (
+ set_transport_variables "server" &&
+ server_path="$(pwd)/server" &&
+ cd file_client_empty &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF &&
+ remote-object-info "file://${server_path}" $hello_oid $tree_oid $commit_oid $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command --buffer remote-object-info file://' '
+ (
+ set_transport_variables "server" &&
+ server_path="$(pwd)/server" &&
+ cd file_client_empty &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" --buffer >actual <<-EOF &&
+ remote-object-info "file://${server_path}" $hello_oid $tree_oid
+ remote-object-info "file://${server_path}" $commit_oid $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ flush
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command remote-object-info file:// default filter' '
+ (
+ set_transport_variables "server" &&
+ server_path="$(pwd)/server" &&
+ cd file_client_empty &&
+
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ git cat-file --batch-command >actual <<-EOF &&
+ remote-object-info "file://${server_path}" $hello_oid $tree_oid
+ remote-object-info "file://${server_path}" $commit_oid $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command -Z remote-object-info file:// default filter' '
+ (
+ set_transport_variables "server" &&
+ server_path="$(pwd)/server" &&
+ cd file_client_empty &&
+
+ printf "%s\0" "$hello_oid $hello_size" >expect &&
+ printf "%s\0" "$tree_oid $tree_size" >>expect &&
+ printf "%s\0" "$commit_oid $commit_size" >>expect &&
+ printf "%s\0" "$tag_oid $tag_size" >>expect &&
+
+ printf "%s\0" "$hello_oid missing" >>expect &&
+ printf "%s\0" "$tree_oid missing" >>expect &&
+ printf "%s\0" "$commit_oid missing" >>expect &&
+ printf "%s\0" "$tag_oid missing" >>expect &&
+
+ batch_input="remote-object-info \"file://${server_path}\" $hello_oid $tree_oid
+remote-object-info \"file://${server_path}\" $commit_oid $tag_oid
+info $hello_oid
+info $tree_oid
+info $commit_oid
+info $tag_oid
+" &&
+ echo_without_newline_nul "$batch_input" >commands_null_delimited &&
+
+ git cat-file --batch-command -Z < commands_null_delimited >actual &&
+ test_cmp expect actual
+ )
+'
+
+# Test --batch-command remote-object-info with 'file://' and
+# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability
+test_expect_success 'batch-command remote-object-info file:// fails when transfer.advertiseobjectinfo=false' '
+ (
+ set_transport_variables "server" &&
+ server_path="$(pwd)/server" &&
+ git -C "${server_path}" config transfer.advertiseobjectinfo false &&
+
+ test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF &&
+ remote-object-info "file://${server_path}" $hello_oid $tree_oid $commit_oid $tag_oid
+ EOF
+ test_grep "object-info capability is not enabled on the server" err &&
+
+ # revert server state back
+ git -C "${server_path}" config transfer.advertiseobjectinfo true
+ )
+'
+
+# Test --batch-command remote-object-info with 'http://' transport with
+# transfer.advertiseobjectinfo set to true, i.e. server has object-info capability
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'create repo to be served by http:// transport' '
+ git init "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config http.receivepack true &&
+ git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config transfer.advertiseobjectinfo true &&
+ echo_without_newline "$hello_content" > $HTTPD_DOCUMENT_ROOT_PATH/http_parent/hello &&
+ git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" update-index --add hello &&
+ git clone "$HTTPD_URL/smart/http_parent" -n "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty"
+'
+
+test_expect_success 'batch-command remote-object-info http://' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
+ remote-object-info "$HTTPD_URL/smart/http_parent" $tree_oid
+ remote-object-info "$HTTPD_URL/smart/http_parent" $commit_oid
+ remote-object-info "$HTTPD_URL/smart/http_parent" $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command remote-object-info http:// one line' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" >actual <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid $commit_oid $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command --buffer remote-object-info http://' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" &&
+
+ # These results prove remote-object-info can get object info from the remote
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ # These results prove remote-object-info did not download objects from the remote
+ echo "$hello_oid missing" >>expect &&
+ echo "$tree_oid missing" >>expect &&
+ echo "$commit_oid missing" >>expect &&
+ echo "$tag_oid missing" >>expect &&
+
+ git cat-file --batch-command="%(objectname) %(objectsize)" --buffer >actual <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid
+ remote-object-info "$HTTPD_URL/smart/http_parent" $commit_oid $tag_oid
+ info $hello_oid
+ info $tree_oid
+ info $commit_oid
+ info $tag_oid
+ flush
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command remote-object-info http:// default filter' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" &&
+
+ echo "$hello_oid $hello_size" >expect &&
+ echo "$tree_oid $tree_size" >>expect &&
+ echo "$commit_oid $commit_size" >>expect &&
+ echo "$tag_oid $tag_size" >>expect &&
+
+ git cat-file --batch-command >actual <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid
+ remote-object-info "$HTTPD_URL/smart/http_parent" $commit_oid $tag_oid
+ EOF
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'batch-command -Z remote-object-info http:// default filter' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_client_empty" &&
+
+ printf "%s\0" "$hello_oid $hello_size" >expect &&
+ printf "%s\0" "$tree_oid $tree_size" >>expect &&
+ printf "%s\0" "$commit_oid $commit_size" >>expect &&
+ printf "%s\0" "$tag_oid $tag_size" >>expect &&
+
+ batch_input="remote-object-info $HTTPD_URL/smart/http_parent $hello_oid $tree_oid
+remote-object-info $HTTPD_URL/smart/http_parent $commit_oid $tag_oid
+" &&
+ echo_without_newline_nul "$batch_input" >commands_null_delimited &&
+
+ git cat-file --batch-command -Z < commands_null_delimited >actual &&
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'remote-object-info fails on unsupported filter option (objectsize:disk)' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+
+ test_must_fail git cat-file --batch-command="%(objectsize:disk)" 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
+ EOF
+ test_grep "%(objectsize:disk) is currently not supported with remote-object-info" err
+ )
+'
+
+test_expect_success 'remote-object-info fails on unsupported filter option (deltabase)' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+
+ test_must_fail git cat-file --batch-command="%(deltabase)" 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
+ EOF
+ test_grep "%(deltabase) is currently not supported with remote-object-info" err
+ )
+'
+
+test_expect_success 'remote-object-info fails on server with legacy protocol' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+
+ test_must_fail git -c protocol.version=0 cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
+ EOF
+ test_grep "remote-object-info requires protocol v2" err
+ )
+'
+
+test_expect_success 'remote-object-info fails on server with legacy protocol with default filter' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+
+ test_must_fail git -c protocol.version=0 cat-file --batch-command 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid
+ EOF
+ test_grep "remote-object-info requires protocol v2" err
+ )
+'
+
+test_expect_success 'remote-object-info fails on malformed OID' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ malformed_object_id="this_id_is_not_valid" &&
+
+ test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $malformed_object_id
+ EOF
+ test_grep "not a valid object name '$malformed_object_id'" err
+ )
+'
+
+test_expect_success 'remote-object-info fails on malformed OID with default filter' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ malformed_object_id="this_id_is_not_valid" &&
+
+ test_must_fail git cat-file --batch-command 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $malformed_object_id
+ EOF
+ test_grep "not a valid object name '$malformed_object_id'" err
+ )
+'
+
+test_expect_success 'remote-object-info fails on not providing OID' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ cd "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+
+ test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent"
+ EOF
+ test_grep "remote-object-info requires objects" err
+ )
+'
+
+
+# Test --batch-command remote-object-info with 'http://' transport and
+# transfer.advertiseobjectinfo set to false, i.e. server does not have object-info capability
+test_expect_success 'batch-command remote-object-info http:// fails when transfer.advertiseobjectinfo=false ' '
+ (
+ set_transport_variables "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config transfer.advertiseobjectinfo false &&
+
+ test_must_fail git cat-file --batch-command="%(objectname) %(objectsize)" 2>err <<-EOF &&
+ remote-object-info "$HTTPD_URL/smart/http_parent" $hello_oid $tree_oid $commit_oid $tag_oid
+ EOF
+ test_grep "object-info capability is not enabled on the server" err &&
+
+ # revert server state back
+ git -C "$HTTPD_DOCUMENT_ROOT_PATH/http_parent" config transfer.advertiseobjectinfo true
+ )
+'
+
+# DO NOT add non-httpd-specific tests here, because the last part of this
+# test script is only executed when httpd is available and enabled.
+
+test_done
diff --git a/transport.c b/transport.c
index 7d3246e12b..81faf8e748 100644
--- a/transport.c
+++ b/transport.c
@@ -470,8 +470,8 @@ static int fetch_refs_via_pack(struct transport *transport,
args.reject_shallow_remote = transport->smart_options->reject_shallow;
args.object_info = transport->smart_options->object_info;
- if (transport->smart_options->object_info
- && transport->smart_options->object_info_oids->nr > 0) {
+ if (transport->smart_options->object_info &&
+ transport->smart_options->object_info_oids->nr > 0) {
struct packet_reader reader;
struct object_info_args obj_info_args = { 0 };
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 10/13] transport: add client support for object-info
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Calvin Wan,
Jonathan Tan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Calvin Wan <calvinwan@google.com>
Sometimes, it is beneficial to retrieve information about an object
without downloading it entirely. The server-side logic for this
functionality was implemented in commit "a2ba162cda (object-info:
support for retrieving object info, 2021-04-20)." And the wire
format is documented at
https://git-scm.com/docs/protocol-v2#_object_info.
This commit introduces client functions to interact with the server.
Currently, the client supports requesting a list of object IDs with
the 'size' feature from a v2 server. If the server does not advertise
this feature (i.e., transfer.advertiseobjectinfo is set to false),
the client will return an error and exit.
Notice that the entire request is written into req_buf before being
sent to the remote. This approach follows the pattern used in the
`send_fetch_request()` logic within fetch-pack.c.
Streaming the request is not addressed in this patch.
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
Makefile | 1 +
fetch-object-info.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++++++
fetch-object-info.h | 22 +++++++++++++
fetch-pack.c | 3 ++
fetch-pack.h | 2 ++
meson.build | 1 +
transport-helper.c | 11 +++++--
transport.c | 28 ++++++++++++++++-
transport.h | 11 +++++++
9 files changed, 166 insertions(+), 3 deletions(-)
diff --git a/Makefile b/Makefile
index 1cec251f43..ec4df39a6b 100644
--- a/Makefile
+++ b/Makefile
@@ -1159,6 +1159,7 @@ LIB_OBJS += ewah/ewah_rlw.o
LIB_OBJS += exec-cmd.o
LIB_OBJS += fetch-negotiator.o
LIB_OBJS += fetch-pack.o
+LIB_OBJS += fetch-object-info.o
LIB_OBJS += fmt-merge-msg.o
LIB_OBJS += fsck.o
LIB_OBJS += fsmonitor.o
diff --git a/fetch-object-info.c b/fetch-object-info.c
new file mode 100644
index 0000000000..9c4ae9bd11
--- /dev/null
+++ b/fetch-object-info.c
@@ -0,0 +1,90 @@
+#include "git-compat-util.h"
+#include "gettext.h"
+#include "hex.h"
+#include "pkt-line.h"
+#include "connect.h"
+#include "oid-array.h"
+#include "odb.h"
+#include "fetch-object-info.h"
+#include "string-list.h"
+
+/* Sends git-cat-file object-info command and its arguments into the request buffer. */
+static void send_object_info_request(const int fd_out, struct object_info_args *args)
+{
+ struct strbuf req_buf = STRBUF_INIT;
+
+ write_command_and_capabilities(&req_buf, "object-info", args->server_options);
+
+ if (unsorted_string_list_has_string(args->object_info_options, "size"))
+ packet_buf_write(&req_buf, "size");
+
+ if (args->oids)
+ for (size_t i = 0; i < args->oids->nr; i++)
+ packet_buf_write(&req_buf, "oid %s", oid_to_hex(&args->oids->oid[i]));
+
+ packet_buf_flush(&req_buf);
+ if (write_in_full(fd_out, req_buf.buf, req_buf.len) < 0)
+ die_errno(_("unable to write request to remote"));
+
+ strbuf_release(&req_buf);
+}
+
+int fetch_object_info(const enum protocol_version version, struct object_info_args *args,
+ struct packet_reader *reader, struct object_info *object_info_data,
+ const int stateless_rpc, const int fd_out)
+{
+ int size_index = -1;
+
+ switch (version) {
+ case protocol_v2:
+ if (!server_supports_v2("object-info"))
+ die(_("object-info capability is not enabled on the server"));
+ send_object_info_request(fd_out, args);
+ break;
+ case protocol_v1:
+ case protocol_v0:
+ die(_("unsupported protocol version. expected v2"));
+ case protocol_unknown_version:
+ BUG("unknown protocol version");
+ }
+
+ for (size_t i = 0; i < args->object_info_options->nr; i++) {
+ if (packet_reader_read(reader) != PACKET_READ_NORMAL) {
+ check_stateless_delimiter(stateless_rpc, reader,
+ "stateless delimiter expected");
+ return -1;
+ }
+
+ if (!string_list_has_string(args->object_info_options, reader->line))
+ return -1;
+
+ if (!strcmp(reader->line, "size")) {
+ size_index = i;
+ for (size_t j = 0; j < args->oids->nr; j++)
+ object_info_data[j].sizep = xcalloc(1, sizeof(*object_info_data[j].sizep));
+ }
+ }
+
+ for (size_t i = 0; packet_reader_read(reader) == PACKET_READ_NORMAL && i < args->oids->nr; i++) {
+ struct string_list object_info_values = STRING_LIST_INIT_DUP;
+
+ string_list_split(&object_info_values, reader->line, " ", -1);
+ if (0 <= size_index) {
+ if (!strcmp(object_info_values.items[1 + size_index].string, "")) {
+ FREE_AND_NULL(object_info_data[i].sizep);
+ string_list_clear(&object_info_values, 0);
+ continue;
+ }
+ if (strtoul_szt(object_info_values.items[1 + size_index].string,
+ 10, object_info_data[i].sizep))
+ die("object-info: ref %s has invalid size %s",
+ object_info_values.items[0].string,
+ object_info_values.items[1 + size_index].string);
+ }
+
+ string_list_clear(&object_info_values, 0);
+ }
+ check_stateless_delimiter(stateless_rpc, reader, "stateless delimiter expected");
+
+ return 0;
+}
diff --git a/fetch-object-info.h b/fetch-object-info.h
new file mode 100644
index 0000000000..d35284bd6b
--- /dev/null
+++ b/fetch-object-info.h
@@ -0,0 +1,22 @@
+#ifndef FETCH_OBJECT_INFO_H
+#define FETCH_OBJECT_INFO_H
+
+#include "pkt-line.h"
+#include "protocol.h"
+#include "odb.h"
+
+struct object_info_args {
+ struct string_list *object_info_options;
+ const struct string_list *server_options;
+ struct oid_array *oids;
+};
+
+/*
+ * Sends git-cat-file object-info command into the request buf and read the
+ * results from packets.
+ */
+int fetch_object_info(enum protocol_version version, struct object_info_args *args,
+ struct packet_reader *reader, struct object_info *object_info_data,
+ int stateless_rpc, int fd_out);
+
+#endif /* FETCH_OBJECT_INFO_H */
diff --git a/fetch-pack.c b/fetch-pack.c
index cdebd3476f..a86c93fc52 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -1742,6 +1742,9 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
if (args->depth > 0 || args->deepen_since || args->deepen_not)
args->deepen = 1;
+ if (args->object_info)
+ state = FETCH_SEND_REQUEST;
+
while (state != FETCH_DONE) {
switch (state) {
case FETCH_CHECK_LOCAL:
diff --git a/fetch-pack.h b/fetch-pack.h
index 6d0dec7f41..5a428f11ed 100644
--- a/fetch-pack.h
+++ b/fetch-pack.h
@@ -16,6 +16,7 @@ struct fetch_pack_args {
const struct string_list *deepen_not;
struct list_objects_filter_options filter_options;
const struct string_list *server_options;
+ struct object_info *object_info_data;
/*
* If not NULL, during packfile negotiation, fetch-pack will send "have"
@@ -43,6 +44,7 @@ struct fetch_pack_args {
unsigned reject_shallow_remote:1;
unsigned deepen:1;
unsigned refetch:1;
+ unsigned object_info:1;
/*
* Indicate that the remote of this request is a promisor remote. The
diff --git a/meson.build b/meson.build
index 3247697f74..145c6882eb 100644
--- a/meson.build
+++ b/meson.build
@@ -347,6 +347,7 @@ libgit_sources = [
'exec-cmd.c',
'fetch-negotiator.c',
'fetch-pack.c',
+ 'fetch-object-info.c',
'fmt-merge-msg.c',
'fsck.c',
'fsmonitor.c',
diff --git a/transport-helper.c b/transport-helper.c
index f195070788..c77599f6fb 100644
--- a/transport-helper.c
+++ b/transport-helper.c
@@ -727,8 +727,8 @@ static int fetch_refs(struct transport *transport,
/*
* If we reach here, then the server, the client, and/or the transport
- * helper does not support protocol v2. --negotiate-only requires
- * protocol v2.
+ * helper does not support protocol v2. --negotiate-only and cat-file
+ * remote-object-info require protocol v2.
*/
if (data->transport_options.acked_commits) {
warning(_("--negotiate-only requires protocol v2"));
@@ -744,6 +744,13 @@ static int fetch_refs(struct transport *transport,
free_refs(dummy);
}
+ /* fail the command explicitly to avoid further commands input. */
+ if (transport->smart_options->object_info)
+ die(_("remote-object-info requires protocol v2"));
+
+ if (!data->get_refs_list_called)
+ get_refs_list_using_list(transport, 0);
+
count = 0;
for (i = 0; i < nr_heads; i++)
if (!(to_fetch[i]->status & REF_STATUS_UPTODATE))
diff --git a/transport.c b/transport.c
index 0f5ec30247..7d3246e12b 100644
--- a/transport.c
+++ b/transport.c
@@ -9,6 +9,7 @@
#include "hook.h"
#include "pkt-line.h"
#include "fetch-pack.h"
+#include "fetch-object-info.h"
#include "remote.h"
#include "connect.h"
#include "send-pack.h"
@@ -467,8 +468,33 @@ static int fetch_refs_via_pack(struct transport *transport,
args.negotiation_restrict_tips = data->options.negotiation_restrict_tips;
args.negotiation_include_tips = data->options.negotiation_include_tips;
args.reject_shallow_remote = transport->smart_options->reject_shallow;
+ args.object_info = transport->smart_options->object_info;
+
+ if (transport->smart_options->object_info
+ && transport->smart_options->object_info_oids->nr > 0) {
+ struct packet_reader reader;
+ struct object_info_args obj_info_args = { 0 };
+
+ obj_info_args.server_options = transport->server_options;
+ obj_info_args.oids = transport->smart_options->object_info_oids;
+ obj_info_args.object_info_options = transport->smart_options->object_info_options;
+ string_list_sort(obj_info_args.object_info_options);
+
+ connect_setup(transport, 0);
+ packet_reader_init(&reader, data->fd[0], NULL, 0,
+ PACKET_READ_CHOMP_NEWLINE |
+ PACKET_READ_GENTLE_ON_EOF |
+ PACKET_READ_DIE_ON_ERR_PACKET);
+
+ data->version = discover_version(&reader);
+ transport->hash_algo = reader.hash_algo;
+
+ ret = fetch_object_info(data->version, &obj_info_args, &reader,
+ data->options.object_info_data, transport->stateless_rpc,
+ data->fd[1]);
+ goto cleanup;
- if (!data->finished_handshake) {
+ } else if (!data->finished_handshake) {
int i;
int must_list_refs = 0;
for (i = 0; i < nr_heads; i++) {
diff --git a/transport.h b/transport.h
index 7e5867cffa..bd60b10af4 100644
--- a/transport.h
+++ b/transport.h
@@ -6,6 +6,7 @@
#include "list-objects-filter-options.h"
#include "string-list.h"
#include "connect.h"
+#include "odb.h"
struct git_transport_options {
unsigned thin : 1;
@@ -31,6 +32,12 @@ struct git_transport_options {
*/
unsigned connectivity_checked:1;
+ /*
+ * Transport will attempt to retrieve only object-info.
+ * If object-info is not supported, the operation will error and exit.
+ */
+ unsigned object_info : 1;
+
int depth;
const char *deepen_since;
const struct string_list *deepen_not;
@@ -55,6 +62,10 @@ struct git_transport_options {
* common commits to this oidset instead of fetching any packfiles.
*/
struct oidset *acked_commits;
+
+ struct oid_array *object_info_oids;
+ struct object_info *object_info_data;
+ struct string_list *object_info_options;
};
enum transport_family {
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 09/13] serve: advertise object-info feature
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Calvin Wan,
Jonathan Tan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Calvin Wan <calvinwan@google.com>
In order for a client to know what object-info components a server can
provide, advertise supported object-info features. This will allow a
client to decide whether to query the server for object-info or fetch
as a fallback.
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
serve.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/serve.c b/serve.c
index 49a6e39b1d..2b07d922b3 100644
--- a/serve.c
+++ b/serve.c
@@ -89,7 +89,7 @@ static void session_id_receive(struct repository *r UNUSED,
trace2_data_string("transfer", NULL, "client-sid", client_sid);
}
-static int object_info_advertise(struct repository *r, struct strbuf *value UNUSED)
+static int object_info_advertise(struct repository *r, struct strbuf *value)
{
if (advertise_object_info == -1 &&
repo_config_get_bool(r, "transfer.advertiseobjectinfo",
@@ -97,6 +97,9 @@ static int object_info_advertise(struct repository *r, struct strbuf *value UNUS
/* disabled by default */
advertise_object_info = 0;
}
+ /* Currently only size is supported */
+ if (value && advertise_object_info)
+ strbuf_addstr(value, "size");
return advertise_object_info;
}
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 08/13] fetch-pack: move fetch initialization
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Calvin Wan,
Jonathan Tan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Calvin Wan <calvinwan@google.com>
There are some variables initialized at the start of the
do_fetch_pack_v2() state machine. Currently, they are initialized
in FETCH_CHECK_LOCAL, which is the initial state set at the beginning
of the function.
However, a subsequent patch will allow for another initial state,
while still requiring these initialized variables.
Move the initialization to be before the state machine,
so that they are set regardless of the initial state.
Note that there is no change in behavior, because we're moving code
from the beginning of the first state to just before the execution of
the state machine.
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
fetch-pack.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/fetch-pack.c b/fetch-pack.c
index 3d32114907..cdebd3476f 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -1736,18 +1736,18 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
reader.me = "fetch-pack";
}
+ /* v2 supports these by default */
+ allow_unadvertised_object_request |= ALLOW_REACHABLE_SHA1;
+ use_sideband = 2;
+ if (args->depth > 0 || args->deepen_since || args->deepen_not)
+ args->deepen = 1;
+
while (state != FETCH_DONE) {
switch (state) {
case FETCH_CHECK_LOCAL:
sort_ref_list(&ref, ref_compare_name);
QSORT(sought, nr_sought, cmp_ref_by_name);
- /* v2 supports these by default */
- allow_unadvertised_object_request |= ALLOW_REACHABLE_SHA1;
- use_sideband = 2;
- if (args->depth > 0 || args->deepen_since || args->deepen_not)
- args->deepen = 1;
-
/* Filter 'ref' by 'sought' and those that aren't local */
mark_complete_and_common_ref(negotiator, args, &ref);
filter_refs(args, &ref, sought, nr_sought);
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 07/13] connect: refactor packet writing
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Jonathan Tan,
Calvin Wan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
Refactor `write_fetch_command_and_capabilities()`, enabling it to serve
both fetch and additional commands.
In this context, "command" refers to the "operations" supported by
Git's wire protocol https://git-scm.com/docs/protocol-v2, such as a Git
subcommand (e.g., git-fetch(1)) or a server-side operation like
"object-info" as implemented in commit a2ba162
(object-info: support for retrieving object info, 2021-04-20).
Refactor the function signature to accept a command instead of the
hardcoded "fetch".
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
connect.c | 8 ++++----
connect.h | 8 ++++++--
fetch-pack.c | 4 ++--
3 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/connect.c b/connect.c
index 1dced8e632..7b472f8e5f 100644
--- a/connect.c
+++ b/connect.c
@@ -700,16 +700,16 @@ int server_supports(const char *feature)
return !!server_feature_value(feature, NULL);
}
-void write_fetch_command_and_capabilities(struct strbuf *req_buf,
- const struct string_list *server_options)
+void write_command_and_capabilities(struct strbuf *req_buf, const char *command,
+ const struct string_list *server_options)
{
const char *hash_name;
int advertise_sid;
repo_config_get_bool(the_repository, "transfer.advertisesid", &advertise_sid);
- ensure_server_supports_v2("fetch");
- packet_buf_write(req_buf, "command=fetch");
+ ensure_server_supports_v2(command);
+ packet_buf_write(req_buf, "command=%s", command);
if (server_supports_v2("agent"))
packet_buf_write(req_buf, "agent=%s", git_user_agent_sanitized());
if (advertise_sid && server_supports_v2("session-id"))
diff --git a/connect.h b/connect.h
index c4f6ea4b0a..c2bf492ed9 100644
--- a/connect.h
+++ b/connect.h
@@ -35,7 +35,11 @@ void check_stateless_delimiter(int stateless_rpc,
const char *error);
struct string_list;
-void write_fetch_command_and_capabilities(struct strbuf *req_buf,
- const struct string_list *server_options);
+/*
+ * Writes a command along with the requested server capabilities/features into a
+ * request buffer.
+ */
+void write_command_and_capabilities(struct strbuf *req_buf, const char *command,
+ const struct string_list *server_options);
#endif
diff --git a/fetch-pack.c b/fetch-pack.c
index 4a8a70b5f3..3d32114907 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -1387,7 +1387,7 @@ static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out,
int done_sent = 0;
struct strbuf req_buf = STRBUF_INIT;
- write_fetch_command_and_capabilities(&req_buf, args->server_options);
+ write_command_and_capabilities(&req_buf, "fetch", args->server_options);
if (args->use_thin_pack)
packet_buf_write(&req_buf, "thin-pack");
@@ -2255,7 +2255,7 @@ void negotiate_using_fetch(const struct oid_array *negotiation_restrict_tips,
the_repository, "%d",
negotiation_round);
strbuf_reset(&req_buf);
- write_fetch_command_and_capabilities(&req_buf, server_options);
+ write_command_and_capabilities(&req_buf, "fetch", server_options);
packet_buf_write(&req_buf, "wait-for-done");
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 06/13] fetch-pack: move function to connect.c
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Jonathan Tan,
Calvin Wan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
write_fetch_command_and_capabilities will be refactored in a subsequent
commit where it will become a more general-purpose function, making it
more accessible to additional commands in the future.
Move `write_fetch_command_and_capabilities()` to `connect.c`, where
there are similar purpose functions.
Because string_list is only used as a pointer, use a forward
declaration [1].
[1]: https://lore.kernel.org/git/Z0RIqUAoEob8lGfM@pks.im/
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
connect.c | 34 ++++++++++++++++++++++++++++++++++
connect.h | 4 ++++
fetch-pack.c | 34 ----------------------------------
3 files changed, 38 insertions(+), 34 deletions(-)
diff --git a/connect.c b/connect.c
index 47e39d2a73..1dced8e632 100644
--- a/connect.c
+++ b/connect.c
@@ -700,6 +700,40 @@ int server_supports(const char *feature)
return !!server_feature_value(feature, NULL);
}
+void write_fetch_command_and_capabilities(struct strbuf *req_buf,
+ const struct string_list *server_options)
+{
+ const char *hash_name;
+ int advertise_sid;
+
+ repo_config_get_bool(the_repository, "transfer.advertisesid", &advertise_sid);
+
+ ensure_server_supports_v2("fetch");
+ packet_buf_write(req_buf, "command=fetch");
+ if (server_supports_v2("agent"))
+ packet_buf_write(req_buf, "agent=%s", git_user_agent_sanitized());
+ if (advertise_sid && server_supports_v2("session-id"))
+ packet_buf_write(req_buf, "session-id=%s", trace2_session_id());
+ if (server_options && server_options->nr) {
+ ensure_server_supports_v2("server-option");
+ for (size_t i = 0; i < server_options->nr; i++)
+ packet_buf_write(req_buf, "server-option=%s",
+ server_options->items[i].string);
+ }
+
+ if (server_feature_v2("object-format", &hash_name)) {
+ const unsigned int hash_algo = hash_algo_by_name(hash_name);
+ if (hash_algo_by_ptr(the_hash_algo) != hash_algo)
+ die(_("mismatched algorithms: client %s; server %s"),
+ the_hash_algo->name, hash_name);
+ packet_buf_write(req_buf, "object-format=%s", the_hash_algo->name);
+ } else if (hash_algo_by_ptr(the_hash_algo) != GIT_HASH_SHA1_LEGACY) {
+ die(_("the server does not support algorithm '%s'"),
+ the_hash_algo->name);
+ }
+ packet_buf_delim(req_buf);
+}
+
static const char *url_scheme_name(enum url_scheme scheme)
{
switch (scheme) {
diff --git a/connect.h b/connect.h
index aa482a37fb..c4f6ea4b0a 100644
--- a/connect.h
+++ b/connect.h
@@ -34,4 +34,8 @@ void check_stateless_delimiter(int stateless_rpc,
struct packet_reader *reader,
const char *error);
+struct string_list;
+void write_fetch_command_and_capabilities(struct strbuf *req_buf,
+ const struct string_list *server_options);
+
#endif
diff --git a/fetch-pack.c b/fetch-pack.c
index ad07603755..4a8a70b5f3 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -1376,40 +1376,6 @@ static int add_haves(struct fetch_negotiator *negotiator,
return haves_added;
}
-static void write_fetch_command_and_capabilities(struct strbuf *req_buf,
- const struct string_list *server_options)
-{
- const char *hash_name;
- int advertise_sid;
-
- repo_config_get_bool(the_repository, "transfer.advertisesid", &advertise_sid);
-
- ensure_server_supports_v2("fetch");
- packet_buf_write(req_buf, "command=fetch");
- if (server_supports_v2("agent"))
- packet_buf_write(req_buf, "agent=%s", git_user_agent_sanitized());
- if (advertise_sid && server_supports_v2("session-id"))
- packet_buf_write(req_buf, "session-id=%s", trace2_session_id());
- if (server_options && server_options->nr) {
- ensure_server_supports_v2("server-option");
- for (size_t i = 0; i < server_options->nr; i++)
- packet_buf_write(req_buf, "server-option=%s",
- server_options->items[i].string);
- }
-
- if (server_feature_v2("object-format", &hash_name)) {
- const unsigned int hash_algo = hash_algo_by_name(hash_name);
- if (hash_algo_by_ptr(the_hash_algo) != hash_algo)
- die(_("mismatched algorithms: client %s; server %s"),
- the_hash_algo->name, hash_name);
- packet_buf_write(req_buf, "object-format=%s", the_hash_algo->name);
- } else if (hash_algo_by_ptr(the_hash_algo) != GIT_HASH_SHA1_LEGACY) {
- die(_("the server does not support algorithm '%s'"),
- the_hash_algo->name);
- }
- packet_buf_delim(req_buf);
-}
-
static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out,
struct fetch_pack_args *args,
const struct ref *wants, struct oidset *common,
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 05/13] fetch-pack: prepare function to be moved
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon, Jonathan Tan,
Calvin Wan
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
`write_fetch_command_and_capabilities()` will be refactored and moved in
subsequent commits where it will become a more general-purpose function,
making it more accessible to additional commands in the future.
To move `write_fetch_command_and_capabilities()` to `connect.c`, we
previously need to adjust how `advertise_sid` is managed. Currently in
`fetch_pack.c`, `advertise_sid` is a static variable, modified using
`repo_config_get_bool()`.
Initialize `advertise_sid` at the begining by directly using
`repo_config_get_bool()`. This change is safe because:
In the original `fetch-pack.c` code, there are only two places that write
`advertise_sid`:
1. In function `do_fetch_pack()`:
if (!server_supports("session_id"))
advertise_sid = 0;
2. In function `fetch_pack_config()`:
repo_config_get_bool("transfer.advertisesid", &advertise_sid);
About 1, since `do_fetch_pack()` is only relevant for protocol v1, this
assignment can be ignored, as `write_fetch_command_and_capabilities()`
is only used in v2.
About 2, `repo_config_get_bool()` is from `config.h` and it's an
out-of-box dependency of `connect.c`, so we can reuse it directly.
Helped-by: Jonathan Tan <jonathantanmy@google.com>
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Calvin Wan <calvinwan@google.com>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
fetch-pack.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fetch-pack.c b/fetch-pack.c
index f13951d154..ad07603755 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -1380,6 +1380,9 @@ static void write_fetch_command_and_capabilities(struct strbuf *req_buf,
const struct string_list *server_options)
{
const char *hash_name;
+ int advertise_sid;
+
+ repo_config_get_bool(the_repository, "transfer.advertisesid", &advertise_sid);
ensure_server_supports_v2("fetch");
packet_buf_write(req_buf, "command=fetch");
@@ -1395,7 +1398,7 @@ static void write_fetch_command_and_capabilities(struct strbuf *req_buf,
}
if (server_feature_v2("object-format", &hash_name)) {
- int hash_algo = hash_algo_by_name(hash_name);
+ const unsigned int hash_algo = hash_algo_by_name(hash_name);
if (hash_algo_by_ptr(the_hash_algo) != hash_algo)
die(_("mismatched algorithms: client %s; server %s"),
the_hash_algo->name, hash_name);
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 04/13] t1006: split test utility functions into new "lib-cat-file.sh"
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Eric Ju <eric.peijian@gmail.com>
This refactor extracts utility functions from the cat-file's test
script "t1006-cat-file.sh" into a new "lib-cat-file.sh" dedicated
library file.
A subsequent commit will need this functions, the goal is to improve
code reuse and readability,enabling future tests to leverage these
utilities without duplicating code.
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
t/lib-cat-file.sh | 16 ++++++++++++++++
t/t1006-cat-file.sh | 13 +------------
2 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/t/lib-cat-file.sh b/t/lib-cat-file.sh
new file mode 100644
index 0000000000..44af232d74
--- /dev/null
+++ b/t/lib-cat-file.sh
@@ -0,0 +1,16 @@
+# Library of git-cat-file related test functions.
+
+# Print a string without a trailing newline.
+echo_without_newline () {
+ printf '%s' "$*"
+}
+
+# Print a string without newlines and replace them with a NULL character (\0).
+echo_without_newline_nul () {
+ echo_without_newline "$@" | tr '\n' '\0'
+}
+
+# Calculate the length of a string.
+strlen () {
+ echo_without_newline "$1" | wc -c | sed -e 's/^ *//'
+}
diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index 8e2c52652c..8360f3bbd9 100755
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -4,6 +4,7 @@ test_description='git cat-file'
. ./test-lib.sh
. "$TEST_DIRECTORY/lib-loose.sh"
+. "$TEST_DIRECTORY"/lib-cat-file.sh
test_cmdmode_usage () {
test_expect_code 129 "$@" 2>err &&
@@ -99,18 +100,6 @@ do
'
done
-echo_without_newline () {
- printf '%s' "$*"
-}
-
-echo_without_newline_nul () {
- echo_without_newline "$@" | tr '\n' '\0'
-}
-
-strlen () {
- echo_without_newline "$1" | wc -c | sed -e 's/^ *//'
-}
-
run_tests () {
type=$1
object_name="$2"
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 03/13] cat-file: declare loop counter inside for()
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Eric Ju <eric.peijian@gmail.com>
Some code used in this series declares variable i and only uses it
in a for loop, not in any other logic outside the loop.
Change the declaration of i to be inside the for loop for readability.
While at it, we also change its type from "int" to "size_t" where the
latter makes more sense.
Helped-by: Christian Couder <chriscool@tuxfamily.org>
Signed-off-by: Eric Ju <eric.peijian@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
builtin/cat-file.c | 13 ++++---------
fetch-pack.c | 3 +--
2 files changed, 5 insertions(+), 11 deletions(-)
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index d6ef8414ee..1e5473ab70 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -718,14 +718,12 @@ static void dispatch_calls(struct batch_options *opt,
struct strbuf *output,
struct expand_data *data,
struct queued_cmd *cmd,
- int nr)
+ size_t nr)
{
- int i;
-
if (!opt->buffer_output)
die(_("flush is only for --buffer mode"));
- for (i = 0; i < nr; i++)
+ for (size_t i = 0; i < nr; i++)
cmd[i].fn(opt, cmd[i].line, output, data);
fflush(stdout);
@@ -733,9 +731,7 @@ static void dispatch_calls(struct batch_options *opt,
static void free_cmds(struct queued_cmd *cmd, size_t *nr)
{
- size_t i;
-
- for (i = 0; i < *nr; i++)
+ for (size_t i = 0; i < *nr; i++)
FREE_AND_NULL(cmd[i].line);
*nr = 0;
@@ -762,7 +758,6 @@ static void batch_objects_command(struct batch_options *opt,
size_t alloc = 0, nr = 0;
while (strbuf_getdelim_strip_crlf(&input, stdin, opt->input_delim) != EOF) {
- int i;
const struct parse_cmd *cmd = NULL;
const char *p = NULL, *cmd_end;
struct queued_cmd call = {0};
@@ -772,7 +767,7 @@ static void batch_objects_command(struct batch_options *opt,
if (isspace(*input.buf))
die(_("whitespace before command: '%s'"), input.buf);
- for (i = 0; i < ARRAY_SIZE(commands); i++) {
+ for (size_t i = 0; i < ARRAY_SIZE(commands); i++) {
if (!skip_prefix(input.buf, commands[i].name, &cmd_end))
continue;
diff --git a/fetch-pack.c b/fetch-pack.c
index 120e01f3cf..f13951d154 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -1388,9 +1388,8 @@ static void write_fetch_command_and_capabilities(struct strbuf *req_buf,
if (advertise_sid && server_supports_v2("session-id"))
packet_buf_write(req_buf, "session-id=%s", trace2_session_id());
if (server_options && server_options->nr) {
- int i;
ensure_server_supports_v2("server-option");
- for (i = 0; i < server_options->nr; i++)
+ for (size_t i = 0; i < server_options->nr; i++)
packet_buf_write(req_buf, "server-option=%s",
server_options->items[i].string);
}
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 02/13] git-compat-util: add strtoul_szt() with error handling
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
From: Eric Ju <eric.peijian@gmail.com>
We already have strtoul_ui() and similar functions that provide proper
error handling using strtoul from the standard library. However,
there isn't currently a variant that returns an unsigned long.
This variant is needed in a subsequent commit to enable returning an
size_t with proper error handling.
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
git-compat-util.h | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/git-compat-util.h b/git-compat-util.h
index 8809776407..7f417f1acf 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -975,6 +975,26 @@ static inline int strtoul_ui(char const *s, int base, unsigned int *result)
return 0;
}
+/*
+ * Convert a string to a size_t using the standard library's strtoul, with
+ * additional error handling to ensure robustness.
+ */
+static inline int strtoul_szt(char const *s, int base, size_t *result)
+{
+ unsigned long ul;
+ char *p;
+
+ errno = 0;
+ /* negative values would be accepted by strtoul */
+ if (strchr(s, '-'))
+ return -1;
+ ul = strtoul(s, &p, base);
+ if (errno || *p || p == s)
+ return -1;
+ *result = ul;
+ return 0;
+}
+
static inline int strtol_i(char const *s, int base, int *result)
{
long ul;
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 01/13] transport-helper: fix memory leak of helper on disconnect
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260625-ps-eric-work-rebase-v14-0-09f7ffe21a53@gmail.com>
disconnect_helper() only frees data inside of the if(data->helper)
block [1]. When the transport is disconnected without the helper
being fully started, data->name allocated in transport_helper_init()
is never freed.
Move FREE_AND_NULL(data->name) outside the conditional block so it's
always freed on disconnect.
[1]: https://lore.kernel.org/git/05fbadbae2184479c87c37675dde7bd79b3e32ab.1716465556.git.ps@pks.im/
Mentored-by: Karthik Nayak <karthik.188@gmail.com>
Mentored-by: Chandra Pratap <chandrapratap3519@gmail.com>
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
transport-helper.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/transport-helper.c b/transport-helper.c
index 80f90eb7ba..f195070788 100644
--- a/transport-helper.c
+++ b/transport-helper.c
@@ -266,9 +266,9 @@ static int disconnect_helper(struct transport *transport)
close(data->helper->out);
fclose(data->out);
res = finish_command(data->helper);
- FREE_AND_NULL(data->name);
FREE_AND_NULL(data->helper);
}
+ FREE_AND_NULL(data->name);
return res;
}
--
2.54.0
^ permalink raw reply related
* [PATCH GSoC v14 00/13] cat-file: add remote-object-info to batch-command
From: Pablo Sabater @ 2026-06-25 12:13 UTC (permalink / raw)
To: git
Cc: pabloosabaterr, chandrapratap3519, chriscool, eric.peijian,
gitster, jltobler, karthik.188, peff, toon
In-Reply-To: <20260619-ps-eric-work-rebase-v13-0-3d4c7315d2f8@gmail.com>
This patch series is a continuation of Eric Ju's (eric.peijian@gmail.com) and
Calvin Wan's (calvinwan@google.com) patch series [1] and [2] respectively.
Sometimes it is beneficial to retrieve information about an object without
having to download it completely. The server logic for retrieving size has
already been implemented and merged in "a2ba162cda (object-info: support for
retrieving object info, 2021-04-20)"[3]. This patch series implement the client
option for it.
Eric's series adds the `remote-object-info` command to
`cat-file --batch-command`. This command allows the client to make an
object-info command request to a server that supports protocol v2.
If the server uses protocol v2 but does not support the object-info capability,
`cat-file --batch-command` will die.
If a user attempts to use `remote-object-info` with protocol v1,
`cat-file --batch-command` will die.
Currently, only the size (%(objectsize)) is supported end to end in this
implementation. The type (%(objecttype)) is known by the client's allow-list
and request path but is not supported on the server side nor the response
parsing. A follow up series will add full end-to-end support for %(objecttype).
The default format for remote-object-info is set to %(objectname) %(objectsize).
Once %(objecttype) is supported, the default format will be unified accordingly.
If the batch command format includes unsupported fields such as %(objecttype),
%(objectsize:disk), or %(deltabase), the command will return empty strings for
each unsupported field.
This series completes Eric's work mainly with the refactor of the validation
of the placeholder with an allow-list that filters what the client asks with
what the server is capable of provide following Jeff King's idea [4].
GitHub CI: https://github.com/pabloosabaterr/git/actions/runs/28159024232
[1]: https://lore.kernel.org/git/20250221190451.12536-1-eric.peijian@gmail.com/
[2]: https://lore.kernel.org/git/20220728230210.2952731-1-calvinwan@google.com/#t
[3]: https://git.kernel.org/pub/scm/git/git.git/commit/?id=a2ba162cda2acc171c3e36acbbc854792b093cb7
[4]: https://lore.kernel.org/git/20250313060250.GH94015@coredump.intra.peff.net/
[5]: https://lore.kernel.org/git/CAN2LT1D3d=yMYVhBjpj5PvyjfTVjwqcFPNViuCJ=f49YbCZuJg@mail.gmail.com/
Changes since v13:
- Changed the introduced strtoul_ul to strtoul_szt as a recent patch
changed the type of object_info.sizep to size_t.
<37d030d8675e94caee2eecb8398691d385d444bd.1781524349.git.gitgitgadget@gmail.com>
- Fixed commit typos and style.
- "fetch-pack: move function to connect.c" is now 2 different commits:
first a cleanup and a second to only move the function.
- Fixed old code brought from the rebase to match upstream: use
SHA1_LEGACY instead of SHA1
- Remove static declarations from cmd_remote_remote_info() and
get_remote_info().
- Add a comment justifying why there will be no overflow on explicit
cast.
Signed-off-by: Pablo Sabater <pabloosabaterr@gmail.com>
---
Calvin Wan (3):
fetch-pack: move fetch initialization
serve: advertise object-info feature
transport: add client support for object-info
Eric Ju (4):
git-compat-util: add strtoul_szt() with error handling
cat-file: declare loop counter inside for()
t1006: split test utility functions into new "lib-cat-file.sh"
cat-file: add remote-object-info to batch-command
Pablo Sabater (6):
transport-helper: fix memory leak of helper on disconnect
fetch-pack: prepare function to be moved
fetch-pack: move function to connect.c
connect: refactor packet writing
cat-file: validate remote atoms with allow_list
cat-file: make remote-object-info allow-list dynamic
Documentation/git-cat-file.adoc | 25 +-
Makefile | 1 +
builtin/cat-file.c | 222 ++++++++++-
connect.c | 34 ++
connect.h | 8 +
fetch-object-info.c | 110 ++++++
fetch-object-info.h | 22 ++
fetch-pack.c | 51 +--
fetch-pack.h | 2 +
git-compat-util.h | 20 +
meson.build | 1 +
object-file.c | 10 +
odb.h | 3 +
serve.c | 5 +-
t/lib-cat-file.sh | 16 +
t/meson.build | 1 +
t/t1006-cat-file.sh | 13 +-
t/t1017-cat-file-remote-object-info.sh | 699 +++++++++++++++++++++++++++++++++
transport-helper.c | 13 +-
transport.c | 28 +-
transport.h | 11 +
21 files changed, 1220 insertions(+), 75 deletions(-)
---
base-commit: ab776a62a78576513ee121424adb19597fbb7613
change-id: 20260608-ps-eric-work-rebase-b73ae84ba671
Best regards,
--
Pablo Sabater <pabloosabaterr@gmail.com>
^ permalink raw reply
* [PATCH v3 4/4] connected: search promisor objects generically
From: Patrick Steinhardt @ 2026-06-25 9:57 UTC (permalink / raw)
To: git; +Cc: Junio C Hamano, Christian Couder
In-Reply-To: <20260625-pks-connected-generic-promisor-checks-v3-0-7308f3b9dc44@pks.im>
When performing connectivity checks we have to figure out whether any of
the new objects are promisor objects, as we cannot assume full
connectivity if so.
This check is performed by iterating through all packfiles in the
repository and searching each of them for the given object. Of course,
this mechanism is quite specific to implementation details of the object
database, as we assume that it uses packfiles in the first place.
Refactor the logic so that we instead use `odb_for_each_object_ext()`
with an object prefix filter and the `ODB_FOR_EACH_OBJECT_PROMISOR_ONLY`
flag. This will yield all objects that have the exact object name and
that are part of a promisor pack in a generic way.
Add a test to verify that we indeed use the optimization.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
connected.c | 35 ++++++++++++++++++++++++-----------
t/t5616-partial-clone.sh | 24 ++++++++++++++++++++++++
2 files changed, 48 insertions(+), 11 deletions(-)
diff --git a/connected.c b/connected.c
index d2b334173f..929b9bd28d 100644
--- a/connected.c
+++ b/connected.c
@@ -11,6 +11,15 @@
#include "packfile.h"
#include "promisor-remote.h"
+static int promised_object_cb(const struct object_id *oid UNUSED,
+ struct object_info *oi UNUSED,
+ void *payload)
+{
+ bool *found = payload;
+ *found = true;
+ return 1;
+}
+
/*
* For partial clones, we don't want to have to do a regular connectivity check
* because we have to enumerate and exclude all promisor objects (slow), and
@@ -30,25 +39,29 @@ static int check_connected_promisor(oid_iterate_fn fn,
void *cb_data,
const struct object_id **oid)
{
+ struct odb_for_each_object_options opts = {
+ .flags = ODB_FOR_EACH_OBJECT_PROMISOR_ONLY,
+ .prefix_hex_len = the_repository->hash_algo->hexsz,
+ };
+ int err;
+
odb_reprepare(the_repository->objects);
do {
- struct packed_git *p;
+ bool found = false;
- repo_for_each_pack(the_repository, p) {
- if (!p->pack_promisor)
- continue;
- if (find_pack_entry_one(*oid, p))
- goto promisor_pack_found;
- }
+ opts.prefix = *oid;
+
+ err = odb_for_each_object_ext(the_repository->objects, NULL,
+ promised_object_cb, &found, &opts);
+ if (err < 0)
+ return err;
/*
* We have found an object that is not part of a promisor pack,
* and thus we cannot skip the full connectivity check.
*/
- return 0;
-
-promisor_pack_found:
- ;
+ if (!found)
+ return 0;
} while ((*oid = fn(cb_data)) != NULL);
return 1;
diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh
index 1c2805acca..905052072d 100755
--- a/t/t5616-partial-clone.sh
+++ b/t/t5616-partial-clone.sh
@@ -97,6 +97,30 @@ test_expect_success 'partial fetch inherits filter settings' '
test_line_count = 5 observed
'
+test_expect_success 'partial fetch does not spawn rev-list connectivity check' '
+ test_when_finished "rm -rf connectivity-remote connectivity-client" &&
+ git init connectivity-remote &&
+ test_commit -C connectivity-remote one &&
+ git -C connectivity-remote config uploadpack.allowfilter 1 &&
+ git -C connectivity-remote config uploadpack.allowanysha1inwant 1 &&
+
+ git clone --no-checkout --filter=blob:none \
+ "file://$(pwd)/connectivity-remote" connectivity-client &&
+
+ # When doing a partial fetch where all tips are part of a promisor pack
+ # we want to skip the connectivity check, as these objects are allowed
+ # to not be fully connected.
+ test_commit -C connectivity-remote two &&
+ GIT_TRACE2_EVENT="$(pwd)/partial.trace" git -C connectivity-client fetch origin &&
+ test_subcommand_flex ! git rev-list --objects --stdin <partial.trace &&
+
+ # Otherwise, when doing a fetch where any of the tips is not part of a
+ # promisor pack, then we must run the connectivity check.
+ test_commit -C connectivity-remote three &&
+ GIT_TRACE2_EVENT="$(pwd)/full.trace" git -C connectivity-client fetch --no-filter origin &&
+ test_subcommand_flex git rev-list --objects --stdin <full.trace
+'
+
# force dynamic object fetch using diff.
# we should only get 1 new blob (for the file in origin/main).
test_expect_success 'verify diff causes dynamic object fetch' '
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v3 3/4] connected: split out promisor-based connectivity check
From: Patrick Steinhardt @ 2026-06-25 9:57 UTC (permalink / raw)
To: git; +Cc: Junio C Hamano, Christian Couder
In-Reply-To: <20260625-pks-connected-generic-promisor-checks-v3-0-7308f3b9dc44@pks.im>
When performing a connectivity check in a partial clone we try to avoid
doing the connectivity check by checking whether all new tips are part
of a promisor pack. This makes use of the fact that we don't expect full
connectivity for promised objects anyway, so it's basically fine if
those objects are not fully connected.
The logic that handles this promisor-based check is somewhat hard to
read though as it uses nested loops and gotos. Pull it out into a
standalone function, which makes it a bit easier to reason about.
We'll also further simplify the function in the next commit.
Suggested-by: Christian Couder <christian.couder@gmail.com>
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
connected.c | 85 ++++++++++++++++++++++++++++++++++++-------------------------
1 file changed, 51 insertions(+), 34 deletions(-)
diff --git a/connected.c b/connected.c
index 7e26976832..d2b334173f 100644
--- a/connected.c
+++ b/connected.c
@@ -11,6 +11,49 @@
#include "packfile.h"
#include "promisor-remote.h"
+/*
+ * For partial clones, we don't want to have to do a regular connectivity check
+ * because we have to enumerate and exclude all promisor objects (slow), and
+ * then the connectivity check itself becomes a no-op because in a partial
+ * clone every object is a promisor object. Instead, just make sure we
+ * received, in a promisor packfile, the objects pointed to by each wanted ref.
+ *
+ * Before checking for promisor packs, be sure we have the latest pack-files
+ * loaded into memory.
+ *
+ * Returns 1 when all object IDs have been found in promisor packs, in which
+ * case we're fully connected and thus done. Returns 0 when we have found
+ * objects in non-promisor packs, in which case we'll have to fall back to the
+ * rev-list-based connectivity checks. Returns a negative error code on error.
+ */
+static int check_connected_promisor(oid_iterate_fn fn,
+ void *cb_data,
+ const struct object_id **oid)
+{
+ odb_reprepare(the_repository->objects);
+ do {
+ struct packed_git *p;
+
+ repo_for_each_pack(the_repository, p) {
+ if (!p->pack_promisor)
+ continue;
+ if (find_pack_entry_one(*oid, p))
+ goto promisor_pack_found;
+ }
+
+ /*
+ * We have found an object that is not part of a promisor pack,
+ * and thus we cannot skip the full connectivity check.
+ */
+ return 0;
+
+promisor_pack_found:
+ ;
+ } while ((*oid = fn(cb_data)) != NULL);
+
+ return 1;
+}
+
/*
* If we feed all the commits we want to verify to this command
*
@@ -46,42 +89,16 @@ int check_connected(oid_iterate_fn fn, void *cb_data,
}
if (repo_has_promisor_remote(the_repository)) {
- /*
- * For partial clones, we don't want to have to do a regular
- * connectivity check because we have to enumerate and exclude
- * all promisor objects (slow), and then the connectivity check
- * itself becomes a no-op because in a partial clone every
- * object is a promisor object. Instead, just make sure we
- * received, in a promisor packfile, the objects pointed to by
- * each wanted ref.
- *
- * Before checking for promisor packs, be sure we have the
- * latest pack-files loaded into memory.
- */
- odb_reprepare(the_repository->objects);
- do {
- struct packed_git *p;
-
- repo_for_each_pack(the_repository, p) {
- if (!p->pack_promisor)
- continue;
- if (find_pack_entry_one(oid, p))
- goto promisor_pack_found;
- }
- /*
- * Fallback to rev-list with oid and the rest of the
- * object IDs provided by fn.
- */
- goto no_promisor_pack_found;
-promisor_pack_found:
- ;
- } while ((oid = fn(cb_data)) != NULL);
- if (opt->err_fd)
- close(opt->err_fd);
- return 0;
+ err = check_connected_promisor(fn, cb_data, &oid);
+ if (err) {
+ if (opt->err_fd)
+ close(opt->err_fd);
+ if (err > 0)
+ err = 0;
+ return err;
+ }
}
-no_promisor_pack_found:
if (opt->shallow_file) {
strvec_push(&rev_list.args, "--shallow-file");
strvec_push(&rev_list.args, opt->shallow_file);
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v3 2/4] odb/source-packed: support flags when iterating an object prefix
From: Patrick Steinhardt @ 2026-06-25 9:57 UTC (permalink / raw)
To: git; +Cc: Junio C Hamano, Christian Couder
In-Reply-To: <20260625-pks-connected-generic-promisor-checks-v3-0-7308f3b9dc44@pks.im>
Callers of `odb_for_each_object()` can specify an optional object name
prefix so that we only yield objects that match it. This is incompatible
though with passing flags at the same time, as we don't yet know to
handle them.
Loosen this restriction by calling `should_exclude_pack()`.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
odb/source-packed.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/odb/source-packed.c b/odb/source-packed.c
index 3afc4bf01f..96fc436770 100644
--- a/odb/source-packed.c
+++ b/odb/source-packed.c
@@ -148,6 +148,7 @@ static int for_each_prefixed_object_in_midx(
const struct odb_for_each_object_options *opts,
struct odb_source_packed_for_each_object_wrapper_data *data)
{
+ bool pack_errors = false;
int ret;
for (; m; m = m->base_midx) {
@@ -176,6 +177,20 @@ static int for_each_prefixed_object_in_midx(
if (!match_hash(len, opts->prefix->hash, current->hash))
break;
+ if (opts->flags) {
+ uint32_t pack_id = nth_midxed_pack_int_id(m, i);
+ struct packed_git *pack;
+
+ if (prepare_midx_pack(m, pack_id)) {
+ pack_errors = true;
+ continue;
+ }
+
+ pack = nth_midxed_pack(m, pack_id);
+ if (should_exclude_pack(pack, opts->flags))
+ continue;
+ }
+
if (data->request) {
struct object_info oi = *data->request;
@@ -198,6 +213,8 @@ static int for_each_prefixed_object_in_midx(
ret = 0;
out:
+ if (!ret && pack_errors)
+ ret = -1;
return ret;
}
@@ -260,9 +277,6 @@ static int odb_source_packed_for_each_prefixed_object(
bool pack_errors = false;
int ret;
- if (opts->flags)
- BUG("flags unsupported");
-
store->skip_mru_updates = true;
m = get_multi_pack_index(store);
@@ -275,6 +289,8 @@ static int odb_source_packed_for_each_prefixed_object(
for (e = packfile_store_get_packs(store); e; e = e->next) {
if (e->pack->multi_pack_index)
continue;
+ if (should_exclude_pack(e->pack, opts->flags))
+ continue;
if (open_pack_index(e->pack)) {
pack_errors = true;
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v3 1/4] odb/source-packed: extract logic to skip certain packs
From: Patrick Steinhardt @ 2026-06-25 9:57 UTC (permalink / raw)
To: git; +Cc: Junio C Hamano, Christian Couder
In-Reply-To: <20260625-pks-connected-generic-promisor-checks-v3-0-7308f3b9dc44@pks.im>
The caller can pass flags that allow them to filter out specific kinds
of objects when iterating objects via `odb_for_each_object()`. This only
works for "normal" iteration though, as we `BUG()` when the user passes
flags and specifies an object prefix.
This limitation will be lifted in the next commit. Prepare for this by
extracting the logic that skips certain kinds of packs so that we can
easily reuse it.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
odb/source-packed.c | 28 ++++++++++++++++++----------
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/odb/source-packed.c b/odb/source-packed.c
index 42c28fba0e..3afc4bf01f 100644
--- a/odb/source-packed.c
+++ b/odb/source-packed.c
@@ -126,6 +126,22 @@ static int match_hash(unsigned len, const unsigned char *a, const unsigned char
return 1;
}
+static bool should_exclude_pack(struct packed_git *p, enum odb_for_each_object_flags flags)
+{
+ if ((flags & ODB_FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
+ return true;
+ if ((flags & ODB_FOR_EACH_OBJECT_PROMISOR_ONLY) &&
+ !p->pack_promisor)
+ return true;
+ if ((flags & ODB_FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS) &&
+ p->pack_keep_in_core)
+ return true;
+ if ((flags & ODB_FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS) &&
+ p->pack_keep)
+ return true;
+ return false;
+}
+
static int for_each_prefixed_object_in_midx(
struct odb_source_packed *store,
struct multi_pack_index *m,
@@ -306,17 +322,9 @@ static int odb_source_packed_for_each_object(struct odb_source *source,
for (e = packfile_store_get_packs(packed); e; e = e->next) {
struct packed_git *p = e->pack;
- if ((opts->flags & ODB_FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
- continue;
- if ((opts->flags & ODB_FOR_EACH_OBJECT_PROMISOR_ONLY) &&
- !p->pack_promisor)
- continue;
- if ((opts->flags & ODB_FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS) &&
- p->pack_keep_in_core)
- continue;
- if ((opts->flags & ODB_FOR_EACH_OBJECT_SKIP_ON_DISK_KEPT_PACKS) &&
- p->pack_keep)
+ if (should_exclude_pack(p, opts->flags))
continue;
+
if (open_pack_index(p)) {
pack_errors = 1;
continue;
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v3 0/4] connected: search promisor objects generically
From: Patrick Steinhardt @ 2026-06-25 9:57 UTC (permalink / raw)
To: git; +Cc: Junio C Hamano, Christian Couder
In-Reply-To: <20260622-pks-connected-generic-promisor-checks-v1-0-25eba2698202@pks.im>
Hi,
this patch series refactors "connected.c" so that we search for promisor
objects in a generic way instead of reaching into internal of the object
database. As a result, the connectivity checks will work properly in
repos that don't use packfiles in the first place.
The series is built on top of 8d96f09e92 (Merge branch
'js/objects-larger-than-4gb-on-windows', 2026-06-19) with
ps/odb-source-packed at 1bba3c035d (odb/source-packed: drop pointer to
"files" parent source, 2026-06-17) merged into it.
Changes in v3:
- Fix reversed logic for whether the promised object was found, which
broke in v2.
- Add a test that verifies that we indeed use the optimized check.
- Match the hash before computing the flags so that we break out of
the loop more eagerly.
- Link to v2: https://patch.msgid.link/20260624-pks-connected-generic-promisor-checks-v2-0-132d73ee47b9@pks.im
Changes in v2:
- Fix the accidentally-dropped call to `odb_reprepare()`.
- Add a preparatory commit that splits out `check_connected_promisor()`.
I think also splitting out `check_connected_rev_list()` would only
have diminishing returns, so I skipped that part.
- Link to v1: https://patch.msgid.link/20260622-pks-connected-generic-promisor-checks-v1-0-25eba2698202@pks.im
Thanks!
Patrick
---
Patrick Steinhardt (4):
odb/source-packed: extract logic to skip certain packs
odb/source-packed: support flags when iterating an object prefix
connected: split out promisor-based connectivity check
connected: search promisor objects generically
connected.c | 98 +++++++++++++++++++++++++++++++-----------------
odb/source-packed.c | 50 +++++++++++++++++-------
t/t5616-partial-clone.sh | 24 ++++++++++++
3 files changed, 125 insertions(+), 47 deletions(-)
Range-diff versus v2:
1: 74d1d04183 = 1: 93b7b3b4cb odb/source-packed: extract logic to skip certain packs
2: 02aa39bf1e ! 2: 3fd0885b85 odb/source-packed: support flags when iterating an object prefix
@@ odb/source-packed.c: static int for_each_prefixed_object_in_midx(
for (; m; m = m->base_midx) {
@@ odb/source-packed.c: static int for_each_prefixed_object_in_midx(
- const struct object_id *current = NULL;
- struct object_id oid;
+ if (!match_hash(len, opts->prefix->hash, current->hash))
+ break;
+ if (opts->flags) {
+ uint32_t pack_id = nth_midxed_pack_int_id(m, i);
@@ odb/source-packed.c: static int for_each_prefixed_object_in_midx(
+ continue;
+ }
+
- current = nth_midxed_object_oid(&oid, m, i);
+ if (data->request) {
+ struct object_info oi = *data->request;
- if (!match_hash(len, opts->prefix->hash, current->hash))
@@ odb/source-packed.c: static int for_each_prefixed_object_in_midx(
ret = 0;
3: ff9df84f65 = 3: 47a4732daf connected: split out promisor-based connectivity check
4: a10d2e6a1e ! 4: 239abf2731 connected: search promisor objects generically
@@ Commit message
flag. This will yield all objects that have the exact object name and
that are part of a promisor pack in a generic way.
+ Add a test to verify that we indeed use the optimization.
+
Signed-off-by: Patrick Steinhardt <ps@pks.im>
## connected.c ##
@@ connected.c
+static int promised_object_cb(const struct object_id *oid UNUSED,
+ struct object_info *oi UNUSED,
-+ void *payload UNUSED)
++ void *payload)
+{
++ bool *found = payload;
++ *found = true;
+ return 1;
+}
+
@@ connected.c: static int check_connected_promisor(oid_iterate_fn fn,
odb_reprepare(the_repository->objects);
do {
- struct packed_git *p;
-+ opts.prefix = *oid;
++ bool found = false;
- repo_for_each_pack(the_repository, p) {
- if (!p->pack_promisor)
@@ connected.c: static int check_connected_promisor(oid_iterate_fn fn,
- if (find_pack_entry_one(*oid, p))
- goto promisor_pack_found;
- }
-+ err = odb_for_each_object_ext(the_repository->objects,
-+ NULL, promised_object_cb,
-+ NULL, &opts);
++ opts.prefix = *oid;
++
++ err = odb_for_each_object_ext(the_repository->objects, NULL,
++ promised_object_cb, &found, &opts);
+ if (err < 0)
+ return err;
@@ connected.c: static int check_connected_promisor(oid_iterate_fn fn,
-
-promisor_pack_found:
- ;
-+ if (err > 0)
++ if (!found)
+ return 0;
} while ((*oid = fn(cb_data)) != NULL);
return 1;
+
+ ## t/t5616-partial-clone.sh ##
+@@ t/t5616-partial-clone.sh: test_expect_success 'partial fetch inherits filter settings' '
+ test_line_count = 5 observed
+ '
+
++test_expect_success 'partial fetch does not spawn rev-list connectivity check' '
++ test_when_finished "rm -rf connectivity-remote connectivity-client" &&
++ git init connectivity-remote &&
++ test_commit -C connectivity-remote one &&
++ git -C connectivity-remote config uploadpack.allowfilter 1 &&
++ git -C connectivity-remote config uploadpack.allowanysha1inwant 1 &&
++
++ git clone --no-checkout --filter=blob:none \
++ "file://$(pwd)/connectivity-remote" connectivity-client &&
++
++ # When doing a partial fetch where all tips are part of a promisor pack
++ # we want to skip the connectivity check, as these objects are allowed
++ # to not be fully connected.
++ test_commit -C connectivity-remote two &&
++ GIT_TRACE2_EVENT="$(pwd)/partial.trace" git -C connectivity-client fetch origin &&
++ test_subcommand_flex ! git rev-list --objects --stdin <partial.trace &&
++
++ # Otherwise, when doing a fetch where any of the tips is not part of a
++ # promisor pack, then we must run the connectivity check.
++ test_commit -C connectivity-remote three &&
++ GIT_TRACE2_EVENT="$(pwd)/full.trace" git -C connectivity-client fetch --no-filter origin &&
++ test_subcommand_flex git rev-list --objects --stdin <full.trace
++'
++
+ # force dynamic object fetch using diff.
+ # we should only get 1 new blob (for the file in origin/main).
+ test_expect_success 'verify diff causes dynamic object fetch' '
---
base-commit: 4a8e7a446f41435e157131162dfe901eca9250fe
change-id: 20260612-pks-connected-generic-promisor-checks-2933bff3028d
^ permalink raw reply
* [PATCH v6 11/11] refs: protect against chicken-and-egg recursion
From: Patrick Steinhardt @ 2026-06-25 9:20 UTC (permalink / raw)
To: git; +Cc: Karthik Nayak, Jeff King, Justin Tobler
In-Reply-To: <20260625-b4-pks-refs-avoid-chdir-notify-reparent-v6-0-41fbca3cf5e3@pks.im>
In the preceding commits we have fixed recursion when creating the
reference backends due to a chicken-and-egg situation with "onbranch"
conditions. Unfortunately, this issue has existed for a while, and we
didn't really have a good mechanism to detect this recursion.
Improve the status quo by detecting the recursion when creating the main
reference store.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
refs.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/refs.c b/refs.c
index 5b773b1c15..1d24637891 100644
--- a/refs.c
+++ b/refs.c
@@ -2359,15 +2359,22 @@ void ref_store_release(struct ref_store *ref_store)
struct ref_store *get_main_ref_store(struct repository *r)
{
+ static bool initializing;
+
if (r->refs_private)
return r->refs_private;
if (!r->gitdir)
BUG("attempting to get main_ref_store outside of repository");
+ if (initializing)
+ BUG("initialization of main ref store is recursing");
+ initializing = true;
r->refs_private = ref_store_init(r, r->ref_storage_format,
r->gitdir, REF_STORE_ALL_CAPS);
r->refs_private = maybe_debug_wrap_ref_store(r->gitdir, r->refs_private);
+ initializing = false;
+
return r->refs_private;
}
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v6 10/11] refs/reftable: lazy-load configuration to fix chicken-and-egg
From: Patrick Steinhardt @ 2026-06-25 9:20 UTC (permalink / raw)
To: git; +Cc: Karthik Nayak, Jeff King, Justin Tobler
In-Reply-To: <20260625-b4-pks-refs-avoid-chdir-notify-reparent-v6-0-41fbca3cf5e3@pks.im>
Same as with the "files" backend, the "reftable" backend also has a
chicken-and-egg problem with "onbranch" conditions. Fix this issue the
same as we did with the "files" backend by lazy-loading configuration.
Now that both the "files" and the "reftable" backend handle this
properly, add a generic test to t1400 that verifies that the user can
configure "core.logAllRefUpdates" via an "onbranch" condition. This is
mostly a nonsensical thing to do in the first place, but it serves as a
good sanity check.
Note that we had to move `should_write_log()` around so that it can
access the new `reftable_be_write_options()` function.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
refs/reftable-backend.c | 146 ++++++++++++++++++++++----------------
t/t0613-reftable-write-options.sh | 19 +++++
t/t1400-update-ref.sh | 12 ++++
3 files changed, 116 insertions(+), 61 deletions(-)
diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c
index 608d71cf10..d74131a5ae 100644
--- a/refs/reftable-backend.c
+++ b/refs/reftable-backend.c
@@ -141,10 +141,21 @@ struct reftable_ref_store {
*/
struct strmap worktree_backends;
struct reftable_stack_options stack_options;
- struct reftable_write_options write_options;
+
+ /*
+ * Options used when writing to or compacting the reftable stacks.
+ * These are parsed from the configuration lazily on first use via
+ * `reftable_be_write_options()` so that we don't have to access the
+ * configuration when initializing the ref store. Do not access these
+ * fields directly, but use the accessor instead.
+ */
+ struct reftable_be_write_options {
+ struct reftable_write_options opts;
+ enum log_refs_config log_all_ref_updates;
+ bool initialized;
+ } write_opts_lazy_loaded;
unsigned int store_flags;
- enum log_refs_config log_all_ref_updates;
int err;
};
@@ -285,26 +296,6 @@ static int backend_for(struct reftable_backend **out,
return ret;
}
-static int should_write_log(struct reftable_ref_store *refs, const char *refname)
-{
- enum log_refs_config log_refs_cfg = refs->log_all_ref_updates;
- if (log_refs_cfg == LOG_REFS_UNSET)
- log_refs_cfg = is_bare_repository() ? LOG_REFS_NONE : LOG_REFS_NORMAL;
-
- switch (log_refs_cfg) {
- case LOG_REFS_NONE:
- return refs_reflog_exists(&refs->base, refname);
- case LOG_REFS_ALWAYS:
- return 1;
- case LOG_REFS_NORMAL:
- if (should_autocreate_reflog(log_refs_cfg, refname))
- return 1;
- return refs_reflog_exists(&refs->base, refname);
- default:
- BUG("unhandled core.logAllRefUpdates value %d", log_refs_cfg);
- }
-}
-
static void fill_reftable_log_record(struct reftable_log_record *log, const struct ident_split *split)
{
const char *tz_begin;
@@ -336,38 +327,72 @@ static int reftable_be_config(const char *var, const char *value,
void *payload)
{
struct reftable_ref_store *refs = payload;
+ struct reftable_be_write_options *opts = &refs->write_opts_lazy_loaded;
if (!strcmp(var, "reftable.blocksize")) {
unsigned long block_size = git_config_ulong(var, value, ctx->kvi);
if (block_size > 16777215)
die("reftable block size cannot exceed 16MB");
- refs->write_options.block_size = block_size;
+ opts->opts.block_size = block_size;
} else if (!strcmp(var, "reftable.restartinterval")) {
unsigned long restart_interval = git_config_ulong(var, value, ctx->kvi);
if (restart_interval > UINT16_MAX)
die("reftable block size cannot exceed %u", (unsigned)UINT16_MAX);
- refs->write_options.restart_interval = restart_interval;
+ opts->opts.restart_interval = restart_interval;
} else if (!strcmp(var, "reftable.indexobjects")) {
- refs->write_options.skip_index_objects = !git_config_bool(var, value);
+ opts->opts.skip_index_objects = !git_config_bool(var, value);
} else if (!strcmp(var, "reftable.geometricfactor")) {
unsigned long factor = git_config_ulong(var, value, ctx->kvi);
if (factor > UINT8_MAX)
die("reftable geometric factor cannot exceed %u", (unsigned)UINT8_MAX);
- refs->write_options.auto_compaction_factor = factor;
+ opts->opts.auto_compaction_factor = factor;
} else if (!strcmp(var, "reftable.locktimeout")) {
int64_t lock_timeout = git_config_int64(var, value, ctx->kvi);
if (lock_timeout > LONG_MAX)
die("reftable lock timeout cannot exceed %"PRIdMAX, (intmax_t)LONG_MAX);
if (lock_timeout < 0 && lock_timeout != -1)
die("reftable lock timeout does not support negative values other than -1");
- refs->write_options.lock_timeout_ms = lock_timeout;
+ opts->opts.lock_timeout_ms = lock_timeout;
} else if (!strcmp(var, "core.logallrefupdates")) {
- refs->log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
+ opts->log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
}
return 0;
}
+static const struct reftable_be_write_options *reftable_be_write_options(struct reftable_ref_store *refs)
+{
+ struct reftable_be_write_options *opts = &refs->write_opts_lazy_loaded;
+ mode_t mask;
+
+ if (opts->initialized)
+ return opts;
+
+ mask = umask(0);
+ umask(mask);
+
+ opts->opts.default_permissions = calc_shared_perm(refs->base.repo, 0666 & ~mask);
+ opts->opts.disable_auto_compact =
+ !git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1);
+ opts->opts.lock_timeout_ms = 100;
+ opts->log_all_ref_updates = LOG_REFS_UNSET;
+
+ repo_config(refs->base.repo, reftable_be_config, refs);
+
+ /*
+ * It is somewhat unfortunate that we have to mirror the default block
+ * size of the reftable library here. But given that the write options
+ * wouldn't be updated by the library here, and given that we require
+ * the proper block size to trim reflog message so that they fit, we
+ * must set up a proper value here.
+ */
+ if (!opts->opts.block_size)
+ opts->opts.block_size = 4096;
+
+ opts->initialized = true;
+ return opts;
+}
+
static void reftable_be_reparent(const char *name UNUSED,
const char *old_cwd,
const char *new_cwd,
@@ -391,10 +416,6 @@ static struct ref_store *reftable_be_init(struct repository *repo,
struct strbuf refdir = STRBUF_INIT;
struct strbuf path = STRBUF_INIT;
bool is_worktree;
- mode_t mask;
-
- mask = umask(0);
- umask(mask);
refs_compute_filesystem_location(gitdir, payload, &is_worktree, &refdir,
&ref_common_dir);
@@ -413,23 +434,6 @@ static struct ref_store *reftable_be_init(struct repository *repo,
default:
BUG("unknown hash algorithm %d", repo->hash_algo->format_id);
}
- refs->write_options.default_permissions = calc_shared_perm(repo, 0666 & ~mask);
- refs->write_options.disable_auto_compact =
- !git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1);
- refs->write_options.lock_timeout_ms = 100;
- refs->log_all_ref_updates = LOG_REFS_UNSET;
-
- repo_config(repo, reftable_be_config, refs);
-
- /*
- * It is somewhat unfortunate that we have to mirror the default block
- * size of the reftable library here. But given that the write options
- * wouldn't be updated by the library here, and given that we require
- * the proper block size to trim reflog message so that they fit, we
- * must set up a proper value here.
- */
- if (!refs->write_options.block_size)
- refs->write_options.block_size = 4096;
/*
* Set up the main reftable stack that is hosted in GIT_COMMON_DIR.
@@ -998,7 +1002,7 @@ static int prepare_transaction_update(struct write_transaction_table_arg **out,
struct reftable_addition *addition;
ret = reftable_stack_new_addition(&addition, be->stack,
- &refs->write_options,
+ &reftable_be_write_options(refs)->opts,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
if (ret) {
if (ret == REFTABLE_LOCK_ERROR)
@@ -1437,6 +1441,26 @@ static int transaction_update_cmp(const void *a, const void *b)
return strcmp(update_a->update->refname, update_b->update->refname);
}
+static int should_write_log(struct reftable_ref_store *refs, const char *refname)
+{
+ enum log_refs_config log_refs_cfg = reftable_be_write_options(refs)->log_all_ref_updates;
+ if (log_refs_cfg == LOG_REFS_UNSET)
+ log_refs_cfg = is_bare_repository() ? LOG_REFS_NONE : LOG_REFS_NORMAL;
+
+ switch (log_refs_cfg) {
+ case LOG_REFS_NONE:
+ return refs_reflog_exists(&refs->base, refname);
+ case LOG_REFS_ALWAYS:
+ return 1;
+ case LOG_REFS_NORMAL:
+ if (should_autocreate_reflog(log_refs_cfg, refname))
+ return 1;
+ return refs_reflog_exists(&refs->base, refname);
+ default:
+ BUG("unhandled core.logAllRefUpdates value %d", log_refs_cfg);
+ }
+}
+
static int write_transaction_table(struct reftable_writer *writer, void *cb_data)
{
struct write_transaction_table_arg *arg = cb_data;
@@ -1571,7 +1595,7 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data
memcpy(log->value.update.old_hash,
tx_update->current_oid.hash, GIT_MAX_RAWSZ);
log->value.update.message =
- xstrndup(u->msg, arg->refs->write_options.block_size / 2);
+ xstrndup(u->msg, reftable_be_write_options(arg->refs)->opts.block_size / 2);
}
}
@@ -1687,9 +1711,9 @@ static int reftable_be_optimize(struct ref_store *ref_store,
stack = refs->main_backend.stack;
if (opts->flags & REFS_OPTIMIZE_AUTO)
- ret = reftable_stack_auto_compact(stack, &refs->write_options);
+ ret = reftable_stack_auto_compact(stack, &reftable_be_write_options(refs)->opts);
else
- ret = reftable_stack_compact_all(stack, &refs->write_options, NULL);
+ ret = reftable_stack_compact_all(stack, &reftable_be_write_options(refs)->opts, NULL);
if (ret < 0) {
ret = error(_("unable to compact stack: %s"),
reftable_error_str(ret));
@@ -1723,7 +1747,7 @@ static int reftable_be_optimize_required(struct ref_store *ref_store,
if (opts->flags & REFS_OPTIMIZE_AUTO)
use_heuristics = true;
- return reftable_stack_compaction_required(stack, &refs->write_options,
+ return reftable_stack_compaction_required(stack, &reftable_be_write_options(refs)->opts,
use_heuristics, required);
}
@@ -1843,7 +1867,7 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
logs[logs_nr].refname = xstrdup(arg->newname);
logs[logs_nr].update_index = deletion_ts;
logs[logs_nr].value.update.message =
- xstrndup(arg->logmsg, arg->refs->write_options.block_size / 2);
+ xstrndup(arg->logmsg, reftable_be_write_options(arg->refs)->opts.block_size / 2);
memcpy(logs[logs_nr].value.update.old_hash, old_ref.value.val1, GIT_MAX_RAWSZ);
logs_nr++;
@@ -1882,7 +1906,7 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
logs[logs_nr].refname = xstrdup(arg->newname);
logs[logs_nr].update_index = creation_ts;
logs[logs_nr].value.update.message =
- xstrndup(arg->logmsg, arg->refs->write_options.block_size / 2);
+ xstrndup(arg->logmsg, reftable_be_write_options(arg->refs)->opts.block_size / 2);
memcpy(logs[logs_nr].value.update.new_hash, old_ref.value.val1, GIT_MAX_RAWSZ);
logs_nr++;
@@ -1981,7 +2005,7 @@ static int reftable_be_rename_ref(struct ref_store *ref_store,
if (ret)
goto done;
ret = reftable_stack_add(arg.be->stack, &write_copy_table, &arg,
- &refs->write_options,
+ &reftable_be_write_options(refs)->opts,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
done:
@@ -2012,7 +2036,7 @@ static int reftable_be_copy_ref(struct ref_store *ref_store,
if (ret)
goto done;
ret = reftable_stack_add(arg.be->stack, &write_copy_table, &arg,
- &refs->write_options,
+ &reftable_be_write_options(refs)->opts,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
done:
@@ -2378,7 +2402,7 @@ static int reftable_be_create_reflog(struct ref_store *ref_store,
arg.stack = be->stack;
ret = reftable_stack_add(be->stack, &write_reflog_existence_table, &arg,
- &refs->write_options,
+ &reftable_be_write_options(refs)->opts,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
done:
@@ -2451,7 +2475,7 @@ static int reftable_be_delete_reflog(struct ref_store *ref_store,
arg.stack = be->stack;
ret = reftable_stack_add(be->stack, &write_reflog_delete_table, &arg,
- &refs->write_options,
+ &reftable_be_write_options(refs)->opts,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
assert(ret != REFTABLE_API_ERROR);
@@ -2574,7 +2598,7 @@ static int reftable_be_reflog_expire(struct ref_store *ref_store,
goto done;
ret = reftable_stack_new_addition(&add, be->stack,
- &refs->write_options,
+ &reftable_be_write_options(refs)->opts,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
if (ret < 0)
goto done;
diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh
index 26b716c75f..a65960d048 100755
--- a/t/t0613-reftable-write-options.sh
+++ b/t/t0613-reftable-write-options.sh
@@ -278,4 +278,23 @@ test_expect_success 'object index can be disabled' '
)
'
+test_expect_success 'write options can be set up via onbranch condition' '
+ test_config_global core.logAllRefUpdates false &&
+ test_when_finished "rm -rf repo" &&
+ init_repo &&
+ (
+ cd repo &&
+ test_commit A &&
+ test_commit B &&
+ cat >.git/include <<-\EOF &&
+ [reftable]
+ blockSize = 123
+ EOF
+ git config includeIf.onbranch:master.path "$(pwd)/.git/include" &&
+ git refs optimize &&
+ test-tool dump-reftable -b .git/reftable/*.ref >stats &&
+ test_grep "block_size: 123" stats
+ )
+'
+
test_done
diff --git a/t/t1400-update-ref.sh b/t/t1400-update-ref.sh
index 1015f335e3..b8c3be6631 100755
--- a/t/t1400-update-ref.sh
+++ b/t/t1400-update-ref.sh
@@ -178,6 +178,18 @@ test_expect_success '--no-create-reflog overrides core.logAllRefUpdates=always'
test_must_fail git reflog exists $outside
'
+test_expect_success 'core.logAllRefUpdates can be set up via onbranch condition' '
+ test_when_finished "git update-ref -d $outside" &&
+ test_when_finished "rm -f .git/include" &&
+ cat >.git/include <<-\EOF &&
+ [core]
+ logAllRefUpdates = always
+ EOF
+ test_config includeIf.onbranch:main.path "$(pwd)/.git/include" &&
+ git update-ref $outside $A &&
+ git reflog exists $outside
+'
+
test_expect_success "create $m (by HEAD)" '
git update-ref HEAD $A &&
test $A = $(git show-ref -s --verify $m)
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v6 09/11] reftable: split up write options
From: Patrick Steinhardt @ 2026-06-25 9:20 UTC (permalink / raw)
To: git; +Cc: Karthik Nayak, Jeff King, Justin Tobler
In-Reply-To: <20260625-b4-pks-refs-avoid-chdir-notify-reparent-v6-0-41fbca3cf5e3@pks.im>
When initializing the reftable stack the caller may optionally pass some
write options. These write options mix up two different concerns though:
- Of course, they allow the caller to configure how new reftables are
being written.
- But they also allow the caller to configure the stack itself, like
its hash ID and the `on_reload` callback.
This is somewhat awkward, as it doesn't easily give the caller the
flexibility to for example write multiple reftables with different
options. Furthermore, this requires us to eagerly parse relevant
configuration when initializing the reftable backend.
Refactor the code by splitting out those options that configure the
stack itself. Creating a new stack will thus only require this limited
set of options, whereas the caller is expected to pass write options to
all functions that end up writing tables.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
refs/reftable-backend.c | 29 +++---
reftable/reftable-stack.h | 30 +++++-
reftable/reftable-writer.h | 17 +---
reftable/stack.c | 100 ++++++++++++-------
reftable/stack.h | 2 +-
reftable/writer.c | 21 ++--
reftable/writer.h | 1 +
t/helper/test-reftable.c | 2 +-
t/unit-tests/lib-reftable.c | 8 +-
t/unit-tests/lib-reftable.h | 2 +
t/unit-tests/u-reftable-merged.c | 9 +-
t/unit-tests/u-reftable-readwrite.c | 38 ++++++--
t/unit-tests/u-reftable-stack.c | 189 ++++++++++++++++--------------------
t/unit-tests/u-reftable-table.c | 8 +-
14 files changed, 258 insertions(+), 198 deletions(-)
diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c
index 5115a3f4ce..608d71cf10 100644
--- a/refs/reftable-backend.c
+++ b/refs/reftable-backend.c
@@ -48,9 +48,9 @@ static void reftable_backend_on_reload(void *payload)
static int reftable_backend_init(struct reftable_backend *be,
const char *path,
- const struct reftable_write_options *_opts)
+ const struct reftable_stack_options *_opts)
{
- struct reftable_write_options opts = *_opts;
+ struct reftable_stack_options opts = *_opts;
opts.on_reload = reftable_backend_on_reload;
opts.on_reload_payload = be;
return reftable_new_stack(&be->stack, path, &opts);
@@ -140,6 +140,7 @@ struct reftable_ref_store {
* is populated lazily when we try to resolve `worktrees/$worktree` refs.
*/
struct strmap worktree_backends;
+ struct reftable_stack_options stack_options;
struct reftable_write_options write_options;
unsigned int store_flags;
@@ -190,7 +191,7 @@ static int backend_for_worktree(struct reftable_backend **out,
CALLOC_ARRAY(*out, 1);
store->err = ret = reftable_backend_init(*out, worktree_dir.buf,
- &store->write_options);
+ &store->stack_options);
if (ret < 0) {
free(*out);
goto out;
@@ -404,10 +405,10 @@ static struct ref_store *reftable_be_init(struct repository *repo,
switch (repo->hash_algo->format_id) {
case GIT_SHA1_FORMAT_ID:
- refs->write_options.hash_id = REFTABLE_HASH_SHA1;
+ refs->stack_options.hash_id = REFTABLE_HASH_SHA1;
break;
case GIT_SHA256_FORMAT_ID:
- refs->write_options.hash_id = REFTABLE_HASH_SHA256;
+ refs->stack_options.hash_id = REFTABLE_HASH_SHA256;
break;
default:
BUG("unknown hash algorithm %d", repo->hash_algo->format_id);
@@ -441,7 +442,7 @@ static struct ref_store *reftable_be_init(struct repository *repo,
}
strbuf_addstr(&path, "/reftable");
refs->err = reftable_backend_init(&refs->main_backend, path.buf,
- &refs->write_options);
+ &refs->stack_options);
if (refs->err)
goto done;
@@ -457,7 +458,7 @@ static struct ref_store *reftable_be_init(struct repository *repo,
strbuf_addstr(&refdir, "/reftable");
refs->err = reftable_backend_init(&refs->worktree_backend, refdir.buf,
- &refs->write_options);
+ &refs->stack_options);
if (refs->err)
goto done;
}
@@ -997,6 +998,7 @@ static int prepare_transaction_update(struct write_transaction_table_arg **out,
struct reftable_addition *addition;
ret = reftable_stack_new_addition(&addition, be->stack,
+ &refs->write_options,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
if (ret) {
if (ret == REFTABLE_LOCK_ERROR)
@@ -1685,9 +1687,9 @@ static int reftable_be_optimize(struct ref_store *ref_store,
stack = refs->main_backend.stack;
if (opts->flags & REFS_OPTIMIZE_AUTO)
- ret = reftable_stack_auto_compact(stack);
+ ret = reftable_stack_auto_compact(stack, &refs->write_options);
else
- ret = reftable_stack_compact_all(stack, NULL);
+ ret = reftable_stack_compact_all(stack, &refs->write_options, NULL);
if (ret < 0) {
ret = error(_("unable to compact stack: %s"),
reftable_error_str(ret));
@@ -1721,8 +1723,8 @@ static int reftable_be_optimize_required(struct ref_store *ref_store,
if (opts->flags & REFS_OPTIMIZE_AUTO)
use_heuristics = true;
- return reftable_stack_compaction_required(stack, use_heuristics,
- required);
+ return reftable_stack_compaction_required(stack, &refs->write_options,
+ use_heuristics, required);
}
struct write_create_symref_arg {
@@ -1979,6 +1981,7 @@ static int reftable_be_rename_ref(struct ref_store *ref_store,
if (ret)
goto done;
ret = reftable_stack_add(arg.be->stack, &write_copy_table, &arg,
+ &refs->write_options,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
done:
@@ -2009,6 +2012,7 @@ static int reftable_be_copy_ref(struct ref_store *ref_store,
if (ret)
goto done;
ret = reftable_stack_add(arg.be->stack, &write_copy_table, &arg,
+ &refs->write_options,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
done:
@@ -2374,6 +2378,7 @@ static int reftable_be_create_reflog(struct ref_store *ref_store,
arg.stack = be->stack;
ret = reftable_stack_add(be->stack, &write_reflog_existence_table, &arg,
+ &refs->write_options,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
done:
@@ -2446,6 +2451,7 @@ static int reftable_be_delete_reflog(struct ref_store *ref_store,
arg.stack = be->stack;
ret = reftable_stack_add(be->stack, &write_reflog_delete_table, &arg,
+ &refs->write_options,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
assert(ret != REFTABLE_API_ERROR);
@@ -2568,6 +2574,7 @@ static int reftable_be_reflog_expire(struct ref_store *ref_store,
goto done;
ret = reftable_stack_new_addition(&add, be->stack,
+ &refs->write_options,
REFTABLE_STACK_NEW_ADDITION_RELOAD);
if (ret < 0)
goto done;
diff --git a/reftable/reftable-stack.h b/reftable/reftable-stack.h
index 5f7be573fa..11f9963f4f 100644
--- a/reftable/reftable-stack.h
+++ b/reftable/reftable-stack.h
@@ -26,11 +26,29 @@
*/
struct reftable_stack;
+/* Options related to opening a stack. */
+struct reftable_stack_options {
+ /*
+ * 4-byte identifier ("sha1", "s256") of the hash. Defaults to SHA1 if
+ * unset.
+ */
+ enum reftable_hash hash_id;
+
+ /*
+ * Callback function to execute whenever the stack is being reloaded.
+ * This can be used e.g. to discard cached information that relies on
+ * the old stack's data. The payload data will be passed as argument to
+ * the callback.
+ */
+ void (*on_reload)(void *payload);
+ void *on_reload_payload;
+};
+
/* open a new reftable stack. The tables along with the table list will be
* stored in 'dir'. Typically, this should be .git/reftables.
*/
int reftable_new_stack(struct reftable_stack **dest, const char *dir,
- const struct reftable_write_options *opts);
+ const struct reftable_stack_options *opts);
/* returns the update_index at which a next table should be written. */
uint64_t reftable_stack_next_update_index(struct reftable_stack *st);
@@ -52,6 +70,7 @@ enum {
*/
int reftable_stack_new_addition(struct reftable_addition **dest,
struct reftable_stack *st,
+ const struct reftable_write_options *opts,
unsigned int flags);
/* Adds a reftable to transaction. */
@@ -77,7 +96,9 @@ void reftable_addition_destroy(struct reftable_addition *add);
int reftable_stack_add(struct reftable_stack *st,
int (*write_table)(struct reftable_writer *wr,
void *write_arg),
- void *write_arg, unsigned flags);
+ void *write_arg,
+ const struct reftable_write_options *opts,
+ unsigned flags);
struct reftable_iterator;
@@ -122,6 +143,7 @@ struct reftable_log_expiry_config {
/* compacts all reftables into a giant table. Expire reflog entries if config is
* non-NULL */
int reftable_stack_compact_all(struct reftable_stack *st,
+ const struct reftable_write_options *opts,
struct reftable_log_expiry_config *config);
/*
@@ -132,11 +154,13 @@ int reftable_stack_compact_all(struct reftable_stack *st,
* compacted to maintain geometric progression.
*/
int reftable_stack_compaction_required(struct reftable_stack *st,
+ const struct reftable_write_options *opts,
bool use_heuristics,
bool *required);
/* heuristically compact unbalanced table stack. */
-int reftable_stack_auto_compact(struct reftable_stack *st);
+int reftable_stack_auto_compact(struct reftable_stack *st,
+ const struct reftable_write_options *opts);
/* delete stale .ref tables. */
int reftable_stack_clean(struct reftable_stack *st);
diff --git a/reftable/reftable-writer.h b/reftable/reftable-writer.h
index a66db415c8..6ff4ddfc60 100644
--- a/reftable/reftable-writer.h
+++ b/reftable/reftable-writer.h
@@ -28,11 +28,6 @@ struct reftable_write_options {
/* how often to write complete keys in each block. */
uint16_t restart_interval;
- /* 4-byte identifier ("sha1", "s256") of the hash.
- * Defaults to SHA1 if unset
- */
- enum reftable_hash hash_id;
-
/* Default mode for creating files. If unset, use 0666 (+umask) */
unsigned int default_permissions;
@@ -60,15 +55,6 @@ struct reftable_write_options {
* negative value will cause us to block indefinitely.
*/
long lock_timeout_ms;
-
- /*
- * Callback function to execute whenever the stack is being reloaded.
- * This can be used e.g. to discard cached information that relies on
- * the old stack's data. The payload data will be passed as argument to
- * the callback.
- */
- void (*on_reload)(void *payload);
- void *on_reload_payload;
};
/* reftable_block_stats holds statistics for a single block type */
@@ -114,7 +100,8 @@ struct reftable_writer;
int reftable_writer_new(struct reftable_writer **out,
ssize_t (*writer_func)(void *, const void *, size_t),
int (*flush_func)(void *),
- void *writer_arg, const struct reftable_write_options *opts);
+ void *writer_arg, enum reftable_hash hash_id,
+ const struct reftable_write_options *opts);
/*
* Set the range of update indices for the records we will add. When writing a
diff --git a/reftable/stack.c b/reftable/stack.c
index 1fba96ddb3..ab12926708 100644
--- a/reftable/stack.c
+++ b/reftable/stack.c
@@ -501,10 +501,10 @@ static int reftable_stack_reload_maybe_reuse(struct reftable_stack *st,
}
int reftable_new_stack(struct reftable_stack **dest, const char *dir,
- const struct reftable_write_options *_opts)
+ const struct reftable_stack_options *_opts)
{
struct reftable_buf list_file_name = REFTABLE_BUF_INIT;
- struct reftable_write_options opts = { 0 };
+ struct reftable_stack_options opts = { 0 };
struct reftable_stack *p;
int err;
@@ -629,6 +629,7 @@ int reftable_stack_reload(struct reftable_stack *st)
struct reftable_addition {
struct reftable_flock tables_list_lock;
struct reftable_stack *stack;
+ struct reftable_write_options opts;
char **new_tables;
size_t new_tables_len, new_tables_cap;
@@ -657,6 +658,7 @@ static void reftable_addition_close(struct reftable_addition *add)
static int reftable_stack_init_addition(struct reftable_addition *add,
struct reftable_stack *st,
+ const struct reftable_write_options *opts,
unsigned int flags)
{
struct reftable_buf lock_file_name = REFTABLE_BUF_INIT;
@@ -664,15 +666,17 @@ static int reftable_stack_init_addition(struct reftable_addition *add,
memset(add, 0, sizeof(*add));
add->stack = st;
+ if (opts)
+ add->opts = *opts;
err = flock_acquire(&add->tables_list_lock, st->list_file,
- st->opts.lock_timeout_ms);
+ add->opts.lock_timeout_ms);
if (err < 0)
goto done;
- if (st->opts.default_permissions) {
+ if (add->opts.default_permissions) {
if (chmod(add->tables_list_lock.path,
- st->opts.default_permissions) < 0) {
+ add->opts.default_permissions) < 0) {
err = REFTABLE_IO_ERROR;
goto done;
}
@@ -702,12 +706,14 @@ static int reftable_stack_init_addition(struct reftable_addition *add,
static int stack_try_add(struct reftable_stack *st,
int (*write_table)(struct reftable_writer *wr,
void *arg),
- void *arg, unsigned flags)
+ void *arg,
+ const struct reftable_write_options *opts,
+ unsigned flags)
{
struct reftable_addition add;
int err;
- err = reftable_stack_init_addition(&add, st, flags);
+ err = reftable_stack_init_addition(&add, st, opts, flags);
if (err < 0)
goto done;
@@ -723,9 +729,11 @@ static int stack_try_add(struct reftable_stack *st,
int reftable_stack_add(struct reftable_stack *st,
int (*write)(struct reftable_writer *wr, void *arg),
- void *arg, unsigned flags)
+ void *arg,
+ const struct reftable_write_options *opts,
+ unsigned flags)
{
- int err = stack_try_add(st, write, arg, flags);
+ int err = stack_try_add(st, write, arg, opts, flags);
if (err < 0) {
if (err == REFTABLE_OUTDATED_ERROR) {
/* Ignore error return, we want to propagate
@@ -810,7 +818,7 @@ int reftable_addition_commit(struct reftable_addition *add)
if (err)
goto done;
- if (!add->stack->opts.disable_auto_compact) {
+ if (!add->opts.disable_auto_compact) {
/*
* Auto-compact the stack to keep the number of tables in
* control. It is possible that a concurrent writer is already
@@ -820,7 +828,7 @@ int reftable_addition_commit(struct reftable_addition *add)
* concurrent writer, which causes `REFTABLE_OUTDATED_ERROR`.
* Both of these errors are benign, so we simply ignore them.
*/
- err = reftable_stack_auto_compact(add->stack);
+ err = reftable_stack_auto_compact(add->stack, &add->opts);
if (err < 0 && err != REFTABLE_LOCK_ERROR &&
err != REFTABLE_OUTDATED_ERROR)
goto done;
@@ -834,6 +842,7 @@ int reftable_addition_commit(struct reftable_addition *add)
int reftable_stack_new_addition(struct reftable_addition **dest,
struct reftable_stack *st,
+ const struct reftable_write_options *opts,
unsigned int flags)
{
int err;
@@ -842,7 +851,7 @@ int reftable_stack_new_addition(struct reftable_addition **dest,
if (!*dest)
return REFTABLE_OUT_OF_MEMORY_ERROR;
- err = reftable_stack_init_addition(*dest, st, flags);
+ err = reftable_stack_init_addition(*dest, st, opts, flags);
if (err) {
reftable_free(*dest);
*dest = NULL;
@@ -862,7 +871,7 @@ int reftable_addition_add(struct reftable_addition *add,
struct reftable_writer *wr = NULL;
struct reftable_tmpfile tab_file = REFTABLE_TMPFILE_INIT;
struct fd_writer writer = {
- .opts = &add->stack->opts,
+ .opts = &add->opts,
};
int err = 0;
@@ -883,9 +892,9 @@ int reftable_addition_add(struct reftable_addition *add,
err = tmpfile_from_pattern(&tab_file, temp_tab_file_name.buf);
if (err < 0)
goto done;
- if (add->stack->opts.default_permissions) {
+ if (add->opts.default_permissions) {
if (chmod(tab_file.path,
- add->stack->opts.default_permissions)) {
+ add->opts.default_permissions)) {
err = REFTABLE_IO_ERROR;
goto done;
}
@@ -893,7 +902,7 @@ int reftable_addition_add(struct reftable_addition *add,
writer.fd = tab_file.fd;
err = reftable_writer_new(&wr, fd_writer_write, fd_writer_flush,
- &writer, &add->stack->opts);
+ &writer, add->stack->opts.hash_id, &add->opts);
if (err < 0)
goto done;
@@ -1066,13 +1075,14 @@ static int stack_write_compact(struct reftable_stack *st,
static int stack_compact_locked(struct reftable_stack *st,
size_t first, size_t last,
struct reftable_log_expiry_config *config,
+ const struct reftable_write_options *opts,
struct reftable_tmpfile *tab_file_out)
{
struct reftable_buf next_name = REFTABLE_BUF_INIT;
struct reftable_buf tab_file_path = REFTABLE_BUF_INIT;
struct reftable_writer *wr = NULL;
struct fd_writer writer= {
- .opts = &st->opts,
+ .opts = opts,
};
struct reftable_tmpfile tab_file = REFTABLE_TMPFILE_INIT;
int err = 0;
@@ -1094,15 +1104,15 @@ static int stack_compact_locked(struct reftable_stack *st,
if (err < 0)
goto done;
- if (st->opts.default_permissions &&
- chmod(tab_file.path, st->opts.default_permissions) < 0) {
+ if (opts->default_permissions &&
+ chmod(tab_file.path, opts->default_permissions) < 0) {
err = REFTABLE_IO_ERROR;
goto done;
}
writer.fd = tab_file.fd;
err = reftable_writer_new(&wr, fd_writer_write, fd_writer_flush,
- &writer, &st->opts);
+ &writer, st->opts.hash_id, opts);
if (err < 0)
goto done;
@@ -1150,6 +1160,7 @@ enum stack_compact_range_flags {
static int stack_compact_range(struct reftable_stack *st,
size_t first, size_t last,
struct reftable_log_expiry_config *expiry,
+ const struct reftable_write_options *opts,
unsigned int flags)
{
struct reftable_buf tables_list_buf = REFTABLE_BUF_INIT;
@@ -1175,7 +1186,7 @@ static int stack_compact_range(struct reftable_stack *st,
* Hold the lock so that we can read "tables.list" and lock all tables
* which are part of the user-specified range.
*/
- err = flock_acquire(&tables_list_lock, st->list_file, st->opts.lock_timeout_ms);
+ err = flock_acquire(&tables_list_lock, st->list_file, opts->lock_timeout_ms);
if (err < 0)
goto done;
@@ -1274,7 +1285,7 @@ static int stack_compact_range(struct reftable_stack *st,
* these tables may end up with an empty new table in case tombstones
* end up cancelling out all refs in that range.
*/
- err = stack_compact_locked(st, first, last, expiry, &new_table);
+ err = stack_compact_locked(st, first, last, expiry, opts, &new_table);
if (err < 0) {
if (err != REFTABLE_EMPTY_TABLE_ERROR)
goto done;
@@ -1286,13 +1297,13 @@ static int stack_compact_range(struct reftable_stack *st,
* "tables.list". We'll then replace the compacted range of tables with
* the new table.
*/
- err = flock_acquire(&tables_list_lock, st->list_file, st->opts.lock_timeout_ms);
+ err = flock_acquire(&tables_list_lock, st->list_file, opts->lock_timeout_ms);
if (err < 0)
goto done;
- if (st->opts.default_permissions) {
+ if (opts->default_permissions) {
if (chmod(tables_list_lock.path,
- st->opts.default_permissions) < 0) {
+ opts->default_permissions) < 0) {
err = REFTABLE_IO_ERROR;
goto done;
}
@@ -1513,10 +1524,16 @@ static int stack_compact_range(struct reftable_stack *st,
}
int reftable_stack_compact_all(struct reftable_stack *st,
+ const struct reftable_write_options *opts,
struct reftable_log_expiry_config *config)
{
+ struct reftable_write_options opts_default = { 0 };
size_t last = st->merged->tables_len ? st->merged->tables_len - 1 : 0;
- return stack_compact_range(st, 0, last, config, 0);
+
+ if (!opts)
+ opts = &opts_default;
+
+ return stack_compact_range(st, 0, last, config, opts, 0);
}
static int segment_size(struct segment *s)
@@ -1601,6 +1618,7 @@ struct segment suggest_compaction_segment(uint64_t *sizes, size_t n,
}
static int stack_segments_for_compaction(struct reftable_stack *st,
+ const struct reftable_write_options *opts,
struct segment *seg)
{
int version = (st->opts.hash_id == REFTABLE_HASH_SHA1) ? 1 : 2;
@@ -1615,13 +1633,14 @@ static int stack_segments_for_compaction(struct reftable_stack *st,
sizes[i] = st->tables[i]->size - overhead;
*seg = suggest_compaction_segment(sizes, st->merged->tables_len,
- st->opts.auto_compaction_factor);
+ opts->auto_compaction_factor);
reftable_free(sizes);
return 0;
}
static int update_segment_if_compaction_required(struct reftable_stack *st,
+ const struct reftable_write_options *opts,
struct segment *seg,
bool use_geometric,
bool *required)
@@ -1638,7 +1657,7 @@ static int update_segment_if_compaction_required(struct reftable_stack *st,
return 0;
}
- err = stack_segments_for_compaction(st, seg);
+ err = stack_segments_for_compaction(st, opts, seg);
if (err)
return err;
@@ -1647,27 +1666,40 @@ static int update_segment_if_compaction_required(struct reftable_stack *st,
}
int reftable_stack_compaction_required(struct reftable_stack *st,
+ const struct reftable_write_options *opts,
bool use_heuristics,
bool *required)
{
+ struct reftable_write_options opts_default = { 0 };
struct segment seg;
- return update_segment_if_compaction_required(st, &seg, use_heuristics,
- required);
+
+ if (!opts)
+ opts = &opts_default;
+
+ return update_segment_if_compaction_required(st, opts, &seg,
+ use_heuristics, required);
}
-int reftable_stack_auto_compact(struct reftable_stack *st)
+int reftable_stack_auto_compact(struct reftable_stack *st,
+ const struct reftable_write_options *opts)
{
+ struct reftable_write_options opts_default = { 0 };
struct segment seg;
bool required;
int err;
- err = update_segment_if_compaction_required(st, &seg, true, &required);
+ if (!opts)
+ opts = &opts_default;
+
+ err = update_segment_if_compaction_required(st, opts, &seg, true,
+ &required);
if (err)
return err;
if (required)
return stack_compact_range(st, seg.start, seg.end - 1,
- NULL, STACK_COMPACT_RANGE_BEST_EFFORT);
+ NULL, opts,
+ STACK_COMPACT_RANGE_BEST_EFFORT);
return 0;
}
@@ -1807,7 +1839,7 @@ static int reftable_stack_clean_locked(struct reftable_stack *st)
int reftable_stack_clean(struct reftable_stack *st)
{
struct reftable_addition *add = NULL;
- int err = reftable_stack_new_addition(&add, st, 0);
+ int err = reftable_stack_new_addition(&add, st, NULL, 0);
if (err < 0) {
goto done;
}
diff --git a/reftable/stack.h b/reftable/stack.h
index bc28f2998a..f7901e6c6f 100644
--- a/reftable/stack.h
+++ b/reftable/stack.h
@@ -20,7 +20,7 @@ struct reftable_stack {
char *reftable_dir;
- struct reftable_write_options opts;
+ struct reftable_stack_options opts;
struct reftable_table **tables;
size_t tables_len;
diff --git a/reftable/writer.c b/reftable/writer.c
index 0133b64975..f850e9d599 100644
--- a/reftable/writer.c
+++ b/reftable/writer.c
@@ -80,9 +80,6 @@ static void options_set_defaults(struct reftable_write_options *opts)
opts->restart_interval = 16;
}
- if (opts->hash_id == 0) {
- opts->hash_id = REFTABLE_HASH_SHA1;
- }
if (opts->block_size == 0) {
opts->block_size = DEFAULT_BLOCK_SIZE;
}
@@ -90,7 +87,7 @@ static void options_set_defaults(struct reftable_write_options *opts)
static int writer_version(struct reftable_writer *w)
{
- return (w->opts.hash_id == 0 || w->opts.hash_id == REFTABLE_HASH_SHA1) ?
+ return (w->hash_id == 0 || w->hash_id == REFTABLE_HASH_SHA1) ?
1 :
2;
}
@@ -107,7 +104,7 @@ static int writer_write_header(struct reftable_writer *w, uint8_t *dest)
if (writer_version(w) == 2) {
uint32_t hash_id;
- switch (w->opts.hash_id) {
+ switch (w->hash_id) {
case REFTABLE_HASH_SHA1:
hash_id = REFTABLE_FORMAT_ID_SHA1;
break;
@@ -134,7 +131,7 @@ static int writer_reinit_block_writer(struct reftable_writer *w, uint8_t typ)
reftable_buf_reset(&w->last_key);
ret = block_writer_init(&w->block_writer_data, typ, w->block,
w->opts.block_size, block_start,
- hash_size(w->opts.hash_id));
+ hash_size(w->hash_id));
if (ret < 0)
return ret;
@@ -147,7 +144,9 @@ static int writer_reinit_block_writer(struct reftable_writer *w, uint8_t typ)
int reftable_writer_new(struct reftable_writer **out,
ssize_t (*writer_func)(void *, const void *, size_t),
int (*flush_func)(void *),
- void *writer_arg, const struct reftable_write_options *_opts)
+ void *writer_arg,
+ enum reftable_hash hash_id,
+ const struct reftable_write_options *_opts)
{
struct reftable_write_options opts = {0};
struct reftable_writer *wp;
@@ -162,6 +161,9 @@ int reftable_writer_new(struct reftable_writer **out,
if (opts.block_size >= (1 << 24))
return REFTABLE_API_ERROR;
+ if (!hash_id)
+ hash_id = REFTABLE_HASH_SHA1;
+
reftable_buf_init(&wp->block_writer_data.last_key);
reftable_buf_init(&wp->last_key);
reftable_buf_init(&wp->scratch);
@@ -173,6 +175,7 @@ int reftable_writer_new(struct reftable_writer **out,
wp->write = writer_func;
wp->write_arg = writer_arg;
wp->opts = opts;
+ wp->hash_id = hash_id;
wp->flush = flush_func;
writer_reinit_block_writer(wp, REFTABLE_BLOCK_TYPE_REF);
@@ -367,7 +370,7 @@ int reftable_writer_add_ref(struct reftable_writer *w,
if (!w->opts.skip_index_objects && reftable_ref_record_val1(ref)) {
reftable_buf_reset(&w->scratch);
err = reftable_buf_add(&w->scratch, (char *)reftable_ref_record_val1(ref),
- hash_size(w->opts.hash_id));
+ hash_size(w->hash_id));
if (err < 0)
goto out;
@@ -379,7 +382,7 @@ int reftable_writer_add_ref(struct reftable_writer *w,
if (!w->opts.skip_index_objects && reftable_ref_record_val2(ref)) {
reftable_buf_reset(&w->scratch);
err = reftable_buf_add(&w->scratch, reftable_ref_record_val2(ref),
- hash_size(w->opts.hash_id));
+ hash_size(w->hash_id));
if (err < 0)
goto out;
diff --git a/reftable/writer.h b/reftable/writer.h
index 9f53610b27..c08fc413e1 100644
--- a/reftable/writer.h
+++ b/reftable/writer.h
@@ -27,6 +27,7 @@ struct reftable_writer {
uint64_t next;
uint64_t min_update_index, max_update_index;
struct reftable_write_options opts;
+ enum reftable_hash hash_id;
/* memory buffer for writing */
uint8_t *block;
diff --git a/t/helper/test-reftable.c b/t/helper/test-reftable.c
index b16c0722c8..fc49fafc34 100644
--- a/t/helper/test-reftable.c
+++ b/t/helper/test-reftable.c
@@ -174,7 +174,7 @@ static int dump_table(struct reftable_merged_table *mt)
static int dump_stack(const char *stackdir, uint32_t hash_id)
{
struct reftable_stack *stack = NULL;
- struct reftable_write_options opts = { .hash_id = hash_id };
+ struct reftable_stack_options opts = { .hash_id = hash_id };
struct reftable_merged_table *merged = NULL;
int err = reftable_new_stack(&stack, stackdir, &opts);
diff --git a/t/unit-tests/lib-reftable.c b/t/unit-tests/lib-reftable.c
index fdb5b11a20..19a3ac8b80 100644
--- a/t/unit-tests/lib-reftable.c
+++ b/t/unit-tests/lib-reftable.c
@@ -25,11 +25,12 @@ static int strbuf_writer_flush(void *arg UNUSED)
}
struct reftable_writer *cl_reftable_strbuf_writer(struct reftable_buf *buf,
+ enum reftable_hash hash_id,
struct reftable_write_options *opts)
{
struct reftable_writer *writer;
int ret = reftable_writer_new(&writer, &strbuf_writer_write, &strbuf_writer_flush,
- buf, opts);
+ buf, hash_id, opts);
cl_assert(!ret);
return writer;
}
@@ -39,6 +40,7 @@ void cl_reftable_write_to_buf(struct reftable_buf *buf,
size_t nrefs,
struct reftable_log_record *logs,
size_t nlogs,
+ enum reftable_hash hash_id,
struct reftable_write_options *_opts)
{
struct reftable_write_options opts = { 0 };
@@ -66,7 +68,7 @@ void cl_reftable_write_to_buf(struct reftable_buf *buf,
min = ui;
}
- writer = cl_reftable_strbuf_writer(buf, &opts);
+ writer = cl_reftable_strbuf_writer(buf, hash_id, &opts);
ret = reftable_writer_set_limits(writer, min, max);
cl_assert(!ret);
@@ -88,7 +90,7 @@ void cl_reftable_write_to_buf(struct reftable_buf *buf,
size_t off = i * (opts.block_size ? opts.block_size
: DEFAULT_BLOCK_SIZE);
if (!off)
- off = header_size(opts.hash_id == REFTABLE_HASH_SHA256 ? 2 : 1);
+ off = header_size(hash_id == REFTABLE_HASH_SHA256 ? 2 : 1);
cl_assert(buf->buf[off] == 'r');
}
diff --git a/t/unit-tests/lib-reftable.h b/t/unit-tests/lib-reftable.h
index d7e6d3136f..caf443d147 100644
--- a/t/unit-tests/lib-reftable.h
+++ b/t/unit-tests/lib-reftable.h
@@ -10,6 +10,7 @@ struct reftable_buf;
void cl_reftable_set_hash(uint8_t *p, int i, enum reftable_hash id);
struct reftable_writer *cl_reftable_strbuf_writer(struct reftable_buf *buf,
+ enum reftable_hash hash_id,
struct reftable_write_options *opts);
void cl_reftable_write_to_buf(struct reftable_buf *buf,
@@ -17,4 +18,5 @@ void cl_reftable_write_to_buf(struct reftable_buf *buf,
size_t nrecords,
struct reftable_log_record *logs,
size_t nlogs,
+ enum reftable_hash hash_id,
struct reftable_write_options *opts);
diff --git a/t/unit-tests/u-reftable-merged.c b/t/unit-tests/u-reftable-merged.c
index 54cb7fc2a7..21232c1e4f 100644
--- a/t/unit-tests/u-reftable-merged.c
+++ b/t/unit-tests/u-reftable-merged.c
@@ -34,7 +34,8 @@ merged_table_from_records(struct reftable_ref_record **refs,
cl_assert(*source != NULL);
for (size_t i = 0; i < n; i++) {
- cl_reftable_write_to_buf(&buf[i], refs[i], sizes[i], NULL, 0, &opts);
+ cl_reftable_write_to_buf(&buf[i], refs[i], sizes[i], NULL, 0,
+ REFTABLE_HASH_SHA1, &opts);
block_source_from_buf(&(*source)[i], &buf[i]);
err = reftable_table_new(&(*tables)[i], &(*source)[i],
@@ -357,7 +358,8 @@ merged_table_from_log_records(struct reftable_log_record **logs,
cl_assert(*source != NULL);
for (size_t i = 0; i < n; i++) {
- cl_reftable_write_to_buf(&buf[i], NULL, 0, logs[i], sizes[i], &opts);
+ cl_reftable_write_to_buf(&buf[i], NULL, 0, logs[i], sizes[i],
+ REFTABLE_HASH_SHA1, &opts);
block_source_from_buf(&(*source)[i], &buf[i]);
err = reftable_table_new(&(*tables)[i], &(*source)[i],
@@ -487,7 +489,8 @@ void test_reftable_merged__default_write_opts(void)
{
struct reftable_write_options opts = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1, &opts);
struct reftable_ref_record rec = {
.refname = (char *) "master",
.update_index = 1,
diff --git a/t/unit-tests/u-reftable-readwrite.c b/t/unit-tests/u-reftable-readwrite.c
index 4d8c4be5f1..5794b460c6 100644
--- a/t/unit-tests/u-reftable-readwrite.c
+++ b/t/unit-tests/u-reftable-readwrite.c
@@ -48,7 +48,6 @@ static void write_table(char ***names, struct reftable_buf *buf, int N,
{
struct reftable_write_options opts = {
.block_size = block_size,
- .hash_id = hash_id,
};
struct reftable_ref_record *refs;
struct reftable_log_record *logs;
@@ -78,7 +77,7 @@ static void write_table(char ***names, struct reftable_buf *buf, int N,
logs[i].value.update.message = (char *) "message";
}
- cl_reftable_write_to_buf(buf, refs, N, logs, N, &opts);
+ cl_reftable_write_to_buf(buf, refs, N, logs, N, hash_id, &opts);
reftable_free(refs);
reftable_free(logs);
@@ -103,6 +102,7 @@ void test_reftable_readwrite__log_buffer_size(void)
.message = (char *) "commit: 9\n",
} } };
struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
&opts);
/* This tests buffer extension for log compression. Must use a random
@@ -143,6 +143,7 @@ void test_reftable_readwrite__log_overflow(void)
},
};
struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
&opts);
memset(msg, 'x', sizeof(msg) - 1);
@@ -157,6 +158,7 @@ void test_reftable_readwrite__log_write_limits(void)
struct reftable_write_options opts = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
&opts);
struct reftable_log_record log = {
.refname = (char *)"refs/head/master",
@@ -202,7 +204,9 @@ void test_reftable_readwrite__log_write_read(void)
struct reftable_table *table;
struct reftable_block_source source = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
+ &opts);
const struct reftable_stats *stats = NULL;
int N = 2, i;
char **names;
@@ -299,6 +303,7 @@ void test_reftable_readwrite__log_zlib_corruption(void)
struct reftable_block_source source = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
&opts);
const struct reftable_stats *stats = NULL;
char message[100] = { 0 };
@@ -531,6 +536,7 @@ static void t_table_refs_for(int indexed)
struct reftable_block_source source = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
&opts);
struct reftable_iterator it = { 0 };
int N = 50, j, i;
@@ -622,7 +628,9 @@ void test_reftable_readwrite__write_empty_table(void)
{
struct reftable_write_options opts = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
+ &opts);
struct reftable_block_source source = { 0 };
struct reftable_table *table = NULL;
struct reftable_ref_record rec = { 0 };
@@ -660,7 +668,9 @@ void test_reftable_readwrite__write_object_id_min_length(void)
.block_size = 75,
};
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
+ &opts);
struct reftable_ref_record ref = {
.update_index = 1,
.value_type = REFTABLE_REF_VAL1,
@@ -691,7 +701,9 @@ void test_reftable_readwrite__write_object_id_length(void)
.block_size = 75,
};
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
+ &opts);
struct reftable_ref_record ref = {
.update_index = 1,
.value_type = REFTABLE_REF_VAL1,
@@ -721,7 +733,9 @@ void test_reftable_readwrite__write_empty_key(void)
{
struct reftable_write_options opts = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
+ &opts);
struct reftable_ref_record ref = {
.refname = (char *) "",
.update_index = 1,
@@ -740,7 +754,9 @@ void test_reftable_readwrite__write_key_order(void)
{
struct reftable_write_options opts = { 0 };
struct reftable_buf buf = REFTABLE_BUF_INIT;
- struct reftable_writer *w = cl_reftable_strbuf_writer(&buf, &opts);
+ struct reftable_writer *w = cl_reftable_strbuf_writer(&buf,
+ REFTABLE_HASH_SHA1,
+ &opts);
struct reftable_ref_record refs[2] = {
{
.refname = (char *) "b",
@@ -787,7 +803,8 @@ void test_reftable_readwrite__write_multiple_indices(void)
int i;
int err;
- writer = cl_reftable_strbuf_writer(&writer_buf, &opts);
+ writer = cl_reftable_strbuf_writer(&writer_buf, REFTABLE_HASH_SHA1,
+ &opts);
reftable_writer_set_limits(writer, 1, 1);
for (i = 0; i < 100; i++) {
struct reftable_ref_record ref = {
@@ -861,7 +878,8 @@ void test_reftable_readwrite__write_multi_level_index(void)
struct reftable_table *table;
int err;
- writer = cl_reftable_strbuf_writer(&writer_buf, &opts);
+ writer = cl_reftable_strbuf_writer(&writer_buf, REFTABLE_HASH_SHA1,
+ &opts);
reftable_writer_set_limits(writer, 1, 1);
for (size_t i = 0; i < 200; i++) {
struct reftable_ref_record ref = {
diff --git a/t/unit-tests/u-reftable-stack.c b/t/unit-tests/u-reftable-stack.c
index b8110cdeee..e6c1635940 100644
--- a/t/unit-tests/u-reftable-stack.c
+++ b/t/unit-tests/u-reftable-stack.c
@@ -111,10 +111,9 @@ static int write_test_ref(struct reftable_writer *wr, void *arg)
static void write_n_ref_tables(struct reftable_stack *st,
size_t n)
{
- int disable_auto_compact;
-
- disable_auto_compact = st->opts.disable_auto_compact;
- st->opts.disable_auto_compact = 1;
+ struct reftable_write_options opts = {
+ .disable_auto_compact = 1,
+ };
for (size_t i = 0; i < n; i++) {
struct reftable_ref_record ref = {
@@ -128,10 +127,8 @@ static void write_n_ref_tables(struct reftable_stack *st,
cl_reftable_set_hash(ref.value.val1, i, REFTABLE_HASH_SHA1);
cl_assert_equal_i(reftable_stack_add(st,
- &write_test_ref, &ref, 0), 0);
+ &write_test_ref, &ref, &opts, 0), 0);
}
-
- st->opts.disable_auto_compact = disable_auto_compact;
}
struct write_log_arg {
@@ -168,10 +165,10 @@ void test_reftable_stack__add_one(void)
struct stat stat_result = { 0 };
int err;
- err = reftable_new_stack(&st, dir, &opts);
+ err = reftable_new_stack(&st, dir, NULL);
cl_assert(!err);
- err = reftable_stack_add(st, write_test_ref, &ref, 0);
+ err = reftable_stack_add(st, write_test_ref, &ref, &opts, 0);
cl_assert(!err);
err = reftable_stack_read_ref(st, ref.refname, &dest);
@@ -210,7 +207,6 @@ void test_reftable_stack__add_one(void)
void test_reftable_stack__uptodate(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st1 = NULL;
struct reftable_stack *st2 = NULL;
char *dir = get_tmp_dir(__LINE__);
@@ -232,15 +228,15 @@ void test_reftable_stack__uptodate(void)
/* simulate multi-process access to the same stack
by creating two stacks for the same directory.
*/
- cl_assert_equal_i(reftable_new_stack(&st1, dir, &opts), 0);
- cl_assert_equal_i(reftable_new_stack(&st2, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st1, dir, NULL), 0);
+ cl_assert_equal_i(reftable_new_stack(&st2, dir, NULL), 0);
cl_assert_equal_i(reftable_stack_add(st1, write_test_ref,
- &ref1, 0), 0);
+ &ref1, NULL, 0), 0);
cl_assert_equal_i(reftable_stack_add(st2, write_test_ref,
- &ref2, 0), REFTABLE_OUTDATED_ERROR);
+ &ref2, NULL, 0), REFTABLE_OUTDATED_ERROR);
cl_assert_equal_i(reftable_stack_reload(st2), 0);
cl_assert_equal_i(reftable_stack_add(st2, write_test_ref,
- &ref2, 0), 0);
+ &ref2, NULL, 0), 0);
reftable_stack_destroy(st1);
reftable_stack_destroy(st2);
clear_dir(dir);
@@ -249,7 +245,6 @@ void test_reftable_stack__uptodate(void)
void test_reftable_stack__transaction_api(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
struct reftable_addition *add = NULL;
@@ -261,11 +256,11 @@ void test_reftable_stack__transaction_api(void)
};
struct reftable_ref_record dest = { 0 };
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
reftable_addition_destroy(add);
- cl_assert_equal_i(reftable_stack_new_addition(&add, st, 0), 0);
+ cl_assert_equal_i(reftable_stack_new_addition(&add, st, NULL, 0), 0);
cl_assert_equal_i(reftable_addition_add(add, write_test_ref,
&ref), 0);
cl_assert_equal_i(reftable_addition_commit(add), 0);
@@ -306,7 +301,7 @@ void test_reftable_stack__transaction_with_reload(void)
cl_assert_equal_i(reftable_new_stack(&st1, dir, NULL), 0);
cl_assert_equal_i(reftable_new_stack(&st2, dir, NULL), 0);
- cl_assert_equal_i(reftable_stack_new_addition(&add, st1, 0), 0);
+ cl_assert_equal_i(reftable_stack_new_addition(&add, st1, NULL, 0), 0);
cl_assert_equal_i(reftable_addition_add(add, write_test_ref,
&refs[0]), 0);
cl_assert_equal_i(reftable_addition_commit(add), 0);
@@ -317,9 +312,9 @@ void test_reftable_stack__transaction_with_reload(void)
* create the addition and lock the stack by default, but allow the
* reload to happen when REFTABLE_STACK_NEW_ADDITION_RELOAD is set.
*/
- cl_assert_equal_i(reftable_stack_new_addition(&add, st2, 0),
+ cl_assert_equal_i(reftable_stack_new_addition(&add, st2, NULL, 0),
REFTABLE_OUTDATED_ERROR);
- cl_assert_equal_i(reftable_stack_new_addition(&add, st2,
+ cl_assert_equal_i(reftable_stack_new_addition(&add, st2, NULL,
REFTABLE_STACK_NEW_ADDITION_RELOAD), 0);
cl_assert_equal_i(reftable_addition_add(add, write_test_ref,
&refs[1]), 0);
@@ -342,12 +337,11 @@ void test_reftable_stack__transaction_with_reload(void)
void test_reftable_stack__transaction_api_performs_auto_compaction(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = {0};
struct reftable_addition *add = NULL;
struct reftable_stack *st = NULL;
size_t n = 20;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (size_t i = 0; i <= n; i++) {
struct reftable_ref_record ref = {
@@ -356,6 +350,9 @@ void test_reftable_stack__transaction_api_performs_auto_compaction(void)
.value.symref = (char *) "master",
};
char name[100];
+ struct reftable_write_options write_opts = {
+ .disable_auto_compact = (i != n),
+ };
snprintf(name, sizeof(name), "branch%04"PRIuMAX, (uintmax_t)i);
ref.refname = name;
@@ -365,10 +362,8 @@ void test_reftable_stack__transaction_api_performs_auto_compaction(void)
* we can ensure that we indeed honor this setting and have
* better control over when exactly auto compaction runs.
*/
- st->opts.disable_auto_compact = i != n;
-
cl_assert_equal_i(reftable_stack_new_addition(&add,
- st, 0), 0);
+ st, &write_opts, 0), 0);
cl_assert_equal_i(reftable_addition_add(add,
write_test_ref, &ref), 0);
cl_assert_equal_i(reftable_addition_commit(add), 0);
@@ -398,15 +393,14 @@ void test_reftable_stack__auto_compaction_fails_gracefully(void)
.value_type = REFTABLE_REF_VAL1,
.value.val1 = {0x01},
};
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st;
struct reftable_buf table_path = REFTABLE_BUF_INIT;
char *dir = get_tmp_dir(__LINE__);
int err;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &ref, 0), 0);
+ &ref, NULL, 0), 0);
cl_assert_equal_i(st->merged->tables_len, 1);
cl_assert_equal_i(st->stats.attempts, 0);
cl_assert_equal_i(st->stats.failures, 0);
@@ -424,7 +418,7 @@ void test_reftable_stack__auto_compaction_fails_gracefully(void)
write_file_buf(table_path.buf, "", 0);
ref.update_index = 2;
- err = reftable_stack_add(st, write_test_ref, &ref, 0);
+ err = reftable_stack_add(st, write_test_ref, &ref, NULL, 0);
cl_assert(!err);
cl_assert_equal_i(st->merged->tables_len, 2);
cl_assert_equal_i(st->stats.attempts, 1);
@@ -443,7 +437,6 @@ static int write_error(struct reftable_writer *wr UNUSED, void *arg)
void test_reftable_stack__update_index_check(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
struct reftable_ref_record ref1 = {
.refname = (char *) "name1",
@@ -458,11 +451,11 @@ void test_reftable_stack__update_index_check(void)
.value.symref = (char *) "master",
};
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &ref1, 0), 0);
+ &ref1, NULL, 0), 0);
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &ref2, 0), REFTABLE_API_ERROR);
+ &ref2, NULL, 0), REFTABLE_API_ERROR);
reftable_stack_destroy(st);
clear_dir(dir);
}
@@ -470,14 +463,13 @@ void test_reftable_stack__update_index_check(void)
void test_reftable_stack__lock_failure(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
int i;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (i = -1; i != REFTABLE_EMPTY_TABLE_ERROR; i--)
cl_assert_equal_i(reftable_stack_add(st, write_error,
- &i, 0), i);
+ &i, NULL, 0), i);
reftable_stack_destroy(st);
clear_dir(dir);
@@ -499,7 +491,7 @@ void test_reftable_stack__add(void)
size_t i, N = ARRAY_SIZE(refs);
int err = 0;
- err = reftable_new_stack(&st, dir, &opts);
+ err = reftable_new_stack(&st, dir, NULL);
cl_assert(!err);
for (i = 0; i < N; i++) {
@@ -521,7 +513,7 @@ void test_reftable_stack__add(void)
for (i = 0; i < N; i++)
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &refs[i], 0), 0);
+ &refs[i], &opts, 0), 0);
for (i = 0; i < N; i++) {
struct write_log_arg arg = {
@@ -529,10 +521,10 @@ void test_reftable_stack__add(void)
.update_index = reftable_stack_next_update_index(st),
};
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), 0);
+ &arg, &opts, 0), 0);
}
- cl_assert_equal_i(reftable_stack_compact_all(st, NULL), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st, &opts, NULL), 0);
for (i = 0; i < N; i++) {
struct reftable_ref_record dest = { 0 };
@@ -584,7 +576,6 @@ void test_reftable_stack__add(void)
void test_reftable_stack__iterator(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
char *dir = get_tmp_dir(__LINE__);
struct reftable_ref_record refs[10] = { 0 };
@@ -593,7 +584,7 @@ void test_reftable_stack__iterator(void)
size_t N = ARRAY_SIZE(refs), i;
int err;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (i = 0; i < N; i++) {
refs[i].refname = xstrfmt("branch%02"PRIuMAX, (uintmax_t)i);
@@ -613,7 +604,7 @@ void test_reftable_stack__iterator(void)
for (i = 0; i < N; i++)
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &refs[i], 0), 0);
+ &refs[i], NULL, 0), 0);
for (i = 0; i < N; i++) {
struct write_log_arg arg = {
@@ -622,7 +613,7 @@ void test_reftable_stack__iterator(void)
};
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), 0);
+ &arg, NULL, 0), 0);
}
reftable_stack_init_ref_iterator(st, &it);
@@ -669,9 +660,6 @@ void test_reftable_stack__iterator(void)
void test_reftable_stack__log_normalize(void)
{
- struct reftable_write_options opts = {
- 0,
- };
struct reftable_stack *st = NULL;
char *dir = get_tmp_dir(__LINE__);
struct reftable_log_record input = {
@@ -693,15 +681,15 @@ void test_reftable_stack__log_normalize(void)
.update_index = 1,
};
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
input.value.update.message = (char *) "one\ntwo";
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), REFTABLE_API_ERROR);
+ &arg, NULL, 0), REFTABLE_API_ERROR);
input.value.update.message = (char *) "one";
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), 0);
+ &arg, NULL, 0), 0);
cl_assert_equal_i(reftable_stack_read_log(st, input.refname,
&dest), 0);
cl_assert_equal_s(dest.value.update.message, "one\n");
@@ -709,7 +697,7 @@ void test_reftable_stack__log_normalize(void)
input.value.update.message = (char *) "two\n";
arg.update_index = 2;
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), 0);
+ &arg, NULL, 0), 0);
cl_assert_equal_i(reftable_stack_read_log(st, input.refname,
&dest), 0);
cl_assert_equal_s(dest.value.update.message, "two\n");
@@ -723,7 +711,6 @@ void test_reftable_stack__log_normalize(void)
void test_reftable_stack__tombstone(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
struct reftable_ref_record refs[2] = { 0 };
struct reftable_log_record logs[2] = { 0 };
@@ -731,7 +718,7 @@ void test_reftable_stack__tombstone(void)
struct reftable_ref_record dest = { 0 };
struct reftable_log_record log_dest = { 0 };
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
/* even entries add the refs, odd entries delete them. */
for (i = 0; i < N; i++) {
@@ -760,7 +747,7 @@ void test_reftable_stack__tombstone(void)
}
for (i = 0; i < N; i++)
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &refs[i], 0), 0);
+ &refs[i], NULL, 0), 0);
for (i = 0; i < N; i++) {
struct write_log_arg arg = {
@@ -768,7 +755,7 @@ void test_reftable_stack__tombstone(void)
.update_index = reftable_stack_next_update_index(st),
};
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), 0);
+ &arg, NULL, 0), 0);
}
cl_assert_equal_i(reftable_stack_read_ref(st, "branch",
@@ -779,7 +766,7 @@ void test_reftable_stack__tombstone(void)
&log_dest), 1);
reftable_log_record_release(&log_dest);
- cl_assert_equal_i(reftable_stack_compact_all(st, NULL), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st, NULL, NULL), 0);
cl_assert_equal_i(reftable_stack_read_ref(st, "branch",
&dest), 1);
cl_assert_equal_i(reftable_stack_read_log(st, "branch",
@@ -799,7 +786,6 @@ void test_reftable_stack__tombstone(void)
void test_reftable_stack__hash_id(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
struct reftable_ref_record ref = {
@@ -808,15 +794,14 @@ void test_reftable_stack__hash_id(void)
.value.symref = (char *) "target",
.update_index = 1,
};
- struct reftable_write_options opts32 = { .hash_id = REFTABLE_HASH_SHA256 };
+ struct reftable_stack_options opts32 = { .hash_id = REFTABLE_HASH_SHA256 };
struct reftable_stack *st32 = NULL;
- struct reftable_write_options opts_default = { 0 };
struct reftable_stack *st_default = NULL;
struct reftable_ref_record dest = { 0 };
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &ref, 0), 0);
+ &ref, NULL, 0), 0);
/* can't read it with the wrong hash ID. */
cl_assert_equal_i(reftable_new_stack(&st32, dir,
@@ -824,7 +809,7 @@ void test_reftable_stack__hash_id(void)
/* check that we can read it back with default opts too. */
cl_assert_equal_i(reftable_new_stack(&st_default, dir,
- &opts_default), 0);
+ NULL), 0);
cl_assert_equal_i(reftable_stack_read_ref(st_default, "master",
&dest), 0);
cl_assert(reftable_ref_record_equal(&ref, &dest,
@@ -855,7 +840,6 @@ void test_reftable_stack__suggest_compaction_segment_nothing(void)
void test_reftable_stack__reflog_expire(void)
{
char *dir = get_tmp_dir(__LINE__);
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
struct reftable_log_record logs[20] = { 0 };
size_t i, N = ARRAY_SIZE(logs) - 1;
@@ -864,7 +848,7 @@ void test_reftable_stack__reflog_expire(void)
};
struct reftable_log_record log = { 0 };
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (i = 1; i <= N; i++) {
char buf[256];
@@ -885,18 +869,18 @@ void test_reftable_stack__reflog_expire(void)
.update_index = reftable_stack_next_update_index(st),
};
cl_assert_equal_i(reftable_stack_add(st, write_test_log,
- &arg, 0), 0);
+ &arg, NULL, 0), 0);
}
- cl_assert_equal_i(reftable_stack_compact_all(st, NULL), 0);
- cl_assert_equal_i(reftable_stack_compact_all(st, &expiry), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st, NULL, NULL), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st, NULL, &expiry), 0);
cl_assert_equal_i(reftable_stack_read_log(st, logs[9].refname,
&log), 1);
cl_assert_equal_i(reftable_stack_read_log(st, logs[11].refname,
&log), 0);
expiry.min_update_index = 15;
- cl_assert_equal_i(reftable_stack_compact_all(st, &expiry), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st, NULL, &expiry), 0);
cl_assert_equal_i(reftable_stack_read_log(st, logs[14].refname,
&log), 1);
cl_assert_equal_i(reftable_stack_read_log(st, logs[16].refname,
@@ -918,15 +902,14 @@ static int write_nothing(struct reftable_writer *wr, void *arg UNUSED)
void test_reftable_stack__empty_add(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
char *dir = get_tmp_dir(__LINE__);
struct reftable_stack *st2 = NULL;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
cl_assert_equal_i(reftable_stack_add(st, write_nothing,
- NULL, 0), 0);
- cl_assert_equal_i(reftable_new_stack(&st2, dir, &opts), 0);
+ NULL, NULL, 0), 0);
+ cl_assert_equal_i(reftable_new_stack(&st2, dir, NULL), 0);
clear_dir(dir);
reftable_stack_destroy(st);
reftable_stack_destroy(st2);
@@ -952,7 +935,7 @@ void test_reftable_stack__auto_compaction(void)
size_t i, N = 100;
int err;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (i = 0; i < N; i++) {
char name[100];
@@ -964,10 +947,10 @@ void test_reftable_stack__auto_compaction(void)
};
snprintf(name, sizeof(name), "branch%04"PRIuMAX, (uintmax_t)i);
- err = reftable_stack_add(st, write_test_ref, &ref, 0);
+ err = reftable_stack_add(st, write_test_ref, &ref, &opts, 0);
cl_assert(!err);
- err = reftable_stack_auto_compact(st);
+ err = reftable_stack_auto_compact(st, &opts);
cl_assert(!err);
cl_assert(i < 2 || st->merged->tables_len < 2 * fastlogN(i, 2));
}
@@ -989,7 +972,7 @@ void test_reftable_stack__auto_compaction_factor(void)
size_t N = 100;
int err;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (size_t i = 0; i < N; i++) {
char name[20];
@@ -1000,7 +983,7 @@ void test_reftable_stack__auto_compaction_factor(void)
};
xsnprintf(name, sizeof(name), "branch%04"PRIuMAX, (uintmax_t)i);
- err = reftable_stack_add(st, &write_test_ref, &ref, 0);
+ err = reftable_stack_add(st, &write_test_ref, &ref, &opts, 0);
cl_assert(!err);
cl_assert(i < 5 || st->merged->tables_len < 5 * fastlogN(i, 5));
@@ -1020,7 +1003,7 @@ void test_reftable_stack__auto_compaction_with_locked_tables(void)
char *dir = get_tmp_dir(__LINE__);
int err;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
write_n_ref_tables(st, 5);
cl_assert_equal_i(st->merged->tables_len, 5);
@@ -1042,7 +1025,7 @@ void test_reftable_stack__auto_compaction_with_locked_tables(void)
* would in theory compact all tables, due to the preexisting lock we
* only compact the newest two tables.
*/
- err = reftable_stack_auto_compact(st);
+ err = reftable_stack_auto_compact(st, &opts);
cl_assert(!err);
cl_assert_equal_i(st->stats.failures, 0);
cl_assert_equal_i(st->merged->tables_len, 4);
@@ -1054,12 +1037,11 @@ void test_reftable_stack__auto_compaction_with_locked_tables(void)
void test_reftable_stack__add_performs_auto_compaction(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
char *dir = get_tmp_dir(__LINE__);
size_t i, n = 20;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
for (i = 0; i <= n; i++) {
struct reftable_ref_record ref = {
@@ -1067,6 +1049,9 @@ void test_reftable_stack__add_performs_auto_compaction(void)
.value_type = REFTABLE_REF_SYMREF,
.value.symref = (char *) "master",
};
+ struct reftable_write_options write_opts = {
+ .disable_auto_compact = (i != n),
+ };
bool required = false;
char buf[128];
@@ -1075,20 +1060,18 @@ void test_reftable_stack__add_performs_auto_compaction(void)
* we can ensure that we indeed honor this setting and have
* better control over when exactly auto compaction runs.
*/
- st->opts.disable_auto_compact = i != n;
-
snprintf(buf, sizeof(buf), "branch-%04"PRIuMAX, (uintmax_t)i);
ref.refname = buf;
cl_assert_equal_i(reftable_stack_add(st, write_test_ref,
- &ref, 0), 0);
+ &ref, &write_opts, 0), 0);
/*
* The stack length should grow continuously for all runs where
* auto compaction is disabled. When enabled, we should merge
* all tables in the stack.
*/
- cl_assert_equal_i(reftable_stack_compaction_required(st, true, &required), 0);
+ cl_assert_equal_i(reftable_stack_compaction_required(st, NULL, true, &required), 0);
if (i != n) {
cl_assert_equal_i(st->merged->tables_len, i + 1);
if (i < 1)
@@ -1115,7 +1098,7 @@ void test_reftable_stack__compaction_with_locked_tables(void)
char *dir = get_tmp_dir(__LINE__);
int err;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
write_n_ref_tables(st, 3);
cl_assert_equal_i(st->merged->tables_len, 3);
@@ -1131,7 +1114,7 @@ void test_reftable_stack__compaction_with_locked_tables(void)
* Compaction is expected to fail given that we were not able to
* compact all tables.
*/
- err = reftable_stack_compact_all(st, NULL);
+ err = reftable_stack_compact_all(st, &opts, NULL);
cl_assert_equal_i(err, REFTABLE_LOCK_ERROR);
cl_assert_equal_i(st->stats.failures, 1);
cl_assert_equal_i(st->merged->tables_len, 3);
@@ -1143,15 +1126,14 @@ void test_reftable_stack__compaction_with_locked_tables(void)
void test_reftable_stack__compaction_concurrent(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st1 = NULL, *st2 = NULL;
char *dir = get_tmp_dir(__LINE__);
- cl_assert_equal_i(reftable_new_stack(&st1, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st1, dir, NULL), 0);
write_n_ref_tables(st1, 3);
- cl_assert_equal_i(reftable_new_stack(&st2, dir, &opts), 0);
- cl_assert_equal_i(reftable_stack_compact_all(st1, NULL), 0);
+ cl_assert_equal_i(reftable_new_stack(&st2, dir, NULL), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st1, NULL, NULL), 0);
reftable_stack_destroy(st1);
reftable_stack_destroy(st2);
@@ -1171,20 +1153,19 @@ static void unclean_stack_close(struct reftable_stack *st)
void test_reftable_stack__compaction_concurrent_clean(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st1 = NULL, *st2 = NULL, *st3 = NULL;
char *dir = get_tmp_dir(__LINE__);
- cl_assert_equal_i(reftable_new_stack(&st1, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st1, dir, NULL), 0);
write_n_ref_tables(st1, 3);
- cl_assert_equal_i(reftable_new_stack(&st2, dir, &opts), 0);
- cl_assert_equal_i(reftable_stack_compact_all(st1, NULL), 0);
+ cl_assert_equal_i(reftable_new_stack(&st2, dir, NULL), 0);
+ cl_assert_equal_i(reftable_stack_compact_all(st1, NULL, NULL), 0);
unclean_stack_close(st1);
unclean_stack_close(st2);
- cl_assert_equal_i(reftable_new_stack(&st3, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st3, dir, NULL), 0);
cl_assert_equal_i(reftable_stack_clean(st3), 0);
cl_assert_equal_i(count_dir_entries(dir), 2);
@@ -1197,7 +1178,6 @@ void test_reftable_stack__compaction_concurrent_clean(void)
void test_reftable_stack__read_across_reload(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st1 = NULL, *st2 = NULL;
struct reftable_ref_record rec = { 0 };
struct reftable_iterator it = { 0 };
@@ -1205,17 +1185,17 @@ void test_reftable_stack__read_across_reload(void)
int err;
/* Create a first stack and set up an iterator for it. */
- cl_assert_equal_i(reftable_new_stack(&st1, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st1, dir, NULL), 0);
write_n_ref_tables(st1, 2);
cl_assert_equal_i(st1->merged->tables_len, 2);
reftable_stack_init_ref_iterator(st1, &it);
cl_assert_equal_i(reftable_iterator_seek_ref(&it, ""), 0);
/* Set up a second stack for the same directory and compact it. */
- err = reftable_new_stack(&st2, dir, &opts);
+ err = reftable_new_stack(&st2, dir, NULL);
cl_assert(!err);
cl_assert_equal_i(st2->merged->tables_len, 2);
- err = reftable_stack_compact_all(st2, NULL);
+ err = reftable_stack_compact_all(st2, NULL, NULL);
cl_assert(!err);
cl_assert_equal_i(st2->merged->tables_len, 1);
@@ -1244,7 +1224,6 @@ void test_reftable_stack__read_across_reload(void)
void test_reftable_stack__reload_with_missing_table(void)
{
- struct reftable_write_options opts = { 0 };
struct reftable_stack *st = NULL;
struct reftable_ref_record rec = { 0 };
struct reftable_iterator it = { 0 };
@@ -1253,7 +1232,7 @@ void test_reftable_stack__reload_with_missing_table(void)
int err;
/* Create a first stack and set up an iterator for it. */
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
write_n_ref_tables(st, 2);
cl_assert_equal_i(st->merged->tables_len, 2);
reftable_stack_init_ref_iterator(st, &it);
@@ -1320,11 +1299,11 @@ void test_reftable_stack__invalid_limit_updates(void)
char *dir = get_tmp_dir(__LINE__);
struct reftable_stack *st = NULL;
- cl_assert_equal_i(reftable_new_stack(&st, dir, &opts), 0);
+ cl_assert_equal_i(reftable_new_stack(&st, dir, NULL), 0);
reftable_addition_destroy(add);
- cl_assert_equal_i(reftable_stack_new_addition(&add, st, 0), 0);
+ cl_assert_equal_i(reftable_stack_new_addition(&add, st, &opts, 0), 0);
/*
* write_limits_after_ref also updates the update indexes after adding
diff --git a/t/unit-tests/u-reftable-table.c b/t/unit-tests/u-reftable-table.c
index 14fae8b199..fae478ee04 100644
--- a/t/unit-tests/u-reftable-table.c
+++ b/t/unit-tests/u-reftable-table.c
@@ -22,7 +22,8 @@ void test_reftable_table__seek_once(void)
struct reftable_buf buf = REFTABLE_BUF_INIT;
int ret;
- cl_reftable_write_to_buf(&buf, records, ARRAY_SIZE(records), NULL, 0, NULL);
+ cl_reftable_write_to_buf(&buf, records, ARRAY_SIZE(records), NULL, 0,
+ REFTABLE_HASH_SHA1, NULL);
block_source_from_buf(&source, &buf);
ret = reftable_table_new(&table, &source, "name");
@@ -64,7 +65,7 @@ void test_reftable_table__reseek(void)
int ret;
cl_reftable_write_to_buf(&buf, records, ARRAY_SIZE(records),
- NULL, 0, NULL);
+ NULL, 0, REFTABLE_HASH_SHA1, NULL);
block_source_from_buf(&source, &buf);
ret = reftable_table_new(&table, &source, "name");
@@ -147,7 +148,8 @@ void test_reftable_table__block_iterator(void)
(uintmax_t) i);
}
- cl_reftable_write_to_buf(&buf, records, nrecords, NULL, 0, NULL);
+ cl_reftable_write_to_buf(&buf, records, nrecords, NULL, 0,
+ REFTABLE_HASH_SHA1, NULL);
block_source_from_buf(&source, &buf);
ret = reftable_table_new(&table, &source, "name");
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v6 08/11] refs/files: lazy-load configuration to fix chicken-and-egg
From: Patrick Steinhardt @ 2026-06-25 9:20 UTC (permalink / raw)
To: git; +Cc: Karthik Nayak, Jeff King, Justin Tobler
In-Reply-To: <20260625-b4-pks-refs-avoid-chdir-notify-reparent-v6-0-41fbca3cf5e3@pks.im>
When initializing the "files" reference backend we read the repository's
config to parse "core.preferSymlinkRefs" and "core.logAllRefUpdates".
This results in a chicken-and-egg problem though, because parsing the
configuration may require us to have access to the reference store
already when an "onbranch" condition exists.
Luckily, all the configuration that we honor only relates to writing
references. Consequently, we don't strictly need that configuration to
be readily available at initialization time, and we can easiliy defer
parsing it to a later point in time.
Implement this fix and add tests that verify that we can indeed properly
parse these config knobs via an "onbranch" condition.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
refs/files-backend.c | 44 +++++++++++++++++++++++++++++++++-----------
t/t0600-reffiles-backend.sh | 21 +++++++++++++++++++++
2 files changed, 54 insertions(+), 11 deletions(-)
diff --git a/refs/files-backend.c b/refs/files-backend.c
index 79fb6735e1..7ffe489f6a 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -84,12 +84,21 @@ struct files_ref_store {
unsigned int store_flags;
char *gitcommondir;
- enum log_refs_config log_all_ref_updates;
- int prefer_symlink_refs;
-
struct ref_cache *loose;
-
struct ref_store *packed_ref_store;
+
+ /*
+ * Options used when writing references. These are parsed from the
+ * config lazily on first use via `files_ref_store_write_options()` so
+ * that we don't have to access the configuration when initializing the
+ * ref store. Do not access these fields directly, but use the accessor
+ * instead.
+ */
+ struct files_ref_store_write_options {
+ enum log_refs_config log_all_ref_updates;
+ int prefer_symlink_refs;
+ bool initialized;
+ } write_opts_lazy_loaded;
};
static void clear_loose_ref_cache(struct files_ref_store *refs)
@@ -121,17 +130,31 @@ static int files_ref_store_config(const char *var, const char *value,
const struct config_context *ctx UNUSED,
void *payload)
{
- struct files_ref_store *refs = payload;
+ struct files_ref_store_write_options *opts = payload;
if (!strcmp(var, "core.prefersymlinkrefs")) {
- refs->prefer_symlink_refs = git_config_bool(var, value);
+ opts->prefer_symlink_refs = git_config_bool(var, value);
} else if (!strcmp(var, "core.logallrefupdates")) {
- refs->log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
+ opts->log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
}
return 0;
}
+static const struct files_ref_store_write_options *files_ref_store_write_options(struct files_ref_store *refs)
+{
+ struct files_ref_store_write_options *opts = &refs->write_opts_lazy_loaded;
+
+ if (opts->initialized)
+ return opts;
+
+ opts->log_all_ref_updates = LOG_REFS_UNSET;
+ repo_config(refs->base.repo, files_ref_store_config, opts);
+
+ opts->initialized = true;
+ return opts;
+}
+
/*
* Create a new submodule ref cache and add it to the internal
* set of caches.
@@ -156,9 +179,7 @@ static struct ref_store *files_ref_store_init(struct repository *repo,
refs->packed_ref_store =
packed_ref_store_init(repo, NULL, refs->gitcommondir, opts);
refs->store_flags = opts->access_flags;
- refs->log_all_ref_updates = LOG_REFS_UNSET;
- repo_config(repo, files_ref_store_config, refs);
chdir_notify_register(NULL, files_ref_store_reparent, refs);
strbuf_release(&refdir);
@@ -1890,7 +1911,7 @@ static int log_ref_setup(struct files_ref_store *refs,
const char *refname, int force_create,
int *logfd, struct strbuf *err)
{
- enum log_refs_config log_refs_cfg = refs->log_all_ref_updates;
+ enum log_refs_config log_refs_cfg = files_ref_store_write_options(refs)->log_all_ref_updates;
struct strbuf logfile_sb = STRBUF_INIT;
char *logfile;
@@ -3301,6 +3322,7 @@ static int files_transaction_finish(struct ref_store *ref_store,
{
struct files_ref_store *refs =
files_downcast(ref_store, 0, "ref_transaction_finish");
+ const struct files_ref_store_write_options *write_opts = files_ref_store_write_options(refs);
size_t i;
int ret = 0;
struct strbuf sb = STRBUF_INIT;
@@ -3340,7 +3362,7 @@ static int files_transaction_finish(struct ref_store *ref_store,
* We try creating a symlink, if that succeeds we continue to the
* next update. If not, we try and create a regular symref.
*/
- if (update->new_target && refs->prefer_symlink_refs)
+ if (update->new_target && write_opts->prefer_symlink_refs)
/*
* By using the `NOT_CONSTANT()` trick, we can avoid
* errors by `clang`'s `-Wunreachable` logic that would
diff --git a/t/t0600-reffiles-backend.sh b/t/t0600-reffiles-backend.sh
index 74bfa2e9ba..bbbf6fa422 100755
--- a/t/t0600-reffiles-backend.sh
+++ b/t/t0600-reffiles-backend.sh
@@ -519,4 +519,25 @@ test_expect_success 'symref transaction supports false symlink config' '
test_cmp expect actual
'
+test_expect_success SYMLINKS,!MINGW,!WITH_BREAKING_CHANGES 'core.preferSymlinkRefs can be set up via onbranch condition' '
+ test_when_finished "git symbolic-ref -d TEST_SYMREF_HEAD" &&
+ test_when_finished "rm -f .git/include" &&
+ git update-ref refs/heads/new @ &&
+ cat >.git/include <<-\EOF &&
+ [core]
+ preferSymlinkRefs = true
+ EOF
+ test_config includeIf.onbranch:"$(git branch --show-current)".path \
+ "$(pwd)/.git/include" &&
+ cat >stdin <<-EOF &&
+ start
+ symref-create TEST_SYMREF_HEAD refs/heads/new
+ prepare
+ commit
+ EOF
+ git update-ref --no-deref --stdin <stdin &&
+ test_path_is_symlink .git/TEST_SYMREF_HEAD &&
+ test "$(test_readlink .git/TEST_SYMREF_HEAD)" = refs/heads/new
+'
+
test_done
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v6 07/11] refs: move parsing of "core.logAllRefUpdates" back into ref stores
From: Patrick Steinhardt @ 2026-06-25 9:20 UTC (permalink / raw)
To: git; +Cc: Karthik Nayak, Jeff King, Justin Tobler
In-Reply-To: <20260625-b4-pks-refs-avoid-chdir-notify-reparent-v6-0-41fbca3cf5e3@pks.im>
In cc42c88945 (refs: extract out reflog config to generic layer,
2026-05-04) we have refactored how we parse "core.logAllRefUpdates" so
that it happens in the generic layer. Unfortunately, this has worsened a
preexisting issue where we may recurse when creating the reference store
because of a chicken-and-egg problem between parsing the configuration
and evaluating "onbranch" conditions.
Prepare for a fix by essentially reverting that change so that we handle
this setting in the respective backends again. The backends are already
parsing other configuration anyway, so by moving the logic back in there
we can ensure that all backend configuration is parsed the same way.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
builtin/checkout.c | 7 +++++--
refs.c | 10 +++++++++-
refs.h | 9 +++++++++
refs/files-backend.c | 20 +++++++++++++++++---
refs/refs-internal.h | 6 ------
refs/reftable-backend.c | 20 +++++++++++---------
repo-settings.c | 16 ----------------
repo-settings.h | 9 ---------
setup.c | 6 +++++-
9 files changed, 56 insertions(+), 47 deletions(-)
diff --git a/builtin/checkout.c b/builtin/checkout.c
index b78b3a1d16..aee84ca897 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -952,10 +952,13 @@ static void update_refs_for_switch(const struct checkout_opts *opts,
const char *old_desc, *reflog_msg;
if (opts->new_branch) {
if (opts->new_orphan_branch) {
- enum log_refs_config log_all_ref_updates =
- repo_settings_get_log_all_ref_updates(the_repository);
+ enum log_refs_config log_all_ref_updates = LOG_REFS_UNSET;
+ const char *value;
char *refname;
+ if (!repo_config_get_string_tmp(the_repository, "core.logallrefupdates", &value))
+ log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
+
refname = mkpathdup("refs/heads/%s", opts->new_orphan_branch);
if (opts->new_branch_log &&
!should_autocreate_reflog(log_all_ref_updates, refname)) {
diff --git a/refs.c b/refs.c
index d3caa9a633..5b773b1c15 100644
--- a/refs.c
+++ b/refs.c
@@ -1053,6 +1053,15 @@ static char *normalize_reflog_message(const char *msg)
return strbuf_detach(&sb, NULL);
}
+enum log_refs_config refs_parse_log_all_ref_updates_config(const char *value)
+{
+ if (value && !strcasecmp(value, "always"))
+ return LOG_REFS_ALWAYS;
+ else if (git_config_bool("core.logallrefupdates", value))
+ return LOG_REFS_NORMAL;
+ return LOG_REFS_NONE;
+}
+
int should_autocreate_reflog(enum log_refs_config log_all_ref_updates,
const char *refname)
{
@@ -2327,7 +2336,6 @@ static struct ref_store *ref_store_init(struct repository *repo,
struct ref_store *refs;
struct ref_store_init_options opts = {
.access_flags = flags,
- .log_all_ref_updates = repo_settings_get_log_all_ref_updates(repo),
};
be = find_ref_storage_backend(format);
diff --git a/refs.h b/refs.h
index 71d5c186d0..a381022c77 100644
--- a/refs.h
+++ b/refs.h
@@ -146,6 +146,15 @@ enum ref_transaction_error refs_verify_refname_available(struct ref_store *refs,
int refs_ref_exists(struct ref_store *refs, const char *refname);
+enum log_refs_config {
+ LOG_REFS_UNSET = -1,
+ LOG_REFS_NONE = 0,
+ LOG_REFS_NORMAL,
+ LOG_REFS_ALWAYS
+};
+
+enum log_refs_config refs_parse_log_all_ref_updates_config(const char *value);
+
int should_autocreate_reflog(enum log_refs_config log_all_ref_updates,
const char *refname);
diff --git a/refs/files-backend.c b/refs/files-backend.c
index 296981584b..79fb6735e1 100644
--- a/refs/files-backend.c
+++ b/refs/files-backend.c
@@ -117,6 +117,21 @@ static void files_ref_store_reparent(const char *name UNUSED,
refs->gitcommondir = tmp;
}
+static int files_ref_store_config(const char *var, const char *value,
+ const struct config_context *ctx UNUSED,
+ void *payload)
+{
+ struct files_ref_store *refs = payload;
+
+ if (!strcmp(var, "core.prefersymlinkrefs")) {
+ refs->prefer_symlink_refs = git_config_bool(var, value);
+ } else if (!strcmp(var, "core.logallrefupdates")) {
+ refs->log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
+ }
+
+ return 0;
+}
+
/*
* Create a new submodule ref cache and add it to the internal
* set of caches.
@@ -141,10 +156,9 @@ static struct ref_store *files_ref_store_init(struct repository *repo,
refs->packed_ref_store =
packed_ref_store_init(repo, NULL, refs->gitcommondir, opts);
refs->store_flags = opts->access_flags;
- refs->log_all_ref_updates = opts->log_all_ref_updates;
-
- repo_config_get_bool(repo, "core.prefersymlinkrefs", &refs->prefer_symlink_refs);
+ refs->log_all_ref_updates = LOG_REFS_UNSET;
+ repo_config(repo, files_ref_store_config, refs);
chdir_notify_register(NULL, files_ref_store_reparent, refs);
strbuf_release(&refdir);
diff --git a/refs/refs-internal.h b/refs/refs-internal.h
index a08d58900e..c3ac7b556f 100644
--- a/refs/refs-internal.h
+++ b/refs/refs-internal.h
@@ -406,12 +406,6 @@ struct ref_store;
struct ref_store_init_options {
/* The kind of operations that the ref_store is allowed to perform. */
unsigned int access_flags;
-
- /*
- * Denotes under what conditions reflogs should be created when updating
- * references.
- */
- enum log_refs_config log_all_ref_updates;
};
/*
diff --git a/refs/reftable-backend.c b/refs/reftable-backend.c
index 8c93070677..5115a3f4ce 100644
--- a/refs/reftable-backend.c
+++ b/refs/reftable-backend.c
@@ -332,34 +332,36 @@ static void fill_reftable_log_record(struct reftable_log_record *log, const stru
static int reftable_be_config(const char *var, const char *value,
const struct config_context *ctx,
- void *_opts)
+ void *payload)
{
- struct reftable_write_options *opts = _opts;
+ struct reftable_ref_store *refs = payload;
if (!strcmp(var, "reftable.blocksize")) {
unsigned long block_size = git_config_ulong(var, value, ctx->kvi);
if (block_size > 16777215)
die("reftable block size cannot exceed 16MB");
- opts->block_size = block_size;
+ refs->write_options.block_size = block_size;
} else if (!strcmp(var, "reftable.restartinterval")) {
unsigned long restart_interval = git_config_ulong(var, value, ctx->kvi);
if (restart_interval > UINT16_MAX)
die("reftable block size cannot exceed %u", (unsigned)UINT16_MAX);
- opts->restart_interval = restart_interval;
+ refs->write_options.restart_interval = restart_interval;
} else if (!strcmp(var, "reftable.indexobjects")) {
- opts->skip_index_objects = !git_config_bool(var, value);
+ refs->write_options.skip_index_objects = !git_config_bool(var, value);
} else if (!strcmp(var, "reftable.geometricfactor")) {
unsigned long factor = git_config_ulong(var, value, ctx->kvi);
if (factor > UINT8_MAX)
die("reftable geometric factor cannot exceed %u", (unsigned)UINT8_MAX);
- opts->auto_compaction_factor = factor;
+ refs->write_options.auto_compaction_factor = factor;
} else if (!strcmp(var, "reftable.locktimeout")) {
int64_t lock_timeout = git_config_int64(var, value, ctx->kvi);
if (lock_timeout > LONG_MAX)
die("reftable lock timeout cannot exceed %"PRIdMAX, (intmax_t)LONG_MAX);
if (lock_timeout < 0 && lock_timeout != -1)
die("reftable lock timeout does not support negative values other than -1");
- opts->lock_timeout_ms = lock_timeout;
+ refs->write_options.lock_timeout_ms = lock_timeout;
+ } else if (!strcmp(var, "core.logallrefupdates")) {
+ refs->log_all_ref_updates = refs_parse_log_all_ref_updates_config(value);
}
return 0;
@@ -398,7 +400,6 @@ static struct ref_store *reftable_be_init(struct repository *repo,
base_ref_store_init(&refs->base, repo, refdir.buf, &refs_be_reftable);
strmap_init(&refs->worktree_backends);
- refs->log_all_ref_updates = opts->log_all_ref_updates;
refs->store_flags = opts->access_flags;
switch (repo->hash_algo->format_id) {
@@ -415,8 +416,9 @@ static struct ref_store *reftable_be_init(struct repository *repo,
refs->write_options.disable_auto_compact =
!git_env_bool("GIT_TEST_REFTABLE_AUTOCOMPACTION", 1);
refs->write_options.lock_timeout_ms = 100;
+ refs->log_all_ref_updates = LOG_REFS_UNSET;
- repo_config(repo, reftable_be_config, &refs->write_options);
+ repo_config(repo, reftable_be_config, refs);
/*
* It is somewhat unfortunate that we have to mirror the default block
diff --git a/repo-settings.c b/repo-settings.c
index 208e09ff17..f3be3b8c5a 100644
--- a/repo-settings.c
+++ b/repo-settings.c
@@ -177,22 +177,6 @@ void repo_settings_set_big_file_threshold(struct repository *repo, unsigned long
repo->settings.big_file_threshold = value;
}
-enum log_refs_config repo_settings_get_log_all_ref_updates(struct repository *repo)
-{
- const char *value;
-
- if (!repo_config_get_string_tmp(repo, "core.logallrefupdates", &value)) {
- if (value && !strcasecmp(value, "always"))
- return LOG_REFS_ALWAYS;
- else if (git_config_bool("core.logallrefupdates", value))
- return LOG_REFS_NORMAL;
- else
- return LOG_REFS_NONE;
- }
-
- return LOG_REFS_UNSET;
-}
-
int repo_settings_get_warn_ambiguous_refs(struct repository *repo)
{
prepare_repo_settings(repo);
diff --git a/repo-settings.h b/repo-settings.h
index cad9c3f0cc..e5253ead02 100644
--- a/repo-settings.h
+++ b/repo-settings.h
@@ -16,13 +16,6 @@ enum fetch_negotiation_setting {
FETCH_NEGOTIATION_NOOP,
};
-enum log_refs_config {
- LOG_REFS_UNSET = -1,
- LOG_REFS_NONE = 0,
- LOG_REFS_NORMAL,
- LOG_REFS_ALWAYS
-};
-
struct repo_settings {
int initialized;
@@ -86,8 +79,6 @@ struct repo_settings {
void prepare_repo_settings(struct repository *r);
void repo_settings_clear(struct repository *r);
-/* Read the value for "core.logAllRefUpdates". */
-enum log_refs_config repo_settings_get_log_all_ref_updates(struct repository *repo);
/* Read the value for "core.warnAmbiguousRefs". */
int repo_settings_get_warn_ambiguous_refs(struct repository *repo);
/* Read the value for "core.hooksPath". */
diff --git a/setup.c b/setup.c
index 79125db565..592753457c 100644
--- a/setup.c
+++ b/setup.c
@@ -2584,10 +2584,14 @@ static int create_default_files(struct repository *repo,
if (is_bare_repository())
repo_config_set(repo, "core.bare", "true");
else {
+ const char *value;
+
repo_config_set(repo, "core.bare", "false");
+
/* allow template config file to override the default */
- if (repo_settings_get_log_all_ref_updates(repo) == LOG_REFS_UNSET)
+ if (repo_config_get_string_tmp(repo, "core.logallrefupdates", &value))
repo_config_set(repo, "core.logallrefupdates", "true");
+
if (needs_work_tree_config(original_git_dir, work_tree))
repo_config_set(repo, "core.worktree", work_tree);
}
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
* [PATCH v6 06/11] repository: free main reference database
From: Patrick Steinhardt @ 2026-06-25 9:20 UTC (permalink / raw)
To: git; +Cc: Karthik Nayak, Jeff King, Justin Tobler
In-Reply-To: <20260625-b4-pks-refs-avoid-chdir-notify-reparent-v6-0-41fbca3cf5e3@pks.im>
While we release worktree and submodule reference databases when
clearing a repository, we don't ever release the main reference
database. This memory leak went unnoticed because its pointer is
kept alive by the "chdir_notify" subsystem.
Fix the memory leak.
Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
repository.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/repository.c b/repository.c
index 187dd471c4..e2b5c6712b 100644
--- a/repository.c
+++ b/repository.c
@@ -421,6 +421,11 @@ void repo_clear(struct repository *repo)
FREE_AND_NULL(repo->remote_state);
}
+ if (repo->refs_private) {
+ ref_store_release(repo->refs_private);
+ FREE_AND_NULL(repo->refs_private);
+ }
+
strmap_for_each_entry(&repo->submodule_ref_stores, &iter, e)
ref_store_release(e->value);
strmap_clear(&repo->submodule_ref_stores, 1);
--
2.55.0.rc1.745.g43192e7977.dirty
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox