-#include "cache.h"
+#include "builtin.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
static const char index_pack_usage[] =
"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
-struct object_entry
-{
+struct object_entry {
struct pack_idx_entry idx;
unsigned long size;
unsigned int hdr_size;
enum object_type type;
enum object_type real_type;
+ unsigned delta_depth;
+ int base_object_no;
};
union delta_base {
struct object_entry *obj;
void *data;
unsigned long size;
+ int ref_first, ref_last;
+ int ofs_first, ofs_last;
};
/*
#define FLAG_LINK (1u<<20)
#define FLAG_CHECKED (1u<<21)
-struct delta_entry
-{
+struct delta_entry {
union delta_base base;
int obj_no;
};
static unsigned char input_buffer[4096];
static unsigned int input_offset, input_len;
static off_t consumed_bytes;
+static unsigned deepest_delta;
static git_SHA_CTX input_ctx;
static uint32_t input_crc32;
static int input_fd, output_fd, pack_fd;
if (from_stdin) {
input_fd = 0;
if (!pack_name) {
- static char tmpfile[PATH_MAX];
- output_fd = odb_mkstemp(tmpfile, sizeof(tmpfile),
+ static char tmp_file[PATH_MAX];
+ output_fd = odb_mkstemp(tmp_file, sizeof(tmp_file),
"pack/tmp_pack_XXXXXX");
- pack_name = xstrdup(tmpfile);
+ pack_name = xstrdup(tmp_file);
} else
output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
if (output_fd < 0)
static NORETURN void bad_object(unsigned long offset, const char *format,
...) __attribute__((format (printf, 2, 3)));
-static void bad_object(unsigned long offset, const char *format, ...)
+static NORETURN void bad_object(unsigned long offset, const char *format, ...)
{
va_list params;
char buf[1024];
die("pack has bad object at offset %lu: %s", offset, buf);
}
+static struct base_data *alloc_base_data(void)
+{
+ struct base_data *base = xmalloc(sizeof(struct base_data));
+ memset(base, 0, sizeof(*base));
+ base->ref_last = -1;
+ base->ofs_last = -1;
+ return base;
+}
+
static void free_base_data(struct base_data *c)
{
if (c->data) {
static void *unpack_entry_data(unsigned long offset, unsigned long size)
{
int status;
- z_stream stream;
+ git_zstream stream;
void *buf = xmalloc(size);
memset(&stream, 0, sizeof(stream));
void *data;
obj->idx.offset = consumed_bytes;
- input_crc32 = crc32(0, Z_NULL, 0);
+ input_crc32 = crc32(0, NULL, 0);
p = fill(1);
c = *p;
off_t from = obj[0].idx.offset + obj[0].hdr_size;
unsigned long len = obj[1].idx.offset - from;
unsigned char *data, *inbuf;
- z_stream stream;
+ git_zstream stream;
int status;
data = xmalloc(obj->size);
return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
}
+/*
+ * This function is part of find_unresolved_deltas(). There are two
+ * walkers going in the opposite ways.
+ *
+ * The first one in find_unresolved_deltas() traverses down from
+ * parent node to children, deflating nodes along the way. However,
+ * memory for deflated nodes is limited by delta_base_cache_limit, so
+ * at some point parent node's deflated content may be freed.
+ *
+ * The second walker is this function, which goes from current node up
+ * to top parent if necessary to deflate the node. In normal
+ * situation, its parent node would be already deflated, so it just
+ * needs to apply delta.
+ *
+ * In the worst case scenario, parent node is no longer deflated because
+ * we're running out of delta_base_cache_limit; we need to re-deflate
+ * parents, possibly up to the top base.
+ *
+ * All deflated objects here are subject to be freed if we exceed
+ * delta_base_cache_limit, just like in find_unresolved_deltas(), we
+ * just need to make sure the last node is not freed.
+ */
static void *get_base_data(struct base_data *c)
{
if (!c->data) {
struct object_entry *obj = c->obj;
+ struct base_data **delta = NULL;
+ int delta_nr = 0, delta_alloc = 0;
- if (is_delta_type(obj->type)) {
- void *base = get_base_data(c->base);
- void *raw = get_data_from_pack(obj);
+ while (is_delta_type(c->obj->type) && !c->data) {
+ ALLOC_GROW(delta, delta_nr + 1, delta_alloc);
+ delta[delta_nr++] = c;
+ c = c->base;
+ }
+ if (!delta_nr) {
+ c->data = get_data_from_pack(obj);
+ c->size = obj->size;
+ base_cache_used += c->size;
+ prune_base_data(c);
+ }
+ for (; delta_nr > 0; delta_nr--) {
+ void *base, *raw;
+ c = delta[delta_nr - 1];
+ obj = c->obj;
+ base = get_base_data(c->base);
+ raw = get_data_from_pack(obj);
c->data = patch_delta(
base, c->base->size,
raw, obj->size,
free(raw);
if (!c->data)
bad_object(obj->idx.offset, "failed to apply delta");
- } else {
- c->data = get_data_from_pack(obj);
- c->size = obj->size;
+ base_cache_used += c->size;
+ prune_base_data(c);
}
-
- base_cache_used += c->size;
- prune_base_data(c);
+ free(delta);
}
return c->data;
}
void *base_data, *delta_data;
delta_obj->real_type = base->obj->real_type;
+ delta_obj->delta_depth = base->obj->delta_depth + 1;
+ if (deepest_delta < delta_obj->delta_depth)
+ deepest_delta = delta_obj->delta_depth;
+ delta_obj->base_object_no = base->obj - objects;
delta_data = get_data_from_pack(delta_obj);
base_data = get_base_data(base);
result->obj = delta_obj;
nr_resolved_deltas++;
}
-static void find_unresolved_deltas(struct base_data *base,
- struct base_data *prev_base)
+static struct base_data *find_unresolved_deltas_1(struct base_data *base,
+ struct base_data *prev_base)
{
- int i, ref_first, ref_last, ofs_first, ofs_last;
-
- /*
- * This is a recursive function. Those brackets should help reducing
- * stack usage by limiting the scope of the delta_base union.
- */
- {
+ if (base->ref_last == -1 && base->ofs_last == -1) {
union delta_base base_spec;
hashcpy(base_spec.sha1, base->obj->idx.sha1);
find_delta_children(&base_spec,
- &ref_first, &ref_last, OBJ_REF_DELTA);
+ &base->ref_first, &base->ref_last, OBJ_REF_DELTA);
memset(&base_spec, 0, sizeof(base_spec));
base_spec.offset = base->obj->idx.offset;
find_delta_children(&base_spec,
- &ofs_first, &ofs_last, OBJ_OFS_DELTA);
- }
+ &base->ofs_first, &base->ofs_last, OBJ_OFS_DELTA);
- if (ref_last == -1 && ofs_last == -1) {
- free(base->data);
- return;
- }
+ if (base->ref_last == -1 && base->ofs_last == -1) {
+ free(base->data);
+ return NULL;
+ }
- link_base_data(prev_base, base);
+ link_base_data(prev_base, base);
+ }
- for (i = ref_first; i <= ref_last; i++) {
- struct object_entry *child = objects + deltas[i].obj_no;
- struct base_data result;
+ if (base->ref_first <= base->ref_last) {
+ struct object_entry *child = objects + deltas[base->ref_first].obj_no;
+ struct base_data *result = alloc_base_data();
assert(child->real_type == OBJ_REF_DELTA);
- resolve_delta(child, base, &result);
- if (i == ref_last && ofs_last == -1)
+ resolve_delta(child, base, result);
+ if (base->ref_first == base->ref_last && base->ofs_last == -1)
free_base_data(base);
- find_unresolved_deltas(&result, base);
+
+ base->ref_first++;
+ return result;
}
- for (i = ofs_first; i <= ofs_last; i++) {
- struct object_entry *child = objects + deltas[i].obj_no;
- struct base_data result;
+ if (base->ofs_first <= base->ofs_last) {
+ struct object_entry *child = objects + deltas[base->ofs_first].obj_no;
+ struct base_data *result = alloc_base_data();
assert(child->real_type == OBJ_OFS_DELTA);
- resolve_delta(child, base, &result);
- if (i == ofs_last)
+ resolve_delta(child, base, result);
+ if (base->ofs_first == base->ofs_last)
free_base_data(base);
- find_unresolved_deltas(&result, base);
+
+ base->ofs_first++;
+ return result;
}
unlink_base_data(base);
+ return NULL;
+}
+
+static void find_unresolved_deltas(struct base_data *base)
+{
+ struct base_data *new_base, *prev_base = NULL;
+ for (;;) {
+ new_base = find_unresolved_deltas_1(base, prev_base);
+
+ if (new_base) {
+ prev_base = base;
+ base = new_base;
+ } else {
+ free(base);
+ base = prev_base;
+ if (!base)
+ return;
+ prev_base = base->base;
+ }
+ }
}
static int compare_delta_entry(const void *a, const void *b)
progress = start_progress("Resolving deltas", nr_deltas);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
- struct base_data base_obj;
+ struct base_data *base_obj = alloc_base_data();
if (is_delta_type(obj->type))
continue;
- base_obj.obj = obj;
- base_obj.data = NULL;
- find_unresolved_deltas(&base_obj, NULL);
+ base_obj->obj = obj;
+ base_obj->data = NULL;
+ find_unresolved_deltas(base_obj);
display_progress(progress, nr_resolved_deltas);
}
}
static int write_compressed(struct sha1file *f, void *in, unsigned int size)
{
- z_stream stream;
+ git_zstream stream;
int status;
unsigned char outbuf[4096];
memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, zlib_compression_level);
+ git_deflate_init(&stream, zlib_compression_level);
stream.next_in = in;
stream.avail_in = size;
do {
stream.next_out = outbuf;
stream.avail_out = sizeof(outbuf);
- status = deflate(&stream, Z_FINISH);
+ status = git_deflate(&stream, Z_FINISH);
sha1write(f, outbuf, sizeof(outbuf) - stream.avail_out);
} while (status == Z_OK);
if (status != Z_STREAM_END)
die("unable to deflate appended object (%d)", status);
size = stream.total_out;
- deflateEnd(&stream);
+ git_deflate_end(&stream);
return size;
}
for (i = 0; i < n; i++) {
struct delta_entry *d = sorted_by_pos[i];
enum object_type type;
- struct base_data base_obj;
+ struct base_data *base_obj = alloc_base_data();
if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
continue;
- base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size);
- if (!base_obj.data)
+ base_obj->data = read_sha1_file(d->base.sha1, &type, &base_obj->size);
+ if (!base_obj->data)
continue;
- if (check_sha1_signature(d->base.sha1, base_obj.data,
- base_obj.size, typename(type)))
+ if (check_sha1_signature(d->base.sha1, base_obj->data,
+ base_obj->size, typename(type)))
die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
- base_obj.obj = append_obj_to_pack(f, d->base.sha1,
- base_obj.data, base_obj.size, type);
- find_unresolved_deltas(&base_obj, NULL);
+ base_obj->obj = append_obj_to_pack(f, d->base.sha1,
+ base_obj->data, base_obj->size, type);
+ find_unresolved_deltas(base_obj);
display_progress(progress, nr_resolved_deltas);
}
free(sorted_by_pos);
free(p);
}
+static void show_pack_info(int stat_only)
+{
+ int i, baseobjects = nr_objects - nr_deltas;
+ unsigned long *chain_histogram = NULL;
+
+ if (deepest_delta)
+ chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long));
+
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = &objects[i];
+
+ if (is_delta_type(obj->type))
+ chain_histogram[obj->delta_depth - 1]++;
+ if (stat_only)
+ continue;
+ printf("%s %-6s %lu %lu %"PRIuMAX,
+ sha1_to_hex(obj->idx.sha1),
+ typename(obj->real_type), obj->size,
+ (unsigned long)(obj[1].idx.offset - obj->idx.offset),
+ (uintmax_t)obj->idx.offset);
+ if (is_delta_type(obj->type)) {
+ struct object_entry *bobj = &objects[obj->base_object_no];
+ printf(" %u %s", obj->delta_depth, sha1_to_hex(bobj->idx.sha1));
+ }
+ putchar('\n');
+ }
+
+ if (baseobjects)
+ printf("non delta: %d object%s\n",
+ baseobjects, baseobjects > 1 ? "s" : "");
+ for (i = 0; i < deepest_delta; i++) {
+ if (!chain_histogram[i])
+ continue;
+ printf("chain length = %d: %lu object%s\n",
+ i + 1,
+ chain_histogram[i],
+ chain_histogram[i] > 1 ? "s" : "");
+ }
+}
+
int cmd_index_pack(int argc, const char **argv, const char *prefix)
{
- int i, fix_thin_pack = 0, verify = 0;
+ int i, fix_thin_pack = 0, verify = 0, stat_only = 0, stat = 0;
const char *curr_pack, *curr_index;
const char *index_name = NULL, *pack_name = NULL;
const char *keep_name = NULL, *keep_msg = NULL;
strict = 1;
} else if (!strcmp(arg, "--verify")) {
verify = 1;
+ } else if (!strcmp(arg, "--verify-stat")) {
+ verify = 1;
+ stat = 1;
+ } else if (!strcmp(arg, "--verify-stat-only")) {
+ verify = 1;
+ stat = 1;
+ stat_only = 1;
} else if (!strcmp(arg, "--keep")) {
keep_msg = "";
} else if (!prefixcmp(arg, "--keep=")) {
if (!index_name)
die("--verify with no packfile name given");
read_idx_option(&opts, index_name);
- opts.flags |= WRITE_IDX_VERIFY;
+ opts.flags |= WRITE_IDX_VERIFY | WRITE_IDX_STRICT;
}
+ if (strict)
+ opts.flags |= WRITE_IDX_STRICT;
curr_pack = open_pack_file(pack_name);
parse_pack_header();
- objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
- deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
+ objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
+ deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
parse_pack_objects(pack_sha1);
if (nr_deltas == nr_resolved_deltas) {
stop_progress(&progress);
if (strict)
check_objects();
+ if (stat)
+ show_pack_info(stat_only);
+
idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
for (i = 0; i < nr_objects; i++)
idx_objects[i] = &objects[i].idx;