aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/git-pack-objects.txt21
-rw-r--r--Documentation/git-repack.txt10
-rwxr-xr-xgit-repack.sh13
-rw-r--r--pack-objects.c448
-rw-r--r--pack.h4
-rw-r--r--sha1_file.c19
6 files changed, 442 insertions, 73 deletions
diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt
index 2d67d3911..4cb2e83fa 100644
--- a/Documentation/git-pack-objects.txt
+++ b/Documentation/git-pack-objects.txt
@@ -8,7 +8,10 @@ git-pack-objects - Create a packed archive of objects.
SYNOPSIS
--------
-'git-pack-objects' [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list
+[verse]
+'git-pack-objects' [-q] [--no-reuse-delta] [--non-empty]
+ [--local] [--incremental] [--window=N] [--depth=N]
+ {--stdout | base-name} < object-list
DESCRIPTION
@@ -32,6 +35,10 @@ Placing both in the pack/ subdirectory of $GIT_OBJECT_DIRECTORY (or
any of the directories on $GIT_ALTERNATE_OBJECT_DIRECTORIES)
enables git to read from such an archive.
+In a packed archive, an object is either stored as a compressed
+whole, or as a difference from some other object. The latter is
+often called a delta.
+
OPTIONS
-------
@@ -74,6 +81,18 @@ base-name::
Only create a packed archive if it would contain at
least one object.
+-q::
+ This flag makes the command not to report its progress
+ on the standard error stream.
+
+--no-reuse-delta::
+ When creating a packed archive in a repository that
+ has existing packs, the command reuses existing deltas.
+ This sometimes results in a slightly suboptimal pack.
+ This flag tells the command not to reuse existing deltas
+ but compute them from scratch.
+
+
Author
------
Written by Linus Torvalds <torvalds@osdl.org>
diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
index 9060fe889..6c0f792da 100644
--- a/Documentation/git-repack.txt
+++ b/Documentation/git-repack.txt
@@ -9,7 +9,7 @@ objects into pack files.
SYNOPSIS
--------
-'git-repack' [-a] [-d] [-l] [-n]
+'git-repack' [-a] [-d] [-f] [-l] [-n] [-q]
DESCRIPTION
-----------
@@ -43,6 +43,14 @@ OPTIONS
Pass the `--local` option to `git pack-objects`, see
gitlink:git-pack-objects[1].
+-f::
+ Pass the `--no-reuse-delta` option to `git pack-objects`, see
+ gitlink:git-pack-objects[1].
+
+-q::
+ Pass the `-q` option to `git pack-objects`, see
+ gitlink:git-pack-objects[1].
+
-n::
Do not update the server information with
`git update-server-info`.
diff --git a/git-repack.sh b/git-repack.sh
index 1fafb6ecf..3d6fec1c9 100755
--- a/git-repack.sh
+++ b/git-repack.sh
@@ -3,17 +3,20 @@
# Copyright (c) 2005 Linus Torvalds
#
-USAGE='[-a] [-d] [-l] [-n]'
+USAGE='[-a] [-d] [-f] [-l] [-n] [-q]'
. git-sh-setup
-no_update_info= all_into_one= remove_redundant= local=
+no_update_info= all_into_one= remove_redundant=
+local= quiet= no_reuse_delta=
while case "$#" in 0) break ;; esac
do
case "$1" in
-n) no_update_info=t ;;
-a) all_into_one=t ;;
-d) remove_redundant=t ;;
- -l) local=t ;;
+ -q) quiet=-q ;;
+ -f) no_reuse_delta=--no-reuse-delta ;;
+ -l) local=--local ;;
*) usage ;;
esac
shift
@@ -39,9 +42,7 @@ case ",$all_into_one," in
find . -type f \( -name '*.pack' -o -name '*.idx' \) -print`
;;
esac
-if [ "$local" ]; then
- pack_objects="$pack_objects --local"
-fi
+pack_objects="$pack_objects $local $quiet $no_reuse_delta"
name=$(git-rev-list --objects $rev_list $(git-rev-parse $rev_parse) 2>&1 |
git-pack-objects --non-empty $pack_objects .tmp-pack) ||
exit 1
diff --git a/pack-objects.c b/pack-objects.c
index c5a5e6160..0c9f4c9d2 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -5,21 +5,45 @@
#include "csum-file.h"
#include <sys/time.h>
-static const char pack_usage[] = "git-pack-objects [-q] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
+static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
struct object_entry {
unsigned char sha1[20];
- unsigned long size;
- unsigned long offset;
- unsigned int depth;
- unsigned int hash;
+ unsigned long size; /* uncompressed size */
+ unsigned long offset; /* offset into the final pack file;
+ * nonzero if already written.
+ */
+ unsigned int depth; /* delta depth */
+ unsigned int delta_limit; /* base adjustment for in-pack delta */
+ unsigned int hash; /* name hint hash */
enum object_type type;
- unsigned long delta_size;
- struct object_entry *delta;
+ enum object_type in_pack_type; /* could be delta */
+ unsigned long delta_size; /* delta data size (uncompressed) */
+ struct object_entry *delta; /* delta base object */
+ struct packed_git *in_pack; /* already in pack */
+ unsigned int in_pack_offset;
+ struct object_entry *delta_child; /* delitified objects who bases me */
+ struct object_entry *delta_sibling; /* other deltified objects who
+ * uses the same base as me
+ */
};
+/*
+ * Objects we are going to pack are colected in objects array (dynamically
+ * expanded). nr_objects & nr_alloc controls this array. They are stored
+ * in the order we see -- typically rev-list --objects order that gives us
+ * nice "minimum seek" order.
+ *
+ * sorted-by-sha ans sorted-by-type are arrays of pointers that point at
+ * elements in the objects array. The former is used to build the pack
+ * index (lists object names in the ascending order to help offset lookup),
+ * and the latter is used to group similar things together by try_delta()
+ * heuristics.
+ */
+
static unsigned char object_list_sha1[20];
static int non_empty = 0;
+static int no_reuse_delta = 0;
static int local = 0;
static int incremental = 0;
static struct object_entry **sorted_by_sha, **sorted_by_type;
@@ -29,6 +53,137 @@ static const char *base_name;
static unsigned char pack_file_sha1[20];
static int progress = 1;
+/*
+ * The object names in objects array are hashed with this hashtable,
+ * to help looking up the entry by object name. Binary search from
+ * sorted_by_sha is also possible but this was easier to code and faster.
+ * This hashtable is built after all the objects are seen.
+ */
+static int *object_ix = NULL;
+static int object_ix_hashsz = 0;
+
+/*
+ * Pack index for existing packs give us easy access to the offsets into
+ * corresponding pack file where each object's data starts, but the entries
+ * do not store the size of the compressed representation (uncompressed
+ * size is easily available by examining the pack entry header). We build
+ * a hashtable of existing packs (pack_revindex), and keep reverse index
+ * here -- pack index file is sorted by object name mapping to offset; this
+ * pack_revindex[].revindex array is an ordered list of offsets, so if you
+ * know the offset of an object, next offset is where its packed
+ * representation ends.
+ */
+struct pack_revindex {
+ struct packed_git *p;
+ unsigned long *revindex;
+} *pack_revindex = NULL;
+static int pack_revindex_hashsz = 0;
+
+/*
+ * stats
+ */
+static int written = 0;
+static int written_delta = 0;
+static int reused = 0;
+static int reused_delta = 0;
+
+static int pack_revindex_ix(struct packed_git *p)
+{
+ unsigned int ui = (unsigned int) p;
+ int i;
+
+ ui = ui ^ (ui >> 16); /* defeat structure alignment */
+ i = (int)(ui % pack_revindex_hashsz);
+ while (pack_revindex[i].p) {
+ if (pack_revindex[i].p == p)
+ return i;
+ if (++i == pack_revindex_hashsz)
+ i = 0;
+ }
+ return -1 - i;
+}
+
+static void prepare_pack_ix(void)
+{
+ int num;
+ struct packed_git *p;
+ for (num = 0, p = packed_git; p; p = p->next)
+ num++;
+ if (!num)
+ return;
+ pack_revindex_hashsz = num * 11;
+ pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
+ for (p = packed_git; p; p = p->next) {
+ num = pack_revindex_ix(p);
+ num = - 1 - num;
+ pack_revindex[num].p = p;
+ }
+ /* revindex elements are lazily initialized */
+}
+
+static int cmp_offset(const void *a_, const void *b_)
+{
+ unsigned long a = *(unsigned long *) a_;
+ unsigned long b = *(unsigned long *) b_;
+ if (a < b)
+ return -1;
+ else if (a == b)
+ return 0;
+ else
+ return 1;
+}
+
+/*
+ * Ordered list of offsets of objects in the pack.
+ */
+static void prepare_pack_revindex(struct pack_revindex *rix)
+{
+ struct packed_git *p = rix->p;
+ int num_ent = num_packed_objects(p);
+ int i;
+ void *index = p->index_base + 256;
+
+ rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1));
+ for (i = 0; i < num_ent; i++) {
+ long hl = *((long *)(index + 24 * i));
+ rix->revindex[i] = ntohl(hl);
+ }
+ /* This knows the pack format -- the 20-byte trailer
+ * follows immediately after the last object data.
+ */
+ rix->revindex[num_ent] = p->pack_size - 20;
+ qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset);
+}
+
+static unsigned long find_packed_object_size(struct packed_git *p,
+ unsigned long ofs)
+{
+ int num;
+ int lo, hi;
+ struct pack_revindex *rix;
+ unsigned long *revindex;
+ num = pack_revindex_ix(p);
+ if (num < 0)
+ die("internal error: pack revindex uninitialized");
+ rix = &pack_revindex[num];
+ if (!rix->revindex)
+ prepare_pack_revindex(rix);
+ revindex = rix->revindex;
+ lo = 0;
+ hi = num_packed_objects(p) + 1;
+ do {
+ int mi = (lo + hi) / 2;
+ if (revindex[mi] == ofs) {
+ return revindex[mi+1] - ofs;
+ }
+ else if (ofs < revindex[mi])
+ hi = mi;
+ else
+ lo = mi + 1;
+ } while (lo < hi);
+ die("internal error: pack revindex corrupt");
+}
+
static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
{
unsigned long othersize, delta_size;
@@ -78,35 +233,69 @@ static unsigned long write_object(struct sha1file *f, struct object_entry *entry
{
unsigned long size;
char type[10];
- void *buf = read_sha1_file(entry->sha1, type, &size);
+ void *buf;
unsigned char header[10];
unsigned hdrlen, datalen;
enum object_type obj_type;
+ int to_reuse = 0;
- if (!buf)
- die("unable to read %s", sha1_to_hex(entry->sha1));
- if (size != entry->size)
- die("object %s size inconsistency (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
-
- /*
- * The object header is a byte of 'type' followed by zero or
- * more bytes of length. For deltas, the 20 bytes of delta sha1
- * follows that.
- */
obj_type = entry->type;
- if (entry->delta) {
- buf = delta_against(buf, size, entry);
- size = entry->delta_size;
- obj_type = OBJ_DELTA;
+ if (! entry->in_pack)
+ to_reuse = 0; /* can't reuse what we don't have */
+ else if (obj_type == OBJ_DELTA)
+ to_reuse = 1; /* check_object() decided it for us */
+ else if (obj_type != entry->in_pack_type)
+ to_reuse = 0; /* pack has delta which is unusable */
+ else if (entry->delta)
+ to_reuse = 0; /* we want to pack afresh */
+ else
+ to_reuse = 1; /* we have it in-pack undeltified,
+ * and we do not need to deltify it.
+ */
+
+ if (! to_reuse) {
+ buf = read_sha1_file(entry->sha1, type, &size);
+ if (!buf)
+ die("unable to read %s", sha1_to_hex(entry->sha1));
+ if (size != entry->size)
+ die("object %s size inconsistency (%lu vs %lu)",
+ sha1_to_hex(entry->sha1), size, entry->size);
+ if (entry->delta) {
+ buf = delta_against(buf, size, entry);
+ size = entry->delta_size;
+ obj_type = OBJ_DELTA;
+ }
+ /*
+ * The object header is a byte of 'type' followed by zero or
+ * more bytes of length. For deltas, the 20 bytes of delta
+ * sha1 follows that.
+ */
+ hdrlen = encode_header(obj_type, size, header);
+ sha1write(f, header, hdrlen);
+
+ if (entry->delta) {
+ sha1write(f, entry->delta, 20);
+ hdrlen += 20;
+ }
+ datalen = sha1write_compressed(f, buf, size);
+ free(buf);
}
- hdrlen = encode_header(obj_type, size, header);
- sha1write(f, header, hdrlen);
- if (entry->delta) {
- sha1write(f, entry->delta, 20);
- hdrlen += 20;
+ else {
+ struct packed_git *p = entry->in_pack;
+ use_packed_git(p);
+
+ datalen = find_packed_object_size(p, entry->in_pack_offset);
+ buf = p->pack_base + entry->in_pack_offset;
+ sha1write(f, buf, datalen);
+ unuse_packed_git(p);
+ hdrlen = 0; /* not really */
+ if (obj_type == OBJ_DELTA)
+ reused_delta++;
+ reused++;
}
- datalen = sha1write_compressed(f, buf, size);
- free(buf);
+ if (obj_type == OBJ_DELTA)
+ written_delta++;
+ written++;
return hdrlen + datalen;
}
@@ -132,7 +321,6 @@ static void write_pack_file(void)
int i;
struct sha1file *f;
unsigned long offset;
- unsigned long mb;
struct pack_header hdr;
if (!base_name)
@@ -148,8 +336,6 @@ static void write_pack_file(void)
offset = write_one(f, objects + i, offset);
sha1close(f, pack_file_sha1, 1);
- mb = offset >> 20;
- offset &= 0xfffff;
}
static void write_index_file(void)
@@ -196,18 +382,20 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash)
{
unsigned int idx = nr_objects;
struct object_entry *entry;
-
- if (incremental || local) {
- struct packed_git *p;
-
- for (p = packed_git; p; p = p->next) {
- struct pack_entry e;
-
- if (find_pack_entry_one(sha1, &e, p)) {
- if (incremental)
- return 0;
- if (local && !p->pack_local)
- return 0;
+ struct packed_git *p;
+ unsigned int found_offset = 0;
+ struct packed_git *found_pack = NULL;
+
+ for (p = packed_git; p; p = p->next) {
+ struct pack_entry e;
+ if (find_pack_entry_one(sha1, &e, p)) {
+ if (incremental)
+ return 0;
+ if (local && !p->pack_local)
+ return 0;
+ if (!found_pack) {
+ found_offset = e.offset;
+ found_pack = e.p;
}
}
}
@@ -221,39 +409,143 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash)
memset(entry, 0, sizeof(*entry));
memcpy(entry->sha1, sha1, 20);
entry->hash = hash;
+ if (found_pack) {
+ entry->in_pack = found_pack;
+ entry->in_pack_offset = found_offset;
+ }
nr_objects = idx+1;
return 1;
}
+static int locate_object_entry_hash(unsigned char *sha1)
+{
+ int i;
+ unsigned int ui;
+ memcpy(&ui, sha1, sizeof(unsigned int));
+ i = ui % object_ix_hashsz;
+ while (0 < object_ix[i]) {
+ if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20))
+ return i;
+ if (++i == object_ix_hashsz)
+ i = 0;
+ }
+ return -1 - i;
+}
+
+static struct object_entry *locate_object_entry(unsigned char *sha1)
+{
+ int i = locate_object_entry_hash(sha1);
+ if (0 <= i)
+ return &objects[object_ix[i]-1];
+ return NULL;
+}
+
static void check_object(struct object_entry *entry)
{
char type[20];
- if (!sha1_object_info(entry->sha1, type, &entry->size)) {
- if (!strcmp(type, "commit")) {
- entry->type = OBJ_COMMIT;
- } else if (!strcmp(type, "tree")) {
- entry->type = OBJ_TREE;
- } else if (!strcmp(type, "blob")) {
- entry->type = OBJ_BLOB;
- } else if (!strcmp(type, "tag")) {
- entry->type = OBJ_TAG;
- } else
- die("unable to pack object %s of type %s",
- sha1_to_hex(entry->sha1), type);
+ if (entry->in_pack) {
+ unsigned char base[20];
+ unsigned long size;
+ struct object_entry *base_entry;
+
+ /* We want in_pack_type even if we do not reuse delta.
+ * There is no point not reusing non-delta representations.
+ */
+ check_reuse_pack_delta(entry->in_pack,
+ entry->in_pack_offset,
+ base, &size,
+ &entry->in_pack_type);
+
+ /* Check if it is delta, and the base is also an object
+ * we are going to pack. If so we will reuse the existing
+ * delta.
+ */
+ if (!no_reuse_delta &&
+ entry->in_pack_type == OBJ_DELTA &&
+ (base_entry = locate_object_entry(base))) {
+
+ /* Depth value does not matter - find_deltas()
+ * will never consider reused delta as the
+ * base object to deltify other objects
+ * against, in order to avoid circular deltas.
+ */
+
+ /* uncompressed size of the delta data */
+ entry->size = entry->delta_size = size;
+ entry->delta = base_entry;
+ entry->type = OBJ_DELTA;
+
+ entry->delta_sibling = base_entry->delta_child;
+ base_entry->delta_child = entry;
+
+ return;
+ }
+ /* Otherwise we would do the usual */
}
- else
+
+ if (sha1_object_info(entry->sha1, type, &entry->size))
die("unable to get type of object %s",
sha1_to_hex(entry->sha1));
+
+ if (!strcmp(type, "commit")) {
+ entry->type = OBJ_COMMIT;
+ } else if (!strcmp(type, "tree")) {
+ entry->type = OBJ_TREE;
+ } else if (!strcmp(type, "blob")) {
+ entry->type = OBJ_BLOB;
+ } else if (!strcmp(type, "tag")) {
+ entry->type = OBJ_TAG;
+ } else
+ die("unable to pack object %s of type %s",
+ sha1_to_hex(entry->sha1), type);
+}
+
+static void hash_objects(void)
+{
+ int i;
+ struct object_entry *oe;
+
+ object_ix_hashsz = nr_objects * 2;
+ object_ix = xcalloc(sizeof(int), object_ix_hashsz);
+ for (i = 0, oe = objects; i < nr_objects; i++, oe++) {
+ int ix = locate_object_entry_hash(oe->sha1);
+ if (0 <= ix) {
+ error("the same object '%s' added twice",
+ sha1_to_hex(oe->sha1));
+ continue;
+ }
+ ix = -1 - ix;
+ object_ix[ix] = i + 1;
+ }
+}
+
+static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
+{
+ struct object_entry *child = me->delta_child;
+ unsigned int m = n;
+ while (child) {
+ unsigned int c = check_delta_limit(child, n + 1);
+ if (m < c)
+ m = c;
+ child = child->delta_sibling;
+ }
+ return m;
}
static void get_object_details(void)
{
int i;
- struct object_entry *entry = objects;
+ struct object_entry *entry;
- for (i = 0; i < nr_objects; i++)
- check_object(entry++);
+ hash_objects();
+ prepare_pack_ix();
+ for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+ check_object(entry);
+ for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+ if (!entry->delta && entry->delta_child)
+ entry->delta_limit =
+ check_delta_limit(entry, 1);
}
typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *);
@@ -326,6 +618,16 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
if (cur_entry->type != old_entry->type)
return -1;
+ /* If the current object is at edge, take the depth the objects
+ * that depend on the current object into account -- otherwise
+ * they would become too deep.
+ */
+ if (cur_entry->delta_child) {
+ if (max_depth <= cur_entry->delta_limit)
+ return 0;
+ max_depth -= cur_entry->delta_limit;
+ }
+
size = cur_entry->size;
if (size < 50)
return -1;
@@ -382,11 +684,19 @@ static void find_deltas(struct object_entry **list, int window, int depth)
eye_candy -= nr_objects / 20;
fputc('.', stderr);
}
+
+ if (entry->delta)
+ /* This happens if we decided to reuse existing
+ * delta from a pack. "!no_reuse_delta &&" is implied.
+ */
+ continue;
+
free(n->data);
n->entry = entry;
n->data = read_sha1_file(entry->sha1, type, &size);
if (size != entry->size)
die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
+
j = window;
while (--j > 0) {
unsigned int other_idx = idx + j;
@@ -411,10 +721,12 @@ static void find_deltas(struct object_entry **list, int window, int depth)
static void prepare_pack(int window, int depth)
{
- get_object_details();
-
if (progress)
fprintf(stderr, "Packing %d objects", nr_objects);
+ get_object_details();
+ if (progress)
+ fputc('.', stderr);
+
sorted_by_type = create_sorted_list(type_size_sort);
if (window && depth)
find_deltas(sorted_by_type, window+1, depth);
@@ -443,8 +755,9 @@ static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
}
}
- fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
- sha1_to_hex(sha1));
+ if (progress)
+ fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
+ sha1_to_hex(sha1));
if (pack_to_stdout) {
if (copy_fd(ifd, 1))
@@ -524,6 +837,10 @@ int main(int argc, char **argv)
progress = 0;
continue;
}
+ if (!strcmp("--no-reuse-delta", arg)) {
+ no_reuse_delta = 1;
+ continue;
+ }
if (!strcmp("--stdout", arg)) {
pack_to_stdout = 1;
continue;
@@ -599,5 +916,8 @@ int main(int argc, char **argv)
puts(sha1_to_hex(object_list_sha1));
}
}
+ if (progress)
+ fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n",
+ nr_objects, written, written_delta, reused, reused_delta);
return 0;
}
diff --git a/pack.h b/pack.h
index 9dafa2b6d..694e0c56f 100644
--- a/pack.h
+++ b/pack.h
@@ -29,5 +29,7 @@ struct pack_header {
};
extern int verify_pack(struct packed_git *, int);
-
+extern int check_reuse_pack_delta(struct packed_git *, unsigned long,
+ unsigned char *, unsigned long *,
+ enum object_type *);
#endif
diff --git a/sha1_file.c b/sha1_file.c
index 1d799f793..9cab99ae7 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -828,6 +828,25 @@ static unsigned long unpack_object_header(struct packed_git *p, unsigned long of
return offset;
}
+int check_reuse_pack_delta(struct packed_git *p, unsigned long offset,
+ unsigned char *base, unsigned long *sizep,
+ enum object_type *kindp)
+{
+ unsigned long ptr;
+ int status = -1;
+
+ use_packed_git(p);
+ ptr = offset;
+ ptr = unpack_object_header(p, ptr, kindp, sizep);
+ if (*kindp != OBJ_DELTA)
+ goto done;
+ memcpy(base, p->pack_base + ptr, 20);
+ status = 0;
+ done:
+ unuse_packed_git(p);
+ return status;
+}
+
void packed_object_info_detail(struct pack_entry *e,
char *type,
unsigned long *size,