bufmgr: Remove freelist, always use clock-sweep

This set of changes removes the list of available buffers and instead simply
uses the clock-sweep algorithm to find and return an available buffer.  This
also removes the have_free_buffer() function and simply caps the
pg_autoprewarm process to at most NBuffers.

While on the surface this appears to be removing an optimization it is in fact
eliminating code that induces overhead in the form of synchronization that is
problematic for multi-core systems.

The main reason for removing the freelist, however, is not the moderate
improvement in scalability, but that having the freelist would require
dedicated complexity in several upcoming patches. As we have not been able to
find a case benefiting from the freelist...

Author: Greg Burd <greg@burd.me>
Reviewed-by: Tomas Vondra <tomas@vondra.me>
Reviewed-by: Andres Freund <andres@anarazel.de>
Discussion: https://postgr.es/m/70C6A5B5-2A20-4D0B-BC73-EB09DD62D61C@getmailspring.com

1 files changed, 1 insertions, 12 deletions

diff --git a/src/include/storage/buf_internals.h b/src/include/storage/buf_internals.h
index 3a210c710f6..dfd614f7ca4 100644
--- a/src/include/storage/buf_internals.h
+++ b/src/include/storage/buf_internals.h
@@ -217,8 +217,7 @@ BufMappingPartitionLockByIndex(uint32 index)
  * single atomic variable.  This layout allow us to do some operations in a
  * single atomic operation, without actually acquiring and releasing spinlock;
  * for instance, increase or decrease refcount.  buf_id field never changes
- * after initialization, so does not need locking.  freeNext is protected by
- * the buffer_strategy_lock not buffer header lock.  The LWLock can take care
+ * after initialization, so does not need locking.  The LWLock can take care
  * of itself.  The buffer header lock is *not* used to control access to the
  * data in the buffer!
  *
@@ -264,7 +263,6 @@ typedef struct BufferDesc
 	pg_atomic_uint32 state;
 
 	int			wait_backend_pgprocno;	/* backend of pin-count waiter */
-	int			freeNext;		/* link in freelist chain */
 
 	PgAioWaitRef io_wref;		/* set iff AIO is in progress */
 	LWLock		content_lock;	/* to lock access to buffer contents */
@@ -361,13 +359,6 @@ BufferDescriptorGetContentLock(const BufferDesc *bdesc)
 }
 
 /*
- * The freeNext field is either the index of the next freelist entry,
- * or one of these special values:
- */
-#define FREENEXT_END_OF_LIST	(-1)
-#define FREENEXT_NOT_IN_LIST	(-2)
-
-/*
  * Functions for acquiring/releasing a shared buffer header's spinlock.  Do
  * not apply these to local buffers!
  */
@@ -444,7 +435,6 @@ extern void TerminateBufferIO(BufferDesc *buf, bool clear_dirty, uint32 set_flag
 extern IOContext IOContextForStrategy(BufferAccessStrategy strategy);
 extern BufferDesc *StrategyGetBuffer(BufferAccessStrategy strategy,
 									 uint32 *buf_state, bool *from_ring);
-extern void StrategyFreeBuffer(BufferDesc *buf);
 extern bool StrategyRejectBuffer(BufferAccessStrategy strategy,
 								 BufferDesc *buf, bool from_ring);
 
@@ -453,7 +443,6 @@ extern void StrategyNotifyBgWriter(int bgwprocno);
 
 extern Size StrategyShmemSize(void);
 extern void StrategyInitialize(bool init);
-extern bool have_free_buffer(void);
 
 /* buf_table.c */
 extern Size BufTableShmemSize(int size);