From 2706550cd4fc9ef53b8fa09d7414e88a31ea6e0e Mon Sep 17 00:00:00 2001
From: Alexander Korotkov <akorotkov@postgresql.org>
Date: Mon, 26 Oct 2020 01:55:31 +0300
Subject: [PATCH v8 3/4] Add conditional variable to wait for next MultXact
 offset in corner case

GetMultiXactIdMembers() has a corner case, when the next multixact offset is
not yet set.  In this case GetMultiXactIdMembers() has to sleep till this offset
is set.  Currently the sleeping is implemented in naive way using pg_sleep()
and retry.  This commit implements sleeping with conditional variable, which
provides more efficient way for waiting till the event.

Discussion: https://postgr.es/m/a7f1c4e1-1015-92a4-2bd4-6736bd13d03e%40postgrespro.ru#c496c4e75fc0605094a0e1f763e6a6ec
Author: Andrey Borodin
Reviewed-by: Kyotaro Horiguchi, Daniel Gustafsson
Reviewed-by: Anastasia Lubennikova, Alexander Korotkov
---
 src/backend/access/transam/multixact.c | 35 ++++++++++++++++++++++++--
 src/backend/postmaster/pgstat.c        |  2 ++
 src/include/pgstat.h                   |  1 +
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/src/backend/access/transam/multixact.c b/src/backend/access/transam/multixact.c
index 171e2ab681..ffd35c2aea 100644
--- a/src/backend/access/transam/multixact.c
+++ b/src/backend/access/transam/multixact.c
@@ -82,6 +82,7 @@
 #include "lib/ilist.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
+#include "pgstat.h"
 #include "postmaster/autovacuum.h"
 #include "storage/lmgr.h"
 #include "storage/pmsignal.h"
@@ -233,6 +234,13 @@ typedef struct MultiXactStateData
 	/* support for members anti-wraparound measures */
 	MultiXactOffset offsetStopLimit;	/* known if oldestOffsetKnown */
 
+	/*
+	 * Conditional variable for waiting till the filling of the next multixact
+	 * will be finished.  See GetMultiXactIdMembers() and RecordNewMultiXact()
+	 * for details.
+	 */
+	ConditionVariable nextoffCV;
+
 	/*
 	 * Per-backend data starts here.  We have two arrays stored in the area
 	 * immediately following the MultiXactStateData struct. Each is indexed by
@@ -892,6 +900,14 @@ RecordNewMultiXact(MultiXactId multi, MultiXactOffset offset,
 	/* Exchange our lock */
 	LWLockRelease(MultiXactOffsetSLRULock);
 
+	/*
+	 * Let everybody know the offset of this mxid is recorded now.  The
+	 * waiters are waiting for the offset of the mxid next of the target to
+	 * know the number of members of the target mxid, so we don't need to wait
+	 * for members of this mxid are recorded.
+	 */
+	ConditionVariableBroadcast(&MultiXactState->nextoffCV);
+
 	LWLockAcquire(MultiXactMemberSLRULock, LW_EXCLUSIVE);
 
 	prev_pageno = -1;
@@ -1389,10 +1405,24 @@ retry:
 		if (nextMXOffset == 0)
 		{
 			/* Corner case 2: next multixact is still being filled in */
+
+			/*
+			 * The recorder of the next mxid is just before writing the
+			 * offset. Wait for the offset to be written.
+			 */
+			ConditionVariablePrepareToSleep(&MultiXactState->nextoffCV);
+
+			/*
+			 * We don't have to recheck if multixact was filled in during
+			 * ConditionVariablePrepareToSleep(), because we were holding
+			 * MultiXactOffsetSLRULock.
+			 */
 			LWLockRelease(MultiXactOffsetSLRULock);
 			lockmode = LW_NONE;
-			CHECK_FOR_INTERRUPTS();
-			pg_usleep(1000L);
+
+			ConditionVariableSleep(&MultiXactState->nextoffCV,
+								   WAIT_EVENT_WAIT_NEXT_MXMEMBERS);
+			ConditionVariableCancelSleep();
 			goto retry;
 		}
 
@@ -1874,6 +1904,7 @@ MultiXactShmemInit(void)
 
 		/* Make sure we zero out the per-backend state */
 		MemSet(MultiXactState, 0, SHARED_MULTIXACT_STATE_SIZE);
+		ConditionVariableInit(&MultiXactState->nextoffCV);
 	}
 	else
 		Assert(found);
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 7c75a25d21..20879fc90e 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -4041,6 +4041,8 @@ pgstat_get_wait_ipc(WaitEventIPC w)
 			break;
 		case WAIT_EVENT_XACT_GROUP_UPDATE:
 			event_name = "XactGroupUpdate";
+		case WAIT_EVENT_WAIT_NEXT_MXMEMBERS:
+			event_name = "MultiXactWaitNextMembers";
 			break;
 			/* no default case, so that compiler will warn */
 	}
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 5954068dec..630ddcf1a5 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -964,6 +964,7 @@ typedef enum
 	WAIT_EVENT_REPLICATION_SLOT_DROP,
 	WAIT_EVENT_SAFE_SNAPSHOT,
 	WAIT_EVENT_SYNC_REP,
+	WAIT_EVENT_WAIT_NEXT_MXMEMBERS,
 	WAIT_EVENT_XACT_GROUP_UPDATE
 } WaitEventIPC;
 
-- 
2.24.3 (Apple Git-128)