Replace buffer I/O locks with condition variables.

1.  Backends waiting for buffer I/O are now interruptible.

2.  If something goes wrong in a backend that is currently performing
I/O, waiting backends no longer wake up until that backend reaches
AbortBufferIO() and broadcasts on the CV.  Previously, any waiters would
wake up (because the I/O lock was automatically released) and then
busy-loop until AbortBufferIO() cleared BM_IO_IN_PROGRESS.

3.  LWLockMinimallyPadded is removed, as it would now be unused.

Author: Robert Haas <robertmhaas@gmail.com>
Reviewed-by: Thomas Munro <thomas.munro@gmail.com>
Reviewed-by: Julien Rouhaud <rjuju123@gmail.com>
Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us> (earlier version, 2016)
Discussion: https://postgr.es/m/CA%2BhUKGJ8nBFrjLuCTuqKN0pd2PQOwj9b_jnsiGFFMDvUxahj_A%40mail.gmail.com
Discussion: https://postgr.es/m/CA+Tgmoaj2aPti0yho7FeEf2qt-JgQPRWb0gci_o1Hfr=C56Xng@mail.gmail.com

1 files changed, 13 insertions, 21 deletions

diff --git a/src/backend/storage/buffer/buf_init.c b/src/backend/storage/buffer/buf_init.c
index e9e4f35bb5f..a299be10430 100644
--- a/src/backend/storage/buffer/buf_init.c
+++ b/src/backend/storage/buffer/buf_init.c
@@ -19,7 +19,7 @@
 
 BufferDescPadded *BufferDescriptors;
 char	   *BufferBlocks;
-LWLockMinimallyPadded *BufferIOLWLockArray = NULL;
+ConditionVariableMinimallyPadded *BufferIOCVArray;
 WritebackContext BackendWritebackContext;
 CkptSortItem *CkptBufferIds;
 
@@ -68,7 +68,7 @@ InitBufferPool(void)
 {
 	bool		foundBufs,
 				foundDescs,
-				foundIOLocks,
+				foundIOCV,
 				foundBufCkpt;
 
 	/* Align descriptors to a cacheline boundary. */
@@ -81,11 +81,11 @@ InitBufferPool(void)
 		ShmemInitStruct("Buffer Blocks",
 						NBuffers * (Size) BLCKSZ, &foundBufs);
 
-	/* Align lwlocks to cacheline boundary */
-	BufferIOLWLockArray = (LWLockMinimallyPadded *)
-		ShmemInitStruct("Buffer IO Locks",
-						NBuffers * (Size) sizeof(LWLockMinimallyPadded),
-						&foundIOLocks);
+	/* Align condition variables to cacheline boundary. */
+	BufferIOCVArray = (ConditionVariableMinimallyPadded *)
+		ShmemInitStruct("Buffer IO Condition Variables",
+						NBuffers * sizeof(ConditionVariableMinimallyPadded),
+						&foundIOCV);
 
 	/*
 	 * The array used to sort to-be-checkpointed buffer ids is located in
@@ -98,10 +98,10 @@ InitBufferPool(void)
 		ShmemInitStruct("Checkpoint BufferIds",
 						NBuffers * sizeof(CkptSortItem), &foundBufCkpt);
 
-	if (foundDescs || foundBufs || foundIOLocks || foundBufCkpt)
+	if (foundDescs || foundBufs || foundIOCV || foundBufCkpt)
 	{
 		/* should find all of these, or none of them */
-		Assert(foundDescs && foundBufs && foundIOLocks && foundBufCkpt);
+		Assert(foundDescs && foundBufs && foundIOCV && foundBufCkpt);
 		/* note: this path is only taken in EXEC_BACKEND case */
 	}
 	else
@@ -131,8 +131,7 @@ InitBufferPool(void)
 			LWLockInitialize(BufferDescriptorGetContentLock(buf),
 							 LWTRANCHE_BUFFER_CONTENT);
 
-			LWLockInitialize(BufferDescriptorGetIOLock(buf),
-							 LWTRANCHE_BUFFER_IO);
+			ConditionVariableInit(BufferDescriptorGetIOCV(buf));
 		}
 
 		/* Correct last entry of linked list */
@@ -169,16 +168,9 @@ BufferShmemSize(void)
 	/* size of stuff controlled by freelist.c */
 	size = add_size(size, StrategyShmemSize());
 
-	/*
-	 * It would be nice to include the I/O locks in the BufferDesc, but that
-	 * would increase the size of a BufferDesc to more than one cache line,
-	 * and benchmarking has shown that keeping every BufferDesc aligned on a
-	 * cache line boundary is important for performance.  So, instead, the
-	 * array of I/O locks is allocated in a separate tranche.  Because those
-	 * locks are not highly contended, we lay out the array with minimal
-	 * padding.
-	 */
-	size = add_size(size, mul_size(NBuffers, sizeof(LWLockMinimallyPadded)));
+	/* size of I/O condition variables */
+	size = add_size(size, mul_size(NBuffers,
+								   sizeof(ConditionVariableMinimallyPadded)));
 	/* to allow aligning the above */
 	size = add_size(size, PG_CACHE_LINE_SIZE);