sync-spread-v4.patch

diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 4df69c2..36da084 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -726,6 +726,53 @@ CheckpointWriteDelay(int flags, double progress)
 }
 
 /*
+ * CheckpointSyncDelay -- yield control to bgwriter during a checkpoint
+ *
+ * This function is called after each file sync performed by mdsync().
+ * It is responsible for keeping the bgwriter's normal activities in
+ * progress during a long checkpoint.
+ */
+void
+CheckpointSyncDelay(void)
+{
+	pg_time_t	now;
+ 	pg_time_t	sync_start_time;
+ 	int			sync_delay_secs;
+ 
+ 	/*
+ 	 * Delay after each sync, in seconds.  This could be a parameter.  But
+ 	 * since ideally this will be auto-tuning in the near future, not
+	 * assigning it a GUC setting yet.
+ 	 */
+#define EXTRA_SYNC_DELAY	3
+
+	/* Do nothing if checkpoint is being executed by non-bgwriter process */
+	if (!am_bg_writer)
+		return;
+
+ 	sync_start_time = (pg_time_t) time(NULL);
+
+	/*
+	 * Perform the usual bgwriter duties.
+	 */
+ 	for (;;)
+ 	{
+		AbsorbFsyncRequests();
+ 		BgBufferSync();
+ 		CheckArchiveTimeout();
+ 		BgWriterNap();
+ 
+ 		/*
+ 		 * Are we there yet?
+ 		 */
+ 		now = (pg_time_t) time(NULL);
+ 		sync_delay_secs = now - sync_start_time;
+ 		if (sync_delay_secs >= EXTRA_SYNC_DELAY)
+			break;
+	}
+}
+
+/*
  * IsCheckpointOnSchedule -- are we on schedule to finish this checkpoint
  *		 in time?
  *
diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 9d585b6..4de0243 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -31,9 +31,6 @@
 #include "pg_trace.h"
 
 
-/* interval for calling AbsorbFsyncRequests in mdsync */
-#define FSYNCS_PER_ABSORB		10
-
 /*
  * Special values for the segno arg to RememberFsyncRequest.
  *
@@ -932,7 +929,6 @@ mdsync(void)
 
 	HASH_SEQ_STATUS hstat;
 	PendingOperationEntry *entry;
-	int			absorb_counter;
 
 	/* Statistics on sync times */
 	int			processed = 0;
@@ -1002,7 +998,6 @@ mdsync(void)
 	mdsync_in_progress = true;
 
 	/* Now scan the hashtable for fsync requests to process */
-	absorb_counter = FSYNCS_PER_ABSORB;
 	hash_seq_init(&hstat, pendingOpsTable);
 	while ((entry = (PendingOperationEntry *) hash_seq_search(&hstat)) != NULL)
 	{
@@ -1027,17 +1022,9 @@ mdsync(void)
 			int			failures;
 
 			/*
-			 * If in bgwriter, we want to absorb pending requests every so
-			 * often to prevent overflow of the fsync request queue.  It is
-			 * unspecified whether newly-added entries will be visited by
-			 * hash_seq_search, but we don't care since we don't need to
-			 * process them anyway.
+			 * If in bgwriter, perform normal duties.
 			 */
-			if (--absorb_counter <= 0)
-			{
-				AbsorbFsyncRequests();
-				absorb_counter = FSYNCS_PER_ABSORB;
-			}
+			CheckpointSyncDelay();
 
 			/*
 			 * The fsync table could contain requests to fsync segments that
@@ -1131,10 +1118,9 @@ mdsync(void)
 				pfree(path);
 
 				/*
-				 * Absorb incoming requests and check to see if canceled.
+				 * If in bgwriter, perform normal duties.
 				 */
-				AbsorbFsyncRequests();
-				absorb_counter = FSYNCS_PER_ABSORB;		/* might as well... */
+				CheckpointSyncDelay();
 
 				if (entry->canceled)
 					break;
diff --git a/src/include/postmaster/bgwriter.h b/src/include/postmaster/bgwriter.h
index eaf2206..6e285cd 100644
--- a/src/include/postmaster/bgwriter.h
+++ b/src/include/postmaster/bgwriter.h
@@ -26,6 +26,7 @@ extern void BackgroundWriterMain(void);
 
 extern void RequestCheckpoint(int flags);
 extern void CheckpointWriteDelay(int flags, double progress);
+extern void CheckpointSyncDelay(void);
 
 extern bool ForwardFsyncRequest(RelFileNodeBackend rnode, ForkNumber forknum,
 					BlockNumber segno);