Re: [PATCH 11/16] reftable/block: make block iterators reseekable
- From
Justin Tobler <jltobler@gmail.com>
- Date
- Apr 2, 2025, 21:24 UTC
- Message-ID
- <5dbbo5wiszgx74ijinu7xkf7ptddoubkzt53sc6cg5ak357fja@x7v2kra4ny32>
- In-Reply-To
- <20250331-pks-reftable-polishing-v1-11-ebed5247434c@pks.im>
On 25/03/31 10:41AM, Patrick Steinhardt wrote:
> Refactor the block iterators so that initialization and seeking are > different from one another. This makes the iterator trivially reseekable > by storing the pointer to the block at initialization time, which we can > then reuse on ever seek.
s/ever/every/
Show 43 quoted lines
> This refactoring prepares the code for exposing a `reftable_iterator`
> interface for blocks in a subsequent commit. Callsites are adjusted
> accordingly.
>
> Signed-off-by: Patrick Steinhardt <ps@pks.im>
> ---
> reftable/block.c | 23 +++++++++++++----------
> reftable/block.h | 21 ++++++++++++++++-----
> reftable/iter.c | 2 +-
> reftable/table.c | 11 +++++++----
> t/unit-tests/t-reftable-block.c | 30 +++++++++++++++---------------
> 5 files changed, 52 insertions(+), 35 deletions(-)
>
> diff --git a/reftable/block.c b/reftable/block.c
> index 576c6caf59b..6e5c1191f5f 100644
> --- a/reftable/block.c
> +++ b/reftable/block.c
> @@ -381,11 +381,16 @@ static uint32_t block_restart_offset(const struct reftable_block *b, size_t idx)
> return reftable_get_be24(b->block.data + b->restart_off + 3 * idx);
> }
>
> -void block_iter_seek_start(struct block_iter *it, const struct reftable_block *block)
> +void block_iter_init(struct block_iter *it, const struct reftable_block *block)
> {
> it->block = block;
> + block_iter_seek_start(it);
> +}
> +
> +void block_iter_seek_start(struct block_iter *it)
> +{
> reftable_buf_reset(&it->last_key);
> - it->next_off = block->header_off + 4;
> + it->next_off = it->block->header_off + 4;
> }
>
> struct restart_needle_less_args {
> @@ -473,12 +478,11 @@ void block_iter_close(struct block_iter *it)
> reftable_buf_release(&it->scratch);
> }
>
> -int block_iter_seek_key(struct block_iter *it, const struct reftable_block *block,
> - struct reftable_buf *want)
> +int block_iter_seek_key(struct block_iter *it, struct reftable_buf *want)Ah so now that we store the `reftable_block` directly as part of `block_iter`, passing the block in `block_iter_seek_key()` becomes redundant. Nice!
Show 133 quoted lines
> {
> struct restart_needle_less_args args = {
> .needle = *want,
> - .block = block,
> + .block = it->block,
> };
> struct reftable_record rec;
> int err = 0;
> @@ -496,7 +500,7 @@ int block_iter_seek_key(struct block_iter *it, const struct reftable_block *bloc
> * restart point. While that works alright, we would end up scanning
> * too many record.
> */
> - i = binsearch(block->restart_count, &restart_needle_less, &args);
> + i = binsearch(it->block->restart_count, &restart_needle_less, &args);
> if (args.error) {
> err = REFTABLE_FORMAT_ERROR;
> goto done;
> @@ -521,12 +525,11 @@ int block_iter_seek_key(struct block_iter *it, const struct reftable_block *bloc
> * starting from the preceding restart point.
> */
> if (i > 0)
> - it->next_off = block_restart_offset(block, i - 1);
> + it->next_off = block_restart_offset(it->block, i - 1);
> else
> - it->next_off = block->header_off + 4;
> - it->block = block;
> + it->next_off = it->block->header_off + 4;
>
> - err = reftable_record_init(&rec, reftable_block_type(block));
> + err = reftable_record_init(&rec, reftable_block_type(it->block));
> if (err < 0)
> goto done;
>
> diff --git a/reftable/block.h b/reftable/block.h
> index 268d5a1e005..1bfd44f56aa 100644
> --- a/reftable/block.h
> +++ b/reftable/block.h
> @@ -79,12 +79,23 @@ struct block_iter {
> .scratch = REFTABLE_BUF_INIT, \
> }
>
> -/* Position `it` at start of the block */
> -void block_iter_seek_start(struct block_iter *it, const struct reftable_block *block);
> +/*
> + * Initialize the block iterator with the given block. The iterator will be
> + * positioned at the first record contained in the block. The block must remain
> + * valid until the end of the iterator's lifetime. It is valid to re-initialize
> + * iterators multiple times.
> + */
> +void block_iter_init(struct block_iter *it, const struct reftable_block *block);
> +
> +/* Position the initialized iterator at the first record of its block. */
> +void block_iter_seek_start(struct block_iter *it);
>
> -/* Position `it` to the `want` key in the block */
> -int block_iter_seek_key(struct block_iter *it, const struct reftable_block *block,
> - struct reftable_buf *want);
> +/*
> + * Position the initialized iterator at the desired record key. It is not an
> + * error in case the record cannot be found. If so, a subsequent call to
> + * `block_iter_next()` will indicate that the iterator is exhausted.
> + */
> +int block_iter_seek_key(struct block_iter *it, struct reftable_buf *want);
>
> /* return < 0 for error, 0 for OK, > 0 for EOF. */
> int block_iter_next(struct block_iter *it, struct reftable_record *rec);
> diff --git a/reftable/iter.c b/reftable/iter.c
> index 74684de8f6a..7a7e8aa4d7e 100644
> --- a/reftable/iter.c
> +++ b/reftable/iter.c
> @@ -139,7 +139,7 @@ static int indexed_table_ref_iter_next_block(struct indexed_table_ref_iter *it)
> /* indexed block does not exist. */
> return REFTABLE_FORMAT_ERROR;
> }
> - block_iter_seek_start(&it->cur, &it->block);
> + block_iter_init(&it->cur, &it->block);
> return 0;
> }
>
> diff --git a/reftable/table.c b/reftable/table.c
> index 3f2e70caac4..5422ed6769c 100644
> --- a/reftable/table.c
> +++ b/reftable/table.c
> @@ -208,7 +208,7 @@ static int table_iter_next_block(struct table_iter *ti)
>
> ti->block_off = next_block_off;
> ti->is_finished = 0;
> - block_iter_seek_start(&ti->bi, &ti->block);
> + block_iter_init(&ti->bi, &ti->block);
>
> return 0;
> }
> @@ -256,7 +256,7 @@ static int table_iter_seek_to(struct table_iter *ti, uint64_t off, uint8_t typ)
>
> ti->typ = reftable_block_type(&ti->block);
> ti->block_off = off;
> - block_iter_seek_start(&ti->bi, &ti->block);
> + block_iter_init(&ti->bi, &ti->block);
> ti->is_finished = 0;
> return 0;
> }
> @@ -349,7 +349,8 @@ static int table_iter_seek_linear(struct table_iter *ti,
> * the wanted key inside of it. If the block does not contain our key
> * we know that the corresponding record does not exist.
> */
> - err = block_iter_seek_key(&ti->bi, &ti->block, &want_key);
> + block_iter_init(&ti->bi, &ti->block);
> + err = block_iter_seek_key(&ti->bi, &want_key);
> if (err < 0)
> goto done;
> err = 0;
> @@ -417,7 +418,9 @@ static int table_iter_seek_indexed(struct table_iter *ti,
> if (err != 0)
> goto done;
>
> - err = block_iter_seek_key(&ti->bi, &ti->block, &want_index.u.idx.last_key);
> + block_iter_init(&ti->bi, &ti->block);
> +
> + err = block_iter_seek_key(&ti->bi, &want_index.u.idx.last_key);
> if (err < 0)
> goto done;
>
> diff --git a/t/unit-tests/t-reftable-block.c b/t/unit-tests/t-reftable-block.c
> index e36ed7ac576..c4ced39a73b 100644
> --- a/t/unit-tests/t-reftable-block.c
> +++ b/t/unit-tests/t-reftable-block.c
> @@ -66,7 +66,8 @@ static void t_ref_block_read_write(void)
> block_source_from_buf(&source ,&block_data);
> reftable_block_init(&block, &source, 0, header_off, block_size, REFTABLE_HASH_SIZE_SHA1);
>
> - block_iter_seek_start(&it, &block);
> + block_iter_init(&it, &block);
> + block_iter_seek_start(&it);If I'm understanding correctly, `block_iter_init()` already invokes `block_iter_seek_start()`. Why do we need to invoke `block_iter_seek_start()` again?
Show 114 quoted lines
>
> for (i = 0; ; i++) {
> ret = block_iter_next(&it, &rec);
> @@ -79,10 +80,9 @@ static void t_ref_block_read_write(void)
> }
>
> for (i = 0; i < N; i++) {
> - block_iter_reset(&it);
> reftable_record_key(&recs[i], &want);
>
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
> @@ -91,7 +91,7 @@ static void t_ref_block_read_write(void)
> check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1));
>
> want.len--;
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
> @@ -156,7 +156,8 @@ static void t_log_block_read_write(void)
> block_source_from_buf(&source, &block_data);
> reftable_block_init(&block, &source, 0, header_off, block_size, REFTABLE_HASH_SIZE_SHA1);
>
> - block_iter_seek_start(&it, &block);
> + block_iter_init(&it, &block);
> + block_iter_seek_start(&it);
>
> for (i = 0; ; i++) {
> ret = block_iter_next(&it, &rec);
> @@ -169,11 +170,10 @@ static void t_log_block_read_write(void)
> }
>
> for (i = 0; i < N; i++) {
> - block_iter_reset(&it);
> reftable_buf_reset(&want);
> check(!reftable_buf_addstr(&want, recs[i].u.log.refname));
>
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
> @@ -182,7 +182,7 @@ static void t_log_block_read_write(void)
> check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1));
>
> want.len--;
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
> @@ -249,7 +249,8 @@ static void t_obj_block_read_write(void)
> block_source_from_buf(&source, &block_data);
> reftable_block_init(&block, &source, 0, header_off, block_size, REFTABLE_HASH_SIZE_SHA1);
>
> - block_iter_seek_start(&it, &block);
> + block_iter_init(&it, &block);
> + block_iter_seek_start(&it);
>
> for (i = 0; ; i++) {
> ret = block_iter_next(&it, &rec);
> @@ -262,10 +263,9 @@ static void t_obj_block_read_write(void)
> }
>
> for (i = 0; i < N; i++) {
> - block_iter_reset(&it);
> reftable_record_key(&recs[i], &want);
>
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
> @@ -334,7 +334,8 @@ static void t_index_block_read_write(void)
> block_source_from_buf(&source, &block_data);
> reftable_block_init(&block, &source, 0, header_off, block_size, REFTABLE_HASH_SIZE_SHA1);
>
> - block_iter_seek_start(&it, &block);
> + block_iter_init(&it, &block);
> + block_iter_seek_start(&it);
>
> for (i = 0; ; i++) {
> ret = block_iter_next(&it, &rec);
> @@ -347,10 +348,9 @@ static void t_index_block_read_write(void)
> }
>
> for (i = 0; i < N; i++) {
> - block_iter_reset(&it);
> reftable_record_key(&recs[i], &want);
>
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
> @@ -359,7 +359,7 @@ static void t_index_block_read_write(void)
> check(reftable_record_equal(&recs[i], &rec, REFTABLE_HASH_SIZE_SHA1));
>
> want.len--;
> - ret = block_iter_seek_key(&it, &block, &want);
> + ret = block_iter_seek_key(&it, &want);
> check_int(ret, ==, 0);
>
> ret = block_iter_next(&it, &rec);
>
> --
> 2.49.0.604.gff1f9ca942.dirty
>
>