#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 "diff.h"
+#include "tree-walk.h"
#include <sys/time.h>
#include <signal.h>
static const char *base_name;
static unsigned char pack_file_sha1[20];
static int progress = 1;
-static volatile int progress_update = 0;
+static volatile sig_atomic_t progress_update = 0;
/*
* The object names in objects array are hashed with this hashtable,
if (object_ix_hashsz < 1024)
object_ix_hashsz = 1024;
object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz);
- object_ix = memset(object_ix, 0, 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)
* but close enough.
*/
hash = (name_hash<<DIRBITS) | (hash & ((1U<<DIRBITS )-1));
-
- if (0) { /* debug */
- n = name + strlen(name);
- if (n != name && n[-1] == '\n')
- n--;
- while (name <= --n)
- fputc(*n, stderr);
- for (p = path; p; p = p->up) {
- fputc('/', stderr);
- n = p->elem + p->len;
- while (p->elem <= --n)
- fputc(*n, stderr);
- }
- fprintf(stderr, "\t%08x\n", hash);
- }
return hash;
}
return status;
}
-static void add_pbase_tree(struct tree_desc *tree, struct name_path *up)
+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 name_cmp_len(const char *name)
+{
+ int i;
+ for (i = 0; name[i] && name[i] != '\n' && name[i] != '/'; i++)
+ ;
+ return i;
+}
+
+static void add_pbase_object(struct tree_desc *tree,
+ struct name_path *up,
+ const char *name,
+ int cmplen)
{
while (tree->size) {
const unsigned char *sha1;
- const char *name;
- unsigned mode, hash;
+ const char *entry_name;
+ int entry_len;
+ unsigned mode;
unsigned long size;
char type[20];
- sha1 = tree_entry_extract(tree, &name, &mode);
+ sha1 = tree_entry_extract(tree, &entry_name, &mode);
update_tree_entry(tree);
- if (!has_sha1_file(sha1))
- continue;
- if (sha1_object_info(sha1, type, &size))
+ entry_len = strlen(entry_name);
+ if (entry_len != cmplen ||
+ memcmp(entry_name, name, cmplen) ||
+ !has_sha1_file(sha1) ||
+ sha1_object_info(sha1, type, &size))
continue;
-
- hash = name_hash(up, name);
- if (!add_object_entry(sha1, hash, 1))
- continue;
-
- if (!strcmp(type, "tree")) {
+ if (name[cmplen] != '/') {
+ unsigned hash = name_hash(up, name);
+ add_object_entry(sha1, hash, 1);
+ return;
+ }
+ if (!strcmp(type, tree_type)) {
struct tree_desc sub;
- void *elem;
struct name_path me;
+ struct pbase_tree_cache *tree;
+ const char *down = name+cmplen+1;
+ int downlen = name_cmp_len(down);
+
+ tree = pbase_tree_get(sha1);
+ if (!tree)
+ return;
+ sub.buf = tree->tree_data;
+ sub.size = tree->tree_size;
+
+ me.up = up;
+ me.elem = entry_name;
+ me.len = entry_len;
+ add_pbase_object(&sub, &me, down, downlen);
+ pbase_tree_put(tree);
+ }
+ }
+}
- elem = read_sha1_file(sha1, type, &sub.size);
- sub.buf = elem;
- if (sub.buf) {
- me.up = up;
- me.elem = name;
- me.len = strlen(name);
- add_pbase_tree(&sub, &me);
- free(elem);
- }
+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 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(NULL, "");
+ 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, NULL, name, cmplen);
}
}
}
static void add_preferred_base(unsigned char *sha1)
{
- struct tree_desc tree;
- void *elem;
+ struct pbase_tree *it;
+ void *data;
+ unsigned long size;
+ unsigned char tree_sha1[20];
- elem = read_object_with_reference(sha1, "tree", &tree.size, NULL);
- tree.buf = elem;
- if (!tree.buf)
+ data = read_object_with_reference(sha1, tree_type, &size, tree_sha1);
+ if (!data)
return;
- if (add_object_entry(sha1, name_hash(NULL, ""), 1))
- add_pbase_tree(&tree, NULL);
- free(elem);
+
+ 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)
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",
max_depth -= cur_entry->delta_limit;
}
- size = cur_entry->size;
- oldsize = old_entry->size;
- sizediff = oldsize > size ? oldsize - size : size - oldsize;
-
- if (size < 50)
- return -1;
if (old_entry->depth >= max_depth)
return 0;
* more space-efficient (deletes don't have to say _what_ they
* delete).
*/
+ size = cur_entry->size;
max_size = size / 2 - 20;
if (cur_entry->delta)
max_size = cur_entry->delta_size-1;
+ oldsize = old_entry->size;
+ sizediff = oldsize < size ? size - oldsize : 0;
if (sizediff >= max_size)
- return -1;
+ return 0;
delta_buf = diff_delta(old->data, oldsize,
cur->data, size, &delta_size, max_size);
if (!delta_buf)
static void progress_interval(int signum)
{
- signal(SIGALRM, progress_interval);
progress_update = 1;
}
*/
continue;
+ if (entry->size < 50)
+ continue;
+
free(n->data);
n->entry = entry;
n->data = read_sha1_file(entry->sha1, type, &size);
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;
setup_git_directory();
prepare_packed_git();
if (progress) {
- struct itimerval v;
- v.it_interval.tv_sec = 1;
- v.it_interval.tv_usec = 0;
- v.it_value = v.it_interval;
- signal(SIGALRM, progress_interval);
- setitimer(ITIMER_REAL, &v, NULL);
fprintf(stderr, "Generating pack...\n");
+ setup_progress_signal();
}
- while (fgets(line, sizeof(line), stdin) != NULL) {
+ for (;;) {
unsigned char sha1[20];
+ unsigned hash;
+
+ 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);
- add_preferred_base(sha1);
+ if (num_preferred_base++ < window)
+ add_preferred_base(sha1);
continue;
}
if (get_sha1_hex(line, sha1))
die("expected sha1, got garbage:\n %s", line);
- add_object_entry(sha1, name_hash(NULL, line+41), 0);
+ hash = name_hash(NULL, 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);