Merge branch 'sp/clip-read-write-to-8mb'

Send a large request to read(2)/write(2) as a smaller but still
reasonably large chunks, which would improve the latency when the
operation needs to be killed and incidentally works around broken
64-bit systems that cannot take a 2GB write or read in one go.

* sp/clip-read-write-to-8mb:
  Revert "compat/clipped-write.c: large write(2) fails on Mac OS X/XNU"
  xread, xwrite: limit size of IO to 8MB

Makefile

@@ -69,9 +69,6 @@ all::
 # Define NO_MSGFMT_EXTENDED_OPTIONS if your implementation of msgfmt
 # doesn't support GNU extensions like --check and --statistics
 #
-# Define NEEDS_CLIPPED_WRITE if your write(2) cannot write more than
-# INT_MAX bytes at once (e.g. MacOS X).
-#
 # Define HAVE_PATHS_H if you have paths.h and want to use the default PATH
 # it specifies.
 #
@@ -1499,11 +1496,6 @@ ifndef NO_MSGFMT_EXTENDED_OPTIONS
 	MSGFMT += --check --statistics
 endif
 
-ifdef NEEDS_CLIPPED_WRITE
-	BASIC_CFLAGS += -DNEEDS_CLIPPED_WRITE
-	COMPAT_OBJS += compat/clipped-write.o
-endif
-
 ifneq (,$(XDL_FAST_HASH))
 	BASIC_CFLAGS += -DXDL_FAST_HASH
 endif

compat/clipped-write.c

@@ -1,13 +0,0 @@
-#include "../git-compat-util.h"
-#undef write
-
-/*
- * Version of write that will write at most INT_MAX bytes.
- * Workaround a xnu bug on Mac OS X
- */
-ssize_t clipped_write(int fildes, const void *buf, size_t nbyte)
-{
-	if (nbyte > INT_MAX)
-		nbyte = INT_MAX;
-	return write(fildes, buf, nbyte);
-}

config.mak.uname

@@ -95,7 +95,6 @@ ifeq ($(uname_S),Darwin)
 	NO_MEMMEM = YesPlease
 	USE_ST_TIMESPEC = YesPlease
 	HAVE_DEV_TTY = YesPlease
-	NEEDS_CLIPPED_WRITE = YesPlease
 	COMPAT_OBJS += compat/precompose_utf8.o
 	BASIC_CFLAGS += -DPRECOMPOSE_UNICODE
 endif

git-compat-util.h

@@ -185,11 +185,6 @@ typedef unsigned long uintptr_t;
 #define probe_utf8_pathname_composition(a,b)
 #endif
 
-#ifdef NEEDS_CLIPPED_WRITE
-ssize_t clipped_write(int fildes, const void *buf, size_t nbyte);
-#define write(x,y,z) clipped_write((x),(y),(z))
-#endif
-
 #ifdef MKDIR_WO_TRAILING_SLASH
 #define mkdir(a,b) compat_mkdir_wo_trailing_slash((a),(b))
 extern int compat_mkdir_wo_trailing_slash(const char*, mode_t);

t/t0021-conversion.sh

@@ -190,4 +190,18 @@ test_expect_success 'required filter clean failure' '
 	test_must_fail git add test.fc
 '
 
+test -n "$GIT_TEST_LONG" && test_set_prereq EXPENSIVE
+
+test_expect_success EXPENSIVE 'filter large file' '
+	git config filter.largefile.smudge cat &&
+	git config filter.largefile.clean cat &&
+	for i in $(test_seq 1 2048); do printf "%1048576d" 1; done >2GB &&
+	echo "2GB filter=largefile" >.gitattributes &&
+	git add 2GB 2>err &&
+	! test -s err &&
+	rm -f 2GB &&
+	git checkout -- 2GB 2>err &&
+	! test -s err
+'
+
 test_done

wrapper.c

@@ -130,6 +130,14 @@ void *xcalloc(size_t nmemb, size_t size)
 	return ret;
 }
 
+/*
+ * Limit size of IO chunks, because huge chunks only cause pain.  OS X
+ * 64-bit is buggy, returning EINVAL if len >= INT_MAX; and even in
+ * the absense of bugs, large chunks can result in bad latencies when
+ * you decide to kill the process.
+ */
+#define MAX_IO_SIZE (8*1024*1024)
+
 /*
  * xread() is the same a read(), but it automatically restarts read()
  * operations with a recoverable error (EAGAIN and EINTR). xread()
@@ -138,6 +146,8 @@ void *xcalloc(size_t nmemb, size_t size)
 ssize_t xread(int fd, void *buf, size_t len)
 {
 	ssize_t nr;
+	if (len > MAX_IO_SIZE)
+	    len = MAX_IO_SIZE;
 	while (1) {
 		nr = read(fd, buf, len);
 		if ((nr < 0) && (errno == EAGAIN || errno == EINTR))
@@ -154,6 +164,8 @@ ssize_t xread(int fd, void *buf, size_t len)
 ssize_t xwrite(int fd, const void *buf, size_t len)
 {
 	ssize_t nr;
+	if (len > MAX_IO_SIZE)
+	    len = MAX_IO_SIZE;
 	while (1) {
 		nr = write(fd, buf, len);
 		if ((nr < 0) && (errno == EAGAIN || errno == EINTR))