If a mmapped file is changed by another program during git-add, it
causes the repository corruption. Disabling mmap() in index_fd() does
not have any negative impact on the overall speed of Git. In fact, it
makes git hash-object to work slightly faster. Here is the best result
before and after patch based on 5 runs on the Linix kernel repository:
Before:
$ git ls-files | time git hash-object --stdin-path > /dev/null
2.15user 0.36system 0:02.52elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+103248minor)pagefaults 0swaps
After:
$ git ls-files | time ../git/git hash-object --stdin-path > /dev/null
2.09user 0.33system 0:02.42elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+1073minor)pagefaults 0swaps
Signed-off-by: Dmitry Potapov <dpotapov@xxxxxxxxx>
---
In this version, I have improved the hint value for regular files to
avoid useless re-allocation and copy.
sha1_file.c | 27 +++++++++++----------------
1 files changed, 11 insertions(+), 16 deletions(-)
diff --git a/sha1_file.c b/sha1_file.c
index 657825e..26c6231 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -2438,22 +2438,17 @@ int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
enum object_type type, const char *path)
{
int ret;
- size_t size = xsize_t(st->st_size);
-
- if (!S_ISREG(st->st_mode)) {
- struct strbuf sbuf = STRBUF_INIT;
- if (strbuf_read(&sbuf, fd, 4096) >= 0)
- ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
- type, path);
- else
- ret = -1;
- strbuf_release(&sbuf);
- } else if (size) {
- void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
- ret = index_mem(sha1, buf, size, write_object, type, path);
- munmap(buf, size);
- } else
- ret = index_mem(sha1, NULL, size, write_object, type, path);
+ struct strbuf sbuf = STRBUF_INIT;
+ /* for regular files, we supply the real file size, otherwise
+ `size' is just a hint */
+ size_t size = S_ISREG(st->st_mode) ? xsize_t(st->st_size) : 4096;
+
+ if (strbuf_read(&sbuf, fd, size) >= 0)
+ ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
+ type, path);
+ else
+ ret = -1;
+ strbuf_release(&sbuf);
close(fd);
return ret;
}
--
1.7.0
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html