git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v7 16/17] run-command: allow capturing of collated output

From
Emily Shaffer <emilyshaffer@google.com>
Date
Dec 22, 2020, 00:02 UTC
Message-ID
<20201222000220.1491091-17-emilyshaffer@google.com>
In-Reply-To
<20201222000220.1491091-1-emilyshaffer@google.com>

Some callers, for example server-side hooks which wish to relay hook output to clients across a transport, want to capture what would normally print to stderr and do something else with it. Allow that via a callback.

By calling the callback regardless of whether there's output available, we allow clients to send e.g. a keepalive if necessary.

Because we expose a strbuf, not a fd or FILE*, there's no need to create a temporary pipe or similar - we can just skip the print to stderr and instead hand it to the caller.

Signed-off-by: Emily Shaffer <emilyshaffer@google.com>
---
Notes:
    Originally when writing this patch I attempted to use a pipe in memory -
    but managing its lifetime was actually pretty tricky, and I found I could
    achieve the same thing with less code by doing it this way. Critique welcome,
    including "no, you really need to do it with a pipe".
 builtin/fetch.c             |  2 +-
 builtin/submodule--helper.c |  2 +-
 hook.c                      |  1 +
 run-command.c               | 33 +++++++++++++++++++++++++--------
 run-command.h               | 18 +++++++++++++++++-
 submodule.c                 |  2 +-
 t/helper/test-run-command.c | 25 ++++++++++++++++++++-----
 t/t0061-run-command.sh      |  7 +++++++
 8 files changed, 73 insertions(+), 17 deletions(-)
diff --git a/builtin/fetch.c b/builtin/fetch.c
index 5e153b5193..6a634085d9 100644
--- a/builtin/fetch.c
+++ b/builtin/fetch.c
@@ -1647,7 +1647,7 @@ static int fetch_multiple(struct string_list *list, int max_children)
 		result = run_processes_parallel_tr2(max_children,
 						    &fetch_next_remote,
 						    &fetch_failed_to_start,
-						    NULL,
+						    NULL, NULL,
 						    &fetch_finished,
 						    &state,
 						    "fetch", "parallel/fetch");
diff --git a/builtin/submodule--helper.c b/builtin/submodule--helper.c
index bb623c1852..8c543d33fd 100644
--- a/builtin/submodule--helper.c
+++ b/builtin/submodule--helper.c
@@ -2294,7 +2294,7 @@ static int update_submodules(struct submodule_update_clone *suc)
 	int i;
 
 	run_processes_parallel_tr2(suc->max_jobs, update_clone_get_next_task,
-				   update_clone_start_failure, NULL,
+				   update_clone_start_failure, NULL, NULL,
 				   update_clone_task_finished, suc, "submodule",
 				   "parallel/update");
 
diff --git a/hook.c b/hook.c
index b63a34d0a6..1439322a29 100644
--- a/hook.c
+++ b/hook.c
@@ -406,6 +406,7 @@ int run_hooks(const char *hookname, struct run_hooks_opt *options)
 				   pick_next_hook,
 				   notify_start_failure,
 				   options->feed_pipe,
+				   NULL,
 				   notify_hook_finished,
 				   &cb_data,
 				   "hook",
diff --git a/run-command.c b/run-command.c
index 7b65c087f8..0dce6bec83 100644
--- a/run-command.c
+++ b/run-command.c
@@ -1549,6 +1549,7 @@ struct parallel_processes {
 	get_next_task_fn get_next_task;
 	start_failure_fn start_failure;
 	feed_pipe_fn feed_pipe;
+	consume_sideband_fn consume_sideband;
 	task_finished_fn task_finished;
 
 	struct {
@@ -1614,6 +1615,7 @@ static void pp_init(struct parallel_processes *pp,
 		    get_next_task_fn get_next_task,
 		    start_failure_fn start_failure,
 		    feed_pipe_fn feed_pipe,
+		    consume_sideband_fn consume_sideband,
 		    task_finished_fn task_finished,
 		    void *data)
 {
@@ -1634,6 +1636,7 @@ static void pp_init(struct parallel_processes *pp,
 	pp->start_failure = start_failure ? start_failure : default_start_failure;
 	pp->feed_pipe = feed_pipe ? feed_pipe : default_feed_pipe;
 	pp->task_finished = task_finished ? task_finished : default_task_finished;
+	pp->consume_sideband = consume_sideband;
 
 	pp->nr_processes = 0;
 	pp->output_owner = 0;
@@ -1670,7 +1673,10 @@ static void pp_cleanup(struct parallel_processes *pp)
 	 * When get_next_task added messages to the buffer in its last
 	 * iteration, the buffered output is non empty.
 	 */
-	strbuf_write(&pp->buffered_output, stderr);
+	if (pp->consume_sideband)
+		pp->consume_sideband(&pp->buffered_output, pp->data);
+	else
+		strbuf_write(&pp->buffered_output, stderr);
 	strbuf_release(&pp->buffered_output);
 
 	sigchain_pop_common();
@@ -1786,9 +1792,13 @@ static void pp_buffer_stderr(struct parallel_processes *pp, int output_timeout)
 static void pp_output(struct parallel_processes *pp)
 {
 	int i = pp->output_owner;
+
 	if (pp->children[i].state == GIT_CP_WORKING &&
 	    pp->children[i].err.len) {
-		strbuf_write(&pp->children[i].err, stderr);
+		if (pp->consume_sideband)
+			pp->consume_sideband(&pp->children[i].err, pp->data);
+		else
+			strbuf_write(&pp->children[i].err, stderr);
 		strbuf_reset(&pp->children[i].err);
 	}
 }
@@ -1827,11 +1837,15 @@ static int pp_collect_finished(struct parallel_processes *pp)
 			strbuf_addbuf(&pp->buffered_output, &pp->children[i].err);
 			strbuf_reset(&pp->children[i].err);
 		} else {
-			strbuf_write(&pp->children[i].err, stderr);
+			/* Output errors, then all other finished child processes */
+			if (pp->consume_sideband) {
+				pp->consume_sideband(&pp->children[i].err, pp->data);
+				pp->consume_sideband(&pp->buffered_output, pp->data);
+			} else {
+				strbuf_write(&pp->children[i].err, stderr);
+				strbuf_write(&pp->buffered_output, stderr);
+			}
 			strbuf_reset(&pp->children[i].err);
-
-			/* Output all other finished child processes */
-			strbuf_write(&pp->buffered_output, stderr);
 			strbuf_reset(&pp->buffered_output);
 
 			/*
@@ -1855,6 +1869,7 @@ int run_processes_parallel(int n,
 			   get_next_task_fn get_next_task,
 			   start_failure_fn start_failure,
 			   feed_pipe_fn feed_pipe,
+			   consume_sideband_fn consume_sideband,
 			   task_finished_fn task_finished,
 			   void *pp_cb)
 {
@@ -1865,7 +1880,7 @@ int run_processes_parallel(int n,
 
 	sigchain_push(SIGPIPE, SIG_IGN);
 
-	pp_init(&pp, n, get_next_task, start_failure, feed_pipe, task_finished, pp_cb);
+	pp_init(&pp, n, get_next_task, start_failure, feed_pipe, consume_sideband, task_finished, pp_cb);
 	while (1) {
 		for (i = 0;
 		    i < spawn_cap && !pp.shutdown &&
@@ -1903,6 +1918,7 @@ int run_processes_parallel(int n,
 int run_processes_parallel_tr2(int n, get_next_task_fn get_next_task,
 			       start_failure_fn start_failure,
 			       feed_pipe_fn feed_pipe,
+			       consume_sideband_fn consume_sideband,
 			       task_finished_fn task_finished, void *pp_cb,
 			       const char *tr2_category, const char *tr2_label)
 {
@@ -1912,7 +1928,8 @@ int run_processes_parallel_tr2(int n, get_next_task_fn get_next_task,
 				   ((n < 1) ? online_cpus() : n));
 
 	result = run_processes_parallel(n, get_next_task, start_failure,
-					feed_pipe, task_finished, pp_cb);
+					feed_pipe, consume_sideband,
+					task_finished, pp_cb);
 
 	trace2_region_leave(tr2_category, tr2_label, NULL);
 
diff --git a/run-command.h b/run-command.h
index e058c0e2c8..2ad8271f56 100644
--- a/run-command.h
+++ b/run-command.h
@@ -450,6 +450,20 @@ typedef int (*feed_pipe_fn)(struct strbuf *pipe,
 			    void *pp_cb,
 			    void *pp_task_cb);
 
+/**
+ * If this callback is provided, instead of collating process output to stderr,
+ * they will be collated into a new pipe. consume_sideband_fn will be called
+ * repeatedly. When output is available on that pipe, it will be contained in
+ * 'output'. But it will be called with an empty 'output' too, to allow for
+ * keepalives or similar operations if necessary.
+ *
+ * pp_cb is the callback cookie as passed into run_processes_parallel.
+ *
+ * Since this callback is provided with the collated output, no task cookie is
+ * provided.
+ */
+typedef void (*consume_sideband_fn)(struct strbuf *output, void *pp_cb);
+
 /**
  * This callback is called on every child process that finished processing.
  *
@@ -485,10 +499,12 @@ int run_processes_parallel(int n,
 			   get_next_task_fn,
 			   start_failure_fn,
 			   feed_pipe_fn,
+			   consume_sideband_fn,
 			   task_finished_fn,
 			   void *pp_cb);
 int run_processes_parallel_tr2(int n, get_next_task_fn, start_failure_fn,
-			       feed_pipe_fn, task_finished_fn, void *pp_cb,
+			       feed_pipe_fn, consume_sideband_fn,
+			       task_finished_fn, void *pp_cb,
 			       const char *tr2_category, const char *tr2_label);
 
 #endif
diff --git a/submodule.c b/submodule.c
index 953f41818c..215bff22d9 100644
--- a/submodule.c
+++ b/submodule.c
@@ -1638,7 +1638,7 @@ int fetch_populated_submodules(struct repository *r,
 	run_processes_parallel_tr2(max_parallel_jobs,
 				   get_next_submodule,
 				   fetch_start_failure,
-				   NULL,
+				   NULL, NULL,
 				   fetch_finish,
 				   &spf,
 				   "submodule", "parallel/fetch");
diff --git a/t/helper/test-run-command.c b/t/helper/test-run-command.c
index 9348184d30..d53db6d11c 100644
--- a/t/helper/test-run-command.c
+++ b/t/helper/test-run-command.c
@@ -51,6 +51,16 @@ static int no_job(struct child_process *cp,
 	return 0;
 }
 
+static void test_consume_sideband(struct strbuf *output, void *cb)
+{
+	FILE *sideband;
+
+	sideband = fopen("./sideband", "a");
+
+	strbuf_write(output, sideband);
+	fclose(sideband);
+}
+
 static int task_finished(int result,
 			 struct strbuf *err,
 			 void *pp_cb,
@@ -201,7 +211,7 @@ static int testsuite(int argc, const char **argv)
 		suite.tests.nr, max_jobs);
 
 	ret = run_processes_parallel(max_jobs, next_test, test_failed,
-				     test_stdin, test_finished, &suite);
+				     test_stdin, NULL, test_finished, &suite);
 
 	if (suite.failed.nr > 0) {
 		ret = 1;
@@ -429,23 +439,28 @@ int cmd__run_command(int argc, const char **argv)
 
 	if (!strcmp(argv[1], "run-command-parallel"))
 		exit(run_processes_parallel(jobs, parallel_next,
-					    NULL, NULL, NULL, &proc));
+					    NULL, NULL, NULL, NULL, &proc));
 
 	if (!strcmp(argv[1], "run-command-abort"))
 		exit(run_processes_parallel(jobs, parallel_next,
-					    NULL, NULL, task_finished, &proc));
+					    NULL, NULL, NULL, task_finished, &proc));
 
 	if (!strcmp(argv[1], "run-command-no-jobs"))
 		exit(run_processes_parallel(jobs, no_job,
-					    NULL, NULL, task_finished, &proc));
+					    NULL, NULL, NULL, task_finished, &proc));
 
 	if (!strcmp(argv[1], "run-command-stdin")) {
 		proc.in = -1;
 		proc.no_stdin = 0;
 		exit (run_processes_parallel(jobs, parallel_next, NULL,
-					     test_stdin, NULL, &proc));
+					     test_stdin, NULL, NULL, &proc));
 	}
 
+	if (!strcmp(argv[1], "run-command-sideband"))
+		exit(run_processes_parallel(jobs, parallel_next, NULL, NULL,
+					    test_consume_sideband, NULL,
+					    &proc));
+
 	fprintf(stderr, "check usage\n");
 	return 1;
 }
diff --git a/t/t0061-run-command.sh b/t/t0061-run-command.sh
index 87759482ad..e99f6c7f44 100755
--- a/t/t0061-run-command.sh
+++ b/t/t0061-run-command.sh
@@ -143,6 +143,13 @@ test_expect_success 'run_command runs in parallel with more tasks than jobs avai
 	test_cmp expect actual
 '
 
+test_expect_success 'run_command can divert output' '
+	test_when_finished rm sideband &&
+	test-tool run-command run-command-sideband 3 sh -c "printf \"%s\n%s\n\" Hello World" 2>actual &&
+	test_must_be_empty actual &&
+	test_cmp expect sideband
+'
+
 cat >expect <<-EOF
 preloaded output of a child
 listening for stdin:

-- 
2.28.0.rc0.142.g3c755180ce-goog
Previous: Jonathan TanNext: Emily Shaffer
Message 75 of 89 in “propose config-based hooks (part I)”
  1. 00/17 propose config-based hooks (part I)Emily Shaffer, Dec 5, 2020
  2. 01/17 doc: propose hooks managed by the configEmily Shaffer, Dec 5, 2020
  3. 02/17 hook: scaffolding for git-hook subcommandEmily Shaffer, Dec 5, 2020
  4. 03/17 hook: add list commandEmily Shaffer, Dec 5, 2020
  5. 04/17 hook: include hookdir hook in listEmily Shaffer, Dec 5, 2020
  6. 06/17 hook: implement hookcmd.<name>.skipEmily Shaffer, Dec 5, 2020
  7. 05/17 hook: respect hook.runHookDirEmily Shaffer, Dec 5, 2020
  8. 08/17 hook: add 'run' subcommandEmily Shaffer, Dec 5, 2020
  9. Phillip WoodDec 11, 2020
  10. Emily ShafferDec 15, 2020
  11. 09/17 hook: replace find_hook() with hook_exists()Emily Shaffer, Dec 5, 2020
  12. 07/17 parse-options: parse into strvecEmily Shaffer, Dec 5, 2020
  13. 11/17 run-command: allow stdin for run_processes_parallelEmily Shaffer, Dec 5, 2020
  14. 10/17 hook: support passing stdin to hooksEmily Shaffer, Dec 5, 2020
  15. 12/17 hook: allow parallel hook executionEmily Shaffer, Dec 5, 2020
  16. 14/17 run-command: add stdin callback for parallelizationEmily Shaffer, Dec 5, 2020
  17. 13/17 hook: allow specifying working directory for hooksEmily Shaffer, Dec 5, 2020
  18. 17/17 hooks: allow callers to capture outputEmily Shaffer, Dec 5, 2020
  19. 15/17 hook: provide stdin by string_list or callbackEmily Shaffer, Dec 5, 2020
  20. SZEDER GáborDec 8, 2020
  21. Emily ShafferDec 8, 2020
  22. 16/17 run-command: allow capturing of collated outputEmily Shaffer, Dec 5, 2020
  23. Josh SteadmonDec 16, 2020
  24. Junio C HamanoDec 16, 2020
  25. Emily ShafferDec 16, 2020
  26. Junio C HamanoDec 16, 2020
  27. Emily ShafferDec 18, 2020
  28. Junio C HamanoDec 18, 2020
  29. 00/17 propose config-based hooks (part I)Emily Shaffer, Dec 22, 2020
  30. 01/17 doc: propose hooks managed by the configEmily Shaffer, Dec 22, 2020
  31. Ævar Arnfjörð BjarmasonJan 23, 2021
  32. Emily ShafferJan 29, 2021
  33. Junio C HamanoFeb 1, 2021
  34. Emily ShafferMar 10, 2021
  35. 02/17 hook: scaffolding for git-hook subcommandEmily Shaffer, Dec 22, 2020
  36. 03/17 hook: add list commandEmily Shaffer, Dec 22, 2020
  37. Jonathan TanJan 31, 2021
  38. Emily ShafferFeb 9, 2021
  39. 04/17 hook: include hookdir hook in listEmily Shaffer, Dec 22, 2020
  40. Jonathan TanJan 31, 2021
  41. Emily ShafferFeb 9, 2021
  42. 05/17 hook: respect hook.runHookDirEmily Shaffer, Dec 22, 2020
  43. Jonathan TanJan 31, 2021
  44. Emily ShafferFeb 9, 2021
  45. 06/17 hook: implement hookcmd.<name>.skipEmily Shaffer, Dec 22, 2020
  46. Jonathan TanJan 31, 2021
  47. Emily ShafferFeb 9, 2021
  48. 08/17 hook: add 'run' subcommandEmily Shaffer, Dec 22, 2020
  49. Jonathan TanJan 31, 2021
  50. Emily ShafferFeb 11, 2021
  51. 07/17 parse-options: parse into strvecEmily Shaffer, Dec 22, 2020
  52. 09/17 hook: replace find_hook() with hook_exists()Emily Shaffer, Dec 22, 2020
  53. Jonathan TanJan 31, 2021
  54. Emily ShafferFeb 12, 2021
  55. Emily ShafferFeb 18, 2021
  56. 10/17 hook: support passing stdin to hooksEmily Shaffer, Dec 22, 2020
  57. 12/17 hook: allow parallel hook executionEmily Shaffer, Dec 22, 2020
  58. Jonathan TanFeb 1, 2021
  59. Emily ShafferFeb 22, 2021
  60. 11/17 run-command: allow stdin for run_processes_parallelEmily Shaffer, Dec 22, 2020
  61. Jonathan TanFeb 1, 2021
  62. Emily ShafferFeb 19, 2021
  63. 14/17 run-command: add stdin callback for parallelizationEmily Shaffer, Dec 22, 2020
  64. Jonathan TanFeb 1, 2021
  65. Emily ShafferFeb 22, 2021
  66. Jonathan TanFeb 23, 2021
  67. Emily ShafferMar 10, 2021
  68. 13/17 hook: allow specifying working directory for hooksEmily Shaffer, Dec 22, 2020
  69. 15/17 hook: provide stdin by string_list or callbackEmily Shaffer, Dec 22, 2020
  70. Jonathan TanFeb 1, 2021
  71. Emily ShafferFeb 23, 2021
  72. Jonathan TanFeb 25, 2021
  73. Emily ShafferMar 2, 2021
  74. Jonathan TanMar 2, 2021
  75. 16/17 run-command: allow capturing of collated outputEmily Shaffer, Dec 22, 2020
  76. 17/17 hooks: allow callers to capture outputEmily Shaffer, Dec 22, 2020
  77. Junio C HamanoDec 22, 2020
  78. Emily ShafferDec 28, 2020
  79. Junio C HamanoDec 28, 2020
  80. 18/17 doc: make git-hook.txt point of truthEmily Shaffer, Dec 28, 2020
  81. Emily ShafferDec 28, 2020
  82. Emily ShafferJan 29, 2021
  83. Josh SteadmonFeb 16, 2021
  84. Junio C HamanoFeb 16, 2021
  85. Josh SteadmonFeb 17, 2021
  86. Junio C HamanoFeb 17, 2021
  87. Junio C HamanoFeb 25, 2021
  88. Emily ShafferMar 1, 2021
  89. Junio C HamanoMar 1, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.