![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/sha1-lookup.c b/sha1-lookup.c
index 4faa638caaab969046ce89d27c8293394c699c84..c4dc55d1f5cd07adcf46865354f841cc587c51f6 100644 (file)
--- a/sha1-lookup.c
+++ b/sha1-lookup.c
#include "cache.h"
#include "sha1-lookup.h"
+static uint32_t take2(const unsigned char *sha1)
+{
+ return ((sha1[0] << 8) | sha1[1]);
+}
+
+/*
+ * Conventional binary search loop looks like this:
+ *
+ * do {
+ * int 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 the 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 update hi with
+ * it.
+ *
+ * - if it is strictly lower than the target, we update lo to be
+ * one slot after it, because we allow lo to be at the target.
+ *
+ * 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.
+ */
+/*
+ * The table should contain "nr" elements.
+ * The sha1 of element i (between 0 and nr - 1) should be returned
+ * by "fn(i, table)".
+ */
+int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
+ sha1_access_fn fn)
+{
+ size_t hi = nr;
+ size_t lo = 0;
+ size_t mi = 0;
+
+ if (!nr)
+ return -1;
+
+ if (nr != 1) {
+ size_t lov, hiv, miv, ofs;
+
+ for (ofs = 0; ofs < 18; ofs += 2) {
+ lov = take2(fn(0, table) + ofs);
+ hiv = take2(fn(nr - 1, table) + ofs);
+ miv = take2(sha1 + ofs);
+ if (miv < lov)
+ return -1;
+ if (hiv < miv)
+ return -1 - nr;
+ if (lov != hiv) {
+ /*
+ * At this point miv could be equal
+ * to hiv (but sha1 could still be higher);
+ * the invariant of (mi < hi) should be
+ * kept.
+ */
+ mi = (nr - 1) * (miv - lov) / (hiv - lov);
+ if (lo <= mi && mi < hi)
+ break;
+ die("BUG: assertion failed in binary search");
+ }
+ }
+ if (18 <= ofs)
+ die("cannot happen -- lo and hi are identical");
+ }
+
+ do {
+ int cmp;
+ cmp = hashcmp(fn(mi, table), sha1);
+ if (!cmp)
+ return mi;
+ if (cmp > 0)
+ hi = mi;
+ else
+ lo = mi + 1;
+ mi = (hi + lo) / 2;
+ } while (lo < hi);
+ return -lo-1;
+}
+
/*
* Conventional binary search loop looks like this:
*
* 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
if (hiv < kyv)
return -1 - hi;
- if (kyv == lov && lov < hiv - 1)
- kyv++;
- else if (kyv == hiv - 1 && lov < kyv)
- kyv--;
-
+ /*
+ * 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) {
if (cmp > 0) {
hi = mi;
hi_key = mi_key;
- }
- else {
+ } else {
lo = mi + 1;
lo_key = mi_key + elem_size;
}