reftable/block: avoid copying block iterators on seek

When seeking a reftable record in a block we need to position the
iterator _before_ the sought-after record so that the next call to
`block_iter_next()` would yield that record. To achieve this, the loop
that performs the linear seeks to restore the previous position once it
has found the record.

This is done by advancing two `block_iter`s: one to check whether the
next record is our sought-after record, and one that we update after
every iteration. This of course involves quite a lot of copying and also
leads to needless memory allocations.

Refactor the code to get rid of the `next` iterator and the copying this
involves. Instead, we can restore the previous offset such that the call
to `next` will return the correct record.

Next to being simpler conceptually this also leads to a nice speedup.
The following benchmark parser 10k refs out of 100k existing refs via
`git-rev-list --no-walk`:

  Benchmark 1: rev-list: print many refs (HEAD~)
    Time (mean ± σ):     170.2 ms ±   1.7 ms    [User: 86.1 ms, System: 83.6 ms]
    Range (min … max):   166.4 ms … 180.3 ms    500 runs

  Benchmark 2: rev-list: print many refs (HEAD~)
    Time (mean ± σ):     161.6 ms ±   1.6 ms    [User: 78.1 ms, System: 83.0 ms]
    Range (min … max):   158.4 ms … 172.3 ms    500 runs

  Summary
    rev-list: print many refs (HEAD) ran
      1.05 ± 0.01 times faster than rev-list: print many refs (HEAD~)

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/reftable/block.c b/reftable/block.c
index c6c4a68ea147522dc7886d3f61f85af94fcf2ad4..3e87460cba96e34b63ec3848fc017c57fc747902 100644 (file)
--- a/reftable/block.c
+++ b/reftable/block.c
@@ -365,16 +365,6 @@ static int restart_needle_less(size_t idx, void *_args)
        return args->needle.len < suffix_len;
 }
 
-void block_iter_copy_from(struct block_iter *dest, const struct block_iter *src)
-{
-       dest->block = src->block;
-       dest->block_len = src->block_len;
-       dest->hash_size = src->hash_size;
-       dest->next_off = src->next_off;
-       strbuf_reset(&dest->last_key);
-       strbuf_addbuf(&dest->last_key, &src->last_key);
-}
-
 int block_iter_next(struct block_iter *it, struct reftable_record *rec)
 {
        struct string_view in = {
@@ -427,7 +417,6 @@ int block_iter_seek_key(struct block_iter *it, const struct block_reader *br,
                .needle = *want,
                .reader = br,
        };
-       struct block_iter next = BLOCK_ITER_INIT;
        struct reftable_record rec;
        int err = 0;
        size_t i;
@@ -486,11 +475,13 @@ int block_iter_seek_key(struct block_iter *it, const struct block_reader *br,
         * far and then back up.
         */
        while (1) {
-               block_iter_copy_from(&next, it);
-               err = block_iter_next(&next, &rec);
+               size_t prev_off = it->next_off;
+
+               err = block_iter_next(it, &rec);
                if (err < 0)
                        goto done;
                if (err > 0) {
+                       it->next_off = prev_off;
                        err = 0;
                        goto done;
                }
@@ -501,18 +492,23 @@ int block_iter_seek_key(struct block_iter *it, const struct block_reader *br,
                 * record does not exist in the block and can thus abort early.
                 * In case it is equal to the sought-after key we have found
                 * the desired record.
+                *
+                * Note that we store the next record's key record directly in
+                * `last_key` without restoring the key of the preceding record
+                * in case we need to go one record back. This is safe to do as
+                * `block_iter_next()` would return the ref whose key is equal
+                * to `last_key` now, and naturally all keys share a prefix
+                * with themselves.
                 */
                reftable_record_key(&rec, &it->last_key);
-               if (strbuf_cmp(&it->last_key, want) >= 0)
+               if (strbuf_cmp(&it->last_key, want) >= 0) {
+                       it->next_off = prev_off;
                        goto done;
-
-               block_iter_copy_from(it, &next);
+               }
        }
 
 done:
-       block_iter_close(&next);
        reftable_record_release(&rec);
-
        return err;
 }
 

diff --git a/reftable/block.h b/reftable/block.h
index c1bd1892cbec12d16522ee1042f65fbda80aced5..ea4384a7e2f99f8455075bbb5e7fb9e6148a901f 100644 (file)
--- a/reftable/block.h
+++ b/reftable/block.h
@@ -121,8 +121,6 @@ void block_iter_seek_start(struct block_iter *it, const struct block_reader *br)
 int block_iter_seek_key(struct block_iter *it, const struct block_reader *br,
                        struct strbuf *want);
 
-void block_iter_copy_from(struct block_iter *dest, const struct block_iter *src);
-
 /* return < 0 for error, 0 for OK, > 0 for EOF. */
 int block_iter_next(struct block_iter *it, struct reftable_record *rec);