From: Michael Paquier <michael@paquier.xyz>
Date: Wed, 10 Sep 2025 02:20:46 +0000 (+0900)
Subject: Replace callers of dynahash.h's my_log() by equivalent in pg_bitutils.h
X-Git-Url: http://waps.l3s.uni-hannover.de/gitweb/?a=commitdiff_plain;p=postgresql.git

Replace callers of dynahash.h's my_log() by equivalent in pg_bitutils.h

All the calls replaced by this commit use 4-byte integers for their
variables used in input of my_log2().  Hence, the limit against
too-large inputs does not really apply.  Thresholds are also applied, as
of:
- In nodeAgg.c, the number of partitions is limited by
HASHAGG_MAX_PARTITIONS.
- In nodeHash.c, ExecChooseHashTableSize() caps its maximum number of
buckets based on HashJoinTuple and palloc() allocation limit.
- In worker.c, the number of subxacts tracked by ApplySubXactData uses
uint32, making pg_ceil_log2_64() safe to use directly.

Several approaches have been discussed, like an integration with
thresholds in pg_bitutils.h, but it was found confusing.  This uses
Dean's idea, which gives a simpler result than what I came up with to be
able to remove dynahash.h.  dynahash.h will be removed in a follow-up
commit, removing some duplication with the ceil log2 routines.

Reviewed-by: Peter Eisentraut <peter@eisentraut.org>
Reviewed-by: Dean Rasheed <dean.a.rasheed@gmail.com>
Discussion: https://postgr.es/m/CAEZATCUJPQD_7sC-wErak2CQGNa6bj2hY-mr8wsBki=kX7f2_A@mail.gmail.com
---

diff --git a/src/backend/executor/nodeAgg.c b/src/backend/executor/nodeAgg.c
index 377e016d732..a4f3d30f307 100644
--- a/src/backend/executor/nodeAgg.c
+++ b/src/backend/executor/nodeAgg.c
@@ -267,7 +267,6 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
-#include "utils/dynahash.h"
 #include "utils/expandeddatum.h"
 #include "utils/injection_point.h"
 #include "utils/logtape.h"
@@ -2115,7 +2114,7 @@ hash_choose_num_partitions(double input_groups, double hashentrysize,
 	npartitions = (int) dpartitions;
 
 	/* ceil(log2(npartitions)) */
-	partition_bits = my_log2(npartitions);
+	partition_bits = pg_ceil_log2_32(npartitions);
 
 	/* make sure that we don't exhaust the hash bits */
 	if (partition_bits + used_bits >= 32)
diff --git a/src/backend/executor/nodeHash.c b/src/backend/executor/nodeHash.c
index 8d2201ab67f..a3415db4e20 100644
--- a/src/backend/executor/nodeHash.c
+++ b/src/backend/executor/nodeHash.c
@@ -36,7 +36,6 @@
 #include "executor/nodeHashjoin.h"
 #include "miscadmin.h"
 #include "port/pg_bitutils.h"
-#include "utils/dynahash.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
 #include "utils/syscache.h"
@@ -340,7 +339,7 @@ MultiExecParallelHash(HashState *node)
 	 */
 	hashtable->curbatch = -1;
 	hashtable->nbuckets = pstate->nbuckets;
-	hashtable->log2_nbuckets = my_log2(hashtable->nbuckets);
+	hashtable->log2_nbuckets = pg_ceil_log2_32(hashtable->nbuckets);
 	hashtable->totalTuples = pstate->total_tuples;
 
 	/*
@@ -480,7 +479,7 @@ ExecHashTableCreate(HashState *state)
 							&nbuckets, &nbatch, &num_skew_mcvs);
 
 	/* nbuckets must be a power of 2 */
-	log2_nbuckets = my_log2(nbuckets);
+	log2_nbuckets = pg_ceil_log2_32(nbuckets);
 	Assert(nbuckets == (1 << log2_nbuckets));
 
 	/*
@@ -3499,7 +3498,7 @@ ExecParallelHashTableSetCurrentBatch(HashJoinTable hashtable, int batchno)
 		dsa_get_address(hashtable->area,
 						hashtable->batches[batchno].shared->buckets);
 	hashtable->nbuckets = hashtable->parallel_state->nbuckets;
-	hashtable->log2_nbuckets = my_log2(hashtable->nbuckets);
+	hashtable->log2_nbuckets = pg_ceil_log2_32(hashtable->nbuckets);
 	hashtable->current_chunk = NULL;
 	hashtable->current_chunk_shared = InvalidDsaPointer;
 	hashtable->batches[batchno].at_least_one_chunk = false;
diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c
index b3cac102373..ee6ac22329f 100644
--- a/src/backend/replication/logical/worker.c
+++ b/src/backend/replication/logical/worker.c
@@ -276,7 +276,6 @@
 #include "storage/procarray.h"
 #include "tcop/tcopprot.h"
 #include "utils/acl.h"
-#include "utils/dynahash.h"
 #include "utils/guc.h"
 #include "utils/inval.h"
 #include "utils/lsyscache.h"
@@ -5115,7 +5114,7 @@ subxact_info_read(Oid subid, TransactionId xid)
 	len = sizeof(SubXactInfo) * subxact_data.nsubxacts;
 
 	/* we keep the maximum as a power of 2 */
-	subxact_data.nsubxacts_max = 1 << my_log2(subxact_data.nsubxacts);
+	subxact_data.nsubxacts_max = 1 << pg_ceil_log2_32(subxact_data.nsubxacts);
 
 	/*
 	 * Allocate subxact information in the logical streaming context. We need