Revision ab7cd7bb8c02dc40ca3a909653e8f56226f9e440 authored by Junio C Hamano on 16 February 2006, 19:55:51 UTC, committed by Junio C Hamano on 22 February 2006, 21:14:57 UTC
This introduces --no-reuse-delta option to disable reusing of
existing delta, which is a large part of the optimization
introduced by this series.  This may become necessary if
repeated repacking makes delta chain too long.  With this, the
output of the command becomes identical to that of the older
implementation.  But the performance suffers greatly.

It still allows reusing non-deltified representations; there is
no point uncompressing and recompressing the whole text.

It also adds a couple more statistics output, while squelching
it under -q flag, which the last round forgot to do.

  $ time old-git-pack-objects --stdout >/dev/null <RL
  Generating pack...
  Done counting 184141 objects.
  Packing 184141 objects....................
  real    12m8.530s       user    11m1.450s       sys     0m57.920s
  $ time git-pack-objects --stdout >/dev/null <RL
  Generating pack...
  Done counting 184141 objects.
  Packing 184141 objects.....................
  Total 184141, written 184141 (delta 138297), reused 178833 (delta 134081)
  real    0m59.549s       user    0m56.670s       sys     0m2.400s
  $ time git-pack-objects --stdout --no-reuse-delta >/dev/null <RL
  Generating pack...
  Done counting 184141 objects.
  Packing 184141 objects.....................
  Total 184141, written 184141 (delta 134833), reused 47904 (delta 0)
  real    11m13.830s      user    9m45.240s       sys     0m44.330s

There is one remaining issue when --no-reuse-delta option is not
used.  It can create delta chains that are deeper than specified.

    A<--B<--C<--D   E   F   G

Suppose we have a delta chain A to D (A is stored in full either
in a pack or as a loose object. B is depth1 delta relative to A,
C is depth2 delta relative to B...) with loose objects E, F, G.
And we are going to pack all of them.

B, C and D are left as delta against A, B and C respectively.
So A, E, F, and G are examined for deltification, and let's say
we decided to keep E expanded, and store the rest as deltas like
this:

    E<--F<--G<--A

Oops.  We ended up making D a bit too deep, didn't we?  B, C and
D form a chain on top of A!

This is because we did not know what the final depth of A would
be, when we checked objects and decided to keep the existing
delta.  Unfortunately, deferring the decision until just before
the deltification is not an option.  To be able to make B, C,
and D candidates for deltification with the rest, we need to
know the type and final unexpanded size of them, but the major
part of the optimization comes from the fact that we do not read
the delta data to do so -- getting the final size is quite an
expensive operation.

To prevent this from happening, we should keep A from being
deltified.  But how would we tell that, cheaply?

To do this most precisely, after check_object() runs, each
object that is used as the base object of some existing delta
needs to be marked with the maximum depth of the objects we
decided to keep deltified (in this case, D is depth 3 relative
to A, so if no other delta chain that is longer than 3 based on
A exists, mark A with 3).  Then when attempting to deltify A, we
would take that number into account to see if the final delta
chain that leads to D becomes too deep.

However, this is a bit cumbersome to compute, so we would cheat
and reduce the maximum depth for A arbitrarily to depth/4 in
this implementation.

Signed-off-by: Junio C Hamano <junkio@cox.net>
1 parent 3f9ac8d
Raw File
tree.c
#include "cache.h"
#include "tree.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include <stdlib.h>

const char *tree_type = "tree";

static int read_one_entry(unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage)
{
	int len;
	unsigned int size;
	struct cache_entry *ce;

	if (S_ISDIR(mode))
		return READ_TREE_RECURSIVE;

	len = strlen(pathname);
	size = cache_entry_size(baselen + len);
	ce = xmalloc(size);

	memset(ce, 0, size);

	ce->ce_mode = create_ce_mode(mode);
	ce->ce_flags = create_ce_flags(baselen + len, stage);
	memcpy(ce->name, base, baselen);
	memcpy(ce->name + baselen, pathname, len+1);
	memcpy(ce->sha1, sha1, 20);
	return add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK);
}

static int match_tree_entry(const char *base, int baselen, const char *path, unsigned int mode, const char **paths)
{
	const char *match;
	int pathlen;

	if (!paths)
		return 1;
	pathlen = strlen(path);
	while ((match = *paths++) != NULL) {
		int matchlen = strlen(match);

		if (baselen >= matchlen) {
			/* If it doesn't match, move along... */
			if (strncmp(base, match, matchlen))
				continue;
			/* The base is a subdirectory of a path which was specified. */
			return 1;
		}

		/* Does the base match? */
		if (strncmp(base, match, baselen))
			continue;

		match += baselen;
		matchlen -= baselen;

		if (pathlen > matchlen)
			continue;

		if (matchlen > pathlen) {
			if (match[pathlen] != '/')
				continue;
			if (!S_ISDIR(mode))
				continue;
		}

		if (strncmp(path, match, pathlen))
			continue;

		return 1;
	}
	return 0;
}

int read_tree_recursive(struct tree *tree,
			const char *base, int baselen,
			int stage, const char **match,
			read_tree_fn_t fn)
{
	struct tree_entry_list *list;
	if (parse_tree(tree))
		return -1;
	list = tree->entries;
	while (list) {
		struct tree_entry_list *current = list;
		list = list->next;
		if (!match_tree_entry(base, baselen, current->name,
				      current->mode, match))
			continue;

		switch (fn(current->item.any->sha1, base, baselen,
			   current->name, current->mode, stage)) {
		case 0:
			continue;
		case READ_TREE_RECURSIVE:
			break;;
		default:
			return -1;
		}
		if (current->directory) {
			int retval;
			int pathlen = strlen(current->name);
			char *newbase;

			newbase = xmalloc(baselen + 1 + pathlen);
			memcpy(newbase, base, baselen);
			memcpy(newbase + baselen, current->name, pathlen);
			newbase[baselen + pathlen] = '/';
			retval = read_tree_recursive(current->item.tree,
						     newbase,
						     baselen + pathlen + 1,
						     stage, match, fn);
			free(newbase);
			if (retval)
				return -1;
			continue;
		}
	}
	return 0;
}

int read_tree(struct tree *tree, int stage, const char **match)
{
	return read_tree_recursive(tree, "", 0, stage, match, read_one_entry);
}

struct tree *lookup_tree(const unsigned char *sha1)
{
	struct object *obj = lookup_object(sha1);
	if (!obj) {
		struct tree *ret = xmalloc(sizeof(struct tree));
		memset(ret, 0, sizeof(struct tree));
		created_object(sha1, &ret->object);
		ret->object.type = tree_type;
		return ret;
	}
	if (!obj->type)
		obj->type = tree_type;
	if (obj->type != tree_type) {
		error("Object %s is a %s, not a tree", 
		      sha1_to_hex(sha1), obj->type);
		return NULL;
	}
	return (struct tree *) obj;
}

int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size)
{
	void *bufptr = buffer;
	struct tree_entry_list **list_p;
	int n_refs = 0;

	if (item->object.parsed)
		return 0;
	item->object.parsed = 1;
	list_p = &item->entries;
	while (size) {
		struct object *obj;
		struct tree_entry_list *entry;
		int len = 1+strlen(bufptr);
		unsigned char *file_sha1 = bufptr + len;
		char *path = strchr(bufptr, ' ');
		unsigned int mode;
		if (size < len + 20 || !path || 
		    sscanf(bufptr, "%o", &mode) != 1)
			return -1;

		entry = xmalloc(sizeof(struct tree_entry_list));
		entry->name = strdup(path + 1);
		entry->directory = S_ISDIR(mode) != 0;
		entry->executable = (mode & S_IXUSR) != 0;
		entry->symlink = S_ISLNK(mode) != 0;
		entry->zeropad = *(char *)bufptr == '0';
		entry->mode = mode;
		entry->next = NULL;

		bufptr += len + 20;
		size -= len + 20;

		if (entry->directory) {
			entry->item.tree = lookup_tree(file_sha1);
			obj = &entry->item.tree->object;
		} else {
			entry->item.blob = lookup_blob(file_sha1);
			obj = &entry->item.blob->object;
		}
		if (obj)
			n_refs++;
		*list_p = entry;
		list_p = &entry->next;
	}

	if (track_object_refs) {
		struct tree_entry_list *entry;
		unsigned i = 0;
		struct object_refs *refs = alloc_object_refs(n_refs);
		for (entry = item->entries; entry; entry = entry->next)
			refs->ref[i++] = entry->item.any;
		set_object_refs(&item->object, refs);
	}

	return 0;
}

int parse_tree(struct tree *item)
{
	 char type[20];
	 void *buffer;
	 unsigned long size;
	 int ret;

	if (item->object.parsed)
		return 0;
	buffer = read_sha1_file(item->object.sha1, type, &size);
	if (!buffer)
		return error("Could not read %s",
			     sha1_to_hex(item->object.sha1));
	if (strcmp(type, tree_type)) {
		free(buffer);
		return error("Object %s not a tree",
			     sha1_to_hex(item->object.sha1));
	}
	ret = parse_tree_buffer(item, buffer, size);
	free(buffer);
	return ret;
}

struct tree *parse_tree_indirect(const unsigned char *sha1)
{
	struct object *obj = parse_object(sha1);
	do {
		if (!obj)
			return NULL;
		if (obj->type == tree_type)
			return (struct tree *) obj;
		else if (obj->type == commit_type)
			obj = &(((struct commit *) obj)->tree->object);
		else if (obj->type == tag_type)
			obj = ((struct tag *) obj)->tagged;
		else
			return NULL;
		if (!obj->parsed)
			parse_object(obj->sha1);
	} while (1);
}
back to top