[PATCH v2 1/2] t: add "test-tool genbytes" to avoid slow tr(1) on macOS

["Kristofer Karlsson via GitGitGadget" <gitgitgadget@gmail.com>]

From: Kristofer Karlsson <krka@spotify.com>

Several tests create fixture data consisting of a single repeated
character with "test-tool genzeros <count> | tr '\000' <char>".  This
works well on platforms where tr(1) is implemented efficiently.

The implementation of tr(1) on macOS supports multi-byte characters,
and processes its input one character at a time through
getwchar() and putwchar(), even in the C locale.  For small inputs
that does not matter, but t4205 generates more than 2GB of data this
way, which makes that test much slower on macOS than on Linux: on the
macOS CI runners, tr(1) alone spends 95 to 123 seconds of CPU time on
it, compared to about 6 seconds on Linux.

Fix this by adding "test-tool genbytes <hex-byte> [<count>]", which
writes the requested byte, given as two lowercase hexadecimal
digits, directly.  Turn "genzeros" into a thin wrapper around the
same code, and rename the file to match.  Use the new helper in all
tests that piped "genzeros" through tr(1), not just t4205, so that
it is the obvious choice for new tests.

This makes t4205 much faster on macOS in CI.  The Linux jobs, shown
for comparison, only save the few seconds that GNU tr(1) took, which
is within the usual noise:

  job                before    after   change
  osx-gcc            821.1s   243.3s   -70.4%
  osx-reftable       911.0s   194.0s   -78.7%
  linux-asan-ubsan   226.7s   222.1s    -2.0%
  linux-leaks        320.2s   298.8s    -6.7%

Signed-off-by: Kristofer Karlsson <krka@spotify.com>
---
 Makefile                          |  2 +-
 t/helper/meson.build              |  2 +-
 t/helper/test-genbytes.c          | 61 +++++++++++++++++++++++++++++++
 t/helper/test-genzeros.c          | 37 -------------------
 t/helper/test-tool.c              |  1 +
 t/helper/test-tool.h              |  1 +
 t/t0613-reftable-write-options.sh |  2 +-
 t/t4205-log-pretty-formats.sh     |  2 +-
 t/t5300-pack-object.sh            |  6 +--
 t/t7006-pager.sh                  |  3 +-
 t/t9850-shell.sh                  |  2 +-
 11 files changed, 72 insertions(+), 47 deletions(-)
 create mode 100644 t/helper/test-genbytes.c
 delete mode 100644 t/helper/test-genzeros.c

diff --git a/Makefile b/Makefile
index c2a6098484..8d214286e0 100644
--- a/Makefile
+++ b/Makefile
@@ -825,8 +825,8 @@ TEST_BUILTINS_OBJS += test-env-helper.o
 TEST_BUILTINS_OBJS += test-example-tap.o
 TEST_BUILTINS_OBJS += test-find-pack.o
 TEST_BUILTINS_OBJS += test-fsmonitor-client.o
+TEST_BUILTINS_OBJS += test-genbytes.o
 TEST_BUILTINS_OBJS += test-genrandom.o
-TEST_BUILTINS_OBJS += test-genzeros.o
 TEST_BUILTINS_OBJS += test-getcwd.o
 TEST_BUILTINS_OBJS += test-hash-speed.o
 TEST_BUILTINS_OBJS += test-hash.o
diff --git a/t/helper/meson.build b/t/helper/meson.build
index ae513b4cdc..f99688c49b 100644
--- a/t/helper/meson.build
+++ b/t/helper/meson.build
@@ -22,8 +22,8 @@ test_tool_sources = [
   'test-example-tap.c',
   'test-find-pack.c',
   'test-fsmonitor-client.c',
+  'test-genbytes.c',
   'test-genrandom.c',
-  'test-genzeros.c',
   'test-getcwd.c',
   'test-hash-speed.c',
   'test-hash.c',
diff --git a/t/helper/test-genbytes.c b/t/helper/test-genbytes.c
new file mode 100644
index 0000000000..b760326b24
--- /dev/null
+++ b/t/helper/test-genbytes.c
@@ -0,0 +1,61 @@
+#define DISABLE_SIGN_COMPARE_WARNINGS
+
+#include "test-tool.h"
+#include "git-compat-util.h"
+#include "hex-ll.h"
+
+/*
+ * Write "count" copies of "byte" to stdout, or an endless stream of them if
+ * "count" is negative.
+ */
+static int generate_bytes(char byte, intmax_t count)
+{
+	char buf[256 * 1024];
+	ssize_t n;
+
+	memset(buf, byte, sizeof(buf));
+
+	/* Writing out individual bytes is slow... */
+	while (count < 0)
+		if (xwrite(1, buf, ARRAY_SIZE(buf)) < 0)
+			die_errno("write error");
+
+	while (count > 0) {
+		n = xwrite(1, buf,
+			   count < ARRAY_SIZE(buf)
+			   ? count : ARRAY_SIZE(buf));
+
+		if (n < 0)
+			die_errno("write error");
+
+		count -= n;
+	}
+
+	return 0;
+}
+
+static intmax_t parse_count(int argc, const char **argv, int pos)
+{
+	return pos < argc ? strtoimax(argv[pos], NULL, 0) : -1;
+}
+
+int cmd__genbytes(int argc, const char **argv)
+{
+	if (argc < 2 || argc > 3 || strlen(argv[1]) != 2 ||
+	    strspn(argv[1], "0123456789abcdef") != 2) {
+		fprintf(stderr, "usage: %s <hex-byte> [<count>]\n", argv[0]);
+		return 1;
+	}
+
+	return generate_bytes(hex2chr(argv[1]), parse_count(argc, argv, 2));
+}
+
+int cmd__genzeros(int argc, const char **argv)
+{
+	if (argc > 2) {
+		fprintf(stderr, "usage: %s [<count>]\n", argv[0]);
+		return 1;
+	}
+
+	return generate_bytes('\0', parse_count(argc, argv, 1));
+}
diff --git a/t/helper/test-genzeros.c b/t/helper/test-genzeros.c
deleted file mode 100644
index b895436a32..0000000000
--- a/t/helper/test-genzeros.c
+++ /dev/null
@@ -1,37 +0,0 @@
-#define DISABLE_SIGN_COMPARE_WARNINGS
-
-#include "test-tool.h"
-#include "git-compat-util.h"
-
-int cmd__genzeros(int argc, const char **argv)
-{
-	/* static, so that it is NUL-initialized */
-	static const char zeros[256 * 1024];
-	intmax_t count;
-	ssize_t n;
-
-	if (argc > 2) {
-		fprintf(stderr, "usage: %s [<count>]\n", argv[0]);
-		return 1;
-	}
-
-	count = argc > 1 ? strtoimax(argv[1], NULL, 0) : -1;
-
-	/* Writing out individual NUL bytes is slow... */
-	while (count < 0)
-		if (xwrite(1, zeros, ARRAY_SIZE(zeros)) < 0)
-			die_errno("write error");
-
-	while (count > 0) {
-		n = xwrite(1, zeros,
-			   count < ARRAY_SIZE(zeros)
-			   ? count : ARRAY_SIZE(zeros));
-
-		if (n < 0)
-			die_errno("write error");
-
-		count -= n;
-	}
-
-	return 0;
-}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index b71a22b43b..af70e2bec7 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -33,6 +33,7 @@ static struct test_cmd cmds[] = {
 	{ "example-tap", cmd__example_tap },
 	{ "find-pack", cmd__find_pack },
 	{ "fsmonitor-client", cmd__fsmonitor_client },
+	{ "genbytes", cmd__genbytes },
 	{ "genrandom", cmd__genrandom },
 	{ "genzeros", cmd__genzeros },
 	{ "getcwd", cmd__getcwd },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index f2885b33d5..c35e7412af 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -26,6 +26,7 @@ int cmd__env_helper(int argc, const char **argv);
 int cmd__example_tap(int argc, const char **argv);
 int cmd__find_pack(int argc, const char **argv);
 int cmd__fsmonitor_client(int argc, const char **argv);
+int cmd__genbytes(int argc, const char **argv);
 int cmd__genrandom(int argc, const char **argv);
 int cmd__genzeros(int argc, const char **argv);
 int cmd__getcwd(int argc, const char **argv);
diff --git a/t/t0613-reftable-write-options.sh b/t/t0613-reftable-write-options.sh
index 0b27d75fe3..b2032a799d 100755
--- a/t/t0613-reftable-write-options.sh
+++ b/t/t0613-reftable-write-options.sh
@@ -146,7 +146,7 @@ test_expect_success 'small block size fails with large reflog message' '
 	(
 		cd repo &&
 		test_commit A &&
-		test-tool genzeros 500 | tr "\000" "a" >logmsg &&
+		test-tool genbytes 61 500 >logmsg &&
 		cat >expect <<-EOF &&
 		fatal: update_ref failed for ref ${SQ}refs/heads/logme${SQ}: reftable: transaction failure: entry too large
 		EOF
diff --git a/t/t4205-log-pretty-formats.sh b/t/t4205-log-pretty-formats.sh
index 01b97c8888..aa51a70a34 100755
--- a/t/t4205-log-pretty-formats.sh
+++ b/t/t4205-log-pretty-formats.sh
@@ -1182,7 +1182,7 @@ test_expect_success EXPENSIVE,SIZE_T_IS_64BIT 'log --pretty with huge commit mes
 '
 
 test_expect_success EXPENSIVE,SIZE_T_IS_64BIT 'set up huge commit' '
-	test-tool genzeros 2147483649 | tr "\000" "1" >expect &&
+	test-tool genbytes 31 2147483649 >expect &&
 	huge_commit=$(git commit-tree -F expect HEAD^{tree})
 '
 
diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh
index aac139e6a0..3c2f83091c 100755
--- a/t/t5300-pack-object.sh
+++ b/t/t5300-pack-object.sh
@@ -9,9 +9,9 @@ test_description='git pack-object'
 
 test_expect_success 'setup' '
 	rm -f .git/index* &&
-	test-tool genzeros 4096 | tr "\000" "a" >a &&
-	test-tool genzeros 4096 | tr "\000" "b" >b &&
-	test-tool genzeros 4096 | tr "\000" "c" >c &&
+	test-tool genbytes 61 4096 >a &&
+	test-tool genbytes 62 4096 >b &&
+	test-tool genbytes 63 4096 >c &&
 	test-tool genrandom "seed a" 2097152 >a_big &&
 	test-tool genrandom "seed b" 2097152 >b_big &&
 	git update-index --add a a_big b b_big c &&
diff --git a/t/t7006-pager.sh b/t/t7006-pager.sh
index 75ca7a25da..f59b3a00a8 100755
--- a/t/t7006-pager.sh
+++ b/t/t7006-pager.sh
@@ -662,8 +662,7 @@ test_expect_success 'setup trace2' '
 '
 
 test_expect_success 'setup large log output' '
-	test-tool genzeros 50000 |
-	tr "\000" "a" |
+	test-tool genbytes 61 50000 |
 	sed "s/a/this is a long commit message/g" >commit-msg &&
 	git commit --allow-empty -F commit-msg
 '
diff --git a/t/t9850-shell.sh b/t/t9850-shell.sh
index 27cc49bbd1..cf05944682 100755
--- a/t/t9850-shell.sh
+++ b/t/t9850-shell.sh
@@ -30,7 +30,7 @@ test_expect_success 'shell allows interactive command' '
 '
 
 test_expect_success 'shell complains of overlong commands' '
-	test-tool genzeros | tr "\000" "a" |
+	test-tool genbytes 61 |
 	test_must_fail git shell 2>err &&
 	test_grep "too long" err
 '
-- 
gitgitgadget