aboutsummaryrefslogtreecommitdiff
path: root/src/include/access/gin_tuple.h
diff options
context:
space:
mode:
authorTomas Vondra <tomas.vondra@postgresql.org>2025-03-03 16:53:03 +0100
committerTomas Vondra <tomas.vondra@postgresql.org>2025-03-03 16:53:06 +0100
commit8492feb98f6df3f0f03e84ed56f0d1cbb2ac514c (patch)
tree8b5775ca7cdb77a61c4ada41b45579e50bc3cf35 /src/include/access/gin_tuple.h
parent3f1db99bfabbb9d4afc41f362d9801512f4c7c65 (diff)
downloadpostgresql-8492feb98f6df3f0f03e84ed56f0d1cbb2ac514c.tar.gz
postgresql-8492feb98f6df3f0f03e84ed56f0d1cbb2ac514c.zip
Allow parallel CREATE INDEX for GIN indexes
Allow using parallel workers to build a GIN index, similarly to BTREE and BRIN. For large tables this may result in significant speedup when the build is CPU-bound. The work is divided so that each worker builds index entries on a subset of the table, determined by the regular parallel scan used to read the data. Each worker uses a local tuplesort to sort and merge the entries for the same key. The TID lists do not overlap (for a given key), which means the merge sort simply concatenates the two lists. The merged entries are written into a shared tuplesort for the leader. The leader needs to merge the sorted entries again, before writing them into the index. But this way a significant part of the work happens in the workers, and the leader is left with merging fewer large entries, which is more efficient. Most of the parallelism infrastructure is a simplified copy of the code used by BTREE indexes, omitting the parts irrelevant for GIN indexes (e.g. uniqueness checks). Original patch by me, with reviews and substantial improvements by Matthias van de Meent, certainly enough to make him a co-author. Author: Tomas Vondra, Matthias van de Meent Reviewed-by: Matthias van de Meent, Andy Fan, Kirill Reshke Discussion: https://postgr.es/m/6ab4003f-a8b8-4d75-a67f-f25ad98582dc%40enterprisedb.com
Diffstat (limited to 'src/include/access/gin_tuple.h')
-rw-r--r--src/include/access/gin_tuple.h44
1 files changed, 44 insertions, 0 deletions
diff --git a/src/include/access/gin_tuple.h b/src/include/access/gin_tuple.h
new file mode 100644
index 00000000000..ce555031335
--- /dev/null
+++ b/src/include/access/gin_tuple.h
@@ -0,0 +1,44 @@
+/*--------------------------------------------------------------------------
+ * gin.h
+ * Public header file for Generalized Inverted Index access method.
+ *
+ * Copyright (c) 2006-2024, PostgreSQL Global Development Group
+ *
+ * src/include/access/gin.h
+ *--------------------------------------------------------------------------
+ */
+#ifndef GIN_TUPLE_
+#define GIN_TUPLE_
+
+#include "access/ginblock.h"
+#include "storage/itemptr.h"
+#include "utils/sortsupport.h"
+
+/*
+ * Data for one key in a GIN index.
+ */
+typedef struct GinTuple
+{
+ int tuplen; /* length of the whole tuple */
+ OffsetNumber attrnum; /* attnum of index key */
+ uint16 keylen; /* bytes in data for key value */
+ int16 typlen; /* typlen for key */
+ bool typbyval; /* typbyval for key */
+ signed char category; /* category: normal or NULL? */
+ int nitems; /* number of TIDs in the data */
+ char data[FLEXIBLE_ARRAY_MEMBER];
+} GinTuple;
+
+static inline ItemPointer
+GinTupleGetFirst(GinTuple *tup)
+{
+ GinPostingList *list;
+
+ list = (GinPostingList *) SHORTALIGN(tup->data + tup->keylen);
+
+ return &list->first;
+}
+
+extern int _gin_compare_tuples(GinTuple *a, GinTuple *b, SortSupport ssup);
+
+#endif /* GIN_TUPLE_H */