Reconsider page size for large objects: rather than stuffing disk pages

as full as possible, seems better to use a tuple size around BLCKSZ/4
so that less space is wasted when a LO tuple is updated.  Also, this
lets us use a logical page size that's an exact power of two, avoiding
partial-page writes when client is sending us stuff in power-of-2
buffer chunks.

diff --git a/src/include/catalog/catversion.h b/src/include/catalog/catversion.h
index f6fd284f34d7ab99d959a08755266dbfdda728f4..56f515b662a44af5196a5d568c8ad3ce6b8fae83 100644 (file)
--- a/src/include/catalog/catversion.h
+++ b/src/include/catalog/catversion.h
@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2000, PostgreSQL, Inc
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: catversion.h,v 1.52 2000/10/24 01:38:41 tgl Exp $
+ * $Id: catversion.h,v 1.53 2000/10/24 03:34:15 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*                         yyyymmddN */
-#define CATALOG_VERSION_NO 200010232
+#define CATALOG_VERSION_NO 200010233
 
 #endif

diff --git a/src/include/storage/large_object.h b/src/include/storage/large_object.h
index 6bb0c4fcf2e6612167641db0e7616b68609f9227..c763012481128e066e0fda1f7926ad22a799fc01 100644 (file)
--- a/src/include/storage/large_object.h
+++ b/src/include/storage/large_object.h
@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1996-2000, PostgreSQL, Inc
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: large_object.h,v 1.18 2000/10/24 01:38:43 tgl Exp $
+ * $Id: large_object.h,v 1.19 2000/10/24 03:34:53 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -47,13 +47,18 @@ typedef struct LargeObjectDesc {
 /*
  * Each "page" (tuple) of a large object can hold this much data
  *
- * Calculation is max tuple size less tuple header, loid field (Oid),
- * pageno field (int32), and varlena header of data (int32).  Note we
- * assume none of the fields will be NULL, hence no need for null bitmap.
+ * We could set this as high as BLCKSZ less some overhead, but it seems
+ * better to make it a smaller value, so that not as much space is used
+ * up when a page-tuple is updated.  Note that the value is deliberately
+ * chosen large enough to trigger the tuple toaster, so that we will
+ * attempt to compress page tuples in-line.  (But they won't be moved off
+ * unless the user creates a toast-table for pg_largeobject...)
+ *
+ * Also, it seems to be a smart move to make the page size be a power of 2,
+ * since clients will often be written to send data in power-of-2 blocks.
+ * This avoids unnecessary tuple updates caused by partial-page writes.
  */
-#define    LOBLKSIZE       (MaxTupleSize \
-                        - MAXALIGN(offsetof(HeapTupleHeaderData, t_bits)) \
-                        - sizeof(Oid) - sizeof(int32) * 2)
+#define    LOBLKSIZE       (BLCKSZ / 4)
 
 
 /*