mirrors/git
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'nd/slim-index-pack-memory-usage'

Browse Source 
Memory usage of "git index-pack" has been trimmed by tens of
per-cent.

* nd/slim-index-pack-memory-usage:
  index-pack: kill union delta_base to save memory
  index-pack: reduce object_entry size to save memory
This commit is contained in:
Junio C Hamano
2015-05-11 14:23:44 -07:00
parent 84e55dcb34 c6458e60ed
commit eb10a85098
1 changed files with 177 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

286
builtin/index-pack.c
View File

@ -18,16 +18,14 @@ static const char index_pack_usage[] =
struct object_entry { struct object_entry {
struct pack_idx_entry idx; struct pack_idx_entry idx;
unsigned long size; unsigned long size;
unsigned int hdr_size; unsigned char hdr_size;
enum object_type type; signed char type;
enum object_type real_type; signed char real_type;
unsigned delta_depth;
int base_object_no;
}; };
union delta_base { struct object_stat {
unsigned char sha1[20]; unsigned delta_depth;
off_t offset; int base_object_no;
}; };
struct base_data { struct base_data {
@ -49,25 +47,28 @@ struct thread_local {
int pack_fd; int pack_fd;
}; };
/*
* Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
* to memcmp() only the first 20 bytes.
*/
#define UNION_BASE_SZ 20
#define FLAG_LINK (1u<<20) #define FLAG_LINK (1u<<20)
#define FLAG_CHECKED (1u<<21) #define FLAG_CHECKED (1u<<21)
struct delta_entry { struct ofs_delta_entry {
union delta_base base; off_t offset;
int obj_no;
};
struct ref_delta_entry {
unsigned char sha1[20];
int obj_no; int obj_no;
}; };
static struct object_entry *objects; static struct object_entry *objects;
static struct delta_entry *deltas; static struct object_stat *obj_stat;
static struct ofs_delta_entry *ofs_deltas;
static struct ref_delta_entry *ref_deltas;
static struct thread_local nothread_data; static struct thread_local nothread_data;
static int nr_objects; static int nr_objects;
static int nr_deltas; static int nr_ofs_deltas;
static int nr_ref_deltas;
static int ref_deltas_alloc;
static int nr_resolved_deltas; static int nr_resolved_deltas;
static int nr_threads; static int nr_threads;
@ -476,7 +477,8 @@ static void *unpack_entry_data(unsigned long offset, unsigned long size,
} }
static void *unpack_raw_entry(struct object_entry *obj, static void *unpack_raw_entry(struct object_entry *obj,
union delta_base *delta_base, off_t *ofs_offset,
unsigned char *ref_sha1,
unsigned char *sha1) unsigned char *sha1)
{ {
unsigned char *p; unsigned char *p;
@ -505,11 +507,10 @@ static void *unpack_raw_entry(struct object_entry *obj,
switch (obj->type) { switch (obj->type) {
case OBJ_REF_DELTA: case OBJ_REF_DELTA:
hashcpy(delta_base->sha1, fill(20)); hashcpy(ref_sha1, fill(20));
use(20); use(20);
break; break;
case OBJ_OFS_DELTA: case OBJ_OFS_DELTA:
memset(delta_base, 0, sizeof(*delta_base));
p = fill(1); p = fill(1);
c = *p; c = *p;
use(1); use(1);
@ -523,8 +524,8 @@ static void *unpack_raw_entry(struct object_entry *obj,
use(1); use(1);
base_offset = (base_offset << 7) + (c & 127); base_offset = (base_offset << 7) + (c & 127);
} }
delta_base->offset = obj->idx.offset - base_offset; *ofs_offset = obj->idx.offset - base_offset;
if (delta_base->offset <= 0 || delta_base->offset >= obj->idx.offset) if (*ofs_offset <= 0 || *ofs_offset >= obj->idx.offset)
bad_object(obj->idx.offset, _("delta base offset is out of bound")); bad_object(obj->idx.offset, _("delta base offset is out of bound"));
break; break;
case OBJ_COMMIT: case OBJ_COMMIT:
@ -608,55 +609,108 @@ static void *get_data_from_pack(struct object_entry *obj)
return unpack_data(obj, NULL, NULL); return unpack_data(obj, NULL, NULL);
} }
static int compare_delta_bases(const union delta_base *base1, static int compare_ofs_delta_bases(off_t offset1, off_t offset2,
const union delta_base *base2, enum object_type type1,
enum object_type type1, enum object_type type2)
enum object_type type2)
{ {
int cmp = type1 - type2; int cmp = type1 - type2;
if (cmp) if (cmp)
return cmp; return cmp;
return memcmp(base1, base2, UNION_BASE_SZ); return offset1 - offset2;
} }
static int find_delta(const union delta_base *base, enum object_type type) static int find_ofs_delta(const off_t offset, enum object_type type)
{ {
int first = 0, last = nr_deltas; int first = 0, last = nr_ofs_deltas;
while (first < last) { while (first < last) {
int next = (first + last) / 2; int next = (first + last) / 2;
struct delta_entry *delta = &deltas[next]; struct ofs_delta_entry *delta = &ofs_deltas[next];
int cmp; int cmp;
cmp = compare_delta_bases(base, &delta->base, cmp = compare_ofs_delta_bases(offset, delta->offset,
type, objects[delta->obj_no].type); type, objects[delta->obj_no].type);
if (!cmp) if (!cmp)
return next; return next;
if (cmp < 0) { if (cmp < 0) {
last = next; last = next;
continue; continue;
} }
first = next+1; first = next+1;
} }
return -first-1; return -first-1;
} }
static void find_delta_children(const union delta_base *base, static void find_ofs_delta_children(off_t offset,
int *first_index, int *last_index, int *first_index, int *last_index,
enum object_type type) enum object_type type)
{ {
int first = find_delta(base, type); int first = find_ofs_delta(offset, type);
int last = first; int last = first;
int end = nr_deltas - 1; int end = nr_ofs_deltas - 1;
if (first < 0) { if (first < 0) {
*first_index = 0; *first_index = 0;
*last_index = -1; *last_index = -1;
return; return;
} }
while (first > 0 && !memcmp(&deltas[first - 1].base, base, UNION_BASE_SZ)) while (first > 0 && ofs_deltas[first - 1].offset == offset)
--first; --first;
while (last < end && !memcmp(&deltas[last + 1].base, base, UNION_BASE_SZ)) while (last < end && ofs_deltas[last + 1].offset == offset)
++last;
*first_index = first;
*last_index = last;
}
static int compare_ref_delta_bases(const unsigned char *sha1,
const unsigned char *sha2,
enum object_type type1,
enum object_type type2)
{
int cmp = type1 - type2;
if (cmp)
return cmp;
return hashcmp(sha1, sha2);
}
static int find_ref_delta(const unsigned char *sha1, enum object_type type)
{
int first = 0, last = nr_ref_deltas;
while (first < last) {
int next = (first + last) / 2;
struct ref_delta_entry *delta = &ref_deltas[next];
int cmp;
cmp = compare_ref_delta_bases(sha1, delta->sha1,
type, objects[delta->obj_no].type);
if (!cmp)
return next;
if (cmp < 0) {
last = next;
continue;
}
first = next+1;
}
return -first-1;
}
static void find_ref_delta_children(const unsigned char *sha1,
int *first_index, int *last_index,
enum object_type type)
{
int first = find_ref_delta(sha1, type);
int last = first;
int end = nr_ref_deltas - 1;
if (first < 0) {
*first_index = 0;
*last_index = -1;
return;
}
while (first > 0 && !hashcmp(ref_deltas[first - 1].sha1, sha1))
--first;
while (last < end && !hashcmp(ref_deltas[last + 1].sha1, sha1))
++last; ++last;
*first_index = first; *first_index = first;
*last_index = last; *last_index = last;
@ -873,13 +927,15 @@ static void resolve_delta(struct object_entry *delta_obj,
void *base_data, *delta_data; void *base_data, *delta_data;
if (show_stat) { if (show_stat) {
delta_obj->delta_depth = base->obj->delta_depth + 1; int i = delta_obj - objects;
int j = base->obj - objects;
obj_stat[i].delta_depth = obj_stat[j].delta_depth + 1;
deepest_delta_lock(); deepest_delta_lock();
if (deepest_delta < delta_obj->delta_depth) if (deepest_delta < obj_stat[i].delta_depth)
deepest_delta = delta_obj->delta_depth; deepest_delta = obj_stat[i].delta_depth;
deepest_delta_unlock(); deepest_delta_unlock();
obj_stat[i].base_object_no = j;
} }
delta_obj->base_object_no = base->obj - objects;
delta_data = get_data_from_pack(delta_obj); delta_data = get_data_from_pack(delta_obj);
base_data = get_base_data(base); base_data = get_base_data(base);
result->obj = delta_obj; result->obj = delta_obj;
@ -902,7 +958,7 @@ static void resolve_delta(struct object_entry *delta_obj,
* "want"; if so, swap in "set" and return true. Otherwise, leave it untouched * "want"; if so, swap in "set" and return true. Otherwise, leave it untouched
* and return false. * and return false.
*/ */
static int compare_and_swap_type(enum object_type *type, static int compare_and_swap_type(signed char *type,
enum object_type want, enum object_type want,
enum object_type set) enum object_type set)
{ {
@ -921,16 +977,13 @@ static struct base_data *find_unresolved_deltas_1(struct base_data *base,
struct base_data *prev_base) struct base_data *prev_base)
{ {
if (base->ref_last == -1 && base->ofs_last == -1) { if (base->ref_last == -1 && base->ofs_last == -1) {
union delta_base base_spec; find_ref_delta_children(base->obj->idx.sha1,
&base->ref_first, &base->ref_last,
OBJ_REF_DELTA);
hashcpy(base_spec.sha1, base->obj->idx.sha1); find_ofs_delta_children(base->obj->idx.offset,
find_delta_children(&base_spec, &base->ofs_first, &base->ofs_last,
&base->ref_first, &base->ref_last, OBJ_REF_DELTA); OBJ_OFS_DELTA);
memset(&base_spec, 0, sizeof(base_spec));
base_spec.offset = base->obj->idx.offset;
find_delta_children(&base_spec,
&base->ofs_first, &base->ofs_last, OBJ_OFS_DELTA);
if (base->ref_last == -1 && base->ofs_last == -1) { if (base->ref_last == -1 && base->ofs_last == -1) {
free(base->data); free(base->data);
@ -941,7 +994,7 @@ static struct base_data *find_unresolved_deltas_1(struct base_data *base,
} }
if (base->ref_first <= base->ref_last) { if (base->ref_first <= base->ref_last) {
struct object_entry *child = objects + deltas[base->ref_first].obj_no; struct object_entry *child = objects + ref_deltas[base->ref_first].obj_no;
struct base_data *result = alloc_base_data(); struct base_data *result = alloc_base_data();
if (!compare_and_swap_type(&child->real_type, OBJ_REF_DELTA, if (!compare_and_swap_type(&child->real_type, OBJ_REF_DELTA,
@ -957,7 +1010,7 @@ static struct base_data *find_unresolved_deltas_1(struct base_data *base,
} }
if (base->ofs_first <= base->ofs_last) { if (base->ofs_first <= base->ofs_last) {
struct object_entry *child = objects + deltas[base->ofs_first].obj_no; struct object_entry *child = objects + ofs_deltas[base->ofs_first].obj_no;
struct base_data *result = alloc_base_data(); struct base_data *result = alloc_base_data();
assert(child->real_type == OBJ_OFS_DELTA); assert(child->real_type == OBJ_OFS_DELTA);
@ -993,15 +1046,20 @@ static void find_unresolved_deltas(struct base_data *base)
} }
} }
static int compare_delta_entry(const void *a, const void *b) static int compare_ofs_delta_entry(const void *a, const void *b)
{ {
const struct delta_entry *delta_a = a; const struct ofs_delta_entry *delta_a = a;
const struct delta_entry *delta_b = b; const struct ofs_delta_entry *delta_b = b;
/* group by type (ref vs ofs) and then by value (sha-1 or offset) */ return delta_a->offset - delta_b->offset;
return compare_delta_bases(&delta_a->base, &delta_b->base, }
objects[delta_a->obj_no].type,
objects[delta_b->obj_no].type); static int compare_ref_delta_entry(const void *a, const void *b)
{
const struct ref_delta_entry *delta_a = a;
const struct ref_delta_entry *delta_b = b;
return hashcmp(delta_a->sha1, delta_b->sha1);
} }
static void resolve_base(struct object_entry *obj) static void resolve_base(struct object_entry *obj)
@ -1047,7 +1105,8 @@ static void *threaded_second_pass(void *data)
static void parse_pack_objects(unsigned char *sha1) static void parse_pack_objects(unsigned char *sha1)
{ {
int i, nr_delays = 0; int i, nr_delays = 0;
struct delta_entry *delta = deltas; struct ofs_delta_entry *ofs_delta = ofs_deltas;
unsigned char ref_delta_sha1[20];
struct stat st; struct stat st;
if (verbose) if (verbose)
@ -1056,12 +1115,18 @@ static void parse_pack_objects(unsigned char *sha1)
nr_objects); nr_objects);
for (i = 0; i < nr_objects; i++) { for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i]; struct object_entry *obj = &objects[i];
void *data = unpack_raw_entry(obj, &delta->base, obj->idx.sha1); void *data = unpack_raw_entry(obj, &ofs_delta->offset,
ref_delta_sha1, obj->idx.sha1);
obj->real_type = obj->type; obj->real_type = obj->type;
if (is_delta_type(obj->type)) { if (obj->type == OBJ_OFS_DELTA) {
nr_deltas++; nr_ofs_deltas++;
delta->obj_no = i; ofs_delta->obj_no = i;
delta++; ofs_delta++;
} else if (obj->type == OBJ_REF_DELTA) {
ALLOC_GROW(ref_deltas, nr_ref_deltas + 1, ref_deltas_alloc);
hashcpy(ref_deltas[nr_ref_deltas].sha1, ref_delta_sha1);
ref_deltas[nr_ref_deltas].obj_no = i;
nr_ref_deltas++;
} else if (!data) { } else if (!data) {
/* large blobs, check later */ /* large blobs, check later */
obj->real_type = OBJ_BAD; obj->real_type = OBJ_BAD;
@ -1112,15 +1177,18 @@ static void resolve_deltas(void)
{ {
int i; int i;
if (!nr_deltas) if (!nr_ofs_deltas && !nr_ref_deltas)
return; return;
/* Sort deltas by base SHA1/offset for fast searching */ /* Sort deltas by base SHA1/offset for fast searching */
qsort(deltas, nr_deltas, sizeof(struct delta_entry), qsort(ofs_deltas, nr_ofs_deltas, sizeof(struct ofs_delta_entry),
compare_delta_entry); compare_ofs_delta_entry);
qsort(ref_deltas, nr_ref_deltas, sizeof(struct ref_delta_entry),
compare_ref_delta_entry);
if (verbose) if (verbose)
progress = start_progress(_("Resolving deltas"), nr_deltas); progress = start_progress(_("Resolving deltas"),
nr_ref_deltas + nr_ofs_deltas);
#ifndef NO_PTHREADS #ifndef NO_PTHREADS
nr_dispatched = 0; nr_dispatched = 0;
@ -1158,7 +1226,7 @@ static void resolve_deltas(void)
static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved); static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved);
static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_sha1) static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_sha1)
{ {
if (nr_deltas == nr_resolved_deltas) { if (nr_ref_deltas + nr_ofs_deltas == nr_resolved_deltas) {
stop_progress(&progress); stop_progress(&progress);
/* Flush remaining pack final 20-byte SHA1. */ /* Flush remaining pack final 20-byte SHA1. */
flush(); flush();
@ -1169,7 +1237,7 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha
struct sha1file *f; struct sha1file *f;
unsigned char read_sha1[20], tail_sha1[20]; unsigned char read_sha1[20], tail_sha1[20];
struct strbuf msg = STRBUF_INIT; struct strbuf msg = STRBUF_INIT;
int nr_unresolved = nr_deltas - nr_resolved_deltas; int nr_unresolved = nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas;
int nr_objects_initial = nr_objects; int nr_objects_initial = nr_objects;
if (nr_unresolved <= 0) if (nr_unresolved <= 0)
die(_("confusion beyond insanity")); die(_("confusion beyond insanity"));
@ -1191,11 +1259,11 @@ static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned cha
die(_("Unexpected tail checksum for %s " die(_("Unexpected tail checksum for %s "
"(disk corruption?)"), curr_pack); "(disk corruption?)"), curr_pack);
} }
if (nr_deltas != nr_resolved_deltas) if (nr_ofs_deltas + nr_ref_deltas != nr_resolved_deltas)
die(Q_("pack has %d unresolved delta", die(Q_("pack has %d unresolved delta",
"pack has %d unresolved deltas", "pack has %d unresolved deltas",
nr_deltas - nr_resolved_deltas), nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas),
nr_deltas - nr_resolved_deltas); nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas);
} }
static int write_compressed(struct sha1file *f, void *in, unsigned int size) static int write_compressed(struct sha1file *f, void *in, unsigned int size)
@ -1254,14 +1322,14 @@ static struct object_entry *append_obj_to_pack(struct sha1file *f,
static int delta_pos_compare(const void *_a, const void *_b) static int delta_pos_compare(const void *_a, const void *_b)
{ {
struct delta_entry *a = *(struct delta_entry **)_a; struct ref_delta_entry *a = *(struct ref_delta_entry **)_a;
struct delta_entry *b = *(struct delta_entry **)_b; struct ref_delta_entry *b = *(struct ref_delta_entry **)_b;
return a->obj_no - b->obj_no; return a->obj_no - b->obj_no;
} }
static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved) static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved)
{ {
struct delta_entry **sorted_by_pos; struct ref_delta_entry **sorted_by_pos;
int i, n = 0; int i, n = 0;
/* /*
@ -1275,28 +1343,25 @@ static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved)
* resolving deltas in the same order as their position in the pack. * resolving deltas in the same order as their position in the pack.
*/ */
sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos)); sorted_by_pos = xmalloc(nr_unresolved * sizeof(*sorted_by_pos));
for (i = 0; i < nr_deltas; i++) { for (i = 0; i < nr_ref_deltas; i++)
if (objects[deltas[i].obj_no].real_type != OBJ_REF_DELTA) sorted_by_pos[n++] = &ref_deltas[i];
continue;
sorted_by_pos[n++] = &deltas[i];
}
qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare); qsort(sorted_by_pos, n, sizeof(*sorted_by_pos), delta_pos_compare);
for (i = 0; i < n; i++) { for (i = 0; i < n; i++) {
struct delta_entry *d = sorted_by_pos[i]; struct ref_delta_entry *d = sorted_by_pos[i];
enum object_type type; enum object_type type;
struct base_data *base_obj = alloc_base_data(); struct base_data *base_obj = alloc_base_data();
if (objects[d->obj_no].real_type != OBJ_REF_DELTA) if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
continue; continue;
base_obj->data = read_sha1_file(d->base.sha1, &type, &base_obj->size); base_obj->data = read_sha1_file(d->sha1, &type, &base_obj->size);
if (!base_obj->data) if (!base_obj->data)
continue; continue;
if (check_sha1_signature(d->base.sha1, base_obj->data, if (check_sha1_signature(d->sha1, base_obj->data,
base_obj->size, typename(type))) base_obj->size, typename(type)))
die(_("local object %s is corrupt"), sha1_to_hex(d->base.sha1)); die(_("local object %s is corrupt"), sha1_to_hex(d->sha1));
base_obj->obj = append_obj_to_pack(f, d->base.sha1, base_obj->obj = append_obj_to_pack(f, d->sha1,
base_obj->data, base_obj->size, type); base_obj->data, base_obj->size, type);
find_unresolved_deltas(base_obj); find_unresolved_deltas(base_obj);
display_progress(progress, nr_resolved_deltas); display_progress(progress, nr_resolved_deltas);
@ -1488,7 +1553,7 @@ static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
static void show_pack_info(int stat_only) static void show_pack_info(int stat_only)
{ {
int i, baseobjects = nr_objects - nr_deltas; int i, baseobjects = nr_objects - nr_ref_deltas - nr_ofs_deltas;
unsigned long *chain_histogram = NULL; unsigned long *chain_histogram = NULL;
if (deepest_delta) if (deepest_delta)
@ -1498,7 +1563,7 @@ static void show_pack_info(int stat_only)
struct object_entry *obj = &objects[i]; struct object_entry *obj = &objects[i];
if (is_delta_type(obj->type)) if (is_delta_type(obj->type))
chain_histogram[obj->delta_depth - 1]++; chain_histogram[obj_stat[i].delta_depth - 1]++;
if (stat_only) if (stat_only)
continue; continue;
printf("%s %-6s %lu %lu %"PRIuMAX, printf("%s %-6s %lu %lu %"PRIuMAX,
@ -1507,8 +1572,8 @@ static void show_pack_info(int stat_only)
(unsigned long)(obj[1].idx.offset - obj->idx.offset), (unsigned long)(obj[1].idx.offset - obj->idx.offset),
(uintmax_t)obj->idx.offset); (uintmax_t)obj->idx.offset);
if (is_delta_type(obj->type)) { if (is_delta_type(obj->type)) {
struct object_entry *bobj = &objects[obj->base_object_no]; struct object_entry *bobj = &objects[obj_stat[i].base_object_no];
printf(" %u %s", obj->delta_depth, sha1_to_hex(bobj->idx.sha1)); printf(" %u %s", obj_stat[i].delta_depth, sha1_to_hex(bobj->idx.sha1));
} }
putchar('\n'); putchar('\n');
} }
@ -1671,11 +1736,14 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
curr_pack = open_pack_file(pack_name); curr_pack = open_pack_file(pack_name);
parse_pack_header(); parse_pack_header();
objects = xcalloc(nr_objects + 1, sizeof(struct object_entry)); objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
deltas = xcalloc(nr_objects, sizeof(struct delta_entry)); if (show_stat)
obj_stat = xcalloc(nr_objects + 1, sizeof(struct object_stat));
ofs_deltas = xcalloc(nr_objects, sizeof(struct ofs_delta_entry));
parse_pack_objects(pack_sha1); parse_pack_objects(pack_sha1);
resolve_deltas(); resolve_deltas();
conclude_pack(fix_thin_pack, curr_pack, pack_sha1); conclude_pack(fix_thin_pack, curr_pack, pack_sha1);
free(deltas); free(ofs_deltas);
free(ref_deltas);
if (strict) if (strict)
foreign_nr = check_objects(); foreign_nr = check_objects();