undef/git-commit-vandalism
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'jk/drop-sha1-entry-pos' into maint

Browse Source 
Code clean-up.

* jk/drop-sha1-entry-pos:
  sha1-lookup: remove sha1_entry_pos() from header file
  sha1_file: drop experimental GIT_USE_LOOKUP search
This commit is contained in:
Junio C Hamano 2017-10-18 14:19:06 +09:00
commit 7c9375db0e
5 changed files with 1 additions and 244 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

216
sha1-lookup.c
View File

@ -99,219 +99,3 @@ int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
} while (lo < hi);
return -lo-1;
}
/*
* Conventional binary search loop looks like this:
*
* unsigned lo, hi;
* do {
* unsigned mi = (lo + hi) / 2;
* int cmp = "entry pointed at by mi" minus "target";
* if (!cmp)
* return (mi is the wanted one)
* if (cmp > 0)
* hi = mi; "mi is larger than target"
* else
* lo = mi+1; "mi is smaller than target"
* } while (lo < hi);
*
* The invariants are:
*
* - When entering the loop, lo points at a slot that is never
* above the target (it could be at the target), hi points at a
* slot that is guaranteed to be above the target (it can never
* be at the target).
*
* - We find a point 'mi' between lo and hi (mi could be the same
* as lo, but never can be as same as hi), and check if it hits
* the target. There are three cases:
*
* - if it is a hit, we are happy.
*
* - if it is strictly higher than the target, we set it to hi,
* and repeat the search.
*
* - if it is strictly lower than the target, we update lo to
* one slot after it, because we allow lo to be at the target.
*
* If the loop exits, there is no matching entry.
*
* When choosing 'mi', we do not have to take the "middle" but
* anywhere in between lo and hi, as long as lo <= mi < hi is
* satisfied. When we somehow know that the distance between the
* target and lo is much shorter than the target and hi, we could
* pick mi that is much closer to lo than the midway.
*
* Now, we can take advantage of the fact that SHA-1 is a good hash
* function, and as long as there are enough entries in the table, we
* can expect uniform distribution. An entry that begins with for
* example "deadbeef..." is much likely to appear much later than in
* the midway of the table. It can reasonably be expected to be near
* 87% (222/256) from the top of the table.
*
* However, we do not want to pick "mi" too precisely. If the entry at
* the 87% in the above example turns out to be higher than the target
* we are looking for, we would end up narrowing the search space down
* only by 13%, instead of 50% we would get if we did a simple binary
* search. So we would want to hedge our bets by being less aggressive.
*
* The table at "table" holds at least "nr" entries of "elem_size"
* bytes each. Each entry has the SHA-1 key at "key_offset". The
* table is sorted by the SHA-1 key of the entries. The caller wants
* to find the entry with "key", and knows that the entry at "lo" is
* not higher than the entry it is looking for, and that the entry at
* "hi" is higher than the entry it is looking for.
*/
int sha1_entry_pos(const void *table,
size_t elem_size,
size_t key_offset,
unsigned lo, unsigned hi, unsigned nr,
const unsigned char *key)
{
const unsigned char *base = table;
const unsigned char *hi_key, *lo_key;
unsigned ofs_0;
static int debug_lookup = -1;
if (debug_lookup < 0)
debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
if (!nr || lo >= hi)
return -1;
if (nr == hi)
hi_key = NULL;
else
hi_key = base + elem_size * hi + key_offset;
lo_key = base + elem_size * lo + key_offset;
ofs_0 = 0;
do {
int cmp;
unsigned ofs, mi, range;
unsigned lov, hiv, kyv;
const unsigned char *mi_key;
range = hi - lo;
if (hi_key) {
for (ofs = ofs_0; ofs < 20; ofs++)
if (lo_key[ofs] != hi_key[ofs])
break;
ofs_0 = ofs;
/*
* byte 0 thru (ofs-1) are the same between
* lo and hi; ofs is the first byte that is
* different.
*
* If ofs==20, then no bytes are different,
* meaning we have entries with duplicate
* keys. We know that we are in a solid run
* of this entry (because the entries are
* sorted, and our lo and hi are the same,
* there can be nothing but this single key
* in between). So we can stop the search.
* Either one of these entries is it (and
* we do not care which), or we do not have
* it.
*
* Furthermore, we know that one of our
* endpoints must be the edge of the run of
* duplicates. For example, given this
* sequence:
*
* idx 0 1 2 3 4 5
* key A C C C C D
*
* If we are searching for "B", we might
* hit the duplicate run at lo=1, hi=3
* (e.g., by first mi=3, then mi=0). But we
* can never have lo > 1, because B < C.
* That is, if our key is less than the
* run, we know that "lo" is the edge, but
* we can say nothing of "hi". Similarly,
* if our key is greater than the run, we
* know that "hi" is the edge, but we can
* say nothing of "lo".
*
* Therefore if we do not find it, we also
* know where it would go if it did exist:
* just on the far side of the edge that we
* know about.
*/
if (ofs == 20) {
mi = lo;
mi_key = base + elem_size * mi + key_offset;
cmp = memcmp(mi_key, key, 20);
if (!cmp)
return mi;
if (cmp < 0)
return -1 - hi;
else
return -1 - lo;
}
hiv = hi_key[ofs_0];
if (ofs_0 < 19)
hiv = (hiv << 8) | hi_key[ofs_0+1];
} else {
hiv = 256;
if (ofs_0 < 19)
hiv <<= 8;
}
lov = lo_key[ofs_0];
kyv = key[ofs_0];
if (ofs_0 < 19) {
lov = (lov << 8) | lo_key[ofs_0+1];
kyv = (kyv << 8) | key[ofs_0+1];
}
assert(lov < hiv);
if (kyv < lov)
return -1 - lo;
if (hiv < kyv)
return -1 - hi;
/*
* Even if we know the target is much closer to 'hi'
* than 'lo', if we pick too precisely and overshoot
* (e.g. when we know 'mi' is closer to 'hi' than to
* 'lo', pick 'mi' that is higher than the target), we
* end up narrowing the search space by a smaller
* amount (i.e. the distance between 'mi' and 'hi')
* than what we would have (i.e. about half of 'lo'
* and 'hi'). Hedge our bets to pick 'mi' less
* aggressively, i.e. make 'mi' a bit closer to the
* middle than we would otherwise pick.
*/
kyv = (kyv * 6 + lov + hiv) / 8;
if (lov < hiv - 1) {
if (kyv == lov)
kyv++;
else if (kyv == hiv)
kyv--;
}
mi = (range - 1) * (kyv - lov) / (hiv - lov) + lo;
if (debug_lookup) {
printf("lo %u hi %u rg %u mi %u ", lo, hi, range, mi);
printf("ofs %u lov %x, hiv %x, kyv %x\n",
ofs_0, lov, hiv, kyv);
}
if (!(lo <= mi && mi < hi))
die("assertion failure lo %u mi %u hi %u %s",
lo, mi, hi, sha1_to_hex(key));
mi_key = base + elem_size * mi + key_offset;
cmp = memcmp(mi_key + ofs_0, key + ofs_0, 20 - ofs_0);
if (!cmp)
return mi;
if (cmp > 0) {
hi = mi;
hi_key = mi_key;
} else {
lo = mi + 1;
lo_key = mi_key + elem_size;
}
} while (lo < hi);
return -lo-1;
}

6
sha1-lookup.h
View File

@ -7,10 +7,4 @@ extern int sha1_pos(const unsigned char *sha1,
void *table,
size_t nr,
sha1_access_fn fn);
extern int sha1_entry_pos(const void *table,
size_t elem_size,
size_t key_offset,
unsigned lo, unsigned hi, unsigned nr,
const unsigned char *key);
#endif

11
sha1_file.c
View File

@ -2761,7 +2761,6 @@ off_t find_pack_entry_one(const unsigned char *sha1,
const uint32_t *level1_ofs = p->index_data;
const unsigned char *index = p->index_data;
unsigned hi, lo, stride;
static int use_lookup = -1;
static int debug_lookup = -1;
if (debug_lookup < 0)
@ -2791,16 +2790,6 @@ off_t find_pack_entry_one(const unsigned char *sha1,
printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
if (use_lookup < 0)
use_lookup = !!getenv("GIT_USE_LOOKUP");
if (use_lookup) {
int pos = sha1_entry_pos(index, stride, 0,
lo, hi, p->num_objects, sha1);
if (pos < 0)
return 0;
return nth_packed_object_offset(p, pos);
}
while (lo < hi) {
unsigned mi = (lo + hi) / 2;
int cmp = hashcmp(index + mi * stride, sha1);

11
t/t5308-pack-detect-duplicates.sh
View File

@ -56,20 +56,11 @@ test_expect_success 'create batch-check test vectors' '
EOF
'
test_expect_success 'lookup in duplicated pack (binary search)' '
test_expect_success 'lookup in duplicated pack' '
git cat-file --batch-check <input >actual &&
test_cmp expect actual
'
test_expect_success 'lookup in duplicated pack (GIT_USE_LOOKUP)' '
(
GIT_USE_LOOKUP=1 &&
export GIT_USE_LOOKUP &&
git cat-file --batch-check <input >actual
) &&
test_cmp expect actual
'
test_expect_success 'index-pack can reject packs with duplicates' '
clear_packs &&
create_pack dups.pack 2 &&

1
t/test-lib.sh
View File

@ -99,7 +99,6 @@ unset VISUAL EMAIL LANGUAGE COLUMNS $("$PERL_PATH" -e '
my $ok = join("|", qw(
TRACE
DEBUG
USE_LOOKUP
TEST
.*_TEST
PROVE