server-skynet-source-3rd-je.../include/jemalloc/internal/chunk.h

84 lines
2.8 KiB
C
Raw Normal View History

/******************************************************************************/
#ifdef JEMALLOC_H_TYPES
/*
* Size and alignment of memory chunks that are allocated by the OS's virtual
* memory system.
*/
#define LG_CHUNK_DEFAULT 18
/* Return the chunk address for allocation address a. */
#define CHUNK_ADDR2BASE(a) \
((void *)((uintptr_t)(a) & ~chunksize_mask))
/* Return the chunk offset of address a. */
#define CHUNK_ADDR2OFFSET(a) \
((size_t)((uintptr_t)(a) & chunksize_mask))
/* Return the smallest chunk multiple that is >= s. */
#define CHUNK_CEILING(s) \
(((s) + chunksize_mask) & ~chunksize_mask)
#endif /* JEMALLOC_H_TYPES */
/******************************************************************************/
#ifdef JEMALLOC_H_STRUCTS
#endif /* JEMALLOC_H_STRUCTS */
/******************************************************************************/
#ifdef JEMALLOC_H_EXTERNS
extern size_t opt_lg_chunk;
extern const char *opt_dss;
extern rtree_t chunks_rtree;
extern size_t chunksize;
extern size_t chunksize_mask; /* (chunksize - 1). */
extern size_t chunk_npages;
bool chunk_register(const void *chunk, const extent_node_t *node);
void chunk_deregister(const void *chunk, const extent_node_t *node);
void *chunk_alloc_base(size_t size);
void *chunk_alloc_cache(arena_t *arena, void *new_addr, size_t size,
size_t alignment, bool *zero, bool dalloc_node);
Attempt to expand huge allocations in-place. This adds support for expanding huge allocations in-place by requesting memory at a specific address from the chunk allocator. It's currently only implemented for the chunk recycling path, although in theory it could also be done by optimistically allocating new chunks. On Linux, it could attempt an in-place mremap. However, that won't work in practice since the heap is grown downwards and memory is not unmapped (in a normal build, at least). Repeated vector reallocation micro-benchmark: #include <string.h> #include <stdlib.h> int main(void) { for (size_t i = 0; i < 100; i++) { void *ptr = NULL; size_t old_size = 0; for (size_t size = 4; size < (1 << 30); size *= 2) { ptr = realloc(ptr, size); if (!ptr) return 1; memset(ptr + old_size, 0xff, size - old_size); old_size = size; } free(ptr); } } The glibc allocator fails to do any in-place reallocations on this benchmark once it passes the M_MMAP_THRESHOLD (default 128k) but it elides the cost of copies via mremap, which is currently not something that jemalloc can use. With this improvement, jemalloc still fails to do any in-place huge reallocations for the first outer loop, but then succeeds 100% of the time for the remaining 99 iterations. The time spent doing allocations and copies drops down to under 5%, with nearly all of it spent doing purging + faulting (when huge pages are disabled) and the array memset. An improved mremap API (MREMAP_RETAIN - #138) would be far more general but this is a portable optimization and would still be useful on Linux for xallocx. Numbers with transparent huge pages enabled: glibc (copies elided via MREMAP_MAYMOVE): 8.471s jemalloc: 17.816s jemalloc + no-op madvise: 13.236s jemalloc + this commit: 6.787s jemalloc + this commit + no-op madvise: 6.144s Numbers with transparent huge pages disabled: glibc (copies elided via MREMAP_MAYMOVE): 15.403s jemalloc: 39.456s jemalloc + no-op madvise: 12.768s jemalloc + this commit: 15.534s jemalloc + this commit + no-op madvise: 6.354s Closes #137
2014-10-04 13:39:32 +08:00
void *chunk_alloc_default(void *new_addr, size_t size, size_t alignment,
bool *zero, unsigned arena_ind);
void *chunk_alloc_wrapper(arena_t *arena, chunk_alloc_t *chunk_alloc,
void *new_addr, size_t size, size_t alignment, bool *zero);
void chunk_record(arena_t *arena, extent_tree_t *chunks_szad,
extent_tree_t *chunks_ad, bool cache, void *chunk, size_t size,
bool zeroed);
void chunk_dalloc_cache(arena_t *arena, void *chunk, size_t size);
void chunk_dalloc_arena(arena_t *arena, void *chunk, size_t size,
bool zeroed);
bool chunk_dalloc_default(void *chunk, size_t size, unsigned arena_ind);
void chunk_dalloc_wrapper(arena_t *arena, chunk_dalloc_t *chunk_dalloc,
void *chunk, size_t size);
bool chunk_boot(void);
void chunk_prefork(void);
void chunk_postfork_parent(void);
void chunk_postfork_child(void);
#endif /* JEMALLOC_H_EXTERNS */
/******************************************************************************/
#ifdef JEMALLOC_H_INLINES
#ifndef JEMALLOC_ENABLE_INLINE
extent_node_t *chunk_lookup(const void *chunk);
#endif
#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_CHUNK_C_))
JEMALLOC_INLINE extent_node_t *
chunk_lookup(const void *chunk)
{
return (rtree_get(&chunks_rtree, (uintptr_t)chunk));
}
#endif
#endif /* JEMALLOC_H_INLINES */
/******************************************************************************/
2010-02-12 06:45:59 +08:00
#include "jemalloc/internal/chunk_dss.h"
#include "jemalloc/internal/chunk_mmap.h"