1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
|
/*****************************************************************************
Copyright (c) 2006, 2013, Oracle and/or its affiliates. All Rights Reserved.
This program is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free Software
Foundation; version 2 of the License.
This program is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
You should have received a copy of the GNU General Public License along with
this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin Street, Suite 500, Boston, MA 02110-1335 USA
*****************************************************************************/
/**************************************************//**
@file buf/buf0buddy.cc
Binary buddy allocator for compressed pages
Created December 2006 by Marko Makela
*******************************************************/
#define THIS_MODULE
#include "buf0buddy.h"
#ifdef UNIV_NONINL
# include "buf0buddy.ic"
#endif
#undef THIS_MODULE
#include "buf0buf.h"
#include "buf0lru.h"
#include "buf0flu.h"
#include "page0zip.h"
#include "srv0start.h"
/** When freeing a buf we attempt to coalesce by looking at its buddy
and deciding whether it is free or not. To ascertain if the buddy is
free we look for BUF_BUDDY_STAMP_FREE at BUF_BUDDY_STAMP_OFFSET
within the buddy. The question is how we can be sure that it is
safe to look at BUF_BUDDY_STAMP_OFFSET.
The answer lies in following invariants:
* All blocks allocated by buddy allocator are used for compressed
page frame.
* A compressed table always have space_id < SRV_LOG_SPACE_FIRST_ID
* BUF_BUDDY_STAMP_OFFSET always points to the space_id field in
a frame.
-- The above is true because we look at these fields when the
corresponding buddy block is free which implies that:
* The block we are looking at must have an address aligned at
the same size that its free buddy has. For example, if we have
a free block of 8K then its buddy's address must be aligned at
8K as well.
* It is possible that the block we are looking at may have been
further divided into smaller sized blocks but its starting
address must still remain the start of a page frame i.e.: it
cannot be middle of a block. For example, if we have a free
block of size 8K then its buddy may be divided into blocks
of, say, 1K, 1K, 2K, 4K but the buddy's address will still be
the starting address of first 1K compressed page.
* What is important to note is that for any given block, the
buddy's address cannot be in the middle of a larger block i.e.:
in above example, our 8K block cannot have a buddy whose address
is aligned on 8K but it is part of a larger 16K block.
*/
/** Offset within buf_buddy_free_t where free or non_free stamps
are written.*/
#define BUF_BUDDY_STAMP_OFFSET FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID
/** Value that we stamp on all buffers that are currently on the zip_free
list. This value is stamped at BUF_BUDDY_STAMP_OFFSET offset */
#define BUF_BUDDY_STAMP_FREE (SRV_LOG_SPACE_FIRST_ID)
/** Stamp value for non-free buffers. Will be overwritten by a non-zero
value by the consumer of the block */
#define BUF_BUDDY_STAMP_NONFREE (0XFFFFFFFF)
#if BUF_BUDDY_STAMP_FREE >= BUF_BUDDY_STAMP_NONFREE
# error "BUF_BUDDY_STAMP_FREE >= BUF_BUDDY_STAMP_NONFREE"
#endif
/** Return type of buf_buddy_is_free() */
enum buf_buddy_state_t {
BUF_BUDDY_STATE_FREE, /*!< If the buddy to completely free */
BUF_BUDDY_STATE_USED, /*!< Buddy currently in used */
BUF_BUDDY_STATE_PARTIALLY_USED/*!< Some sub-blocks in the buddy
are in use */
};
#ifdef UNIV_DEBUG_VALGRIND
/**********************************************************************//**
Invalidate memory area that we won't access while page is free */
UNIV_INLINE
void
buf_buddy_mem_invalid(
/*==================*/
buf_buddy_free_t* buf, /*!< in: block to check */
ulint i) /*!< in: index of zip_free[] */
{
const size_t size = BUF_BUDDY_LOW << i;
ut_ad(i <= BUF_BUDDY_SIZES);
UNIV_MEM_ASSERT_W(buf, size);
UNIV_MEM_INVALID(buf, size);
}
#else /* UNIV_DEBUG_VALGRIND */
# define buf_buddy_mem_invalid(buf, i) ut_ad((i) <= BUF_BUDDY_SIZES)
#endif /* UNIV_DEBUG_VALGRIND */
/**********************************************************************//**
Check if a buddy is stamped free.
@return whether the buddy is free */
UNIV_INLINE __attribute__((warn_unused_result))
bool
buf_buddy_stamp_is_free(
/*====================*/
const buf_buddy_free_t* buf) /*!< in: block to check */
{
return(mach_read_from_4(buf->stamp.bytes + BUF_BUDDY_STAMP_OFFSET)
== BUF_BUDDY_STAMP_FREE);
}
/**********************************************************************//**
Stamps a buddy free. */
UNIV_INLINE
void
buf_buddy_stamp_free(
/*=================*/
buf_buddy_free_t* buf, /*!< in/out: block to stamp */
ulint i) /*!< in: block size */
{
ut_d(memset(buf, static_cast<int>(i), BUF_BUDDY_LOW << i));
buf_buddy_mem_invalid(buf, i);
mach_write_to_4(buf->stamp.bytes + BUF_BUDDY_STAMP_OFFSET,
BUF_BUDDY_STAMP_FREE);
buf->stamp.size = i;
}
/**********************************************************************//**
Stamps a buddy nonfree.
@param[in/out] buf block to stamp
@param[in] i block size */
#define buf_buddy_stamp_nonfree(buf, i) do { \
buf_buddy_mem_invalid(buf, i); \
memset(buf->stamp.bytes + BUF_BUDDY_STAMP_OFFSET, 0xff, 4); \
} while (0)
#if BUF_BUDDY_STAMP_NONFREE != 0xffffffff
# error "BUF_BUDDY_STAMP_NONFREE != 0xffffffff"
#endif
/**********************************************************************//**
Get the offset of the buddy of a compressed page frame.
@return the buddy relative of page */
UNIV_INLINE
void*
buf_buddy_get(
/*==========*/
byte* page, /*!< in: compressed page */
ulint size) /*!< in: page size in bytes */
{
ut_ad(ut_is_2pow(size));
ut_ad(size >= BUF_BUDDY_LOW);
ut_ad(BUF_BUDDY_LOW <= UNIV_ZIP_SIZE_MIN);
ut_ad(size < BUF_BUDDY_HIGH);
ut_ad(BUF_BUDDY_HIGH == UNIV_PAGE_SIZE);
ut_ad(!ut_align_offset(page, size));
if (((ulint) page) & size) {
return(page - size);
} else {
return(page + size);
}
}
/** Validate a given zip_free list. */
struct CheckZipFree {
ulint i;
CheckZipFree(ulint i) : i (i) {}
void operator()(const buf_buddy_free_t* elem) const
{
ut_a(buf_buddy_stamp_is_free(elem));
ut_a(elem->stamp.size <= i);
}
};
#define BUF_BUDDY_LIST_VALIDATE(bp, i) \
UT_LIST_VALIDATE(list, buf_buddy_free_t, \
bp->zip_free[i], CheckZipFree(i))
#ifdef UNIV_DEBUG
/**********************************************************************//**
Debug function to validate that a buffer is indeed free i.e.: in the
zip_free[].
@return true if free */
UNIV_INLINE
bool
buf_buddy_check_free(
/*=================*/
buf_pool_t* buf_pool,/*!< in: buffer pool instance */
const buf_buddy_free_t* buf, /*!< in: block to check */
ulint i) /*!< in: index of buf_pool->zip_free[] */
{
const ulint size = BUF_BUDDY_LOW << i;
ut_ad(mutex_own(&buf_pool->zip_free_mutex));
ut_ad(!ut_align_offset(buf, size));
ut_ad(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
buf_buddy_free_t* itr;
for (itr = UT_LIST_GET_FIRST(buf_pool->zip_free[i]);
itr && itr != buf;
itr = UT_LIST_GET_NEXT(list, itr)) {
}
return(itr == buf);
}
#endif /* UNIV_DEBUG */
/**********************************************************************//**
Checks if a buf is free i.e.: in the zip_free[].
@retval BUF_BUDDY_STATE_FREE if fully free
@retval BUF_BUDDY_STATE_USED if currently in use
@retval BUF_BUDDY_STATE_PARTIALLY_USED if partially in use. */
static __attribute__((warn_unused_result))
buf_buddy_state_t
buf_buddy_is_free(
/*==============*/
buf_buddy_free_t* buf, /*!< in: block to check */
ulint i) /*!< in: index of
buf_pool->zip_free[] */
{
#ifdef UNIV_DEBUG
const ulint size = BUF_BUDDY_LOW << i;
ut_ad(!ut_align_offset(buf, size));
ut_ad(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
#endif /* UNIV_DEBUG */
/* We assume that all memory from buf_buddy_alloc()
is used for compressed page frames. */
/* We look inside the allocated objects returned by
buf_buddy_alloc() and assume that each block is a compressed
page that contains one of the following in space_id.
* BUF_BUDDY_STAMP_FREE if the block is in a zip_free list or
* BUF_BUDDY_STAMP_NONFREE if the block has been allocated but
not initialized yet or
* A valid space_id of a compressed tablespace
The call below attempts to read from free memory. The memory
is "owned" by the buddy allocator (and it has been allocated
from the buffer pool), so there is nothing wrong about this. */
if (!buf_buddy_stamp_is_free(buf)) {
return(BUF_BUDDY_STATE_USED);
}
/* A block may be free but a fragment of it may still be in use.
To guard against that we write the free block size in terms of
zip_free index at start of stamped block. Note that we can
safely rely on this value only if the buf is free. */
ut_ad(buf->stamp.size <= i);
return(buf->stamp.size == i
? BUF_BUDDY_STATE_FREE
: BUF_BUDDY_STATE_PARTIALLY_USED);
}
/**********************************************************************//**
Add a block to the head of the appropriate buddy free list. */
UNIV_INLINE
void
buf_buddy_add_to_free(
/*==================*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
buf_buddy_free_t* buf, /*!< in,own: block to be freed */
ulint i) /*!< in: index of
buf_pool->zip_free[] */
{
ut_ad(mutex_own(&buf_pool->zip_free_mutex));
ut_ad(buf_pool->zip_free[i].start != buf);
buf_buddy_stamp_free(buf, i);
UT_LIST_ADD_FIRST(list, buf_pool->zip_free[i], buf);
ut_d(BUF_BUDDY_LIST_VALIDATE(buf_pool, i));
}
/**********************************************************************//**
Remove a block from the appropriate buddy free list. */
UNIV_INLINE
void
buf_buddy_remove_from_free(
/*=======================*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
buf_buddy_free_t* buf, /*!< in,own: block to be freed */
ulint i) /*!< in: index of
buf_pool->zip_free[] */
{
ut_ad(mutex_own(&buf_pool->zip_free_mutex));
ut_ad(buf_buddy_check_free(buf_pool, buf, i));
UT_LIST_REMOVE(list, buf_pool->zip_free[i], buf);
buf_buddy_stamp_nonfree(buf, i);
}
/**********************************************************************//**
Try to allocate a block from buf_pool->zip_free[].
@return allocated block, or NULL if buf_pool->zip_free[] was empty */
static
buf_buddy_free_t*
buf_buddy_alloc_zip(
/*================*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
ulint i) /*!< in: index of buf_pool->zip_free[] */
{
buf_buddy_free_t* buf;
ut_ad(mutex_own(&buf_pool->zip_free_mutex));
ut_a(i < BUF_BUDDY_SIZES);
ut_a(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
ut_d(BUF_BUDDY_LIST_VALIDATE(buf_pool, i));
buf = UT_LIST_GET_FIRST(buf_pool->zip_free[i]);
if (buf) {
buf_buddy_remove_from_free(buf_pool, buf, i);
} else if (i + 1 < BUF_BUDDY_SIZES) {
/* Attempt to split. */
buf = buf_buddy_alloc_zip(buf_pool, i + 1);
if (buf) {
buf_buddy_free_t* buddy =
reinterpret_cast<buf_buddy_free_t*>(
buf->stamp.bytes
+ (BUF_BUDDY_LOW << i));
ut_ad(!buf_pool_contains_zip(buf_pool, buddy));
buf_buddy_add_to_free(buf_pool, buddy, i);
}
}
if (buf) {
/* Trash the page other than the BUF_BUDDY_STAMP_NONFREE. */
UNIV_MEM_TRASH(buf, ~i, BUF_BUDDY_STAMP_OFFSET);
UNIV_MEM_TRASH(BUF_BUDDY_STAMP_OFFSET + 4
+ buf->stamp.bytes, ~i,
(BUF_BUDDY_LOW << i)
- (BUF_BUDDY_STAMP_OFFSET + 4));
ut_ad(mach_read_from_4(buf->stamp.bytes
+ BUF_BUDDY_STAMP_OFFSET)
== BUF_BUDDY_STAMP_NONFREE);
}
return(buf);
}
/**********************************************************************//**
Deallocate a buffer frame of UNIV_PAGE_SIZE. */
static
void
buf_buddy_block_free(
/*=================*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
void* buf) /*!< in: buffer frame to deallocate */
{
const ulint fold = BUF_POOL_ZIP_FOLD_PTR(buf);
buf_page_t* bpage;
buf_block_t* block;
ut_ad(!mutex_own(&buf_pool->zip_mutex));
ut_a(!ut_align_offset(buf, UNIV_PAGE_SIZE));
mutex_enter(&buf_pool->zip_hash_mutex);
HASH_SEARCH(hash, buf_pool->zip_hash, fold, buf_page_t*, bpage,
ut_ad(buf_page_get_state(bpage) == BUF_BLOCK_MEMORY
&& bpage->in_zip_hash && !bpage->in_page_hash),
((buf_block_t*) bpage)->frame == buf);
ut_a(bpage);
ut_a(buf_page_get_state(bpage) == BUF_BLOCK_MEMORY);
ut_ad(!bpage->in_page_hash);
ut_ad(bpage->in_zip_hash);
ut_d(bpage->in_zip_hash = FALSE);
HASH_DELETE(buf_page_t, hash, buf_pool->zip_hash, fold, bpage);
mutex_exit(&buf_pool->zip_hash_mutex);
ut_d(memset(buf, 0, UNIV_PAGE_SIZE));
UNIV_MEM_INVALID(buf, UNIV_PAGE_SIZE);
block = (buf_block_t*) bpage;
mutex_enter(&block->mutex);
buf_LRU_block_free_non_file_page(block);
mutex_exit(&block->mutex);
ut_ad(buf_pool->buddy_n_frames > 0);
ut_d(buf_pool->buddy_n_frames--);
}
/**********************************************************************//**
Allocate a buffer block to the buddy allocator. */
static
void
buf_buddy_block_register(
/*=====================*/
buf_block_t* block) /*!< in: buffer frame to allocate */
{
buf_pool_t* buf_pool = buf_pool_from_block(block);
const ulint fold = BUF_POOL_ZIP_FOLD(block);
ut_ad(!mutex_own(&buf_pool->zip_mutex));
ut_ad(buf_block_get_state(block) == BUF_BLOCK_READY_FOR_USE);
buf_block_set_state(block, BUF_BLOCK_MEMORY);
ut_a(block->frame);
ut_a(!ut_align_offset(block->frame, UNIV_PAGE_SIZE));
ut_ad(!block->page.in_page_hash);
ut_ad(!block->page.in_zip_hash);
ut_d(block->page.in_zip_hash = TRUE);
mutex_enter(&buf_pool->zip_hash_mutex);
HASH_INSERT(buf_page_t, hash, buf_pool->zip_hash, fold, &block->page);
mutex_exit(&buf_pool->zip_hash_mutex);
ut_d(buf_pool->buddy_n_frames++);
}
/**********************************************************************//**
Allocate a block from a bigger object.
@return allocated block */
static
void*
buf_buddy_alloc_from(
/*=================*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
void* buf, /*!< in: a block that is free to use */
ulint i, /*!< in: index of
buf_pool->zip_free[] */
ulint j) /*!< in: size of buf as an index
of buf_pool->zip_free[] */
{
ulint offs = BUF_BUDDY_LOW << j;
ut_ad(mutex_own(&buf_pool->zip_free_mutex));
ut_ad(j <= BUF_BUDDY_SIZES);
ut_ad(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
ut_ad(j >= i);
ut_ad(!ut_align_offset(buf, offs));
/* Add the unused parts of the block to the free lists. */
while (j > i) {
buf_buddy_free_t* zip_buf;
offs >>= 1;
j--;
zip_buf = reinterpret_cast<buf_buddy_free_t*>(
reinterpret_cast<byte*>(buf) + offs);
buf_buddy_add_to_free(buf_pool, zip_buf, j);
}
buf_buddy_stamp_nonfree(reinterpret_cast<buf_buddy_free_t*>(buf), i);
return(buf);
}
/**********************************************************************//**
Allocate a block. The thread calling this function must hold
buf_pool->LRU_list_mutex and must not hold buf_pool->zip_mutex or any
block->mutex. The buf_pool->LRU_list_mutex may be released and reacquired.
@return allocated block, never NULL */
UNIV_INTERN
void*
buf_buddy_alloc_low(
/*================*/
buf_pool_t* buf_pool, /*!< in/out: buffer pool instance */
ulint i, /*!< in: index of buf_pool->zip_free[],
or BUF_BUDDY_SIZES */
ibool* lru) /*!< in: pointer to a variable that
will be assigned TRUE if storage was
allocated from the LRU list and
buf_pool->LRU_list_mutex was
temporarily released */
{
buf_block_t* block;
ut_ad(lru);
ut_ad(mutex_own(&buf_pool->LRU_list_mutex));
ut_ad(!mutex_own(&buf_pool->zip_mutex));
ut_ad(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
if (i < BUF_BUDDY_SIZES) {
/* Try to allocate from the buddy system. */
mutex_enter(&buf_pool->zip_free_mutex);
block = (buf_block_t*) buf_buddy_alloc_zip(buf_pool, i);
if (block) {
goto func_exit;
}
mutex_exit(&buf_pool->zip_free_mutex);
}
/* Try allocating from the buf_pool->free list. */
block = buf_LRU_get_free_only(buf_pool);
if (block) {
goto alloc_big;
}
/* Try replacing an uncompressed page in the buffer pool. */
mutex_exit(&buf_pool->LRU_list_mutex);
block = buf_LRU_get_free_block(buf_pool);
*lru = TRUE;
mutex_enter(&buf_pool->LRU_list_mutex);
alloc_big:
buf_buddy_block_register(block);
mutex_enter(&buf_pool->zip_free_mutex);
block = (buf_block_t*) buf_buddy_alloc_from(
buf_pool, block->frame, i, BUF_BUDDY_SIZES);
func_exit:
buf_pool->buddy_stat[i].used++;
mutex_exit(&buf_pool->zip_free_mutex);
return(block);
}
/**********************************************************************//**
Try to relocate a block. The caller must hold zip_free_mutex, and this
function will release and lock it again.
@return true if relocated */
static
bool
buf_buddy_relocate(
/*===============*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
void* src, /*!< in: block to relocate */
void* dst, /*!< in: free block to relocate to */
ulint i) /*!< in: index of
buf_pool->zip_free[] */
{
buf_page_t* bpage;
const ulint size = BUF_BUDDY_LOW << i;
ulint space;
ulint offset;
ut_ad(mutex_own(&buf_pool->zip_free_mutex));
ut_ad(!mutex_own(&buf_pool->zip_mutex));
ut_ad(!ut_align_offset(src, size));
ut_ad(!ut_align_offset(dst, size));
ut_ad(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
UNIV_MEM_ASSERT_W(dst, size);
space = mach_read_from_4((const byte*) src
+ FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
offset = mach_read_from_4((const byte*) src
+ FIL_PAGE_OFFSET);
/* Suppress Valgrind warnings about conditional jump
on uninitialized value. */
UNIV_MEM_VALID(&space, sizeof space);
UNIV_MEM_VALID(&offset, sizeof offset);
ut_ad(space != BUF_BUDDY_STAMP_FREE);
mutex_exit(&buf_pool->zip_free_mutex);
ulint fold = buf_page_address_fold(space, offset);
prio_rw_lock_t* hash_lock = buf_page_hash_lock_get(buf_pool, fold);
rw_lock_x_lock(hash_lock);
bpage = buf_page_hash_get_low(buf_pool, space, offset, fold);
if (!bpage || bpage->zip.data != src) {
/* The block has probably been freshly
allocated by buf_LRU_get_free_block() but not
added to buf_pool->page_hash yet. Obviously,
it cannot be relocated. */
rw_lock_x_unlock(hash_lock);
mutex_enter(&buf_pool->zip_free_mutex);
return(false);
}
if (page_zip_get_size(&bpage->zip) != size) {
/* The block is of different size. We would
have to relocate all blocks covered by src.
For the sake of simplicity, give up. */
ut_ad(page_zip_get_size(&bpage->zip) < size);
rw_lock_x_unlock(hash_lock);
mutex_enter(&buf_pool->zip_free_mutex);
return(false);
}
/* The block must have been allocated, but it may
contain uninitialized data. */
UNIV_MEM_ASSERT_W(src, size);
ib_mutex_t* block_mutex = buf_page_get_mutex(bpage);
mutex_enter(block_mutex);
mutex_enter(&buf_pool->zip_free_mutex);
if (buf_page_can_relocate(bpage)) {
/* Relocate the compressed page. */
ullint usec = ut_time_us(NULL);
ut_a(bpage->zip.data == src);
/* Note: This is potentially expensive, we need a better
solution here. We go with correctness for now. */
::memcpy(dst, src, size);
bpage->zip.data = reinterpret_cast<page_zip_t*>(dst);
rw_lock_x_unlock(hash_lock);
mutex_exit(block_mutex);
buf_buddy_mem_invalid(
reinterpret_cast<buf_buddy_free_t*>(src), i);
buf_buddy_stat_t* buddy_stat = &buf_pool->buddy_stat[i];
++buddy_stat->relocated;
buddy_stat->relocated_usec += ut_time_us(NULL) - usec;
return(true);
}
rw_lock_x_unlock(hash_lock);
mutex_exit(block_mutex);
return(false);
}
/**********************************************************************//**
Deallocate a block. */
UNIV_INTERN
void
buf_buddy_free_low(
/*===============*/
buf_pool_t* buf_pool, /*!< in: buffer pool instance */
void* buf, /*!< in: block to be freed, must not be
pointed to by the buffer pool */
ulint i) /*!< in: index of buf_pool->zip_free[],
or BUF_BUDDY_SIZES */
{
buf_buddy_free_t* buddy;
ut_ad(!mutex_own(&buf_pool->zip_mutex));
ut_ad(i <= BUF_BUDDY_SIZES);
ut_ad(i >= buf_buddy_get_slot(UNIV_ZIP_SIZE_MIN));
mutex_enter(&buf_pool->zip_free_mutex);
ut_ad(buf_pool->buddy_stat[i].used > 0);
buf_pool->buddy_stat[i].used--;
recombine:
UNIV_MEM_ASSERT_AND_ALLOC(buf, BUF_BUDDY_LOW << i);
if (i == BUF_BUDDY_SIZES) {
mutex_exit(&buf_pool->zip_free_mutex);
buf_buddy_block_free(buf_pool, buf);
return;
}
ut_ad(i < BUF_BUDDY_SIZES);
ut_ad(buf == ut_align_down(buf, BUF_BUDDY_LOW << i));
ut_ad(!buf_pool_contains_zip(buf_pool, buf));
/* Do not recombine blocks if there are few free blocks.
We may waste up to 15360*max_len bytes to free blocks
(1024 + 2048 + 4096 + 8192 = 15360) */
if (UT_LIST_GET_LEN(buf_pool->zip_free[i]) < 16) {
goto func_exit;
}
/* Try to combine adjacent blocks. */
buddy = reinterpret_cast<buf_buddy_free_t*>(
buf_buddy_get(reinterpret_cast<byte*>(buf),
BUF_BUDDY_LOW << i));
switch (buf_buddy_is_free(buddy, i)) {
case BUF_BUDDY_STATE_FREE:
/* The buddy is free: recombine */
buf_buddy_remove_from_free(buf_pool, buddy, i);
buddy_is_free:
ut_ad(!buf_pool_contains_zip(buf_pool, buddy));
i++;
buf = ut_align_down(buf, BUF_BUDDY_LOW << i);
goto recombine;
case BUF_BUDDY_STATE_USED:
ut_d(BUF_BUDDY_LIST_VALIDATE(buf_pool, i));
/* The buddy is not free. Is there a free block of
this size? */
if (buf_buddy_free_t* zip_buf =
UT_LIST_GET_FIRST(buf_pool->zip_free[i])) {
/* Remove the block from the free list, because
a successful buf_buddy_relocate() will overwrite
zip_free->list. */
buf_buddy_remove_from_free(buf_pool, zip_buf, i);
/* Try to relocate the buddy of buf to the free
block. */
if (buf_buddy_relocate(buf_pool, buddy, zip_buf, i)) {
goto buddy_is_free;
}
buf_buddy_add_to_free(buf_pool, zip_buf, i);
}
break;
case BUF_BUDDY_STATE_PARTIALLY_USED:
/* Some sub-blocks in the buddy are still in use.
Relocation will fail. No need to try. */
break;
}
func_exit:
/* Free the block to the buddy list. */
buf_buddy_add_to_free(buf_pool,
reinterpret_cast<buf_buddy_free_t*>(buf),
i);
mutex_exit(&buf_pool->zip_free_mutex);
}
|