7 files changed, 311 insertions, 0 deletions
diff --git a/contrib/pg_buffercache/Makefile b/contrib/pg_buffercache/Makefile
new file mode 100644
index 0000000..2ab8c65
--- /dev/null
+++ b/contrib/pg_buffercache/Makefile
@@ -0,0 +1,22 @@
+# contrib/pg_buffercache/Makefile
+
+MODULE_big = pg_buffercache
+OBJS = \
+	$(WIN32RES) \
+	pg_buffercache_pages.o
+
+EXTENSION = pg_buffercache
+DATA = pg_buffercache--1.2.sql pg_buffercache--1.2--1.3.sql \
+	pg_buffercache--1.1--1.2.sql pg_buffercache--1.0--1.1.sql
+PGFILEDESC = "pg_buffercache - monitoring of shared buffer cache in real-time"
+
+ifdef USE_PGXS
+PG_CONFIG = pg_config
+PGXS := $(shell $(PG_CONFIG) --pgxs)
+include $(PGXS)
+else
+subdir = contrib/pg_buffercache
+top_builddir = ../..
+include $(top_builddir)/src/Makefile.global
+include $(top_srcdir)/contrib/contrib-global.mk
+endif
diff --git a/contrib/pg_buffercache/pg_buffercache--1.0--1.1.sql b/contrib/pg_buffercache/pg_buffercache--1.0--1.1.sql
new file mode 100644
index 0000000..54d02f5
--- /dev/null
+++ b/contrib/pg_buffercache/pg_buffercache--1.0--1.1.sql
@@ -0,0 +1,11 @@
+/* contrib/pg_buffercache/pg_buffercache--1.0--1.1.sql */
+
+-- complain if script is sourced in psql, rather than via ALTER EXTENSION
+\echo Use "ALTER EXTENSION pg_buffercache UPDATE TO '1.1'" to load this file. \quit
+
+-- Upgrade view to 1.1. format
+CREATE OR REPLACE VIEW pg_buffercache AS
+	SELECT P.* FROM pg_buffercache_pages() AS P
+	(bufferid integer, relfilenode oid, reltablespace oid, reldatabase oid,
+	 relforknumber int2, relblocknumber int8, isdirty bool, usagecount int2,
+	 pinning_backends int4);
diff --git a/contrib/pg_buffercache/pg_buffercache--1.1--1.2.sql b/contrib/pg_buffercache/pg_buffercache--1.1--1.2.sql
new file mode 100644
index 0000000..5997aad
--- /dev/null
+++ b/contrib/pg_buffercache/pg_buffercache--1.1--1.2.sql
@@ -0,0 +1,6 @@
+/* contrib/pg_buffercache/pg_buffercache--1.1--1.2.sql */
+
+-- complain if script is sourced in psql, rather than via ALTER EXTENSION
+\echo Use "ALTER EXTENSION pg_buffercache UPDATE TO '1.2'" to load this file. \quit
+
+ALTER FUNCTION pg_buffercache_pages() PARALLEL SAFE;
diff --git a/contrib/pg_buffercache/pg_buffercache--1.2--1.3.sql b/contrib/pg_buffercache/pg_buffercache--1.2--1.3.sql
new file mode 100644
index 0000000..b37ef01
--- /dev/null
+++ b/contrib/pg_buffercache/pg_buffercache--1.2--1.3.sql
@@ -0,0 +1,7 @@
+/* contrib/pg_buffercache/pg_buffercache--1.2--1.3.sql */
+
+-- complain if script is sourced in psql, rather than via ALTER EXTENSION
+\echo Use "ALTER EXTENSION pg_buffercache UPDATE TO '1.3'" to load this file. \quit
+
+GRANT EXECUTE ON FUNCTION pg_buffercache_pages() TO pg_monitor;
+GRANT SELECT ON pg_buffercache TO pg_monitor;
diff --git a/contrib/pg_buffercache/pg_buffercache--1.2.sql b/contrib/pg_buffercache/pg_buffercache--1.2.sql
new file mode 100644
index 0000000..6ee5d84
--- /dev/null
+++ b/contrib/pg_buffercache/pg_buffercache--1.2.sql
@@ -0,0 +1,21 @@
+/* contrib/pg_buffercache/pg_buffercache--1.2.sql */
+
+-- complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION pg_buffercache" to load this file. \quit
+
+-- Register the function.
+CREATE FUNCTION pg_buffercache_pages()
+RETURNS SETOF RECORD
+AS 'MODULE_PATHNAME', 'pg_buffercache_pages'
+LANGUAGE C PARALLEL SAFE;
+
+-- Create a view for convenient access.
+CREATE VIEW pg_buffercache AS
+	SELECT P.* FROM pg_buffercache_pages() AS P
+	(bufferid integer, relfilenode oid, reltablespace oid, reldatabase oid,
+	 relforknumber int2, relblocknumber int8, isdirty bool, usagecount int2,
+	 pinning_backends int4);
+
+-- Don't want these to be available to public.
+REVOKE ALL ON FUNCTION pg_buffercache_pages() FROM PUBLIC;
+REVOKE ALL ON pg_buffercache FROM PUBLIC;
diff --git a/contrib/pg_buffercache/pg_buffercache.control b/contrib/pg_buffercache/pg_buffercache.control
new file mode 100644
index 0000000..8c060ae
--- /dev/null
+++ b/contrib/pg_buffercache/pg_buffercache.control
@@ -0,0 +1,5 @@
+# pg_buffercache extension
+comment = 'examine the shared buffer cache'
+default_version = '1.3'
+module_pathname = '$libdir/pg_buffercache'
+relocatable = true
diff --git a/contrib/pg_buffercache/pg_buffercache_pages.c b/contrib/pg_buffercache/pg_buffercache_pages.c
new file mode 100644
index 0000000..1bd579f
--- /dev/null
+++ b/contrib/pg_buffercache/pg_buffercache_pages.c
@@ -0,0 +1,239 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_buffercache_pages.c
+ *	  display some contents of the buffer cache
+ *
+ *	  contrib/pg_buffercache/pg_buffercache_pages.c
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "access/htup_details.h"
+#include "catalog/pg_type.h"
+#include "funcapi.h"
+#include "storage/buf_internals.h"
+#include "storage/bufmgr.h"
+
+
+#define NUM_BUFFERCACHE_PAGES_MIN_ELEM	8
+#define NUM_BUFFERCACHE_PAGES_ELEM	9
+
+PG_MODULE_MAGIC;
+
+/*
+ * Record structure holding the to be exposed cache data.
+ */
+typedef struct
+{
+	uint32		bufferid;
+	Oid			relfilenode;
+	Oid			reltablespace;
+	Oid			reldatabase;
+	ForkNumber	forknum;
+	BlockNumber blocknum;
+	bool		isvalid;
+	bool		isdirty;
+	uint16		usagecount;
+
+	/*
+	 * An int32 is sufficiently large, as MAX_BACKENDS prevents a buffer from
+	 * being pinned by too many backends and each backend will only pin once
+	 * because of bufmgr.c's PrivateRefCount infrastructure.
+	 */
+	int32		pinning_backends;
+} BufferCachePagesRec;
+
+
+/*
+ * Function context for data persisting over repeated calls.
+ */
+typedef struct
+{
+	TupleDesc	tupdesc;
+	BufferCachePagesRec *record;
+} BufferCachePagesContext;
+
+
+/*
+ * Function returning data from the shared buffer cache - buffer number,
+ * relation node/tablespace/database/blocknum and dirty indicator.
+ */
+PG_FUNCTION_INFO_V1(pg_buffercache_pages);
+
+Datum
+pg_buffercache_pages(PG_FUNCTION_ARGS)
+{
+	FuncCallContext *funcctx;
+	Datum		result;
+	MemoryContext oldcontext;
+	BufferCachePagesContext *fctx;	/* User function context. */
+	TupleDesc	tupledesc;
+	TupleDesc	expected_tupledesc;
+	HeapTuple	tuple;
+
+	if (SRF_IS_FIRSTCALL())
+	{
+		int			i;
+
+		funcctx = SRF_FIRSTCALL_INIT();
+
+		/* Switch context when allocating stuff to be used in later calls */
+		oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
+
+		/* Create a user function context for cross-call persistence */
+		fctx = (BufferCachePagesContext *) palloc(sizeof(BufferCachePagesContext));
+
+		/*
+		 * To smoothly support upgrades from version 1.0 of this extension
+		 * transparently handle the (non-)existence of the pinning_backends
+		 * column. We unfortunately have to get the result type for that... -
+		 * we can't use the result type determined by the function definition
+		 * without potentially crashing when somebody uses the old (or even
+		 * wrong) function definition though.
+		 */
+		if (get_call_result_type(fcinfo, NULL, &expected_tupledesc) != TYPEFUNC_COMPOSITE)
+			elog(ERROR, "return type must be a row type");
+
+		if (expected_tupledesc->natts < NUM_BUFFERCACHE_PAGES_MIN_ELEM ||
+			expected_tupledesc->natts > NUM_BUFFERCACHE_PAGES_ELEM)
+			elog(ERROR, "incorrect number of output arguments");
+
+		/* Construct a tuple descriptor for the result rows. */
+		tupledesc = CreateTemplateTupleDesc(expected_tupledesc->natts);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 1, "bufferid",
+						   INT4OID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 2, "relfilenode",
+						   OIDOID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 3, "reltablespace",
+						   OIDOID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 4, "reldatabase",
+						   OIDOID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 5, "relforknumber",
+						   INT2OID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 6, "relblocknumber",
+						   INT8OID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 7, "isdirty",
+						   BOOLOID, -1, 0);
+		TupleDescInitEntry(tupledesc, (AttrNumber) 8, "usage_count",
+						   INT2OID, -1, 0);
+
+		if (expected_tupledesc->natts == NUM_BUFFERCACHE_PAGES_ELEM)
+			TupleDescInitEntry(tupledesc, (AttrNumber) 9, "pinning_backends",
+							   INT4OID, -1, 0);
+
+		fctx->tupdesc = BlessTupleDesc(tupledesc);
+
+		/* Allocate NBuffers worth of BufferCachePagesRec records. */
+		fctx->record = (BufferCachePagesRec *)
+			MemoryContextAllocHuge(CurrentMemoryContext,
+								   sizeof(BufferCachePagesRec) * NBuffers);
+
+		/* Set max calls and remember the user function context. */
+		funcctx->max_calls = NBuffers;
+		funcctx->user_fctx = fctx;
+
+		/* Return to original context when allocating transient memory */
+		MemoryContextSwitchTo(oldcontext);
+
+		/*
+		 * Scan through all the buffers, saving the relevant fields in the
+		 * fctx->record structure.
+		 *
+		 * We don't hold the partition locks, so we don't get a consistent
+		 * snapshot across all buffers, but we do grab the buffer header
+		 * locks, so the information of each buffer is self-consistent.
+		 */
+		for (i = 0; i < NBuffers; i++)
+		{
+			BufferDesc *bufHdr;
+			uint32		buf_state;
+
+			bufHdr = GetBufferDescriptor(i);
+			/* Lock each buffer header before inspecting. */
+			buf_state = LockBufHdr(bufHdr);
+
+			fctx->record[i].bufferid = BufferDescriptorGetBuffer(bufHdr);
+			fctx->record[i].relfilenode = bufHdr->tag.rnode.relNode;
+			fctx->record[i].reltablespace = bufHdr->tag.rnode.spcNode;
+			fctx->record[i].reldatabase = bufHdr->tag.rnode.dbNode;
+			fctx->record[i].forknum = bufHdr->tag.forkNum;
+			fctx->record[i].blocknum = bufHdr->tag.blockNum;
+			fctx->record[i].usagecount = BUF_STATE_GET_USAGECOUNT(buf_state);
+			fctx->record[i].pinning_backends = BUF_STATE_GET_REFCOUNT(buf_state);
+
+			if (buf_state & BM_DIRTY)
+				fctx->record[i].isdirty = true;
+			else
+				fctx->record[i].isdirty = false;
+
+			/* Note if the buffer is valid, and has storage created */
+			if ((buf_state & BM_VALID) && (buf_state & BM_TAG_VALID))
+				fctx->record[i].isvalid = true;
+			else
+				fctx->record[i].isvalid = false;
+
+			UnlockBufHdr(bufHdr, buf_state);
+		}
+	}
+
+	funcctx = SRF_PERCALL_SETUP();
+
+	/* Get the saved state */
+	fctx = funcctx->user_fctx;
+
+	if (funcctx->call_cntr < funcctx->max_calls)
+	{
+		uint32		i = funcctx->call_cntr;
+		Datum		values[NUM_BUFFERCACHE_PAGES_ELEM];
+		bool		nulls[NUM_BUFFERCACHE_PAGES_ELEM];
+
+		values[0] = Int32GetDatum(fctx->record[i].bufferid);
+		nulls[0] = false;
+
+		/*
+		 * Set all fields except the bufferid to null if the buffer is unused
+		 * or not valid.
+		 */
+		if (fctx->record[i].blocknum == InvalidBlockNumber ||
+			fctx->record[i].isvalid == false)
+		{
+			nulls[1] = true;
+			nulls[2] = true;
+			nulls[3] = true;
+			nulls[4] = true;
+			nulls[5] = true;
+			nulls[6] = true;
+			nulls[7] = true;
+			/* unused for v1.0 callers, but the array is always long enough */
+			nulls[8] = true;
+		}
+		else
+		{
+			values[1] = ObjectIdGetDatum(fctx->record[i].relfilenode);
+			nulls[1] = false;
+			values[2] = ObjectIdGetDatum(fctx->record[i].reltablespace);
+			nulls[2] = false;
+			values[3] = ObjectIdGetDatum(fctx->record[i].reldatabase);
+			nulls[3] = false;
+			values[4] = ObjectIdGetDatum(fctx->record[i].forknum);
+			nulls[4] = false;
+			values[5] = Int64GetDatum((int64) fctx->record[i].blocknum);
+			nulls[5] = false;
+			values[6] = BoolGetDatum(fctx->record[i].isdirty);
+			nulls[6] = false;
+			values[7] = Int16GetDatum(fctx->record[i].usagecount);
+			nulls[7] = false;
+			/* unused for v1.0 callers, but the array is always long enough */
+			values[8] = Int32GetDatum(fctx->record[i].pinning_backends);
+			nulls[8] = false;
+		}
+
+		/* Build and return the tuple. */
+		tuple = heap_form_tuple(fctx->tupdesc, values, nulls);
+		result = HeapTupleGetDatum(tuple);
+
+		SRF_RETURN_NEXT(funcctx, result);
+	}
+	else
+		SRF_RETURN_DONE(funcctx);
+}