4cfe55166e
This adds a new `sdallocx` function to the external API, allowing the size to be passed by the caller. It avoids some extra reads in the thread cache fast path. In the case where stats are enabled, this avoids the work of calculating the size from the pointer. An assertion validates the size that's passed in, so enabling debugging will allow users of the API to debug cases where an incorrect size is passed in. The performance win for a contrived microbenchmark doing an allocation and immediately freeing it is ~10%. It may have a different impact on a real workload. Closes #28
58 lines
1.0 KiB
C
58 lines
1.0 KiB
C
#include "test/jemalloc_test.h"
|
|
|
|
#define MAXALIGN (((size_t)1) << 25)
|
|
#define NITER 4
|
|
|
|
TEST_BEGIN(test_basic)
|
|
{
|
|
void *ptr = mallocx(64, 0);
|
|
sdallocx(ptr, 64, 0);
|
|
}
|
|
TEST_END
|
|
|
|
TEST_BEGIN(test_alignment_and_size)
|
|
{
|
|
size_t nsz, sz, alignment, total;
|
|
unsigned i;
|
|
void *ps[NITER];
|
|
|
|
for (i = 0; i < NITER; i++)
|
|
ps[i] = NULL;
|
|
|
|
for (alignment = 8;
|
|
alignment <= MAXALIGN;
|
|
alignment <<= 1) {
|
|
total = 0;
|
|
for (sz = 1;
|
|
sz < 3 * alignment && sz < (1U << 31);
|
|
sz += (alignment >> (LG_SIZEOF_PTR-1)) - 1) {
|
|
for (i = 0; i < NITER; i++) {
|
|
nsz = nallocx(sz, MALLOCX_ALIGN(alignment) |
|
|
MALLOCX_ZERO);
|
|
ps[i] = mallocx(sz, MALLOCX_ALIGN(alignment) |
|
|
MALLOCX_ZERO);
|
|
total += nsz;
|
|
if (total >= (MAXALIGN << 1))
|
|
break;
|
|
}
|
|
for (i = 0; i < NITER; i++) {
|
|
if (ps[i] != NULL) {
|
|
sdallocx(ps[i], sz,
|
|
MALLOCX_ALIGN(alignment));
|
|
ps[i] = NULL;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
TEST_END
|
|
|
|
int
|
|
main(void)
|
|
{
|
|
|
|
return (test(
|
|
test_basic,
|
|
test_alignment_and_size));
|
|
}
|