From bdc6cfcd12f5c95799328e05aa4bfa75cfe3e79f Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Wed, 10 Sep 2025 16:15:08 -0400 Subject: Eliminate duplicative hashtempcxt in nodeSubplan.c. Instead of building a separate memory context that's used just for running hash functions, make the hash functions run in the per-tuple context of the node's innerecontext. This saves a little space at runtime, and it avoids needing to reset two contexts instead of one inside buildSubPlanHash's main loop. This largely reverts commit 133924e13. That's safe to do now because bf6c614a2 decoupled the evaluation context used by TupleHashTableMatch from that used for hash function evaluation, so that there's no longer a risk of resetting the innerecontext too soon. Per discussion of bug #19040, although this is not directly a fix for that. Author: Tom Lane Reviewed-by: Haiyang Li Reviewed-by: Fei Changhong Discussion: https://postgr.es/m/19040-c9b6073ef814f48c@postgresql.org --- src/include/nodes/execnodes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'src/include/nodes/execnodes.h') diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index de782014b2d..71857feae48 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -1020,7 +1020,6 @@ typedef struct SubPlanState bool havehashrows; /* true if hashtable is not empty */ bool havenullrows; /* true if hashnulls is not empty */ MemoryContext hashtablecxt; /* memory context containing hash tables */ - MemoryContext hashtempcxt; /* temp memory context for hash tables */ ExprContext *innerecontext; /* econtext for computing inner tuples */ int numCols; /* number of columns being hashed */ /* each of the remaining fields is an array of length numCols: */ -- cgit v1.2.3