#include "cache.h"
#include "object.h"
+#include "blob.h"
+#include "commit.h"
+#include "tag.h"
+#include "tree.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
+#include "tree-walk.h"
#include <sys/time.h>
+#include <signal.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; /* uncompressed size */
- unsigned long offset; /* offset into the final pack file (nonzero if already written) */
+ 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;
+ 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 */
- enum object_type in_pack_type; /* could be delta */
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
+ */
+ int preferred_base; /* we do not pack this, but is encouraged to
+ * be used as the base objectto delta huge
+ * objects against.
+ */
};
/*
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;
static struct object_entry *objects = NULL;
-static int nr_objects = 0, nr_alloc = 0;
+static int nr_objects = 0, nr_alloc = 0, nr_result = 0;
static const char *base_name;
static unsigned char pack_file_sha1[20];
static int progress = 1;
+static volatile sig_atomic_t progress_update = 0;
/*
* The object names in objects array are hashed with this hashtable,
* 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;
+ unsigned long ui = (unsigned long)p;
int i;
ui = ui ^ (ui >> 16); /* defeat structure alignment */
rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1));
for (i = 0; i < num_ent; i++) {
- long hl = *((long *)(index + 24 * i));
+ unsigned int hl = *((unsigned int *)(index + 24 * i));
rix->revindex[i] = ntohl(hl);
}
/* This knows the pack format -- the 20-byte trailer
return n;
}
-static unsigned long write_object(struct sha1file *f, struct object_entry *entry)
+static unsigned long write_object(struct sha1file *f,
+ struct object_entry *entry)
{
unsigned long size;
char type[10];
unsigned char header[10];
unsigned hdrlen, datalen;
enum object_type obj_type;
+ int to_reuse = 0;
+
+ if (entry->preferred_base)
+ return 0;
obj_type = entry->type;
- if (!entry->in_pack ||
- (obj_type != entry->in_pack_type)) {
+ 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));
sha1write(f, buf, datalen);
unuse_packed_git(p);
hdrlen = 0; /* not really */
+ if (obj_type == OBJ_DELTA)
+ reused_delta++;
reused++;
}
+ if (obj_type == OBJ_DELTA)
+ written_delta++;
written++;
return hdrlen + datalen;
}
int i;
struct sha1file *f;
unsigned long offset;
- unsigned long mb;
struct pack_header hdr;
+ unsigned last_percent = 999;
+ int do_progress = 0;
if (!base_name)
f = sha1fd(1, "<stdout>");
- else
- f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack");
+ else {
+ f = sha1create("%s-%s.%s", base_name,
+ sha1_to_hex(object_list_sha1), "pack");
+ do_progress = progress;
+ }
+ if (do_progress)
+ fprintf(stderr, "Writing %d objects.\n", nr_result);
+
hdr.hdr_signature = htonl(PACK_SIGNATURE);
hdr.hdr_version = htonl(PACK_VERSION);
- hdr.hdr_entries = htonl(nr_objects);
+ hdr.hdr_entries = htonl(nr_result);
sha1write(f, &hdr, sizeof(hdr));
offset = sizeof(hdr);
- for (i = 0; i < nr_objects; i++)
+ if (!nr_result)
+ goto done;
+ for (i = 0; i < nr_objects; i++) {
offset = write_one(f, objects + i, offset);
-
+ if (do_progress) {
+ unsigned percent = written * 100 / nr_result;
+ if (progress_update || percent != last_percent) {
+ fprintf(stderr, "%4u%% (%u/%u) done\r",
+ percent, written, nr_result);
+ progress_update = 0;
+ last_percent = percent;
+ }
+ }
+ }
+ if (do_progress)
+ fputc('\n', stderr);
+ done:
sha1close(f, pack_file_sha1, 1);
}
static void write_index_file(void)
{
int i;
- struct sha1file *f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "idx");
+ struct sha1file *f = sha1create("%s-%s.%s", base_name,
+ sha1_to_hex(object_list_sha1), "idx");
struct object_entry **list = sorted_by_sha;
- struct object_entry **last = list + nr_objects;
+ struct object_entry **last = list + nr_result;
unsigned int array[256];
/*
* Write the actual SHA1 entries..
*/
list = sorted_by_sha;
- for (i = 0; i < nr_objects; i++) {
+ for (i = 0; i < nr_result; i++) {
struct object_entry *entry = *list++;
unsigned int offset = htonl(entry->offset);
sha1write(f, &offset, 4);
sha1close(f, NULL, 1);
}
-static int add_object_entry(unsigned char *sha1, unsigned int hash)
+static int locate_object_entry_hash(const 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(const unsigned char *sha1)
+{
+ int i;
+
+ if (!object_ix_hashsz)
+ return NULL;
+
+ i = locate_object_entry_hash(sha1);
+ if (0 <= i)
+ return &objects[object_ix[i]-1];
+ return NULL;
+}
+
+static void rehash_objects(void)
+{
+ int i;
+ struct object_entry *oe;
+
+ object_ix_hashsz = nr_objects * 3;
+ if (object_ix_hashsz < 1024)
+ object_ix_hashsz = 1024;
+ object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz);
+ memset(object_ix, 0, 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)
+ continue;
+ ix = -1 - ix;
+ object_ix[ix] = i + 1;
+ }
+}
+
+static unsigned name_hash(const char *name)
+{
+ unsigned char c;
+ unsigned hash = 0;
+
+ /*
+ * This effectively just creates a sortable number from the
+ * last sixteen non-whitespace characters. Last characters
+ * count "most", so things that end in ".c" sort together.
+ */
+ while ((c = *name++) != 0) {
+ if (isspace(c))
+ continue;
+ hash = (hash >> 2) + (c << 24);
+ }
+ return hash;
+}
+
+static int add_object_entry(const unsigned char *sha1, unsigned hash, int exclude)
{
unsigned int idx = nr_objects;
struct object_entry *entry;
struct packed_git *p;
- unsigned int found_offset;
- struct packed_git *found_pack;
-
- 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;
+ unsigned int found_offset = 0;
+ struct packed_git *found_pack = NULL;
+ int ix, status = 0;
+
+ if (!exclude) {
+ 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;
+ }
}
}
}
+ if ((entry = locate_object_entry(sha1)) != NULL)
+ goto already_added;
if (idx >= nr_alloc) {
unsigned int needed = (idx + 1024) * 3 / 2;
nr_alloc = needed;
}
entry = objects + idx;
+ nr_objects = idx + 1;
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;
+
+ if (object_ix_hashsz * 3 <= nr_objects * 4)
+ rehash_objects();
+ else {
+ ix = locate_object_entry_hash(entry->sha1);
+ if (0 <= ix)
+ die("internal error in object hashing.");
+ object_ix[-1 - ix] = idx + 1;
}
- nr_objects = idx+1;
- return 1;
+ status = 1;
+
+ already_added:
+ if (progress_update) {
+ fprintf(stderr, "Counting objects...%d\r", nr_objects);
+ progress_update = 0;
+ }
+ if (exclude)
+ entry->preferred_base = 1;
+ else {
+ if (found_pack) {
+ entry->in_pack = found_pack;
+ entry->in_pack_offset = found_offset;
+ }
+ }
+ return status;
+}
+
+struct pbase_tree_cache {
+ unsigned char sha1[20];
+ int ref;
+ int temporary;
+ void *tree_data;
+ unsigned long tree_size;
+};
+
+static struct pbase_tree_cache *(pbase_tree_cache[256]);
+static int pbase_tree_cache_ix(const unsigned char *sha1)
+{
+ return sha1[0] % ARRAY_SIZE(pbase_tree_cache);
+}
+static int pbase_tree_cache_ix_incr(int ix)
+{
+ return (ix+1) % ARRAY_SIZE(pbase_tree_cache);
+}
+
+static struct pbase_tree {
+ struct pbase_tree *next;
+ /* This is a phony "cache" entry; we are not
+ * going to evict it nor find it through _get()
+ * mechanism -- this is for the toplevel node that
+ * would almost always change with any commit.
+ */
+ struct pbase_tree_cache pcache;
+} *pbase_tree;
+
+static struct pbase_tree_cache *pbase_tree_get(const unsigned char *sha1)
+{
+ struct pbase_tree_cache *ent, *nent;
+ void *data;
+ unsigned long size;
+ char type[20];
+ int neigh;
+ int my_ix = pbase_tree_cache_ix(sha1);
+ int available_ix = -1;
+
+ /* pbase-tree-cache acts as a limited hashtable.
+ * your object will be found at your index or within a few
+ * slots after that slot if it is cached.
+ */
+ for (neigh = 0; neigh < 8; neigh++) {
+ ent = pbase_tree_cache[my_ix];
+ if (ent && !memcmp(ent->sha1, sha1, 20)) {
+ ent->ref++;
+ return ent;
+ }
+ else if (((available_ix < 0) && (!ent || !ent->ref)) ||
+ ((0 <= available_ix) &&
+ (!ent && pbase_tree_cache[available_ix])))
+ available_ix = my_ix;
+ if (!ent)
+ break;
+ my_ix = pbase_tree_cache_ix_incr(my_ix);
+ }
+
+ /* Did not find one. Either we got a bogus request or
+ * we need to read and perhaps cache.
+ */
+ data = read_sha1_file(sha1, type, &size);
+ if (!data)
+ return NULL;
+ if (strcmp(type, tree_type)) {
+ free(data);
+ return NULL;
+ }
+
+ /* We need to either cache or return a throwaway copy */
+
+ if (available_ix < 0)
+ ent = NULL;
+ else {
+ ent = pbase_tree_cache[available_ix];
+ my_ix = available_ix;
+ }
+
+ if (!ent) {
+ nent = xmalloc(sizeof(*nent));
+ nent->temporary = (available_ix < 0);
+ }
+ else {
+ /* evict and reuse */
+ free(ent->tree_data);
+ nent = ent;
+ }
+ memcpy(nent->sha1, sha1, 20);
+ nent->tree_data = data;
+ nent->tree_size = size;
+ nent->ref = 1;
+ if (!nent->temporary)
+ pbase_tree_cache[my_ix] = nent;
+ return nent;
+}
+
+static void pbase_tree_put(struct pbase_tree_cache *cache)
+{
+ if (!cache->temporary) {
+ cache->ref--;
+ return;
+ }
+ free(cache->tree_data);
+ free(cache);
}
-static int locate_object_entry_hash(unsigned char *sha1)
+static int name_cmp_len(const char *name)
{
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;
+ for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++)
+ ;
+ return i;
+}
+
+static void add_pbase_object(struct tree_desc *tree,
+ const char *name,
+ int cmplen,
+ const char *fullname)
+{
+ struct name_entry entry;
+
+ while (tree_entry(tree,&entry)) {
+ unsigned long size;
+ char type[20];
+
+ if (entry.pathlen != cmplen ||
+ memcmp(entry.path, name, cmplen) ||
+ !has_sha1_file(entry.sha1) ||
+ sha1_object_info(entry.sha1, type, &size))
+ continue;
+ if (name[cmplen] != '/') {
+ unsigned hash = name_hash(fullname);
+ add_object_entry(entry.sha1, hash, 1);
+ return;
+ }
+ if (!strcmp(type, tree_type)) {
+ struct tree_desc sub;
+ struct pbase_tree_cache *tree;
+ const char *down = name+cmplen+1;
+ int downlen = name_cmp_len(down);
+
+ tree = pbase_tree_get(entry.sha1);
+ if (!tree)
+ return;
+ sub.buf = tree->tree_data;
+ sub.size = tree->tree_size;
+
+ add_pbase_object(&sub, down, downlen, fullname);
+ pbase_tree_put(tree);
+ }
}
- return -1 - i;
}
-static struct object_entry *locate_object_entry(unsigned char *sha1)
+static unsigned *done_pbase_paths;
+static int done_pbase_paths_num;
+static int done_pbase_paths_alloc;
+static int done_pbase_path_pos(unsigned hash)
{
- int i = locate_object_entry_hash(sha1);
- if (0 <= i)
- return &objects[object_ix[i]-1];
- return NULL;
+ int lo = 0;
+ int hi = done_pbase_paths_num;
+ while (lo < hi) {
+ int mi = (hi + lo) / 2;
+ if (done_pbase_paths[mi] == hash)
+ return mi;
+ if (done_pbase_paths[mi] < hash)
+ hi = mi;
+ else
+ lo = mi + 1;
+ }
+ return -lo-1;
+}
+
+static int check_pbase_path(unsigned hash)
+{
+ int pos = (!done_pbase_paths) ? -1 : done_pbase_path_pos(hash);
+ if (0 <= pos)
+ return 1;
+ pos = -pos - 1;
+ if (done_pbase_paths_alloc <= done_pbase_paths_num) {
+ done_pbase_paths_alloc = alloc_nr(done_pbase_paths_alloc);
+ done_pbase_paths = xrealloc(done_pbase_paths,
+ done_pbase_paths_alloc *
+ sizeof(unsigned));
+ }
+ done_pbase_paths_num++;
+ if (pos < done_pbase_paths_num)
+ memmove(done_pbase_paths + pos + 1,
+ done_pbase_paths + pos,
+ (done_pbase_paths_num - pos - 1) * sizeof(unsigned));
+ done_pbase_paths[pos] = hash;
+ return 0;
+}
+
+static void add_preferred_base_object(char *name, unsigned hash)
+{
+ struct pbase_tree *it;
+ int cmplen = name_cmp_len(name);
+
+ if (check_pbase_path(hash))
+ return;
+
+ for (it = pbase_tree; it; it = it->next) {
+ if (cmplen == 0) {
+ hash = name_hash("");
+ add_object_entry(it->pcache.sha1, hash, 1);
+ }
+ else {
+ struct tree_desc tree;
+ tree.buf = it->pcache.tree_data;
+ tree.size = it->pcache.tree_size;
+ add_pbase_object(&tree, name, cmplen, name);
+ }
+ }
+}
+
+static void add_preferred_base(unsigned char *sha1)
+{
+ struct pbase_tree *it;
+ void *data;
+ unsigned long size;
+ unsigned char tree_sha1[20];
+
+ data = read_object_with_reference(sha1, tree_type, &size, tree_sha1);
+ if (!data)
+ return;
+
+ for (it = pbase_tree; it; it = it->next) {
+ if (!memcmp(it->pcache.sha1, tree_sha1, 20)) {
+ free(data);
+ return;
+ }
+ }
+
+ it = xcalloc(1, sizeof(*it));
+ it->next = pbase_tree;
+ pbase_tree = it;
+
+ memcpy(it->pcache.sha1, tree_sha1, 20);
+ it->pcache.tree_data = data;
+ it->pcache.tree_size = size;
}
static void check_object(struct object_entry *entry)
{
char type[20];
- if (entry->in_pack) {
+ if (entry->in_pack && !entry->preferred_base) {
+ 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.
*/
- unsigned char base[20];
- unsigned long size;
- struct object_entry *base_entry;
- if (!check_reuse_pack_delta(entry->in_pack,
- entry->in_pack_offset,
- base, &size,
- &entry->in_pack_type) &&
- (base_entry = locate_object_entry(base))) {
- /* We do not know depth at this point, but it
- * does not matter. Getting delta_chain_length
- * with packed_object_info_detail() is not so
- * expensive, so we could do that later if we
- * wanted to. Calling sha1_object_info to get
- * the true size (and later an uncompressed
- * representation) of deeply deltified object
- * is quite expensive.
+ if (!no_reuse_delta &&
+ entry->in_pack_type == OBJ_DELTA &&
+ (base_entry = locate_object_entry(base)) &&
+ (!base_entry->preferred_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.
*/
- entry->depth = 1;
- /* uncompressed size */
+
+ /* 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 */
die("unable to get type of object %s",
sha1_to_hex(entry->sha1));
- if (!strcmp(type, "commit")) {
+ if (!strcmp(type, commit_type)) {
entry->type = OBJ_COMMIT;
- } else if (!strcmp(type, "tree")) {
+ } else if (!strcmp(type, tree_type)) {
entry->type = OBJ_TREE;
- } else if (!strcmp(type, "blob")) {
+ } else if (!strcmp(type, blob_type)) {
entry->type = OBJ_BLOB;
- } else if (!strcmp(type, "tag")) {
+ } else if (!strcmp(type, tag_type)) {
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)
+static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
{
- 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;
+ 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;
- hash_objects();
prepare_pack_ix();
- for (i = 0; i < nr_objects; i++)
- check_object(entry++);
+ for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+ check_object(entry);
+
+ if (nr_objects == nr_result) {
+ /*
+ * Depth of objects that depend on the entry -- this
+ * is subtracted from depth-max to break too deep
+ * delta chain because of delta data reusing.
+ * However, we loosen this restriction when we know we
+ * are creating a thin pack -- it will have to be
+ * expanded on the other end anyway, so do not
+ * artificially cut the delta chain and let it go as
+ * deep as it wants.
+ */
+ 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 *);
return memcmp(a->sha1, b->sha1, 20);
}
+static struct object_entry **create_final_object_list(void)
+{
+ struct object_entry **list;
+ int i, j;
+
+ for (i = nr_result = 0; i < nr_objects; i++)
+ if (!objects[i].preferred_base)
+ nr_result++;
+ list = xmalloc(nr_result * sizeof(struct object_entry *));
+ for (i = j = 0; i < nr_objects; i++) {
+ if (!objects[i].preferred_base)
+ list[j++] = objects + i;
+ }
+ current_sort = sha1_sort;
+ qsort(list, nr_result, sizeof(struct object_entry *), sort_comparator);
+ return list;
+}
+
static int type_size_sort(const struct object_entry *a, const struct object_entry *b)
{
if (a->type < b->type)
return -1;
if (a->hash > b->hash)
return 1;
+ if (a->preferred_base < b->preferred_base)
+ return -1;
+ if (a->preferred_base > b->preferred_base)
+ return 1;
if (a->size < b->size)
return -1;
if (a->size > b->size)
struct unpacked {
struct object_entry *entry;
void *data;
+ struct delta_index *index;
};
/*
* more importantly, the bigger file is likely the more recent
* one.
*/
-static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_depth)
+static int try_delta(struct unpacked *trg, struct unpacked *src,
+ struct delta_index *src_index, unsigned max_depth)
{
- struct object_entry *cur_entry = cur->entry;
- struct object_entry *old_entry = old->entry;
- unsigned long size, oldsize, delta_size, sizediff;
- long max_size;
+ struct object_entry *trg_entry = trg->entry;
+ struct object_entry *src_entry = src->entry;
+ unsigned long size, src_size, delta_size, sizediff, max_size;
void *delta_buf;
/* Don't bother doing diffs between different types */
- if (cur_entry->type != old_entry->type)
+ if (trg_entry->type != src_entry->type)
return -1;
- size = cur_entry->size;
- if (size < 50)
- return -1;
- oldsize = old_entry->size;
- sizediff = oldsize > size ? oldsize - size : size - oldsize;
- if (sizediff > size / 8)
+ /* We do not compute delta to *create* objects we are not
+ * going to pack.
+ */
+ if (trg_entry->preferred_base)
return -1;
- if (old_entry->depth >= max_depth)
- return 0;
/*
- * NOTE!
- *
- * We always delta from the bigger to the smaller, since that's
- * more space-efficient (deletes don't have to say _what_ they
- * delete).
+ * If the current object is at pack edge, take the depth the
+ * objects that depend on the current object into account --
+ * otherwise they would become too deep.
*/
- max_size = size / 2 - 20;
- if (cur_entry->delta)
- max_size = cur_entry->delta_size-1;
+ if (trg_entry->delta_child) {
+ if (max_depth <= trg_entry->delta_limit)
+ return 0;
+ max_depth -= trg_entry->delta_limit;
+ }
+ if (src_entry->depth >= max_depth)
+ return 0;
+
+ /* Now some size filtering heuristics. */
+ size = trg_entry->size;
+ max_size = size/2 - 20;
+ max_size = max_size * (max_depth - src_entry->depth) / max_depth;
+ if (max_size == 0)
+ return 0;
+ if (trg_entry->delta && trg_entry->delta_size <= max_size)
+ max_size = trg_entry->delta_size-1;
+ src_size = src_entry->size;
+ sizediff = src_size < size ? size - src_size : 0;
if (sizediff >= max_size)
- return -1;
- delta_buf = diff_delta(old->data, oldsize,
- cur->data, size, &delta_size, max_size);
+ return 0;
+
+ delta_buf = create_delta(src_index, trg->data, size, &delta_size, max_size);
if (!delta_buf)
return 0;
- cur_entry->delta = old_entry;
- cur_entry->delta_size = delta_size;
- cur_entry->depth = old_entry->depth + 1;
+
+ trg_entry->delta = src_entry;
+ trg_entry->delta_size = delta_size;
+ trg_entry->depth = src_entry->depth + 1;
free(delta_buf);
- return 0;
+ return 1;
+}
+
+static void progress_interval(int signum)
+{
+ progress_update = 1;
}
static void find_deltas(struct object_entry **list, int window, int depth)
int i, idx;
unsigned int array_size = window * sizeof(struct unpacked);
struct unpacked *array = xmalloc(array_size);
- int eye_candy;
+ unsigned processed = 0;
+ unsigned last_percent = 999;
memset(array, 0, array_size);
i = nr_objects;
idx = 0;
- eye_candy = i - (nr_objects / 20);
+ if (progress)
+ fprintf(stderr, "Deltifying %d objects.\n", nr_result);
while (--i >= 0) {
struct object_entry *entry = list[i];
char type[10];
int j;
- if (progress && i <= eye_candy) {
- eye_candy -= nr_objects / 20;
- fputc('.', stderr);
+ if (!entry->preferred_base)
+ processed++;
+
+ if (progress) {
+ unsigned percent = processed * 100 / nr_result;
+ if (percent != last_percent || progress_update) {
+ fprintf(stderr, "%4u%% (%u/%u) done\r",
+ percent, processed, nr_result);
+ progress_update = 0;
+ last_percent = percent;
+ }
}
if (entry->delta)
/* This happens if we decided to reuse existing
- * delta from a pack.
+ * delta from a pack. "!no_reuse_delta &&" is implied.
*/
continue;
+ if (entry->size < 50)
+ continue;
+ free_delta_index(n->index);
+ n->index = NULL;
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);
+ 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;
m = array + other_idx;
if (!m->entry)
break;
- if (try_delta(n, m, depth) < 0)
+ if (try_delta(n, m, m->index, depth) < 0)
break;
}
+ /* if we made n a delta, and if n is already at max
+ * depth, leaving it in the window is pointless. we
+ * should evict it first.
+ */
+ if (entry->delta && depth <= entry->depth)
+ continue;
+
+ n->index = create_delta_index(n->data, size);
+ if (!n->index)
+ die("out of memory");
+
idx++;
if (idx >= window)
idx = 0;
}
- for (i = 0; i < window; ++i)
+ if (progress)
+ fputc('\n', stderr);
+
+ for (i = 0; i < window; ++i) {
+ free_delta_index(array[i].index);
free(array[i].data);
+ }
free(array);
}
static void prepare_pack(int window, int depth)
{
- if (progress)
- fprintf(stderr, "Packing %d objects", nr_objects);
get_object_details();
- if (progress)
- fprintf(stderr, ".");
-
sorted_by_type = create_sorted_list(type_size_sort);
if (window && depth)
find_deltas(sorted_by_type, window+1, depth);
- if (progress)
- fputc('\n', stderr);
- write_pack_file();
}
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))
return 1;
}
+static void setup_progress_signal(void)
+{
+ struct sigaction sa;
+ struct itimerval v;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_handler = progress_interval;
+ sigemptyset(&sa.sa_mask);
+ sa.sa_flags = SA_RESTART;
+ sigaction(SIGALRM, &sa, NULL);
+
+ v.it_interval.tv_sec = 1;
+ v.it_interval.tv_usec = 0;
+ v.it_value = v.it_interval;
+ setitimer(ITIMER_REAL, &v, NULL);
+}
+
int main(int argc, char **argv)
{
SHA_CTX ctx;
- char line[PATH_MAX + 20];
+ char line[40 + 1 + PATH_MAX + 2];
int window = 10, depth = 10, pack_to_stdout = 0;
struct object_entry **list;
+ int num_preferred_base = 0;
int i;
- struct timeval prev_tv;
- int eye_candy = 0;
- int eye_candy_incr = 500;
-
setup_git_directory();
+ progress = isatty(2);
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
usage(pack_usage);
continue;
}
+ if (!strcmp("--progress", arg)) {
+ progress = 1;
+ continue;
+ }
if (!strcmp("-q", arg)) {
progress = 0;
continue;
}
+ if (!strcmp("--no-reuse-delta", arg)) {
+ no_reuse_delta = 1;
+ continue;
+ }
if (!strcmp("--stdout", arg)) {
pack_to_stdout = 1;
continue;
usage(pack_usage);
prepare_packed_git();
+
if (progress) {
fprintf(stderr, "Generating pack...\n");
- gettimeofday(&prev_tv, NULL);
+ setup_progress_signal();
}
- while (fgets(line, sizeof(line), stdin) != NULL) {
- unsigned int hash;
- char *p;
+
+ for (;;) {
unsigned char sha1[20];
+ unsigned hash;
- if (progress && (eye_candy <= nr_objects)) {
- fprintf(stderr, "Counting objects...%d\r", nr_objects);
- if (eye_candy && (50 <= eye_candy_incr)) {
- struct timeval tv;
- int time_diff;
- gettimeofday(&tv, NULL);
- time_diff = (tv.tv_sec - prev_tv.tv_sec);
- time_diff <<= 10;
- time_diff += (tv.tv_usec - prev_tv.tv_usec);
- if ((1 << 9) < time_diff)
- eye_candy_incr += 50;
- else if (50 < eye_candy_incr)
- eye_candy_incr -= 50;
- }
- eye_candy += eye_candy_incr;
+ if (!fgets(line, sizeof(line), stdin)) {
+ if (feof(stdin))
+ break;
+ if (!ferror(stdin))
+ die("fgets returned NULL, not EOF, not error!");
+ if (errno != EINTR)
+ die("fgets: %s", strerror(errno));
+ clearerr(stdin);
+ continue;
+ }
+
+ if (line[0] == '-') {
+ if (get_sha1_hex(line+1, sha1))
+ die("expected edge sha1, got garbage:\n %s",
+ line+1);
+ if (num_preferred_base++ < window)
+ add_preferred_base(sha1);
+ continue;
}
if (get_sha1_hex(line, sha1))
die("expected sha1, got garbage:\n %s", line);
- hash = 0;
- p = line+40;
- while (*p) {
- unsigned char c = *p++;
- if (isspace(c))
- continue;
- hash = hash * 11 + c;
- }
- add_object_entry(sha1, hash);
+ hash = name_hash(line+41);
+ add_preferred_base_object(line+41, hash);
+ add_object_entry(sha1, hash, 0);
}
if (progress)
fprintf(stderr, "Done counting %d objects.\n", nr_objects);
- if (non_empty && !nr_objects)
+ sorted_by_sha = create_final_object_list();
+ if (non_empty && !nr_result)
return 0;
- sorted_by_sha = create_sorted_list(sha1_sort);
SHA1_Init(&ctx);
list = sorted_by_sha;
- for (i = 0; i < nr_objects; i++) {
+ for (i = 0; i < nr_result; i++) {
struct object_entry *entry = *list++;
SHA1_Update(&ctx, entry->sha1, 20);
}
SHA1_Final(object_list_sha1, &ctx);
+ if (progress && (nr_objects != nr_result))
+ fprintf(stderr, "Result has %d objects.\n", nr_result);
if (reuse_cached_pack(object_list_sha1, pack_to_stdout))
;
else {
- prepare_pack(window, depth);
+ if (nr_result)
+ prepare_pack(window, depth);
+ if (progress && pack_to_stdout) {
+ /* the other end usually displays progress itself */
+ struct itimerval v = {{0,},};
+ setitimer(ITIMER_REAL, &v, NULL);
+ signal(SIGALRM, SIG_IGN );
+ progress_update = 0;
+ }
+ write_pack_file();
if (!pack_to_stdout) {
write_index_file();
puts(sha1_to_hex(object_list_sha1));
}
}
- fprintf(stderr, "Total %d, written %d, reused %d\n",
- nr_objects, written, reused);
+ if (progress)
+ fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n",
+ nr_result, written, written_delta, reused, reused_delta);
return 0;
}