Add specialized object allocator

This creates a simple specialized object allocator for basic
objects.

This avoids wasting space with malloc overhead (metadata and
extra alignment), since the specialized allocator knows the
alignment, and that objects, once allocated, are never freed.

It also allows us to track some basic statistics about object
allocations. For example, for the mozilla import, it shows
object usage as follows:

     blobs:   627629 (14710 kB)
     trees:  1119035 (34969 kB)
   commits:   196423  (8440 kB)
      tags:     1336    (46 kB)

and the simpler allocator shaves off about 2.5% off the memory
footprint off a "git-rev-list --all --objects", and is a bit
faster too.

[ Side note: this concludes the series of "save memory in object storage".
  The thing is, there simply isn't much more to be saved on the objects.

  Doing "git-rev-list --all --objects" on the mozilla archive has a final
  total RSS of 131498 pages for me: that's about 513MB. Of that, the
  object overhead is now just 56MB, the rest is going somewhere else (put
  another way: the fact that this patch shaves off 2.5% of the total
  memory overhead, considering that objects are now not much more than 10%
  of the total shows how big the wasted space really was: this makes
  object allocations much more memory- and time-efficient).

  I haven't looked at where the rest is, but I suspect the bulk of it is
  just the pack-file loading. It may be that we should pack the tree
  objects separately from the blob objects: for git-rev-list --objects, we
  don't actually ever need to even look at the blobs, but since trees and
  blobs are interspersed in the pack-file, we end up not being dense in
  the tree accesses, so we end up looking at more pages than we strictly
  need to.

  So with a 535MB pack-file, it's entirely possible - even likely - that
  most of the remaining RSS is just the mmap of the pack-file itself. We
  don't need to map in _all_ of it, but we do end up mapping a fair
  amount. ]

Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
This commit is contained in:
Linus Torvalds 2006-06-19 10:44:15 -07:00 committed by Junio C Hamano
parent 64e86c5786
commit 855419f764
7 changed files with 67 additions and 5 deletions

View File

@ -216,7 +216,7 @@ LIB_OBJS = \
server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \ server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
tag.o tree.o usage.o config.o environment.o ctype.o copy.o \ tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \ fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
$(DIFF_OBJS) alloc.o $(DIFF_OBJS)
BUILTIN_OBJS = \ BUILTIN_OBJS = \
builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \ builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \

51
alloc.c Normal file
View File

@ -0,0 +1,51 @@
/*
* alloc.c - specialized allocator for internal objects
*
* Copyright (C) 2006 Linus Torvalds
*
* The standard malloc/free wastes too much space for objects, partly because
* it maintains all the allocation infrastructure (which isn't needed, since
* we never free an object descriptor anyway), but even more because it ends
* up with maximal alignment because it doesn't know what the object alignment
* for the new allocation is.
*/
#include "cache.h"
#include "object.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "tag.h"
#define BLOCKING 1024
#define DEFINE_ALLOCATOR(name) \
static unsigned int name##_allocs; \
struct name *alloc_##name##_node(void) \
{ \
static int nr; \
static struct name *block; \
\
if (!nr) { \
nr = BLOCKING; \
block = xcalloc(BLOCKING, sizeof(struct name)); \
} \
nr--; \
name##_allocs++; \
return block++; \
}
DEFINE_ALLOCATOR(blob)
DEFINE_ALLOCATOR(tree)
DEFINE_ALLOCATOR(commit)
DEFINE_ALLOCATOR(tag)
#define REPORT(name) \
fprintf(stderr, "%10s: %8u (%zu kB)\n", #name, name##_allocs, name##_allocs*sizeof(struct name) >> 10)
void alloc_report(void)
{
REPORT(blob);
REPORT(tree);
REPORT(commit);
REPORT(tag);
}

2
blob.c
View File

@ -8,7 +8,7 @@ struct blob *lookup_blob(const unsigned char *sha1)
{ {
struct object *obj = lookup_object(sha1); struct object *obj = lookup_object(sha1);
if (!obj) { if (!obj) {
struct blob *ret = xcalloc(1, sizeof(struct blob)); struct blob *ret = alloc_blob_node();
created_object(sha1, &ret->object); created_object(sha1, &ret->object);
ret->object.type = TYPE_BLOB; ret->object.type = TYPE_BLOB;
return ret; return ret;

11
cache.h
View File

@ -384,4 +384,15 @@ extern void setup_pager(void);
int decode_85(char *dst, char *line, int linelen); int decode_85(char *dst, char *line, int linelen);
void encode_85(char *buf, unsigned char *data, int bytes); void encode_85(char *buf, unsigned char *data, int bytes);
/* alloc.c */
struct blob;
struct tree;
struct commit;
struct tag;
extern struct blob *alloc_blob_node(void);
extern struct tree *alloc_tree_node(void);
extern struct commit *alloc_commit_node(void);
extern struct tag *alloc_tag_node(void);
extern void alloc_report(void);
#endif /* CACHE_H */ #endif /* CACHE_H */

View File

@ -84,7 +84,7 @@ struct commit *lookup_commit(const unsigned char *sha1)
{ {
struct object *obj = lookup_object(sha1); struct object *obj = lookup_object(sha1);
if (!obj) { if (!obj) {
struct commit *ret = xcalloc(1, sizeof(struct commit)); struct commit *ret = alloc_commit_node();
created_object(sha1, &ret->object); created_object(sha1, &ret->object);
ret->object.type = TYPE_COMMIT; ret->object.type = TYPE_COMMIT;
return ret; return ret;

2
tag.c
View File

@ -19,7 +19,7 @@ struct tag *lookup_tag(const unsigned char *sha1)
{ {
struct object *obj = lookup_object(sha1); struct object *obj = lookup_object(sha1);
if (!obj) { if (!obj) {
struct tag *ret = xcalloc(1, sizeof(struct tag)); struct tag *ret = alloc_tag_node();
created_object(sha1, &ret->object); created_object(sha1, &ret->object);
ret->object.type = TYPE_TAG; ret->object.type = TYPE_TAG;
return ret; return ret;

2
tree.c
View File

@ -129,7 +129,7 @@ struct tree *lookup_tree(const unsigned char *sha1)
{ {
struct object *obj = lookup_object(sha1); struct object *obj = lookup_object(sha1);
if (!obj) { if (!obj) {
struct tree *ret = xcalloc(1, sizeof(struct tree)); struct tree *ret = alloc_tree_node();
created_object(sha1, &ret->object); created_object(sha1, &ret->object);
ret->object.type = TYPE_TREE; ret->object.type = TYPE_TREE;
return ret; return ret;