mirror of
https://github.com/git/git.git
synced 2024-10-28 04:49:43 +01:00
csum-file.c: use unsafe SHA-1 implementation when available
Update hashwrite() and friends to use the unsafe_-variants of hashing functions, calling for e.g., "the_hash_algo->unsafe_update_fn()" instead of "the_hash_algo->update_fn()". These callers only use the_hash_algo to produce a checksum, which we depend on for data integrity, but not for cryptographic purposes, so these callers are safe to use the unsafe (non-collision detecting) SHA-1 implementation. To time this, I took a freshly packed copy of linux.git, and ran the following with and without the OPENSSL_SHA1_UNSAFE=1 build-knob. Both versions were compiled with -O3: $ git for-each-ref --format='%(objectname)' refs/heads refs/tags >in $ valgrind --tool=callgrind ~/src/git/git-pack-objects \ --revs --stdout --all-progress --use-bitmap-index <in >/dev/null Without OPENSSL_SHA1_UNSAFE=1 (that is, using the collision-detecting SHA-1 implementation for both cryptographic and non-cryptographic purposes), we spend a significant amount of our instruction count in hashwrite(): $ callgrind_annotate --inclusive=yes | grep hashwrite | head -n1 159,998,868,413 (79.42%) /home/ttaylorr/src/git/csum-file.c:hashwrite [/home/ttaylorr/src/git/git-pack-objects] , and the resulting "clone" takes 19.219 seconds of wall clock time, 18.94 seconds of user time and 0.28 seconds of system time. Compiling with OPENSSL_SHA1_UNSAFE=1, we spend ~60% fewer instructions in hashwrite(): $ callgrind_annotate --inclusive=yes | grep hashwrite | head -n1 59,164,001,176 (58.79%) /home/ttaylorr/src/git/csum-file.c:hashwrite [/home/ttaylorr/src/git/git-pack-objects] , and generate the resulting "clone" much faster, in only 11.597 seconds of wall time, 11.37 seconds of user time, and 0.23 seconds of system time, for a ~40% speed-up. Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
parent
06c92dafb8
commit
1b9e9be8b4
1 changed files with 9 additions and 9 deletions
18
csum-file.c
18
csum-file.c
|
@ -50,7 +50,7 @@ void hashflush(struct hashfile *f)
|
||||||
|
|
||||||
if (offset) {
|
if (offset) {
|
||||||
if (!f->skip_hash)
|
if (!f->skip_hash)
|
||||||
the_hash_algo->update_fn(&f->ctx, f->buffer, offset);
|
the_hash_algo->unsafe_update_fn(&f->ctx, f->buffer, offset);
|
||||||
flush(f, f->buffer, offset);
|
flush(f, f->buffer, offset);
|
||||||
f->offset = 0;
|
f->offset = 0;
|
||||||
}
|
}
|
||||||
|
@ -73,7 +73,7 @@ int finalize_hashfile(struct hashfile *f, unsigned char *result,
|
||||||
if (f->skip_hash)
|
if (f->skip_hash)
|
||||||
hashclr(f->buffer, the_repository->hash_algo);
|
hashclr(f->buffer, the_repository->hash_algo);
|
||||||
else
|
else
|
||||||
the_hash_algo->final_fn(f->buffer, &f->ctx);
|
the_hash_algo->unsafe_final_fn(f->buffer, &f->ctx);
|
||||||
|
|
||||||
if (result)
|
if (result)
|
||||||
hashcpy(result, f->buffer, the_repository->hash_algo);
|
hashcpy(result, f->buffer, the_repository->hash_algo);
|
||||||
|
@ -128,7 +128,7 @@ void hashwrite(struct hashfile *f, const void *buf, unsigned int count)
|
||||||
* f->offset is necessarily zero.
|
* f->offset is necessarily zero.
|
||||||
*/
|
*/
|
||||||
if (!f->skip_hash)
|
if (!f->skip_hash)
|
||||||
the_hash_algo->update_fn(&f->ctx, buf, nr);
|
the_hash_algo->unsafe_update_fn(&f->ctx, buf, nr);
|
||||||
flush(f, buf, nr);
|
flush(f, buf, nr);
|
||||||
} else {
|
} else {
|
||||||
/*
|
/*
|
||||||
|
@ -174,7 +174,7 @@ static struct hashfile *hashfd_internal(int fd, const char *name,
|
||||||
f->name = name;
|
f->name = name;
|
||||||
f->do_crc = 0;
|
f->do_crc = 0;
|
||||||
f->skip_hash = 0;
|
f->skip_hash = 0;
|
||||||
the_hash_algo->init_fn(&f->ctx);
|
the_hash_algo->unsafe_init_fn(&f->ctx);
|
||||||
|
|
||||||
f->buffer_len = buffer_len;
|
f->buffer_len = buffer_len;
|
||||||
f->buffer = xmalloc(buffer_len);
|
f->buffer = xmalloc(buffer_len);
|
||||||
|
@ -208,7 +208,7 @@ void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpo
|
||||||
{
|
{
|
||||||
hashflush(f);
|
hashflush(f);
|
||||||
checkpoint->offset = f->total;
|
checkpoint->offset = f->total;
|
||||||
the_hash_algo->clone_fn(&checkpoint->ctx, &f->ctx);
|
the_hash_algo->unsafe_clone_fn(&checkpoint->ctx, &f->ctx);
|
||||||
}
|
}
|
||||||
|
|
||||||
int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
|
int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
|
||||||
|
@ -219,7 +219,7 @@ int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint
|
||||||
lseek(f->fd, offset, SEEK_SET) != offset)
|
lseek(f->fd, offset, SEEK_SET) != offset)
|
||||||
return -1;
|
return -1;
|
||||||
f->total = offset;
|
f->total = offset;
|
||||||
the_hash_algo->clone_fn(&f->ctx, &checkpoint->ctx);
|
the_hash_algo->unsafe_clone_fn(&f->ctx, &checkpoint->ctx);
|
||||||
f->offset = 0; /* hashflush() was called in checkpoint */
|
f->offset = 0; /* hashflush() was called in checkpoint */
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
@ -245,9 +245,9 @@ int hashfile_checksum_valid(const unsigned char *data, size_t total_len)
|
||||||
if (total_len < the_hash_algo->rawsz)
|
if (total_len < the_hash_algo->rawsz)
|
||||||
return 0; /* say "too short"? */
|
return 0; /* say "too short"? */
|
||||||
|
|
||||||
the_hash_algo->init_fn(&ctx);
|
the_hash_algo->unsafe_init_fn(&ctx);
|
||||||
the_hash_algo->update_fn(&ctx, data, data_len);
|
the_hash_algo->unsafe_update_fn(&ctx, data, data_len);
|
||||||
the_hash_algo->final_fn(got, &ctx);
|
the_hash_algo->unsafe_final_fn(got, &ctx);
|
||||||
|
|
||||||
return hasheq(got, data + data_len, the_repository->hash_algo);
|
return hasheq(got, data + data_len, the_repository->hash_algo);
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue