MDEV-27058: Reduce the size of buf_block_t and buf_page_t

buf_page_t::frame: Moved from buf_block_t::frame.
All 'thin' buf_page_t describing compressed-only ROW_FORMAT=COMPRESSED
pages will have frame=nullptr, while all 'fat' buf_block_t
will have a non-null frame pointing to aligned innodb_page_size bytes.
This eliminates the need for separate states for
BUF_BLOCK_FILE_PAGE and BUF_BLOCK_ZIP_PAGE.

buf_page_t::lock: Moved from buf_block_t::lock. That is, all block
descriptors will have a page latch. The IO_PIN state that was used
for discarding or creating the uncompressed page frame of a
ROW_FORMAT=COMPRESSED block is replaced by a combination of read-fix
and page X-latch.

page_zip_des_t::fix: Replaces state_, buf_fix_count_, io_fix_, status
of buf_page_t with a single std::atomic<uint32_t>. All modifications
will use store(), fetch_add(), fetch_sub(). This space was previously
wasted to alignment on 64-bit systems. We will use the following encoding
that combines a state (partly read-fix or write-fix) and a buffer-fix
count:

buf_page_t::NOT_USED=0 (previously BUF_BLOCK_NOT_USED)
buf_page_t::MEMORY=1 (previously BUF_BLOCK_MEMORY)
buf_page_t::REMOVE_HASH=2 (previously BUF_BLOCK_REMOVE_HASH)
buf_page_t::FREED=3 + fix: pages marked as freed in the file
buf_page_t::UNFIXED=1U<<29 + fix: normal pages
buf_page_t::IBUF_EXIST=2U<<29 + fix: normal pages; may need ibuf merge
buf_page_t::REINIT=3U<<29 + fix: reinitialized pages (skip doublewrite)
buf_page_t::READ_FIX=4U<<29 + fix: read-fixed pages (also X-latched)
buf_page_t::WRITE_FIX=5U<<29 + fix: write-fixed pages (also U-latched)
buf_page_t::WRITE_FIX_IBUF=6U<<29 + fix: write-fixed; may have ibuf
buf_page_t::WRITE_FIX_REINIT=7U<<29 + fix: write-fixed (no doublewrite)

buf_page_t::write_complete(): Change WRITE_FIX or WRITE_FIX_REINIT to
UNFIXED, and WRITE_FIX_IBUF to IBUF_EXIST, before releasing the U-latch.

buf_page_t::read_complete(): Renamed from buf_page_read_complete().
Change READ_FIX to UNFIXED or IBUF_EXIST, before releasing the X-latch.

buf_page_t::can_relocate(): If the page latch is being held or waited for,
or the block is buffer-fixed or io-fixed, return false. (The condition
on the page latch is new.)

Outside buf_page_get_gen(), buf_page_get_low() and buf_page_free(), we
will acquire the page latch before fix(), and unfix() before unlocking.

buf_page_t::flush(): Replaces buf_flush_page(). Optimize the
handling of FREED pages.

buf_pool_t::release_freed_page(): Assume that buf_pool.mutex is held
by the caller.

buf_page_t::is_read_fixed(), buf_page_t::is_write_fixed(): New predicates.

buf_page_get_low(): Ignore guesses that are read-fixed because they
may not yet be registered in buf_pool.page_hash and buf_pool.LRU.

buf_page_optimistic_get(): Acquire latch before buffer-fixing.

buf_page_make_young(): Leave read-fixed blocks alone, because they
might not be registered in buf_pool.LRU yet.

recv_sys_t::recover_deferred(), recv_sys_t::recover_low():
Possibly fix MDEV-26326, by holding a page X-latch instead of
only buffer-fixing the page.

1 files changed, 9 insertions, 9 deletions

diff --git a/storage/innobase/buf/buf0buddy.cc b/storage/innobase/buf/buf0buddy.cc
index 125dac5333e..3d476fbac77 100644
--- a/storage/innobase/buf/buf0buddy.cc
+++ b/storage/innobase/buf/buf0buddy.cc
@@ -354,11 +354,11 @@ buf_buddy_block_free(void* buf)
 	ut_a(!ut_align_offset(buf, srv_page_size));
 
 	HASH_SEARCH(hash, &buf_pool.zip_hash, fold, buf_page_t*, bpage,
-		    ut_ad(bpage->state() == BUF_BLOCK_MEMORY
+		    ut_ad(bpage->state() == buf_page_t::MEMORY
 			  && bpage->in_zip_hash),
-		    ((buf_block_t*) bpage)->frame == buf);
+		    bpage->frame == buf);
 	ut_a(bpage);
-	ut_a(bpage->state() == BUF_BLOCK_MEMORY);
+	ut_a(bpage->state() == buf_page_t::MEMORY);
 	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);
@@ -383,10 +383,10 @@ buf_buddy_block_register(
 	buf_block_t*	block)	/*!< in: buffer frame to allocate */
 {
 	const ulint	fold = BUF_POOL_ZIP_FOLD(block);
-	ut_ad(block->page.state() == BUF_BLOCK_MEMORY);
+	ut_ad(block->page.state() == buf_page_t::MEMORY);
 
-	ut_a(block->frame);
-	ut_a(!ut_align_offset(block->frame, srv_page_size));
+	ut_a(block->page.frame);
+	ut_a(!ut_align_offset(block->page.frame, srv_page_size));
 
 	ut_ad(!block->page.in_zip_hash);
 	ut_d(block->page.in_zip_hash = true);
@@ -462,8 +462,8 @@ byte *buf_buddy_alloc_low(ulint i, bool *lru)
 alloc_big:
 	buf_buddy_block_register(block);
 
-	block = (buf_block_t*) buf_buddy_alloc_from(
-		block->frame, i, BUF_BUDDY_SIZES);
+	block = reinterpret_cast<buf_block_t*>(
+		buf_buddy_alloc_from(block->page.frame, i, BUF_BUDDY_SIZES));
 
 func_exit:
 	buf_pool.buddy_stat[i].used++;
@@ -694,7 +694,7 @@ buf_buddy_realloc(void* buf, ulint size)
 
 		block = reinterpret_cast<buf_block_t*>(
 			buf_buddy_alloc_from(
-				block->frame, i, BUF_BUDDY_SIZES));
+				block->page.frame, i, BUF_BUDDY_SIZES));
 	}
 
 	buf_pool.buddy_stat[i].used++;