git/reftable/pq.c

103 lines
1.8 KiB
C
Raw Normal View History

/*
Copyright 2020 Google LLC
Use of this source code is governed by a BSD-style
license that can be found in the LICENSE file or at
https://developers.google.com/open-source/licenses/bsd
*/
#include "pq.h"
#include "reftable-record.h"
#include "system.h"
#include "basics.h"
int pq_less(struct pq_entry *a, struct pq_entry *b)
{
struct strbuf ak = STRBUF_INIT;
struct strbuf bk = STRBUF_INIT;
int cmp = 0;
reftable_record_key(&a->rec, &ak);
reftable_record_key(&b->rec, &bk);
cmp = strbuf_cmp(&ak, &bk);
strbuf_release(&ak);
strbuf_release(&bk);
if (cmp == 0)
return a->index > b->index;
return cmp < 0;
}
struct pq_entry merged_iter_pqueue_top(struct merged_iter_pqueue pq)
{
return pq.heap[0];
}
int merged_iter_pqueue_is_empty(struct merged_iter_pqueue pq)
{
return pq.len == 0;
}
struct pq_entry merged_iter_pqueue_remove(struct merged_iter_pqueue *pq)
{
int i = 0;
struct pq_entry e = pq->heap[0];
pq->heap[0] = pq->heap[pq->len - 1];
pq->len--;
i = 0;
while (i < pq->len) {
int min = i;
int j = 2 * i + 1;
int k = 2 * i + 2;
if (j < pq->len && pq_less(&pq->heap[j], &pq->heap[i])) {
min = j;
}
if (k < pq->len && pq_less(&pq->heap[k], &pq->heap[min])) {
min = k;
}
if (min == i) {
break;
}
SWAP(pq->heap[i], pq->heap[min]);
i = min;
}
return e;
}
void merged_iter_pqueue_add(struct merged_iter_pqueue *pq, const struct pq_entry *e)
{
int i = 0;
reftable: introduce macros to grow arrays 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> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2024-02-06 06:35:23 +00:00
REFTABLE_ALLOC_GROW(pq->heap, pq->len + 1, pq->cap);
pq->heap[pq->len++] = *e;
reftable: introduce macros to grow arrays 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> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2024-02-06 06:35:23 +00:00
i = pq->len - 1;
while (i > 0) {
int j = (i - 1) / 2;
if (pq_less(&pq->heap[j], &pq->heap[i])) {
break;
}
SWAP(pq->heap[j], pq->heap[i]);
i = j;
}
}
void merged_iter_pqueue_release(struct merged_iter_pqueue *pq)
{
int i = 0;
for (i = 0; i < pq->len; i++) {
reftable_record_release(&pq->heap[i].rec);
}
FREE_AND_NULL(pq->heap);
pq->len = pq->cap = 0;
}