From: Dmitry Potapov <dpotapov@gmail.com>
Date: Sun, 21 Feb 2010 06:32:19 +0000 (+0300)
Subject: hash-object: don't use mmap() for small files
X-Git-Tag: v1.7.0.2~10^2
X-Git-Url: http://git.tremily.us/?a=commitdiff_plain;h=ea68b0ce9f8ce8da3e360aed3cbd6720159ffbee;p=git.git

hash-object: don't use mmap() for small files

Using read() instead of mmap() can be 39% speed up for 1Kb files and is
1% speed up 1Mb files. For larger files, it is better to use mmap(),
because the difference between is not significant, and when there is not
enough memory, mmap() performs much better, because it avoids swapping.

Signed-off-by: Dmitry Potapov <dpotapov@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---

diff --git a/sha1_file.c b/sha1_file.c
index 657825e14..037515960 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -2434,6 +2434,8 @@ static int index_mem(unsigned char *sha1, void *buf, size_t size,
 	return ret;
 }
 
+#define SMALL_FILE_SIZE (32*1024)
+
 int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
 	     enum object_type type, const char *path)
 {
@@ -2448,6 +2450,14 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
 		else
 			ret = -1;
 		strbuf_release(&sbuf);
+	} else if (size <= SMALL_FILE_SIZE) {
+		char *buf = xmalloc(size);
+		if (size == read_in_full(fd, buf, size))
+			ret = index_mem(sha1, buf, size, write_object, type,
+					path);
+		else
+			ret = error("short read %s", strerror(errno));
+		free(buf);
 	} else if (size) {
 		void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
 		ret = index_mem(sha1, buf, size, write_object, type, path);