Install a search tree depth limit in GIN bulk-insert operations, to prevent

them from degrading badly when the input is sorted or nearly so.  In this
scenario the tree is unbalanced to the point of becoming a mere linked list,
so insertions become O(N^2).  The easiest and most safely back-patchable
solution is to stop growing the tree sooner, ie limit the growth of N.  We
might later consider a rebalancing tree algorithm, but it's not clear that
the benefit would be worth the cost and complexity.  Per report from Sergey
Burladyan and an earlier complaint from Heikki.

Back-patch to 8.2; older versions didn't have GIN indexes.

diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c
index 31af4a82f1d2887cf5eca9a658638c80ef73e017..c5a8a86bbd7bd9eb4dc644fb6afcd5ca1747ad3b 100644 (file)
--- a/src/backend/access/gin/gininsert.c
+++ b/src/backend/access/gin/gininsert.c
@@ -8,7 +8,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *                     $PostgreSQL: pgsql/src/backend/access/gin/gininsert.c,v 1.11.2.1 2008/11/13 17:42:18 tgl Exp $
+ *                     $PostgreSQL: pgsql/src/backend/access/gin/gininsert.c,v 1.11.2.2 2009/03/24 22:06:24 tgl Exp $
  *-------------------------------------------------------------------------
  */
 
@@ -238,7 +238,9 @@ ginBuildCallback(Relation index, HeapTuple htup, Datum *values,
        buildstate->indtuples += ginHeapTupleBulkInsert(buildstate, *values, &htup->t_self);
 
        /* If we've maxed out our available memory, dump everything to the index */
-       if (buildstate->accum.allocatedMemory >= maintenance_work_mem * 1024L)
+       /* Also dump if the tree seems to be getting too unbalanced */
+       if (buildstate->accum.allocatedMemory >= maintenance_work_mem * 1024L ||
+               buildstate->accum.maxdepth > GIN_MAX_TREE_DEPTH)
        {
                ItemPointerData *list;
                Datum           entry;

diff --git a/src/include/access/gin.h b/src/include/access/gin.h
index 8e3a25e9d4301b26b66f17941aad177e1a7e5e38..75aa7a5935f1b44022e825c764f0d5c181ff0890 100644 (file)
--- a/src/include/access/gin.h
+++ b/src/include/access/gin.h
@@ -4,7 +4,7 @@
  *
  *     Copyright (c) 2006-2008, PostgreSQL Global Development Group
  *
- *     $PostgreSQL: pgsql/src/include/access/gin.h,v 1.16.2.1 2008/04/22 17:54:19 teodor Exp $
+ *     $PostgreSQL: pgsql/src/include/access/gin.h,v 1.16.2.2 2009/03/24 22:06:24 tgl Exp $
  *--------------------------------------------------------------------------
  */
 
@@ -32,6 +32,14 @@
 #define GIN_CONSISTENT_PROC                       4
 #define GINNProcs                                         4
 
+/*
+ * Max depth allowed in search tree during bulk inserts.  This is to keep from
+ * degenerating to O(N^2) behavior when the tree is unbalanced due to sorted
+ * or nearly-sorted input.  (Perhaps it would be better to use a balanced-tree
+ * algorithm, but in common cases that would only add useless overhead.)
+ */
+#define GIN_MAX_TREE_DEPTH 100
+
 /*
  * Page opaque data in a inverted index page.
  *
@@ -314,12 +322,9 @@ extern IndexTuple ginPageGetLinkItup(Buffer buf);
 
 /* gindatapage.c */
 extern int     compareItemPointers(ItemPointer a, ItemPointer b);
-extern void
-MergeItemPointers(
-                                 ItemPointerData *dst,
+extern void MergeItemPointers(ItemPointerData *dst,
                                  ItemPointerData *a, uint32 na,
-                                 ItemPointerData *b, uint32 nb
-);
+                                 ItemPointerData *b, uint32 nb);
 
 extern void GinDataPageAddItem(Page page, void *data, OffsetNumber offset);
 extern void PageDeletePostingItem(Page page, OffsetNumber offset);