Re: [PATCH 10/15] run-command API: add nascent "struct run_process_parallel_opts"

Phillip Wood <phillip.wood123@xxxxxxxxx> · Fri, 7 Oct 2022 10:55:42 +0100

On 30/09/2022 12:28, Ævar Arnfjörð Bjarmason wrote:
As noted in fd3aaf53f71 (run-command: add an "ungroup" option to
run_process_parallel(), 2022-06-07) which added the "ungroup" passing
it to "run_process_parallel()" via the global
"run_processes_parallel_ungroup" variable was a compromise to get the
smallest possible regression fix for "maint" at the time.

This follow-up to that is a start at passing that parameter and others
via a new "struct run_process_parallel_opts", as the earlier
version[1] of what became fd3aaf53f71 did.

For now we're only changing how data is passed internally to
"run-command.c", i.e. from "run_process_parallel()" to
pp_init(). Subsequent commits will change "run_processes_parallel()"
itself, as well as the "run_processes_parallel_tr2()" wrapper
function.

This is a very welcome change, but I'd have found it easier to follow if 
patches 10-12 were squashed together. There is a lot of code that gets 
added only to be deleted or moved in a following commit. A single patch 
would be bigger but they'd be less changes to review overall. As far as 
I can tell the overall change is good.

Best Wishes

Phillip

1. https://lore.kernel.org/git/cover-v2-0.8-00000000000-20220518T195858Z-avarab@xxxxxxxxx/

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@xxxxxxxxx>
---
  run-command.c | 38 ++++++++++++++++++++++----------------
  run-command.h | 44 +++++++++++++++++++++++++++++++++++++++++---
  2 files changed, 63 insertions(+), 19 deletions(-)

diff --git a/run-command.c b/run-command.c
index 31a856f8b9a..f82fc7f1515 100644
--- a/run-command.c
+++ b/run-command.c
@@ -1563,21 +1563,21 @@ static void handle_children_on_signal(int signo)
  }
  
  static void pp_init(struct parallel_processes *pp,
-		    unsigned int jobs,
-		    get_next_task_fn get_next_task,
-		    start_failure_fn start_failure,
-		    task_finished_fn task_finished,
-		    void *data, int ungroup)
+		    const struct run_process_parallel_opts *opts)
  {
  	unsigned int i;
+	void *data = opts->data;
+	get_next_task_fn get_next_task = opts->get_next_task;
+	start_failure_fn start_failure = opts->start_failure;
+	task_finished_fn task_finished = opts->task_finished;
  
-	if (!jobs)
+	if (!opts->jobs)
  		BUG("you must provide a non-zero number of jobs!");
  
-	pp->max_processes = jobs;
+	pp->max_processes = opts->jobs;
  
  	trace_printf("run_processes_parallel: preparing to run up to %d tasks",
-		     jobs);
+		     opts->jobs);
  
  	pp->data = data;
  	if (!get_next_task)
@@ -1590,12 +1590,12 @@ static void pp_init(struct parallel_processes *pp,
  	pp->nr_processes = 0;
  	pp->output_owner = 0;
  	pp->shutdown = 0;
-	pp->ungroup = ungroup;
-	CALLOC_ARRAY(pp->children, jobs);
+	pp->ungroup = opts->ungroup;
+	CALLOC_ARRAY(pp->children, opts->jobs);
  	if (!pp->ungroup)
-		CALLOC_ARRAY(pp->pfd, jobs);
+		CALLOC_ARRAY(pp->pfd, opts->jobs);
  
-	for (i = 0; i < jobs; i++) {
+	for (i = 0; i < opts->jobs; i++) {
  		strbuf_init(&pp->children[i].err, 0);
  		child_process_init(&pp->children[i].process);
  		if (pp->pfd) {
@@ -1793,14 +1793,20 @@ void run_processes_parallel(unsigned int jobs,
  	int i, code;
  	int output_timeout = 100;
  	int spawn_cap = 4;
-	int ungroup = run_processes_parallel_ungroup;
  	struct parallel_processes pp = PARALLEL_PROCESSES_INIT;
+	const struct run_process_parallel_opts opts = {
+		.jobs = jobs,
+		.get_next_task = get_next_task,
+		.start_failure = start_failure,
+		.task_finished = task_finished,
+		.ungroup = run_processes_parallel_ungroup,
+		.data = pp_cb,
+	};
  
  	/* unset for the next API user */
  	run_processes_parallel_ungroup = 0;
  
-	pp_init(&pp, jobs, get_next_task, start_failure, task_finished, pp_cb,
-		ungroup);
+	pp_init(&pp, &opts);
  	while (1) {
  		for (i = 0;
  		    i < spawn_cap && !pp.shutdown &&
@@ -1817,7 +1823,7 @@ void run_processes_parallel(unsigned int jobs,
  		}
  		if (!pp.nr_processes)
  			break;
-		if (ungroup) {
+		if (opts.ungroup) {
  			int i;
  
  			for (i = 0; i < pp.max_processes; i++)
diff --git a/run-command.h b/run-command.h
index 4502bdc64dc..210fb9e8bc4 100644
--- a/run-command.h
+++ b/run-command.h
@@ -458,6 +458,47 @@ typedef int (*task_finished_fn)(int result,
  				void *pp_cb,
  				void *pp_task_cb);
  
+/**
+ * Option used by run_processes_parallel(), { 0 }-initialized means no
+ * options.
+ */
+struct run_process_parallel_opts
+{
+	/**
+	 * jobs: see 'jobs' in run_processes_parallel() below.
+	 */
+	int jobs;
+
+	/**
+	 * ungroup: see 'ungroup' in run_processes_parallel() below.
+	 */
+	unsigned int ungroup:1;
+
+	/**
+	 * get_next_task: See get_next_task_fn() above. This must be
+	 * specified.
+	 */
+	get_next_task_fn get_next_task;
+
+	/**
+	 * start_failure: See start_failure_fn() above. This can be
+	 * NULL to omit any special handling.
+	 */
+	start_failure_fn start_failure;
+
+	/**
+	 * task_finished: See task_finished_fn() above. This can be
+	 * NULL to omit any special handling.
+	 */
+	task_finished_fn task_finished;
+
+	/**
+	 * data: user data, will be passed as "pp_cb" to the callback
+	 * parameters.
+	 */
+	void *data;
+};
+
  /**
   * Runs up to 'jobs' processes at the same time. Whenever a process can be
   * started, the callback get_next_task_fn is called to obtain the data
@@ -467,9 +508,6 @@ typedef int (*task_finished_fn)(int result,
   * (both stdout and stderr) is routed to stderr in a manner that output
   * from different tasks does not interleave (but see "ungroup" below).
   *
- * start_failure_fn and task_finished_fn can be NULL to omit any
- * special handling.
- *
   * If the "ungroup" option isn't specified, the API will set the
   * "stdout_to_stderr" parameter in "struct child_process" and provide
   * the callbacks with a "struct strbuf *out" parameter to write output







