sha1write: don't copy full sized buffers

No need to memcpy() source buffer data when we might just process the
data in place instead of accumulating it into a separate buffer.
This is the case when a whole buffer would have been copied, summed,
written out and then discarded right away.

Also move the CRC32 processing within the loop so the data is more likely
to remain in the L1 CPU cache between the CRC32 sum, SHA1 sum and the
write call.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/csum-file.c b/csum-file.c
index 28389541a32454f2d988bb02e4268ffe12755bbc..bb70c75ee1ed54a11ce31d7092ef6e35cae37c04 100644 (file)
--- a/csum-file.c
+++ b/csum-file.c
@@ -11,10 +11,8 @@
 #include "progress.h"
 #include "csum-file.h"
 
-static void sha1flush(struct sha1file *f, unsigned int count)
+static void sha1flush(struct sha1file *f, void *buf, unsigned int count)
 {
-       void *buf = f->buffer;
-
        for (;;) {
                int ret = xwrite(f->fd, buf, count);
                if (ret > 0) {
@@ -39,7 +37,7 @@ int sha1close(struct sha1file *f, unsigned char *result, unsigned int flags)
 
        if (offset) {
                SHA1_Update(&f->ctx, f->buffer, offset);
-               sha1flush(f, offset);
+               sha1flush(f, f->buffer, offset);
                f->offset = 0;
        }
        SHA1_Final(f->buffer, &f->ctx);
@@ -47,7 +45,7 @@ int sha1close(struct sha1file *f, unsigned char *result, unsigned int flags)
                hashcpy(result, f->buffer);
        if (flags & (CSUM_CLOSE | CSUM_FSYNC)) {
                /* write checksum and close fd */
-               sha1flush(f, 20);
+               sha1flush(f, f->buffer, 20);
                if (flags & CSUM_FSYNC)
                        fsync_or_die(f->fd, f->name);
                if (close(f->fd))
@@ -62,21 +60,30 @@ int sha1close(struct sha1file *f, unsigned char *result, unsigned int flags)
 
 int sha1write(struct sha1file *f, void *buf, unsigned int count)
 {
-       if (f->do_crc)
-               f->crc32 = crc32(f->crc32, buf, count);
        while (count) {
                unsigned offset = f->offset;
                unsigned left = sizeof(f->buffer) - offset;
                unsigned nr = count > left ? left : count;
+               void *data;
+
+               if (f->do_crc)
+                       f->crc32 = crc32(f->crc32, buf, nr);
+
+               if (nr == sizeof(f->buffer)) {
+                       /* process full buffer directly without copy */
+                       data = buf;
+               } else {
+                       memcpy(f->buffer + offset, buf, nr);
+                       data = f->buffer;
+               }
 
-               memcpy(f->buffer + offset, buf, nr);
                count -= nr;
                offset += nr;
                buf = (char *) buf + nr;
                left -= nr;
                if (!left) {
-                       SHA1_Update(&f->ctx, f->buffer, offset);
-                       sha1flush(f, offset);
+                       SHA1_Update(&f->ctx, data, offset);
+                       sha1flush(f, data, offset);
                        offset = 0;
                }
                f->offset = offset;