diff mbox series

[v3,1/9] reftable: introduce macros to grow arrays

Message ID 12bd721ddff7020eb9e9ebd4e797d50193250bc0.1707200355.git.ps@pks.im (mailing list archive)
State Accepted
Commit f6b58c1be40ba4bd6e7f2364acfe5fa34ce04120
Headers show
Series reftable: code style improvements | expand

Commit Message

Patrick Steinhardt Feb. 6, 2024, 6:35 a.m. UTC
Throughout the reftable library we have many cases where we need to grow
arrays. In order to avoid too many reallocations, we roughly double the
capacity of the array on each iteration. The resulting code pattern is
duplicated across many sites.

We have similar patterns in our main codebase, which is why we have
eventually introduced an `ALLOC_GROW()` macro to abstract it away and
avoid some code duplication. We cannot easily reuse this macro here
though because `ALLOC_GROW()` uses `REALLOC_ARRAY()`, which in turn will
call realloc(3P) to grow the array. The reftable code is structured as a
library though (even if the boundaries are fuzzy), and one property this
brings with it is that it is possible to plug in your own allocators. So
instead of using realloc(3P), we need to use `reftable_realloc()` that
knows to use the user-provided implementation.

So let's introduce two new macros `REFTABLE_REALLOC_ARRAY()` and
`REFTABLE_ALLOC_GROW()` that mirror what we do in our main codebase,
with two modifications:

  - They use `reftable_realloc()`, as explained above.

  - They use a different growth factor of `2 * cap + 1` instead of `(cap
    + 16) * 3 / 2`.

The second change is because we know a bit more about the allocation
patterns in the reftable library. In most cases, we end up only having a
handful of items in the array and don't end up growing them. The initial
capacity that our normal growth factor uses (which is 24) would thus end
up over-allocating in a lot of code paths. This effect is measurable:

  - Before change:

      HEAP SUMMARY:
          in use at exit: 671,983 bytes in 152 blocks
        total heap usage: 3,843,446 allocs, 3,843,294 frees, 223,761,402 bytes allocated

  - After change with a growth factor of `(2 * alloc + 1)`:

      HEAP SUMMARY:
          in use at exit: 671,983 bytes in 152 blocks
        total heap usage: 3,843,446 allocs, 3,843,294 frees, 223,761,410 bytes allocated

  - After change with a growth factor of `(alloc + 16)* 2 / 3`:

      HEAP SUMMARY:
          in use at exit: 671,983 bytes in 152 blocks
        total heap usage: 3,833,673 allocs, 3,833,521 frees, 4,728,251,742 bytes allocated

While the total heap usage is roughly the same, we do end up allocating
significantly more bytes with our usual growth factor (in fact, roughly
21 times as many).

Convert the reftable library to use these new macros.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 reftable/basics.c      |  8 ++------
 reftable/basics.h      | 11 +++++++++++
 reftable/block.c       |  7 +------
 reftable/merged_test.c | 20 ++++++--------------
 reftable/pq.c          |  8 ++------
 reftable/stack.c       | 29 ++++++++++++-----------------
 reftable/writer.c      | 14 ++------------
 7 files changed, 36 insertions(+), 61 deletions(-)
diff mbox series

Patch

diff --git a/reftable/basics.c b/reftable/basics.c
index f761e48028..af9004cec2 100644
--- a/reftable/basics.c
+++ b/reftable/basics.c
@@ -89,17 +89,13 @@  void parse_names(char *buf, int size, char ***namesp)
 			next = end;
 		}
 		if (p < next) {
-			if (names_len == names_cap) {
-				names_cap = 2 * names_cap + 1;
-				names = reftable_realloc(
-					names, names_cap * sizeof(*names));
-			}
+			REFTABLE_ALLOC_GROW(names, names_len + 1, names_cap);
 			names[names_len++] = xstrdup(p);
 		}
 		p = next + 1;
 	}
 
-	names = reftable_realloc(names, (names_len + 1) * sizeof(*names));
+	REFTABLE_REALLOC_ARRAY(names, names_len + 1);
 	names[names_len] = NULL;
 	*namesp = names;
 }
diff --git a/reftable/basics.h b/reftable/basics.h
index 096b36862b..2f855cd724 100644
--- a/reftable/basics.h
+++ b/reftable/basics.h
@@ -53,6 +53,17 @@  void *reftable_realloc(void *p, size_t sz);
 void reftable_free(void *p);
 void *reftable_calloc(size_t sz);
 
+#define REFTABLE_REALLOC_ARRAY(x, alloc) (x) = reftable_realloc((x), st_mult(sizeof(*(x)), (alloc)))
+#define REFTABLE_ALLOC_GROW(x, nr, alloc) \
+	do { \
+		if ((nr) > alloc) { \
+			alloc = 2 * (alloc) + 1; \
+			if (alloc < (nr)) \
+				alloc = (nr); \
+			REFTABLE_REALLOC_ARRAY(x, alloc); \
+		} \
+	} while (0)
+
 /* Find the longest shared prefix size of `a` and `b` */
 struct strbuf;
 int common_prefix_size(struct strbuf *a, struct strbuf *b);
diff --git a/reftable/block.c b/reftable/block.c
index 1df3d8a0f0..6952d0facf 100644
--- a/reftable/block.c
+++ b/reftable/block.c
@@ -51,12 +51,7 @@  static int block_writer_register_restart(struct block_writer *w, int n,
 	if (2 + 3 * rlen + n > w->block_size - w->next)
 		return -1;
 	if (is_restart) {
-		if (w->restart_len == w->restart_cap) {
-			w->restart_cap = w->restart_cap * 2 + 1;
-			w->restarts = reftable_realloc(
-				w->restarts, sizeof(uint32_t) * w->restart_cap);
-		}
-
+		REFTABLE_ALLOC_GROW(w->restarts, w->restart_len + 1, w->restart_cap);
 		w->restarts[w->restart_len++] = w->next;
 	}
 
diff --git a/reftable/merged_test.c b/reftable/merged_test.c
index 46908f738f..e05351e035 100644
--- a/reftable/merged_test.c
+++ b/reftable/merged_test.c
@@ -231,14 +231,10 @@  static void test_merged(void)
 	while (len < 100) { /* cap loops/recursion. */
 		struct reftable_ref_record ref = { NULL };
 		int err = reftable_iterator_next_ref(&it, &ref);
-		if (err > 0) {
+		if (err > 0)
 			break;
-		}
-		if (len == cap) {
-			cap = 2 * cap + 1;
-			out = reftable_realloc(
-				out, sizeof(struct reftable_ref_record) * cap);
-		}
+
+		REFTABLE_ALLOC_GROW(out, len + 1, cap);
 		out[len++] = ref;
 	}
 	reftable_iterator_destroy(&it);
@@ -368,14 +364,10 @@  static void test_merged_logs(void)
 	while (len < 100) { /* cap loops/recursion. */
 		struct reftable_log_record log = { NULL };
 		int err = reftable_iterator_next_log(&it, &log);
-		if (err > 0) {
+		if (err > 0)
 			break;
-		}
-		if (len == cap) {
-			cap = 2 * cap + 1;
-			out = reftable_realloc(
-				out, sizeof(struct reftable_log_record) * cap);
-		}
+
+		REFTABLE_ALLOC_GROW(out, len + 1, cap);
 		out[len++] = log;
 	}
 	reftable_iterator_destroy(&it);
diff --git a/reftable/pq.c b/reftable/pq.c
index dcefeb793a..2461daf5ff 100644
--- a/reftable/pq.c
+++ b/reftable/pq.c
@@ -75,13 +75,9 @@  void merged_iter_pqueue_add(struct merged_iter_pqueue *pq, const struct pq_entry
 {
 	int i = 0;
 
-	if (pq->len == pq->cap) {
-		pq->cap = 2 * pq->cap + 1;
-		pq->heap = reftable_realloc(pq->heap,
-					    pq->cap * sizeof(struct pq_entry));
-	}
-
+	REFTABLE_ALLOC_GROW(pq->heap, pq->len + 1, pq->cap);
 	pq->heap[pq->len++] = *e;
+
 	i = pq->len - 1;
 	while (i > 0) {
 		int j = (i - 1) / 2;
diff --git a/reftable/stack.c b/reftable/stack.c
index bf3869ce70..1dfab99e96 100644
--- a/reftable/stack.c
+++ b/reftable/stack.c
@@ -551,7 +551,7 @@  struct reftable_addition {
 	struct reftable_stack *stack;
 
 	char **new_tables;
-	int new_tables_len;
+	size_t new_tables_len, new_tables_cap;
 	uint64_t next_update_index;
 };
 
@@ -602,8 +602,9 @@  static int reftable_stack_init_addition(struct reftable_addition *add,
 
 static void reftable_addition_close(struct reftable_addition *add)
 {
-	int i = 0;
 	struct strbuf nm = STRBUF_INIT;
+	size_t i;
+
 	for (i = 0; i < add->new_tables_len; i++) {
 		stack_filename(&nm, add->stack, add->new_tables[i]);
 		unlink(nm.buf);
@@ -613,6 +614,7 @@  static void reftable_addition_close(struct reftable_addition *add)
 	reftable_free(add->new_tables);
 	add->new_tables = NULL;
 	add->new_tables_len = 0;
+	add->new_tables_cap = 0;
 
 	delete_tempfile(&add->lock_file);
 	strbuf_release(&nm);
@@ -631,8 +633,8 @@  int reftable_addition_commit(struct reftable_addition *add)
 {
 	struct strbuf table_list = STRBUF_INIT;
 	int lock_file_fd = get_tempfile_fd(add->lock_file);
-	int i = 0;
 	int err = 0;
+	size_t i;
 
 	if (add->new_tables_len == 0)
 		goto done;
@@ -660,12 +662,12 @@  int reftable_addition_commit(struct reftable_addition *add)
 	}
 
 	/* success, no more state to clean up. */
-	for (i = 0; i < add->new_tables_len; i++) {
+	for (i = 0; i < add->new_tables_len; i++)
 		reftable_free(add->new_tables[i]);
-	}
 	reftable_free(add->new_tables);
 	add->new_tables = NULL;
 	add->new_tables_len = 0;
+	add->new_tables_cap = 0;
 
 	err = reftable_stack_reload_maybe_reuse(add->stack, 1);
 	if (err)
@@ -792,11 +794,9 @@  int reftable_addition_add(struct reftable_addition *add,
 		goto done;
 	}
 
-	add->new_tables = reftable_realloc(add->new_tables,
-					   sizeof(*add->new_tables) *
-						   (add->new_tables_len + 1));
-	add->new_tables[add->new_tables_len] = strbuf_detach(&next_name, NULL);
-	add->new_tables_len++;
+	REFTABLE_ALLOC_GROW(add->new_tables, add->new_tables_len + 1,
+			    add->new_tables_cap);
+	add->new_tables[add->new_tables_len++] = strbuf_detach(&next_name, NULL);
 done:
 	if (tab_fd > 0) {
 		close(tab_fd);
@@ -1367,17 +1367,12 @@  static int stack_check_addition(struct reftable_stack *st,
 	while (1) {
 		struct reftable_ref_record ref = { NULL };
 		err = reftable_iterator_next_ref(&it, &ref);
-		if (err > 0) {
+		if (err > 0)
 			break;
-		}
 		if (err < 0)
 			goto done;
 
-		if (len >= cap) {
-			cap = 2 * cap + 1;
-			refs = reftable_realloc(refs, cap * sizeof(refs[0]));
-		}
-
+		REFTABLE_ALLOC_GROW(refs, len + 1, cap);
 		refs[len++] = ref;
 	}
 
diff --git a/reftable/writer.c b/reftable/writer.c
index ee4590e20f..4483bb21c3 100644
--- a/reftable/writer.c
+++ b/reftable/writer.c
@@ -200,12 +200,7 @@  static void writer_index_hash(struct reftable_writer *w, struct strbuf *hash)
 		return;
 	}
 
-	if (key->offset_len == key->offset_cap) {
-		key->offset_cap = 2 * key->offset_cap + 1;
-		key->offsets = reftable_realloc(
-			key->offsets, sizeof(uint64_t) * key->offset_cap);
-	}
-
+	REFTABLE_ALLOC_GROW(key->offsets, key->offset_len + 1, key->offset_cap);
 	key->offsets[key->offset_len++] = off;
 }
 
@@ -674,12 +669,7 @@  static int writer_flush_nonempty_block(struct reftable_writer *w)
 	if (err < 0)
 		return err;
 
-	if (w->index_cap == w->index_len) {
-		w->index_cap = 2 * w->index_cap + 1;
-		w->index = reftable_realloc(
-			w->index,
-			sizeof(struct reftable_index_record) * w->index_cap);
-	}
+	REFTABLE_ALLOC_GROW(w->index, w->index_len + 1, w->index_cap);
 
 	ir.offset = w->next;
 	strbuf_reset(&ir.last_key);