#include "cache.h"
+#define BLKSIZE 512
+
static const char pack_redundant_usage[] =
"git-pack-redundant [ --verbose ] [ --alt-odb ] < --all | <.pack filename> ...>";
-int load_all_packs = 0, verbose = 0, alt_odb = 0;
+static int load_all_packs, verbose, alt_odb;
struct llist_item {
struct llist_item *next;
- char *sha1;
+ const unsigned char *sha1;
};
-struct llist {
+static struct llist {
struct llist_item *front;
struct llist_item *back;
size_t size;
} *all_objects; /* all objects which must be present in local packfiles */
-struct pack_list {
+static struct pack_list {
struct pack_list *next;
struct packed_git *pack;
struct llist *unique_objects;
struct pll {
struct pll *next;
struct pack_list *pl;
- size_t pl_size;
};
-inline void llist_free(struct llist *list)
+static struct llist_item *free_nodes;
+
+static inline void llist_item_put(struct llist_item *item)
+{
+ item->next = free_nodes;
+ free_nodes = item;
+}
+
+static inline struct llist_item *llist_item_get(void)
+{
+ struct llist_item *new;
+ if ( free_nodes ) {
+ new = free_nodes;
+ free_nodes = free_nodes->next;
+ } else {
+ int i = 1;
+ new = xmalloc(sizeof(struct llist_item) * BLKSIZE);
+ for(;i < BLKSIZE; i++) {
+ llist_item_put(&new[i]);
+ }
+ }
+ return new;
+}
+
+static void llist_free(struct llist *list)
{
while((list->back = list->front)) {
list->front = list->front->next;
- free(list->back);
+ llist_item_put(list->back);
}
free(list);
}
-inline void llist_init(struct llist **list)
+static inline void llist_init(struct llist **list)
{
*list = xmalloc(sizeof(struct llist));
(*list)->front = (*list)->back = NULL;
(*list)->size = 0;
}
-struct llist * llist_copy(struct llist *list)
+static struct llist * llist_copy(struct llist *list)
{
struct llist *ret;
struct llist_item *new, *old, *prev;
-
+
llist_init(&ret);
if ((ret->size = list->size) == 0)
return ret;
- new = ret->front = xmalloc(sizeof(struct llist_item));
+ new = ret->front = llist_item_get();
new->sha1 = list->front->sha1;
old = list->front->next;
while (old) {
prev = new;
- new = xmalloc(sizeof(struct llist_item));
+ new = llist_item_get();
prev->next = new;
new->sha1 = old->sha1;
old = old->next;
}
new->next = NULL;
ret->back = new;
-
+
return ret;
}
-inline struct llist_item * llist_insert(struct llist *list,
- struct llist_item *after, char *sha1)
+static inline struct llist_item *llist_insert(struct llist *list,
+ struct llist_item *after,
+ const unsigned char *sha1)
{
- struct llist_item *new = xmalloc(sizeof(struct llist_item));
+ struct llist_item *new = llist_item_get();
new->sha1 = sha1;
new->next = NULL;
return new;
}
-inline struct llist_item * llist_insert_back(struct llist *list, char *sha1)
+static inline struct llist_item *llist_insert_back(struct llist *list,
+ const unsigned char *sha1)
{
return llist_insert(list, list->back, sha1);
}
-inline struct llist_item * llist_insert_sorted_unique(struct llist *list,
- char *sha1, struct llist_item *hint)
+static inline struct llist_item *llist_insert_sorted_unique(struct llist *list,
+ const unsigned char *sha1, struct llist_item *hint)
{
struct llist_item *prev = NULL, *l;
l = (hint == NULL) ? list->front : hint;
while (l) {
- int cmp = memcmp(l->sha1, sha1, 20);
+ int cmp = hashcmp(l->sha1, sha1);
if (cmp > 0) { /* we insert before this entry */
return llist_insert(list, prev, sha1);
}
}
/* returns a pointer to an item in front of sha1 */
-inline struct llist_item * llist_sorted_remove(struct llist *list, char *sha1,
- struct llist_item *hint)
+static inline struct llist_item * llist_sorted_remove(struct llist *list, const unsigned char *sha1, struct llist_item *hint)
{
struct llist_item *prev, *l;
l = (hint == NULL) ? list->front : hint;
prev = NULL;
while (l) {
- int cmp = memcmp(l->sha1, sha1, 20);
+ int cmp = hashcmp(l->sha1, sha1);
if (cmp > 0) /* not in list, since sorted */
return prev;
if(!cmp) { /* found */
prev->next = l->next;
if (l == list->back)
list->back = prev;
- free(l);
+ llist_item_put(l);
list->size--;
return prev;
}
}
/* computes A\B */
-void llist_sorted_difference_inplace(struct llist *A,
+static void llist_sorted_difference_inplace(struct llist *A,
struct llist *B)
{
struct llist_item *hint, *b;
}
}
-inline struct pack_list * pack_list_insert(struct pack_list **pl,
+static inline struct pack_list * pack_list_insert(struct pack_list **pl,
struct pack_list *entry)
{
struct pack_list *p = xmalloc(sizeof(struct pack_list));
return p;
}
-inline size_t pack_list_size(struct pack_list *pl)
+static inline size_t pack_list_size(struct pack_list *pl)
{
size_t ret = 0;
while(pl) {
return ret;
}
-struct pack_list * pack_list_difference(struct pack_list *A,
- struct pack_list *B)
+static struct pack_list * pack_list_difference(const struct pack_list *A,
+ const struct pack_list *B)
{
- struct pack_list *ret, *pl;
+ struct pack_list *ret;
+ const struct pack_list *pl;
if (A == NULL)
return NULL;
return ret;
}
-void cmp_two_packs(struct pack_list *p1, struct pack_list *p2)
+static void cmp_two_packs(struct pack_list *p1, struct pack_list *p2)
{
- int p1_off, p2_off;
- void *p1_base, *p2_base;
+ unsigned long p1_off = 0, p2_off = 0, p1_step, p2_step;
+ const unsigned char *p1_base, *p2_base;
struct llist_item *p1_hint = NULL, *p2_hint = NULL;
-
- p1_off = p2_off = 256 * 4 + 4;
- p1_base = (void *)p1->pack->index_base;
- p2_base = (void *)p2->pack->index_base;
- while (p1_off <= p1->pack->index_size - 3 * 20 &&
- p2_off <= p2->pack->index_size - 3 * 20)
+ p1_base = p1->pack->index_data;
+ p2_base = p2->pack->index_data;
+ p1_base += 256 * 4 + ((p1->pack->index_version < 2) ? 4 : 8);
+ p2_base += 256 * 4 + ((p2->pack->index_version < 2) ? 4 : 8);
+ p1_step = (p1->pack->index_version < 2) ? 24 : 20;
+ p2_step = (p2->pack->index_version < 2) ? 24 : 20;
+
+ while (p1_off < p1->pack->num_objects * p1_step &&
+ p2_off < p2->pack->num_objects * p2_step)
{
- int cmp = memcmp(p1_base + p1_off, p2_base + p2_off, 20);
+ int cmp = hashcmp(p1_base + p1_off, p2_base + p2_off);
/* cmp ~ p1 - p2 */
if (cmp == 0) {
p1_hint = llist_sorted_remove(p1->unique_objects,
p1_base + p1_off, p1_hint);
p2_hint = llist_sorted_remove(p2->unique_objects,
p1_base + p1_off, p2_hint);
- p1_off+=24;
- p2_off+=24;
+ p1_off += p1_step;
+ p2_off += p2_step;
continue;
}
if (cmp < 0) { /* p1 has the object, p2 doesn't */
- p1_off+=24;
+ p1_off += p1_step;
} else { /* p2 has the object, p1 doesn't */
- p2_off+=24;
+ p2_off += p2_step;
}
}
}
-void pll_insert(struct pll **pll, struct pll **hint_table)
+static void pll_free(struct pll *l)
{
- struct pll *prev;
- int i = (*pll)->pl_size - 1;
-
- if (hint_table[i] == NULL) {
- hint_table[i--] = *pll;
- for (; i >= 0; --i) {
- if (hint_table[i] != NULL)
- break;
+ struct pll *old;
+ struct pack_list *opl;
+
+ while (l) {
+ old = l;
+ while (l->pl) {
+ opl = l->pl;
+ l->pl = opl->next;
+ free(opl);
}
- if (hint_table[i] == NULL) /* no elements in list */
- die("Why did this happen?");
+ l = l->next;
+ free(old);
}
-
- prev = hint_table[i];
- while (prev->next && prev->next->pl_size < (*pll)->pl_size)
- prev = prev->next;
-
- (*pll)->next = prev->next;
- prev->next = *pll;
}
/* all the permutations have to be free()d at the same time,
* since they refer to each other
*/
-struct pll * get_all_permutations(struct pack_list *list)
+static struct pll * get_permutations(struct pack_list *list, int n)
{
- struct pll *subset, *pll, *new_pll = NULL; /*silence warning*/
- static struct pll **hint = NULL;
- if (hint == NULL)
- hint = xcalloc(pack_list_size(list), sizeof(struct pll *));
-
- if (list == NULL)
+ struct pll *subset, *ret = NULL, *new_pll = NULL, *pll;
+
+ if (list == NULL || pack_list_size(list) < n || n == 0)
return NULL;
- if (list->next == NULL) {
- new_pll = xmalloc(sizeof(struct pll));
- hint[0] = new_pll;
- new_pll->next = NULL;
- new_pll->pl = list;
- new_pll->pl_size = 1;
- return new_pll;
+ if (n == 1) {
+ while (list) {
+ new_pll = xmalloc(sizeof(pll));
+ new_pll->pl = NULL;
+ pack_list_insert(&new_pll->pl, list);
+ new_pll->next = ret;
+ ret = new_pll;
+ list = list->next;
+ }
+ return ret;
}
- pll = subset = get_all_permutations(list->next);
- while (pll) {
- if (pll->pl->pack == list->pack) {
- pll = pll->next;
- continue;
+ while (list->next) {
+ subset = get_permutations(list->next, n - 1);
+ while (subset) {
+ new_pll = xmalloc(sizeof(pll));
+ new_pll->pl = subset->pl;
+ pack_list_insert(&new_pll->pl, list);
+ new_pll->next = ret;
+ ret = new_pll;
+ subset = subset->next;
}
- new_pll = xmalloc(sizeof(struct pll));
-
- new_pll->pl = xmalloc(sizeof(struct pack_list));
- memcpy(new_pll->pl, list, sizeof(struct pack_list));
- new_pll->pl->next = pll->pl;
- new_pll->pl_size = pll->pl_size + 1;
-
- pll_insert(&new_pll, hint);
-
- pll = pll->next;
- }
- /* add ourself */
- new_pll = xmalloc(sizeof(struct pll));
- new_pll->pl = xmalloc(sizeof(struct pack_list));
- memcpy(new_pll->pl, list, sizeof(struct pack_list));
- new_pll->pl->next = NULL;
- new_pll->pl_size = 1;
- pll_insert(&new_pll, hint);
-
- return hint[0];
+ list = list->next;
+ }
+ return ret;
}
-int is_superset(struct pack_list *pl, struct llist *list)
+static int is_superset(struct pack_list *pl, struct llist *list)
{
struct llist *diff;
diff = llist_copy(list);
while (pl) {
- llist_sorted_difference_inplace(diff,
- pl->all_objects);
+ llist_sorted_difference_inplace(diff, pl->all_objects);
if (diff->size == 0) { /* we're done */
llist_free(diff);
return 1;
return 0;
}
-size_t sizeof_union(struct packed_git *p1, struct packed_git *p2)
+static size_t sizeof_union(struct packed_git *p1, struct packed_git *p2)
{
size_t ret = 0;
- int p1_off, p2_off;
- void *p1_base, *p2_base;
-
- p1_off = p2_off = 256 * 4 + 4;
- p1_base = (void *)p1->index_base;
- p2_base = (void *)p2->index_base;
-
- while (p1_off <= p1->index_size - 3 * 20 &&
- p2_off <= p2->index_size - 3 * 20)
+ unsigned long p1_off = 0, p2_off = 0, p1_step, p2_step;
+ const unsigned char *p1_base, *p2_base;
+
+ p1_base = p1->index_data;
+ p2_base = p2->index_data;
+ p1_base += 256 * 4 + ((p1->index_version < 2) ? 4 : 8);
+ p2_base += 256 * 4 + ((p2->index_version < 2) ? 4 : 8);
+ p1_step = (p1->index_version < 2) ? 24 : 20;
+ p2_step = (p2->index_version < 2) ? 24 : 20;
+
+ while (p1_off < p1->num_objects * p1_step &&
+ p2_off < p2->num_objects * p2_step)
{
- int cmp = memcmp(p1_base + p1_off, p2_base + p2_off, 20);
+ int cmp = hashcmp(p1_base + p1_off, p2_base + p2_off);
/* cmp ~ p1 - p2 */
if (cmp == 0) {
ret++;
- p1_off+=24;
- p2_off+=24;
+ p1_off += p1_step;
+ p2_off += p2_step;
continue;
}
if (cmp < 0) { /* p1 has the object, p2 doesn't */
- p1_off+=24;
+ p1_off += p1_step;
} else { /* p2 has the object, p1 doesn't */
- p2_off+=24;
+ p2_off += p2_step;
}
}
return ret;
}
/* another O(n^2) function ... */
-size_t get_pack_redundancy(struct pack_list *pl)
+static size_t get_pack_redundancy(struct pack_list *pl)
{
struct pack_list *subset;
+ size_t ret = 0;
if (pl == NULL)
return 0;
- size_t ret = 0;
while ((subset = pl->next)) {
while(subset) {
ret += sizeof_union(pl->pack, subset->pack);
return ret;
}
-inline size_t pack_set_bytecount(struct pack_list *pl)
+static inline off_t pack_set_bytecount(struct pack_list *pl)
{
- size_t ret = 0;
+ off_t ret = 0;
while (pl) {
ret += pl->pack->pack_size;
ret += pl->pack->index_size;
return ret;
}
-void minimize(struct pack_list **min)
+static void minimize(struct pack_list **min)
{
struct pack_list *pl, *unique = NULL,
*non_unique = NULL, *min_perm = NULL;
struct pll *perm, *perm_all, *perm_ok = NULL, *new_perm;
struct llist *missing;
- size_t min_perm_size = (size_t)-1, perm_size;
+ off_t min_perm_size = 0, perm_size;
+ int n;
pl = local_packs;
while (pl) {
missing = llist_copy(all_objects);
pl = unique;
while (pl) {
- llist_sorted_difference_inplace(missing,
- pl->all_objects);
+ llist_sorted_difference_inplace(missing, pl->all_objects);
pl = pl->next;
}
}
/* find the permutations which contain all missing objects */
- perm_all = perm = get_all_permutations(non_unique);
- while (perm) {
- if (perm_ok && perm->pl_size > perm_ok->pl_size)
- break; /* ignore all larger permutations */
- if (is_superset(perm->pl, missing)) {
- new_perm = xmalloc(sizeof(struct pll));
- memcpy(new_perm, perm, sizeof(struct pll));
- new_perm->next = perm_ok;
- perm_ok = new_perm;
+ for (n = 1; n <= pack_list_size(non_unique) && !perm_ok; n++) {
+ perm_all = perm = get_permutations(non_unique, n);
+ while (perm) {
+ if (is_superset(perm->pl, missing)) {
+ new_perm = xmalloc(sizeof(struct pll));
+ memcpy(new_perm, perm, sizeof(struct pll));
+ new_perm->next = perm_ok;
+ perm_ok = new_perm;
+ }
+ perm = perm->next;
}
- perm = perm->next;
+ if (perm_ok)
+ break;
+ pll_free(perm_all);
}
-
if (perm_ok == NULL)
die("Internal error: No complete sets found!\n");
perm = perm_ok;
while (perm) {
perm_size = pack_set_bytecount(perm->pl);
- if (min_perm_size > perm_size) {
+ if (!min_perm_size || min_perm_size > perm_size) {
min_perm_size = perm_size;
min_perm = perm->pl;
}
}
}
-void load_all_objects()
+static void load_all_objects(void)
{
struct pack_list *pl = local_packs;
struct llist_item *hint, *l;
- int i;
llist_init(&all_objects);
while (pl) {
- i = 0;
hint = NULL;
l = pl->all_objects->front;
while (l) {
}
/* this scales like O(n^2) */
-void cmp_local_packs()
+static void cmp_local_packs(void)
{
struct pack_list *subset, *pl = local_packs;
}
}
-void scan_alt_odb_packs()
+static void scan_alt_odb_packs(void)
{
struct pack_list *local, *alt;
alt->all_objects);
local = local->next;
}
+ llist_sorted_difference_inplace(all_objects, alt->all_objects);
alt = alt->next;
}
}
-struct pack_list * add_pack(struct packed_git *p)
+static struct pack_list * add_pack(struct packed_git *p)
{
struct pack_list l;
- size_t off;
- void *base;
+ unsigned long off = 0, step;
+ const unsigned char *base;
if (!p->pack_local && !(alt_odb || verbose))
return NULL;
l.pack = p;
llist_init(&l.all_objects);
- off = 256 * 4 + 4;
- base = (void *)p->index_base;
- while (off <= p->index_size - 3 * 20) {
+ if (open_pack_index(p))
+ return NULL;
+
+ base = p->index_data;
+ base += 256 * 4 + ((p->index_version < 2) ? 4 : 8);
+ step = (p->index_version < 2) ? 24 : 20;
+ while (off < p->num_objects * step) {
llist_insert_back(l.all_objects, base + off);
- off += 24;
+ off += step;
}
/* this list will be pruned in cmp_two_packs later */
l.unique_objects = llist_copy(l.all_objects);
return pack_list_insert(&altodb_packs, &l);
}
-struct pack_list * add_pack_file(char *filename)
+static struct pack_list * add_pack_file(char *filename)
{
struct packed_git *p = packed_git;
die("Filename %s not found in packed_git\n", filename);
}
-void load_all()
+static void load_all(void)
{
struct packed_git *p = packed_git;
{
int i;
struct pack_list *min, *red, *pl;
+ struct llist *ignore;
+ unsigned char *sha1;
+ char buf[42]; /* 40 byte sha1 + \n + \0 */
+
+ setup_git_directory();
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
if (alt_odb)
scan_alt_odb_packs();
+ /* ignore objects given on stdin */
+ llist_init(&ignore);
+ if (!isatty(0)) {
+ while (fgets(buf, sizeof(buf), stdin)) {
+ sha1 = xmalloc(20);
+ if (get_sha1_hex(buf, sha1))
+ die("Bad sha1 on stdin: %s", buf);
+ llist_insert_sorted_unique(ignore, sha1, NULL);
+ }
+ }
+ llist_sorted_difference_inplace(all_objects, ignore);
+ pl = local_packs;
+ while (pl) {
+ llist_sorted_difference_inplace(pl->unique_objects, ignore);
+ pl = pl->next;
+ }
+
minimize(&min);
if (verbose) {
pl->pack->pack_name);
pl = pl->next;
}
+ if (verbose)
+ fprintf(stderr, "%luMB of redundant packs in total.\n",
+ (unsigned long)pack_set_bytecount(red)/(1024*1024));
return 0;
}