bufmgr: use AIO in checkpointer, bgwriter

This is far from ready - just included to be able to exercise AIO writes and
get some preliminary numbers.  In all likelihood this will instead be based
on-top of work by Thomas Munro instead of the preceding commit.

TODO;

- This doesn't implement bgwriter_flush_after, checkpointer_flush_after

  I think that's not too hard to do, it's mainly round tuits.

- The queuing logic doesn't carefully respect pin limits

  That might be ok for checkpointer and bgwriter, but the infrastructure
  should be usable outside of this as well.

Author: anarazel

src/backend/postmaster/bgwriter.c

@@ -38,11 +38,13 @@
 #include "postmaster/auxprocess.h"
 #include "postmaster/bgwriter.h"
 #include "postmaster/interrupt.h"
+#include "storage/aio.h"
 #include "storage/aio_subsys.h"
 #include "storage/buf_internals.h"
 #include "storage/bufmgr.h"
 #include "storage/condition_variable.h"
 #include "storage/fd.h"
+#include "storage/io_queue.h"
 #include "storage/lwlock.h"
 #include "storage/proc.h"
 #include "storage/procsignal.h"
@@ -90,6 +92,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 	sigjmp_buf	local_sigjmp_buf;
 	MemoryContext bgwriter_context;
 	bool		prev_hibernate;
+	IOQueue    *ioq;
 	WritebackContext wb_context;
 
 	Assert(startup_data_len == 0);
@@ -131,6 +134,7 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 											 ALLOCSET_DEFAULT_SIZES);
 	MemoryContextSwitchTo(bgwriter_context);
 
+	ioq = io_queue_create(128, 0);
 	WritebackContextInit(&wb_context, &bgwriter_flush_after);
 
 	/*
@@ -228,12 +232,22 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
 
+		/*
+		 * FIXME: this is theoretically racy, but I didn't want to copy
+		 * ProcessMainLoopInterrupts() remaining body here.
+		 */
+		if (ShutdownRequestPending)
+		{
+			io_queue_wait_all(ioq);
+			io_queue_free(ioq);
+		}
+
 		ProcessMainLoopInterrupts();
 
 		/*
 		 * Do one cycle of dirty-buffer writing.
 		 */
-		can_hibernate = BgBufferSync(&wb_context);
+		can_hibernate = BgBufferSync(ioq, &wb_context);
 
 		/* Report pending statistics to the cumulative stats system */
 		pgstat_report_bgwriter();
@@ -250,6 +264,9 @@ BackgroundWriterMain(const void *startup_data, size_t startup_data_len)
 			smgrdestroyall();
 		}
 
+		/* finish IO before sleeping, to avoid blocking other backends */
+		io_queue_wait_all(ioq);
+
 		/*
 		 * Log a new xl_running_xacts every now and then so replication can
 		 * get into a consistent state faster (think of suboverflowed

src/backend/postmaster/checkpointer.c

@@ -49,10 +49,12 @@
 #include "postmaster/bgwriter.h"
 #include "postmaster/interrupt.h"
 #include "replication/syncrep.h"
+#include "storage/aio.h"
 #include "storage/aio_subsys.h"
 #include "storage/bufmgr.h"
 #include "storage/condition_variable.h"
 #include "storage/fd.h"
+#include "storage/io_queue.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
 #include "storage/pmsignal.h"
@@ -766,7 +768,7 @@ ImmediateCheckpointRequested(void)
  * fraction between 0.0 meaning none, and 1.0 meaning all done.
  */
 void
-CheckpointWriteDelay(int flags, double progress)
+CheckpointWriteDelay(IOQueue *ioq, int flags, double progress)
 {
 	static int	absorb_counter = WRITES_PER_ABSORB;
 
@@ -800,6 +802,13 @@ CheckpointWriteDelay(int flags, double progress)
 		/* Report interim statistics to the cumulative stats system */
 		pgstat_report_checkpointer();
 
+		/*
+		 * Ensure all pending IO is submitted to avoid unnecessary delays for
+		 * other processes.
+		 */
+		io_queue_wait_all(ioq);
+
+
 		/*
 		 * This sleep used to be connected to bgwriter_delay, typically 200ms.
 		 * That resulted in more frequent wakeups if not much work to do.