v2-0001-Get-rid-of-WALBufMappingLock.patch

From 709ef74a8424fe626e2a2170eb9a8a1493e23cb6 Mon Sep 17 00:00:00 2001
From: Yura Sokolov <y.sokolov@postgrespro.ru>
Date: Sat, 18 Jan 2025 23:50:09 +0300
Subject: [PATCH v2 1/2] Get rid of WALBufMappingLock

Allow many backends to concurrently initialize XLog buffers.
This way `MemSet((char *) NewPage, 0, XLOG_BLCKSZ);` is not under single
LWLock in exclusive mode.

Algorithm:
- backend first reserves page for initialization,
- then it ensures it was written out,
- this it initialized it and signals concurrent initializers using
  ConditionVariable,
- when enough pages reserved for initialization for this backend, it
  ensures all required pages completes initialization.

Many backends concurrently reserve pages, initialize them, and advance
XLogCtl->InitializedUpTo to point latest initialized page.
---
 src/backend/access/transam/xlog.c             | 144 +++++++++++-------
 .../utils/activity/wait_event_names.txt       |   2 +-
 src/include/storage/lwlocklist.h              |   2 +-
 3 files changed, 90 insertions(+), 58 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 9c270e7d466..c4b80ede5da 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -302,11 +302,6 @@ static bool doPageWrites;
  * so it's a plain spinlock.  The other locks are held longer (potentially
  * over I/O operations), so we use LWLocks for them.  These locks are:
  *
- * WALBufMappingLock: must be held to replace a page in the WAL buffer cache.
- * It is only held while initializing and changing the mapping.  If the
- * contents of the buffer being replaced haven't been written yet, the mapping
- * lock is released while the write is done, and reacquired afterwards.
- *
  * WALWriteLock: must be held to write WAL buffers to disk (XLogWrite or
  * XLogFlush).
  *
@@ -472,22 +467,33 @@ typedef struct XLogCtlData
 	pg_atomic_uint64 logWriteResult;	/* last byte + 1 written out */
 	pg_atomic_uint64 logFlushResult;	/* last byte + 1 flushed */
 
+	/*
+	 * Latest initialized or reserved for inititalization page in the cache
+	 * (last byte position + 1).
+	 *
+	 * It should be advanced before identity of a buffer will be changed to.
+	 * To change the identity of a buffer that's still dirty, the old page
+	 * needs to be written out first, and for that you need WALWriteLock, and
+	 * you need to ensure that there are no in-progress insertions to the page
+	 * by calling WaitXLogInsertionsToFinish().
+	 */
+	pg_atomic_uint64 InitializeReserved;
+
 	/*
 	 * Latest initialized page in the cache (last byte position + 1).
 	 *
-	 * To change the identity of a buffer (and InitializedUpTo), you need to
-	 * hold WALBufMappingLock.  To change the identity of a buffer that's
-	 * still dirty, the old page needs to be written out first, and for that
-	 * you need WALWriteLock, and you need to ensure that there are no
-	 * in-progress insertions to the page by calling
-	 * WaitXLogInsertionsToFinish().
+	 * It is updated to successfully initialized buffer's identities.
 	 */
-	XLogRecPtr	InitializedUpTo;
+	pg_atomic_uint64 InitializedUpTo;
+
+	/* Notification for update of InitializedUpTo. */
+	ConditionVariable InitializedUpToCondVar;
 
 	/*
 	 * These values do not change after startup, although the pointed-to pages
-	 * and xlblocks values certainly do.  xlblocks values are protected by
-	 * WALBufMappingLock.
+	 * and xlblocks values certainly do.  xlblocks values are changed
+	 * lock-free with cooperation with InitializeReserved+InitializedUpTo and
+	 * check for write position.
 	 */
 	char	   *pages;			/* buffers for unwritten XLOG pages */
 	pg_atomic_uint64 *xlblocks; /* 1st byte ptr-s + XLOG_BLCKSZ */
@@ -810,9 +816,9 @@ XLogInsertRecord(XLogRecData *rdata,
 	 * fullPageWrites from changing until the insertion is finished.
 	 *
 	 * Step 2 can usually be done completely in parallel. If the required WAL
-	 * page is not initialized yet, you have to grab WALBufMappingLock to
-	 * initialize it, but the WAL writer tries to do that ahead of insertions
-	 * to avoid that from happening in the critical path.
+	 * page is not initialized yet, you have to go through AdvanceXLInsertBuffer,
+	 * which will ensure it is initialized. But the WAL writer tries to do that
+	 * ahead of insertions to avoid that from happening in the critical path.
 	 *
 	 *----------
 	 */
@@ -1991,32 +1997,43 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 	XLogRecPtr	NewPageEndPtr = InvalidXLogRecPtr;
 	XLogRecPtr	NewPageBeginPtr;
 	XLogPageHeader NewPage;
+	XLogRecPtr	ReservedPtr;
 	int			npages pg_attribute_unused() = 0;
 
-	LWLockAcquire(WALBufMappingLock, LW_EXCLUSIVE);
-
-	/*
-	 * Now that we have the lock, check if someone initialized the page
-	 * already.
-	 */
-	while (upto >= XLogCtl->InitializedUpTo || opportunistic)
+	/* Try to initialize pages we need in WAL buffer. */
+	ReservedPtr = pg_atomic_read_u64(&XLogCtl->InitializeReserved);
+	while (upto >= ReservedPtr || opportunistic)
 	{
-		nextidx = XLogRecPtrToBufIdx(XLogCtl->InitializedUpTo);
-
 		/*
-		 * Get ending-offset of the buffer page we need to replace (this may
-		 * be zero if the buffer hasn't been used yet).  Fall through if it's
-		 * already written out.
+		 * Get ending-offset of the buffer page we need to replace.
+		 *
+		 * We don't lookup into xlblocks, but rather calculate position we
+		 * must wait to be written. If it was written, xlblocks will have this
+		 * position (or uninitialized)
 		 */
-		OldPageRqstPtr = pg_atomic_read_u64(&XLogCtl->xlblocks[nextidx]);
-		if (LogwrtResult.Write < OldPageRqstPtr)
+		if (ReservedPtr + XLOG_BLCKSZ > XLOG_BLCKSZ * XLOGbuffers)
+			OldPageRqstPtr = ReservedPtr + XLOG_BLCKSZ - XLOG_BLCKSZ * XLOGbuffers;
+		else
+			OldPageRqstPtr = InvalidXLogRecPtr;
+
+		if (LogwrtResult.Write < OldPageRqstPtr && opportunistic)
 		{
 			/*
-			 * Nope, got work to do. If we just want to pre-initialize as much
-			 * as we can without flushing, give up now.
+			 * If we just want to pre-initialize as much as we can without
+			 * flushing, give up now.
 			 */
-			if (opportunistic)
-				break;
+			upto = ReservedPtr - 1;
+			break;
+		}
+
+		/* Actually reserve the page for initialization. */
+		if (!pg_atomic_compare_exchange_u64(&XLogCtl->InitializeReserved, &ReservedPtr, ReservedPtr + XLOG_BLCKSZ))
+			continue;
+
+		/* Fall through if it's already written out. */
+		if (LogwrtResult.Write < OldPageRqstPtr)
+		{
+			/* Nope, got work to do. */
 
 			/* Advance shared memory write request position */
 			SpinLockAcquire(&XLogCtl->info_lck);
@@ -2031,14 +2048,6 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 			RefreshXLogWriteResult(LogwrtResult);
 			if (LogwrtResult.Write < OldPageRqstPtr)
 			{
-				/*
-				 * Must acquire write lock. Release WALBufMappingLock first,
-				 * to make sure that all insertions that we need to wait for
-				 * can finish (up to this same position). Otherwise we risk
-				 * deadlock.
-				 */
-				LWLockRelease(WALBufMappingLock);
-
 				WaitXLogInsertionsToFinish(OldPageRqstPtr);
 
 				LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);
@@ -2060,9 +2069,6 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 					PendingWalStats.wal_buffers_full++;
 					TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
 				}
-				/* Re-acquire WALBufMappingLock and retry */
-				LWLockAcquire(WALBufMappingLock, LW_EXCLUSIVE);
-				continue;
 			}
 		}
 
@@ -2070,19 +2076,26 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 		 * Now the next buffer slot is free and we can set it up to be the
 		 * next output page.
 		 */
-		NewPageBeginPtr = XLogCtl->InitializedUpTo;
+		NewPageBeginPtr = ReservedPtr;
 		NewPageEndPtr = NewPageBeginPtr + XLOG_BLCKSZ;
+		nextidx = XLogRecPtrToBufIdx(ReservedPtr);
 
-		Assert(XLogRecPtrToBufIdx(NewPageBeginPtr) == nextidx);
+#ifdef USE_ASSERT_CHECKING
+		{
+			XLogRecPtr	storedBound = pg_atomic_read_u64(&XLogCtl->xlblocks[nextidx]);
+
+			Assert(storedBound == OldPageRqstPtr || storedBound == InvalidXLogRecPtr);
+		}
+#endif
 
 		NewPage = (XLogPageHeader) (XLogCtl->pages + nextidx * (Size) XLOG_BLCKSZ);
 
 		/*
-		 * Mark the xlblock with InvalidXLogRecPtr and issue a write barrier
-		 * before initializing. Otherwise, the old page may be partially
-		 * zeroed but look valid.
+		 * Mark the xlblock with (InvalidXLogRecPtr+1) and issue a write
+		 * barrier before initializing. Otherwise, the old page may be
+		 * partially zeroed but look valid.
 		 */
-		pg_atomic_write_u64(&XLogCtl->xlblocks[nextidx], InvalidXLogRecPtr);
+		pg_atomic_write_u64(&XLogCtl->xlblocks[nextidx], InvalidXLogRecPtr + 1);
 		pg_write_barrier();
 
 		/*
@@ -2139,11 +2152,25 @@ AdvanceXLInsertBuffer(XLogRecPtr upto, TimeLineID tli, bool opportunistic)
 		pg_write_barrier();
 
 		pg_atomic_write_u64(&XLogCtl->xlblocks[nextidx], NewPageEndPtr);
-		XLogCtl->InitializedUpTo = NewPageEndPtr;
+
+		while (pg_atomic_compare_exchange_u64(&XLogCtl->InitializedUpTo, &NewPageBeginPtr, NewPageEndPtr))
+		{
+			NewPageBeginPtr = NewPageEndPtr;
+			nextidx = XLogRecPtrToBufIdx(NewPageBeginPtr);
+			NewPageEndPtr = pg_atomic_read_u64(&XLogCtl->xlblocks[nextidx]);
+
+			if (NewPageEndPtr < NewPageBeginPtr + XLOG_BLCKSZ)
+				ConditionVariableBroadcast(&XLogCtl->InitializedUpToCondVar);
+			if (NewPageEndPtr != NewPageBeginPtr + XLOG_BLCKSZ)
+				break;
+		}
 
 		npages++;
 	}
-	LWLockRelease(WALBufMappingLock);
+
+	while (upto >= pg_atomic_read_u64(&XLogCtl->InitializedUpTo))
+		ConditionVariableSleep(&XLogCtl->InitializedUpToCondVar, WAIT_EVENT_WAL_BUFFER_INIT);
+	ConditionVariableCancelSleep();
 
 #ifdef WAL_DEBUG
 	if (XLOG_DEBUG && npages > 0)
@@ -5044,6 +5071,10 @@ XLOGShmemInit(void)
 	pg_atomic_init_u64(&XLogCtl->logWriteResult, InvalidXLogRecPtr);
 	pg_atomic_init_u64(&XLogCtl->logFlushResult, InvalidXLogRecPtr);
 	pg_atomic_init_u64(&XLogCtl->unloggedLSN, InvalidXLogRecPtr);
+
+	pg_atomic_init_u64(&XLogCtl->InitializeReserved, InvalidXLogRecPtr);
+	pg_atomic_init_u64(&XLogCtl->InitializedUpTo, InvalidXLogRecPtr);
+	ConditionVariableInit(&XLogCtl->InitializedUpToCondVar);
 }
 
 /*
@@ -6063,7 +6094,7 @@ StartupXLOG(void)
 		memset(page + len, 0, XLOG_BLCKSZ - len);
 
 		pg_atomic_write_u64(&XLogCtl->xlblocks[firstIdx], endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ);
-		XLogCtl->InitializedUpTo = endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ;
+		pg_atomic_write_u64(&XLogCtl->InitializedUpTo, endOfRecoveryInfo->lastPageBeginPtr + XLOG_BLCKSZ);
 	}
 	else
 	{
@@ -6072,8 +6103,9 @@ StartupXLOG(void)
 		 * let the first attempt to insert a log record to initialize the next
 		 * buffer.
 		 */
-		XLogCtl->InitializedUpTo = EndOfLog;
+		pg_atomic_write_u64(&XLogCtl->InitializedUpTo, EndOfLog);
 	}
+	pg_atomic_write_u64(&XLogCtl->InitializeReserved, pg_atomic_read_u64(&XLogCtl->InitializedUpTo));
 
 	/*
 	 * Update local and shared status.  This is OK to do without any locks
diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt
index e199f071628..ccf73781d81 100644
--- a/src/backend/utils/activity/wait_event_names.txt
+++ b/src/backend/utils/activity/wait_event_names.txt
@@ -155,6 +155,7 @@ REPLICATION_SLOT_DROP	"Waiting for a replication slot to become inactive so it c
 RESTORE_COMMAND	"Waiting for <xref linkend="guc-restore-command"/> to complete."
 SAFE_SNAPSHOT	"Waiting to obtain a valid snapshot for a <literal>READ ONLY DEFERRABLE</literal> transaction."
 SYNC_REP	"Waiting for confirmation from a remote server during synchronous replication."
+WAL_BUFFER_INIT	"Waiting on WAL buffer to be initialized."
 WAL_RECEIVER_EXIT	"Waiting for the WAL receiver to exit."
 WAL_RECEIVER_WAIT_START	"Waiting for startup process to send initial data for streaming replication."
 WAL_SUMMARY_READY	"Waiting for a new WAL summary to be generated."
@@ -310,7 +311,6 @@ XidGen	"Waiting to allocate a new transaction ID."
 ProcArray	"Waiting to access the shared per-process data structures (typically, to get a snapshot or report a session's transaction ID)."
 SInvalRead	"Waiting to retrieve messages from the shared catalog invalidation queue."
 SInvalWrite	"Waiting to add a message to the shared catalog invalidation queue."
-WALBufMapping	"Waiting to replace a page in WAL buffers."
 WALWrite	"Waiting for WAL buffers to be written to disk."
 ControlFile	"Waiting to read or update the <filename>pg_control</filename> file or create a new WAL file."
 MultiXactGen	"Waiting to read or update shared multixact state."
diff --git a/src/include/storage/lwlocklist.h b/src/include/storage/lwlocklist.h
index cf565452382..ff897515769 100644
--- a/src/include/storage/lwlocklist.h
+++ b/src/include/storage/lwlocklist.h
@@ -37,7 +37,7 @@ PG_LWLOCK(3, XidGen)
 PG_LWLOCK(4, ProcArray)
 PG_LWLOCK(5, SInvalRead)
 PG_LWLOCK(6, SInvalWrite)
-PG_LWLOCK(7, WALBufMapping)
+/* 7 was WALBufMapping */
 PG_LWLOCK(8, WALWrite)
 PG_LWLOCK(9, ControlFile)
 /* 10 was CheckpointLock */
-- 
2.43.0