* [PATCHv10 1/7] submodule-config: keep update strategy around
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
2016-02-12 2:03 ` [PATCHv10 2/7] submodule-config: drop check against NULL Stefan Beller
` (5 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
Currently submodule.<name>.update is only handled by git-submodule.sh.
C code will start to need to make use of that value as more of the
functionality of git-submodule.sh moves into library code in C.
Add the update field to 'struct submodule' and populate it so it can
be read as sm->update or from sm->update_command.
Signed-off-by: Stefan Beller <sbeller@google.com>
---
submodule-config.c | 12 ++++++++++++
submodule-config.h | 2 ++
submodule.c | 19 +++++++++++++++++++
submodule.h | 16 ++++++++++++++++
4 files changed, 49 insertions(+)
diff --git a/submodule-config.c b/submodule-config.c
index fe8ceab..254067b 100644
--- a/submodule-config.c
+++ b/submodule-config.c
@@ -194,6 +194,8 @@ static struct submodule *lookup_or_create_by_name(struct submodule_cache *cache,
submodule->path = NULL;
submodule->url = NULL;
+ submodule->update_strategy.type = SM_UPDATE_UNSPECIFIED;
+ submodule->update_strategy.command = NULL;
submodule->fetch_recurse = RECURSE_SUBMODULES_NONE;
submodule->ignore = NULL;
@@ -340,6 +342,16 @@ static int parse_config(const char *var, const char *value, void *data)
free((void *) submodule->url);
submodule->url = xstrdup(value);
}
+ } else if (!strcmp(item.buf, "update")) {
+ if (!value)
+ ret = config_error_nonbool(var);
+ else if (!me->overwrite &&
+ submodule->update_strategy.type != SM_UPDATE_UNSPECIFIED)
+ warn_multiple_config(me->commit_sha1, submodule->name,
+ "update");
+ else if (parse_submodule_update_strategy(value,
+ &submodule->update_strategy) < 0)
+ die(_("invalid value for %s"), var);
}
strbuf_release(&name);
diff --git a/submodule-config.h b/submodule-config.h
index 9bfa65a..e4857f5 100644
--- a/submodule-config.h
+++ b/submodule-config.h
@@ -2,6 +2,7 @@
#define SUBMODULE_CONFIG_CACHE_H
#include "hashmap.h"
+#include "submodule.h"
#include "strbuf.h"
/*
@@ -14,6 +15,7 @@ struct submodule {
const char *url;
int fetch_recurse;
const char *ignore;
+ struct submodule_update_strategy update_strategy;
/* the sha1 blob id of the responsible .gitmodules file */
unsigned char gitmodules_sha1[20];
};
diff --git a/submodule.c b/submodule.c
index b83939c..8fd4512 100644
--- a/submodule.c
+++ b/submodule.c
@@ -210,6 +210,25 @@ void gitmodules_config(void)
}
}
+int parse_submodule_update_strategy(const char *value,
+ struct submodule_update_strategy *dst)
+{
+ dst->command = NULL;
+ if (!strcmp(value, "none"))
+ dst->type = SM_UPDATE_NONE;
+ else if (!strcmp(value, "checkout"))
+ dst->type = SM_UPDATE_CHECKOUT;
+ else if (!strcmp(value, "rebase"))
+ dst->type = SM_UPDATE_REBASE;
+ else if (!strcmp(value, "merge"))
+ dst->type = SM_UPDATE_MERGE;
+ else if (skip_prefix(value, "!", &dst->command))
+ dst->type = SM_UPDATE_COMMAND;
+ else
+ return -1;
+ return 0;
+}
+
void handle_ignore_submodules_arg(struct diff_options *diffopt,
const char *arg)
{
diff --git a/submodule.h b/submodule.h
index e06eaa5..9a86124 100644
--- a/submodule.h
+++ b/submodule.h
@@ -14,6 +14,20 @@ enum {
RECURSE_SUBMODULES_ON = 2
};
+enum submodule_update_type {
+ SM_UPDATE_UNSPECIFIED = 0,
+ SM_UPDATE_CHECKOUT,
+ SM_UPDATE_REBASE,
+ SM_UPDATE_MERGE,
+ SM_UPDATE_NONE,
+ SM_UPDATE_COMMAND
+};
+
+struct submodule_update_strategy {
+ enum submodule_update_type type;
+ const char *command;
+};
+
int is_staging_gitmodules_ok(void);
int update_path_in_gitmodules(const char *oldpath, const char *newpath);
int remove_path_from_gitmodules(const char *path);
@@ -22,6 +36,8 @@ void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt,
const char *path);
int submodule_config(const char *var, const char *value, void *cb);
void gitmodules_config(void);
+int parse_submodule_update_strategy(const char *value,
+ struct submodule_update_strategy *dst);
void handle_ignore_submodules_arg(struct diff_options *diffopt, const char *);
void show_submodule_summary(FILE *f, const char *path,
const char *line_prefix,
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv10 2/7] submodule-config: drop check against NULL
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
2016-02-12 2:03 ` [PATCHv10 1/7] submodule-config: keep update strategy around Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
2016-02-12 2:03 ` [PATCHv10 3/7] fetching submodules: respect `submodule.fetchJobs` config option Stefan Beller
` (4 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
Adhere to the common coding style of Git and not check explicitly
for NULL throughout the file. There are still other occurrences in the
code base but that is usually inside of conditions with side effects.
Signed-off-by: Stefan Beller <sbeller@google.com>
---
submodule-config.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/submodule-config.c b/submodule-config.c
index 254067b..afd294b 100644
--- a/submodule-config.c
+++ b/submodule-config.c
@@ -295,7 +295,7 @@ static int parse_config(const char *var, const char *value, void *data)
if (!strcmp(item.buf, "path")) {
if (!value)
ret = config_error_nonbool(var);
- else if (!me->overwrite && submodule->path != NULL)
+ else if (!me->overwrite && submodule->path)
warn_multiple_config(me->commit_sha1, submodule->name,
"path");
else {
@@ -319,7 +319,7 @@ static int parse_config(const char *var, const char *value, void *data)
} else if (!strcmp(item.buf, "ignore")) {
if (!value)
ret = config_error_nonbool(var);
- else if (!me->overwrite && submodule->ignore != NULL)
+ else if (!me->overwrite && submodule->ignore)
warn_multiple_config(me->commit_sha1, submodule->name,
"ignore");
else if (strcmp(value, "untracked") &&
@@ -335,7 +335,7 @@ static int parse_config(const char *var, const char *value, void *data)
} else if (!strcmp(item.buf, "url")) {
if (!value) {
ret = config_error_nonbool(var);
- } else if (!me->overwrite && submodule->url != NULL) {
+ } else if (!me->overwrite && submodule->url) {
warn_multiple_config(me->commit_sha1, submodule->name,
"url");
} else {
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv10 3/7] fetching submodules: respect `submodule.fetchJobs` config option
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
2016-02-12 2:03 ` [PATCHv10 1/7] submodule-config: keep update strategy around Stefan Beller
2016-02-12 2:03 ` [PATCHv10 2/7] submodule-config: drop check against NULL Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
2016-02-12 2:03 ` [PATCHv10 4/7] submodule update: direct error message to stderr Stefan Beller
` (3 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
This allows to configure fetching and updating in parallel
without having the command line option.
This moved the responsibility to determine how many parallel processes
to start from builtin/fetch to submodule.c as we need a way to communicate
"The user did not specify the number of parallel processes in the command
line options" in the builtin fetch. The submodule code takes care of
the precedence (CLI > config > default).
Signed-off-by: Stefan Beller <sbeller@google.com>
---
Documentation/config.txt | 6 ++++++
builtin/fetch.c | 2 +-
submodule.c | 16 +++++++++++++++-
submodule.h | 2 ++
t/t5526-fetch-submodules.sh | 14 ++++++++++++++
5 files changed, 38 insertions(+), 2 deletions(-)
diff --git a/Documentation/config.txt b/Documentation/config.txt
index 27f02be..eb9ae85 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -2715,6 +2715,12 @@ submodule.<name>.ignore::
"--ignore-submodules" option. The 'git submodule' commands are not
affected by this setting.
+submodule.fetchJobs::
+ Specifies how many submodules are fetched/cloned at the same time.
+ A positive integer allows up to that number of submodules fetched
+ in parallel. A value of 0 will give some reasonable default.
+ If unset, it defaults to 1.
+
tag.sort::
This variable controls the sort ordering of tags when displayed by
linkgit:git-tag[1]. Without the "--sort=<value>" option provided, the
diff --git a/builtin/fetch.c b/builtin/fetch.c
index 8e74213..91f0862 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -37,7 +37,7 @@ static int prune = -1; /* unspecified */
static int all, append, dry_run, force, keep, multiple, update_head_ok, verbosity;
static int progress = -1, recurse_submodules = RECURSE_SUBMODULES_DEFAULT;
static int tags = TAGS_DEFAULT, unshallow, update_shallow;
-static int max_children = 1;
+static int max_children = -1;
static const char *depth;
static const char *upload_pack;
static struct strbuf default_rla = STRBUF_INIT;
diff --git a/submodule.c b/submodule.c
index 8fd4512..263cb2a 100644
--- a/submodule.c
+++ b/submodule.c
@@ -15,6 +15,7 @@
#include "thread-utils.h"
static int config_fetch_recurse_submodules = RECURSE_SUBMODULES_ON_DEMAND;
+static int parallel_jobs = 1;
static struct string_list changed_submodule_paths;
static int initialized_fetch_ref_tips;
static struct sha1_array ref_tips_before_fetch;
@@ -169,7 +170,12 @@ void set_diffopt_flags_from_submodule_config(struct diff_options *diffopt,
int submodule_config(const char *var, const char *value, void *cb)
{
- if (starts_with(var, "submodule."))
+ if (!strcmp(var, "submodule.fetchjobs")) {
+ parallel_jobs = git_config_int(var, value);
+ if (parallel_jobs < 0)
+ die(_("negative values not allowed for submodule.fetchJobs"));
+ return 0;
+ } else if (starts_with(var, "submodule."))
return parse_submodule_config_option(var, value);
else if (!strcmp(var, "fetch.recursesubmodules")) {
config_fetch_recurse_submodules = parse_fetch_recurse_submodules_arg(var, value);
@@ -770,6 +776,9 @@ int fetch_populated_submodules(const struct argv_array *options,
argv_array_push(&spf.args, "--recurse-submodules-default");
/* default value, "--submodule-prefix" and its value are added later */
+ if (max_parallel_jobs < 0)
+ max_parallel_jobs = parallel_jobs;
+
calculate_changed_submodule_paths();
run_processes_parallel(max_parallel_jobs,
get_next_submodule,
@@ -1116,3 +1125,8 @@ void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir)
strbuf_release(&rel_path);
free((void *)real_work_tree);
}
+
+int parallel_submodules(void)
+{
+ return parallel_jobs;
+}
diff --git a/submodule.h b/submodule.h
index 9a86124..7ef3775 100644
--- a/submodule.h
+++ b/submodule.h
@@ -27,6 +27,7 @@ struct submodule_update_strategy {
enum submodule_update_type type;
const char *command;
};
+#define SUBMODULE_UPDATE_STRATEGY_INIT {SM_UPDATE_UNSPECIFIED, NULL}
int is_staging_gitmodules_ok(void);
int update_path_in_gitmodules(const char *oldpath, const char *newpath);
@@ -58,5 +59,6 @@ int find_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_nam
struct string_list *needs_pushing);
int push_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_name);
void connect_work_tree_and_git_dir(const char *work_tree, const char *git_dir);
+int parallel_submodules(void);
#endif
diff --git a/t/t5526-fetch-submodules.sh b/t/t5526-fetch-submodules.sh
index 1241146..954d0e4 100755
--- a/t/t5526-fetch-submodules.sh
+++ b/t/t5526-fetch-submodules.sh
@@ -471,4 +471,18 @@ test_expect_success "don't fetch submodule when newly recorded commits are alrea
test_i18ncmp expect.err actual.err
'
+test_expect_success 'fetching submodules respects parallel settings' '
+ git config fetch.recurseSubmodules true &&
+ (
+ cd downstream &&
+ GIT_TRACE=$(pwd)/trace.out git fetch --jobs 7 &&
+ grep "7 tasks" trace.out &&
+ git config submodule.fetchJobs 8 &&
+ GIT_TRACE=$(pwd)/trace.out git fetch &&
+ grep "8 tasks" trace.out &&
+ GIT_TRACE=$(pwd)/trace.out git fetch --jobs 9 &&
+ grep "9 tasks" trace.out
+ )
+'
+
test_done
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv10 4/7] submodule update: direct error message to stderr
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
` (2 preceding siblings ...)
2016-02-12 2:03 ` [PATCHv10 3/7] fetching submodules: respect `submodule.fetchJobs` config option Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
2016-02-12 2:03 ` [PATCHv10 5/7] git submodule update: have a dedicated helper for cloning Stefan Beller
` (2 subsequent siblings)
6 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
Reroute the error message for specified but initialized submodules
to stderr instead of stdout.
Signed-off-by: Stefan Beller <sbeller@google.com>
---
git-submodule.sh | 4 ++--
t/t7400-submodule-basic.sh | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/git-submodule.sh b/git-submodule.sh
index 9bc5c5f..9ee86d4 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -693,7 +693,7 @@ cmd_update()
if test "$update_module" = "none"
then
- echo "Skipping submodule '$displaypath'"
+ echo >&2 "Skipping submodule '$displaypath'"
continue
fi
@@ -702,7 +702,7 @@ cmd_update()
# Only mention uninitialized submodules when its
# path have been specified
test "$#" != "0" &&
- say "$(eval_gettext "Submodule path '\$displaypath' not initialized
+ say >&2 "$(eval_gettext "Submodule path '\$displaypath' not initialized
Maybe you want to use 'update --init'?")"
continue
fi
diff --git a/t/t7400-submodule-basic.sh b/t/t7400-submodule-basic.sh
index 540771c..5991e3c 100755
--- a/t/t7400-submodule-basic.sh
+++ b/t/t7400-submodule-basic.sh
@@ -462,7 +462,7 @@ test_expect_success 'update --init' '
git config --remove-section submodule.example &&
test_must_fail git config submodule.example.url &&
- git submodule update init > update.out &&
+ git submodule update init 2> update.out &&
cat update.out &&
test_i18ngrep "not initialized" update.out &&
test_must_fail git rev-parse --resolve-git-dir init/.git &&
@@ -480,7 +480,7 @@ test_expect_success 'update --init from subdirectory' '
mkdir -p sub &&
(
cd sub &&
- git submodule update ../init >update.out &&
+ git submodule update ../init 2>update.out &&
cat update.out &&
test_i18ngrep "not initialized" update.out &&
test_must_fail git rev-parse --resolve-git-dir ../init/.git &&
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv10 5/7] git submodule update: have a dedicated helper for cloning
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
` (3 preceding siblings ...)
2016-02-12 2:03 ` [PATCHv10 4/7] submodule update: direct error message to stderr Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
2016-02-12 22:27 ` Stefan Beller
2016-02-12 2:03 ` [PATCHv10 6/7] submodule update: expose parallelism to the user Stefan Beller
2016-02-12 2:03 ` [PATCHv10 7/7] clone: allow an explicit argument for parallel submodule clones Stefan Beller
6 siblings, 1 reply; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
This introduces a new helper function in git submodule--helper
which takes care of cloning all submodules, which we want to
parallelize eventually.
Some tests (such as empty URL, update_mode=none) are required in the
helper to make the decision for cloning. These checks have been
moved into the C function as well (no need to repeat them in the
shell script).
Signed-off-by: Stefan Beller <sbeller@google.com>
---
builtin/submodule--helper.c | 236 ++++++++++++++++++++++++++++++++++++++++++++
git-submodule.sh | 45 +++------
2 files changed, 247 insertions(+), 34 deletions(-)
diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index f4c3eff..e865fca 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -255,6 +255,241 @@ static int module_clone(int argc, const char **argv, const char *prefix)
return 0;
}
+static int git_submodule_config(const char *var, const char *value, void *cb)
+{
+ return submodule_config(var, value, cb);
+}
+
+struct submodule_update_clone {
+ /* states */
+ int count;
+ int print_unmatched;
+ /* configuration */
+ int quiet;
+ const char *reference;
+ const char *depth;
+ const char *recursive_prefix;
+ const char *prefix;
+ struct module_list list;
+ struct string_list projectlines;
+ struct submodule_update_strategy update;
+ struct pathspec pathspec;
+};
+#define SUBMODULE_UPDATE_CLONE_INIT {0, 0, 0, NULL, NULL, NULL, NULL, MODULE_LIST_INIT, STRING_LIST_INIT_DUP, SUBMODULE_UPDATE_STRATEGY_INIT}
+
+static int update_clone_inspect_next_task(struct child_process *cp,
+ struct strbuf *err,
+ struct submodule_update_clone *pp,
+ void **pp_task_cb,
+ const struct cache_entry *ce)
+{
+ const struct submodule *sub = NULL;
+ struct strbuf displaypath_sb = STRBUF_INIT;
+ struct strbuf sb = STRBUF_INIT;
+ const char *displaypath = NULL;
+ char *url = NULL;
+ int needs_cloning = 0;
+
+ if (ce_stage(ce)) {
+ if (pp->recursive_prefix)
+ strbuf_addf(err, "Skipping unmerged submodule %s/%s\n",
+ pp->recursive_prefix, ce->name);
+ else
+ strbuf_addf(err, "Skipping unmerged submodule %s\n",
+ ce->name);
+ goto cleanup;
+ }
+
+ sub = submodule_from_path(null_sha1, ce->name);
+
+ if (pp->recursive_prefix)
+ displaypath = relative_path(pp->recursive_prefix,
+ ce->name, &displaypath_sb);
+ else
+ displaypath = ce->name;
+
+ if (pp->update.type == SM_UPDATE_NONE ||
+ (pp->update.type == SM_UPDATE_UNSPECIFIED &&
+ sub->update_strategy.type == SM_UPDATE_NONE)) {
+ strbuf_addf(err, "Skipping submodule '%s'\n",
+ displaypath);
+ goto cleanup;
+ }
+
+ /*
+ * Looking up the url in .git/config.
+ * We must not fall back to .gitmodules as we only want
+ * to process configured submodules.
+ */
+ strbuf_reset(&sb);
+ strbuf_addf(&sb, "submodule.%s.url", sub->name);
+ git_config_get_string(sb.buf, &url);
+ if (!url) {
+ /*
+ * Only mention uninitialized submodules when its
+ * path have been specified
+ */
+ if (pp->pathspec.nr)
+ strbuf_addf(err, _("Submodule path '%s' not initialized\n"
+ "Maybe you want to use 'update --init'?"),
+ displaypath);
+ goto cleanup;
+ }
+
+ strbuf_reset(&sb);
+ strbuf_addf(&sb, "%s/.git", ce->name);
+ needs_cloning = !file_exists(sb.buf);
+
+ strbuf_reset(&sb);
+ strbuf_addf(&sb, "%06o %s %d %d\t%s\n", ce->ce_mode,
+ sha1_to_hex(ce->sha1), ce_stage(ce),
+ needs_cloning, ce->name);
+ string_list_append(&pp->projectlines, sb.buf);
+
+ if (needs_cloning) {
+ cp->git_cmd = 1;
+ cp->no_stdin = 1;
+ cp->stdout_to_stderr = 1;
+ cp->err = -1;
+ argv_array_push(&cp->args, "submodule--helper");
+ argv_array_push(&cp->args, "clone");
+ if (pp->quiet)
+ argv_array_push(&cp->args, "--quiet");
+
+ if (pp->prefix)
+ argv_array_pushl(&cp->args, "--prefix", pp->prefix, NULL);
+
+ argv_array_pushl(&cp->args, "--path", sub->path, NULL);
+ argv_array_pushl(&cp->args, "--name", sub->name, NULL);
+ argv_array_pushl(&cp->args, "--url", strdup(url), NULL);
+ if (pp->reference)
+ argv_array_push(&cp->args, pp->reference);
+ if (pp->depth)
+ argv_array_push(&cp->args, pp->depth);
+
+
+ }
+
+cleanup:
+ free(url);
+ strbuf_reset(&displaypath_sb);
+ strbuf_reset(&sb);
+
+ return needs_cloning;
+}
+
+static int update_clone_get_next_task(struct child_process *cp,
+ struct strbuf *err,
+ void *pp_cb,
+ void **pp_task_cb)
+{
+ struct submodule_update_clone *pp = pp_cb;
+
+ for (; pp->count < pp->list.nr; pp->count++) {
+ const struct cache_entry *ce = pp->list.entries[pp->count];
+ if (update_clone_inspect_next_task(cp, err, pp,
+ pp_task_cb, ce)) {
+ pp->count++;
+ return 1;
+ }
+ }
+ return 0;
+}
+
+static int update_clone_start_failure(struct child_process *cp,
+ struct strbuf *err,
+ void *pp_cb,
+ void *pp_task_cb)
+{
+ struct submodule_update_clone *pp = pp_cb;
+
+ strbuf_addf(err, "error when starting a child process");
+ pp->print_unmatched = 1;
+
+ return 1;
+}
+
+static int update_clone_task_finished(int result,
+ struct child_process *cp,
+ struct strbuf *err,
+ void *pp_cb,
+ void *pp_task_cb)
+{
+ struct submodule_update_clone *pp = pp_cb;
+
+ if (!result) {
+ return 0;
+ } else {
+ strbuf_addf(err, "error in one child process");
+ pp->print_unmatched = 1;
+ return 1;
+ }
+}
+
+static int update_clone(int argc, const char **argv, const char *prefix)
+{
+ const char *update = NULL;
+ struct string_list_item *item;
+ struct submodule_update_clone pp = SUBMODULE_UPDATE_CLONE_INIT;
+
+ struct option module_list_options[] = {
+ OPT_STRING(0, "prefix", &prefix,
+ N_("path"),
+ N_("path into the working tree")),
+ OPT_STRING(0, "recursive_prefix", &pp.recursive_prefix,
+ N_("path"),
+ N_("path into the working tree, across nested "
+ "submodule boundaries")),
+ OPT_STRING(0, "update", &update,
+ N_("string"),
+ N_("update command for submodules")),
+ OPT_STRING(0, "reference", &pp.reference, "<repository>",
+ N_("Use the local reference repository "
+ "instead of a full clone")),
+ OPT_STRING(0, "depth", &pp.depth, "<depth>",
+ N_("Create a shallow clone truncated to the "
+ "specified number of revisions")),
+ OPT__QUIET(&pp.quiet, N_("do't print cloning progress")),
+ OPT_END()
+ };
+
+ const char *const git_submodule_helper_usage[] = {
+ N_("git submodule--helper list [--prefix=<path>] [<path>...]"),
+ NULL
+ };
+ pp.prefix = prefix;
+
+ argc = parse_options(argc, argv, prefix, module_list_options,
+ git_submodule_helper_usage, 0);
+
+ if (update)
+ if (parse_submodule_update_strategy(update, &pp.update) < 0)
+ die(_("bad value for update parameter"));
+
+ if (module_list_compute(argc, argv, prefix, &pp.pathspec, &pp.list) < 0) {
+ printf("#unmatched\n");
+ return 1;
+ }
+
+ gitmodules_config();
+ /* Overlay the parsed .gitmodules file with .git/config */
+ git_config(git_submodule_config, NULL);
+ run_processes_parallel(1, update_clone_get_next_task,
+ update_clone_start_failure,
+ update_clone_task_finished,
+ &pp);
+
+ if (pp.print_unmatched) {
+ printf("#unmatched\n");
+ return 1;
+ }
+
+ for_each_string_list_item(item, &pp.projectlines)
+ utf8_fprintf(stdout, "%s", item->string);
+
+ return 0;
+}
+
struct cmd_struct {
const char *cmd;
int (*fn)(int, const char **, const char *);
@@ -264,6 +499,7 @@ static struct cmd_struct commands[] = {
{"list", module_list},
{"name", module_name},
{"clone", module_clone},
+ {"update-clone", update_clone}
};
int cmd_submodule__helper(int argc, const char **argv, const char *prefix)
diff --git a/git-submodule.sh b/git-submodule.sh
index 9ee86d4..9f554fb 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -664,17 +664,18 @@ cmd_update()
cmd_init "--" "$@" || return
fi
- cloned_modules=
- git submodule--helper list --prefix "$wt_prefix" "$@" | {
+ git submodule--helper update-clone ${GIT_QUIET:+--quiet} \
+ ${wt_prefix:+--prefix "$wt_prefix"} \
+ ${prefix:+--recursive_prefix "$prefix"} \
+ ${update:+--update "$update"} \
+ ${reference:+--reference "$reference"} \
+ ${depth:+--depth "$depth"} \
+ "$@" | {
err=
- while read mode sha1 stage sm_path
+ while read mode sha1 stage just_cloned sm_path
do
die_if_unmatched "$mode"
- if test "$stage" = U
- then
- echo >&2 "Skipping unmerged submodule $prefix$sm_path"
- continue
- fi
+
name=$(git submodule--helper name "$sm_path") || exit
url=$(git config submodule."$name".url)
branch=$(get_submodule_config "$name" branch master)
@@ -691,27 +692,10 @@ cmd_update()
displaypath=$(relative_path "$prefix$sm_path")
- if test "$update_module" = "none"
- then
- echo >&2 "Skipping submodule '$displaypath'"
- continue
- fi
-
- if test -z "$url"
- then
- # Only mention uninitialized submodules when its
- # path have been specified
- test "$#" != "0" &&
- say >&2 "$(eval_gettext "Submodule path '\$displaypath' not initialized
-Maybe you want to use 'update --init'?")"
- continue
- fi
-
- if ! test -d "$sm_path"/.git && ! test -f "$sm_path"/.git
+ if test $just_cloned -eq 1
then
- git submodule--helper clone ${GIT_QUIET:+--quiet} --prefix "$prefix" --path "$sm_path" --name "$name" --url "$url" "$reference" "$depth" || exit
- cloned_modules="$cloned_modules;$name"
subsha1=
+ update_module=checkout
else
subsha1=$(clear_local_git_env; cd "$sm_path" &&
git rev-parse --verify HEAD) ||
@@ -751,13 +735,6 @@ Maybe you want to use 'update --init'?")"
die "$(eval_gettext "Unable to fetch in submodule path '\$displaypath'")"
fi
- # Is this something we just cloned?
- case ";$cloned_modules;" in
- *";$name;"*)
- # then there is no local change to integrate
- update_module=checkout ;;
- esac
-
must_die_on_failure=
case "$update_module" in
checkout)
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread* Re: [PATCHv10 5/7] git submodule update: have a dedicated helper for cloning
2016-02-12 2:03 ` [PATCHv10 5/7] git submodule update: have a dedicated helper for cloning Stefan Beller
@ 2016-02-12 22:27 ` Stefan Beller
0 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 22:27 UTC (permalink / raw)
To: git@vger.kernel.org, Junio C Hamano
Cc: Jonathan Nieder, Jens Lehmann, Stefan Beller
On Thu, Feb 11, 2016 at 6:03 PM, Stefan Beller <sbeller@google.com> wrote:
> This introduces a new helper function in git submodule--helper
> which takes care of cloning all submodules, which we want to
> parallelize eventually.
>
> Some tests (such as empty URL, update_mode=none) are required in the
> helper to make the decision for cloning. These checks have been
> moved into the C function as well (no need to repeat them in the
> shell script).
>
> Signed-off-by: Stefan Beller <sbeller@google.com>
> ---
> builtin/submodule--helper.c | 236 ++++++++++++++++++++++++++++++++++++++++++++
> git-submodule.sh | 45 +++------
> 2 files changed, 247 insertions(+), 34 deletions(-)
>
> diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
> index f4c3eff..e865fca 100644
> --- a/builtin/submodule--helper.c
> +++ b/builtin/submodule--helper.c
> @@ -255,6 +255,241 @@ static int module_clone(int argc, const char **argv, const char *prefix)
> return 0;
> }
>
> +static int git_submodule_config(const char *var, const char *value, void *cb)
> +{
> + return submodule_config(var, value, cb);
> +}
This is the thing I forgot to address.
Next reroll will inline submodule_config directly.
Stefan
^ permalink raw reply [flat|nested] 9+ messages in thread
* [PATCHv10 6/7] submodule update: expose parallelism to the user
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
` (4 preceding siblings ...)
2016-02-12 2:03 ` [PATCHv10 5/7] git submodule update: have a dedicated helper for cloning Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
2016-02-12 2:03 ` [PATCHv10 7/7] clone: allow an explicit argument for parallel submodule clones Stefan Beller
6 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
Expose possible parallelism either via the "--jobs" CLI parameter or
the "submodule.fetchJobs" setting.
By having the variable initialized to -1, we make sure 0 can be passed
into the parallel processing machine, which will then pick as many parallel
workers as there are CPUs.
Signed-off-by: Stefan Beller <sbeller@google.com>
---
Documentation/git-submodule.txt | 7 ++++++-
builtin/submodule--helper.c | 16 ++++++++++++----
git-submodule.sh | 9 +++++++++
t/t7406-submodule-update.sh | 12 ++++++++++++
4 files changed, 39 insertions(+), 5 deletions(-)
diff --git a/Documentation/git-submodule.txt b/Documentation/git-submodule.txt
index 1572f05..13adebf 100644
--- a/Documentation/git-submodule.txt
+++ b/Documentation/git-submodule.txt
@@ -16,7 +16,7 @@ SYNOPSIS
'git submodule' [--quiet] deinit [-f|--force] [--] <path>...
'git submodule' [--quiet] update [--init] [--remote] [-N|--no-fetch]
[-f|--force] [--rebase|--merge] [--reference <repository>]
- [--depth <depth>] [--recursive] [--] [<path>...]
+ [--depth <depth>] [--recursive] [--jobs <n>] [--] [<path>...]
'git submodule' [--quiet] summary [--cached|--files] [(-n|--summary-limit) <n>]
[commit] [--] [<path>...]
'git submodule' [--quiet] foreach [--recursive] <command>
@@ -377,6 +377,11 @@ for linkgit:git-clone[1]'s `--reference` and `--shared` options carefully.
clone with a history truncated to the specified number of revisions.
See linkgit:git-clone[1]
+-j <n>::
+--jobs <n>::
+ This option is only valid for the update command.
+ Clone new submodules in parallel with as many jobs.
+ Defaults to the `submodule.fetchJobs` option.
<path>...::
Paths to submodule(s). When specified this will restrict the command
diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index e865fca..09007a5 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -429,6 +429,7 @@ static int update_clone_task_finished(int result,
static int update_clone(int argc, const char **argv, const char *prefix)
{
const char *update = NULL;
+ int max_jobs = -1;
struct string_list_item *item;
struct submodule_update_clone pp = SUBMODULE_UPDATE_CLONE_INIT;
@@ -449,6 +450,8 @@ static int update_clone(int argc, const char **argv, const char *prefix)
OPT_STRING(0, "depth", &pp.depth, "<depth>",
N_("Create a shallow clone truncated to the "
"specified number of revisions")),
+ OPT_INTEGER('j', "jobs", &max_jobs,
+ N_("parallel jobs")),
OPT__QUIET(&pp.quiet, N_("do't print cloning progress")),
OPT_END()
};
@@ -474,10 +477,15 @@ static int update_clone(int argc, const char **argv, const char *prefix)
gitmodules_config();
/* Overlay the parsed .gitmodules file with .git/config */
git_config(git_submodule_config, NULL);
- run_processes_parallel(1, update_clone_get_next_task,
- update_clone_start_failure,
- update_clone_task_finished,
- &pp);
+
+ if (max_jobs < 0)
+ max_jobs = parallel_submodules();
+
+ run_processes_parallel(max_jobs,
+ update_clone_get_next_task,
+ update_clone_start_failure,
+ update_clone_task_finished,
+ &pp);
if (pp.print_unmatched) {
printf("#unmatched\n");
diff --git a/git-submodule.sh b/git-submodule.sh
index 9f554fb..10c5af9 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -645,6 +645,14 @@ cmd_update()
--depth=*)
depth=$1
;;
+ -j|--jobs)
+ case "$2" in '') usage ;; esac
+ jobs="--jobs=$2"
+ shift
+ ;;
+ --jobs=*)
+ jobs=$1
+ ;;
--)
shift
break
@@ -670,6 +678,7 @@ cmd_update()
${update:+--update "$update"} \
${reference:+--reference "$reference"} \
${depth:+--depth "$depth"} \
+ ${jobs:+$jobs} \
"$@" | {
err=
while read mode sha1 stage just_cloned sm_path
diff --git a/t/t7406-submodule-update.sh b/t/t7406-submodule-update.sh
index 68ea31d..815b4d1 100755
--- a/t/t7406-submodule-update.sh
+++ b/t/t7406-submodule-update.sh
@@ -774,4 +774,16 @@ test_expect_success 'submodule update --recursive drops module name before recur
test_i18ngrep "Submodule path .deeper/submodule/subsubmodule.: checked out" actual
)
'
+
+test_expect_success 'submodule update can be run in parallel' '
+ (cd super2 &&
+ GIT_TRACE=$(pwd)/trace.out git submodule update --jobs 7 &&
+ grep "7 tasks" trace.out &&
+ git config submodule.fetchJobs 8 &&
+ GIT_TRACE=$(pwd)/trace.out git submodule update &&
+ grep "8 tasks" trace.out &&
+ GIT_TRACE=$(pwd)/trace.out git submodule update --jobs 9 &&
+ grep "9 tasks" trace.out
+ )
+'
test_done
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv10 7/7] clone: allow an explicit argument for parallel submodule clones
2016-02-12 2:03 [PATCHv10 0/7] Expose submodule parallelism to the user Stefan Beller
` (5 preceding siblings ...)
2016-02-12 2:03 ` [PATCHv10 6/7] submodule update: expose parallelism to the user Stefan Beller
@ 2016-02-12 2:03 ` Stefan Beller
6 siblings, 0 replies; 9+ messages in thread
From: Stefan Beller @ 2016-02-12 2:03 UTC (permalink / raw)
To: git, gitster; +Cc: jrnieder, Jens.Lehmann, Stefan Beller
Just pass it along to "git submodule update", which may pick reasonable
defaults if you don't specify an explicit number.
Signed-off-by: Stefan Beller <sbeller@google.com>
---
Documentation/git-clone.txt | 6 +++++-
builtin/clone.c | 19 +++++++++++++------
t/t7406-submodule-update.sh | 15 +++++++++++++++
3 files changed, 33 insertions(+), 7 deletions(-)
diff --git a/Documentation/git-clone.txt b/Documentation/git-clone.txt
index 789b668..cb7966a 100644
--- a/Documentation/git-clone.txt
+++ b/Documentation/git-clone.txt
@@ -14,7 +14,7 @@ SYNOPSIS
[-o <name>] [-b <name>] [-u <upload-pack>] [--reference <repository>]
[--dissociate] [--separate-git-dir <git dir>]
[--depth <depth>] [--[no-]single-branch]
- [--recursive | --recurse-submodules] [--] <repository>
+ [--recursive | --recurse-submodules] [--jobs <n>] [--] <repository>
[<directory>]
DESCRIPTION
@@ -220,6 +220,10 @@ objects from the source repository into a pack in the cloned repository.
The result is Git repository can be separated from working
tree.
+-j <n>::
+--jobs <n>::
+ The number of submodules fetched at the same time.
+ Defaults to the `submodule.fetchJobs` option.
<repository>::
The (possibly remote) repository to clone from. See the
diff --git a/builtin/clone.c b/builtin/clone.c
index bcba080..191f522 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -50,6 +50,7 @@ static int option_progress = -1;
static struct string_list option_config;
static struct string_list option_reference;
static int option_dissociate;
+static int max_jobs = -1;
static struct option builtin_clone_options[] = {
OPT__VERBOSITY(&option_verbosity),
@@ -72,6 +73,8 @@ static struct option builtin_clone_options[] = {
N_("initialize submodules in the clone")),
OPT_BOOL(0, "recurse-submodules", &option_recursive,
N_("initialize submodules in the clone")),
+ OPT_INTEGER('j', "jobs", &max_jobs,
+ N_("number of submodules cloned in parallel")),
OPT_STRING(0, "template", &option_template, N_("template-directory"),
N_("directory from which templates will be used")),
OPT_STRING_LIST(0, "reference", &option_reference, N_("repo"),
@@ -95,10 +98,6 @@ static struct option builtin_clone_options[] = {
OPT_END()
};
-static const char *argv_submodule[] = {
- "submodule", "update", "--init", "--recursive", NULL
-};
-
static const char *get_repo_path_1(struct strbuf *path, int *is_bundle)
{
static char *suffix[] = { "/.git", "", ".git/.git", ".git" };
@@ -727,8 +726,16 @@ static int checkout(void)
err |= run_hook_le(NULL, "post-checkout", sha1_to_hex(null_sha1),
sha1_to_hex(sha1), "1", NULL);
- if (!err && option_recursive)
- err = run_command_v_opt(argv_submodule, RUN_GIT_CMD);
+ if (!err && option_recursive) {
+ struct argv_array args = ARGV_ARRAY_INIT;
+ argv_array_pushl(&args, "submodule", "update", "--init", "--recursive", NULL);
+
+ if (max_jobs != -1)
+ argv_array_pushf(&args, "--jobs=%d", max_jobs);
+
+ err = run_command_v_opt(args.argv, RUN_GIT_CMD);
+ argv_array_clear(&args);
+ }
return err;
}
diff --git a/t/t7406-submodule-update.sh b/t/t7406-submodule-update.sh
index 815b4d1..0791df7 100755
--- a/t/t7406-submodule-update.sh
+++ b/t/t7406-submodule-update.sh
@@ -786,4 +786,19 @@ test_expect_success 'submodule update can be run in parallel' '
grep "9 tasks" trace.out
)
'
+
+test_expect_success 'git clone passes the parallel jobs config on to submodules' '
+ test_when_finished "rm -rf super4" &&
+ GIT_TRACE=$(pwd)/trace.out git clone --recurse-submodules --jobs 7 . super4 &&
+ grep "7 tasks" trace.out &&
+ rm -rf super4 &&
+ git config --global submodule.fetchJobs 8 &&
+ GIT_TRACE=$(pwd)/trace.out git clone --recurse-submodules . super4 &&
+ grep "8 tasks" trace.out &&
+ rm -rf super4 &&
+ GIT_TRACE=$(pwd)/trace.out git clone --recurse-submodules --jobs 9 . super4 &&
+ grep "9 tasks" trace.out &&
+ rm -rf super4
+'
+
test_done
--
2.7.1.292.g18a4ced.dirty
^ permalink raw reply related [flat|nested] 9+ messages in thread