MIME-Version: 1.0
References: <567ED6CA.2040504@sigaev.ru>
 <CAPpHfdt58O5jzKMjkScNbGecM5JqfaMfdGLjs4rk5XisfjTNBw@mail.gmail.com>
 <16a7e3aa-24c0-4986-8820-ea2857bd7b6b@postgrespro.ru>
 <421656a9-5df7-41bb-9d58-1c1edbd5dc3e@postgrespro.ru>
 <28c727ba-5260-42a8-88b0-4ecdeeca6ef8@postgrespro.ru>
 <4c1c2c0b-802f-45ae-a7cd-007bfd8957cf@postgrespro.ru>
 <52f0d302-7963-452f-8c5a-f66d261514eb@postgrespro.ru>
 <43ad8a48-b980-410d-a83c-5beebf82a4ed@postgrespro.ru>
 <b5a5b515-6f38-431a-98b8-d30abae62fde@postgrespro.ru>
 <be8ae03d-9eb3-4adb-beb8-3b356b3c68bb@postgrespro.ru>
 <CAPpHfdu-_j6=E9CHjSGu0=SidfTqdtj7qk78dCdW-=4RFDHBDw@mail.gmail.com>
 <04ef16eb-46c1-4ce7-9f68-d1c80ef0be81@postgrespro.ru>
 <CA+TgmoZCgP6FrBQEusn4yaWm02XU8OPeoEMk91q7PRBgwaAkFw@mail.gmail.com>
 <cfdc7fef-cf0b-437b-89fa-62ffd6677f7d@postgrespro.ru>
 <59e67a40-95a8-4d74-ae4e-027ea0f59084@postgrespro.ru>
 <59b77a8a-29d6-4727-bf26-4a30a6a9719a@postgrespro.ru>
 <32d23d97-d07f-4d44-9933-ba3295fb3ed8@postgrespro.ru>
 <aec17a1a-9de0-4994-8a53-c6b4e64afb17@postgrespro.ru>
In-Reply-To: <aec17a1a-9de0-4994-8a53-c6b4e64afb17@postgrespro.ru>
From: jian he <jian.universality@gmail.com>
Date: Tue, 30 Jan 2024 22:15:20 +0800
Message-ID: 
 <CACJufxGXhJ823cdAdp2Ho7qC-HZ3_-dtdj-myaAi_u9RQLn45g@mail.gmail.com>
Subject: Re: POC, WIP: OR-clause support for indexes
To: Andrei Lepikhov <a.lepikhov@postgrespro.ru>
Cc: Alena Rybakina <a.rybakina@postgrespro.ru>,
 Robert Haas <robertmhaas@gmail.com>,
	pgsql-hackers@postgresql.org, Alexander Korotkov <aekorotkov@gmail.com>,
	Peter Geoghegan <pg@bowt.ie>, "Finnerty, Jim" <jfinnert@amazon.com>,
 Marcos Pegoraro <marcos@f10.com.br>, teodor@sigaev.ru,
	Ranier Vilela <ranier.vf@gmail.com>,
 Tomas Vondra <tomas.vondra@enterprisedb.com>,
	Peter Eisentraut <peter@eisentraut.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Archived-At: 
 <https://www.postgresql.org/message-id/CACJufxGXhJ823cdAdp2Ho7qC-HZ3_-dtdj-myaAi_u9RQLn45g%40mail.gmail.com>
Precedence: bulk

On Tue, Dec 5, 2023 at 6:55=E2=80=AFPM Andrei Lepikhov
<a.lepikhov@postgrespro.ru> wrote:
>
> Here is fresh version with the pg_dump.pl regex fixed. Now it must pass
> buildfarm.

+JumbleState *
+JumbleExpr(Expr *expr, uint64 *queryId)
+{
+ JumbleState *jstate =3D NULL;
+
+ Assert(queryId !=3D NULL);
+
+ jstate =3D (JumbleState *) palloc(sizeof(JumbleState));
+
+ /* Set up workspace for query jumbling */
+ jstate->jumble =3D (unsigned char *) palloc(JUMBLE_SIZE);
+ jstate->jumble_len =3D 0;
+ jstate->clocations_buf_size =3D 32;
+ jstate->clocations =3D (LocationLen *)
+ palloc(jstate->clocations_buf_size * sizeof(LocationLen));
+ jstate->clocations_count =3D 0;
+ jstate->highest_extern_param_id =3D 0;
+
+ /* Compute query ID */
+ _jumbleNode(jstate, (Node *) expr);
+ *queryId =3D DatumGetUInt64(hash_any_extended(jstate->jumble,
+ jstate->jumble_len,
+ 0));
+
+ if (*queryId =3D=3D UINT64CONST(0))
+ *queryId =3D UINT64CONST(1);
+
+ return jstate;
+}

+/*
+ * Hash function that's compatible with guc_name_compare
+ */
+static uint32
+orclause_hash(const void *data, Size keysize)
+{
+ OrClauseGroupKey   *key =3D (OrClauseGroupKey *) data;
+ uint64 hash;
+
+ (void) JumbleExpr(key->expr, &hash);
+ hash +=3D ((uint64) key->opno + (uint64) key->exprtype) % UINT64_MAX;
+ return hash;
+}

correct me if i am wrong:
in orclause_hash, you just want to return a uint32, then why does the
JumbleExpr function return struct JumbleState.
here JumbleExpr, we just simply hash part of a Query struct,
so JumbleExpr's queryId would be confused with JumbleQuery function's query=
Id.

not sure the purpose of the following:
+ if (*queryId =3D=3D UINT64CONST(0))
+ *queryId =3D UINT64CONST(1);

even if  *queryId is 0
`hash +=3D ((uint64) key->opno + (uint64) key->exprtype) % UINT64_MAX;`
will make the hash return non-zero?

+ MemSet(&info, 0, sizeof(info));
i am not sure this is necessary.

Some comments on OrClauseGroupEntry would be great.

seems there is no doc.

create or replace function retint(int) returns int as
$func$
begin return $1 + round(10 * random()); end
$func$ LANGUAGE plpgsql;

set enable_or_transformation to on;
EXPLAIN (COSTS OFF)
SELECT count(*) FROM tenk1
WHERE thousand =3D 42 AND (tenthous * retint(1) =3D NULL OR tenthous *
retint(1) =3D 3) OR thousand =3D 41;

returns:
                                                    QUERY PLAN
---------------------------------------------------------------------------=
----------------------------------------
 Aggregate
   ->  Seq Scan on tenk1
         Filter: (((thousand =3D 42) AND ((tenthous * retint(1)) =3D ANY
('{NULL,3}'::integer[]))) OR (thousand =3D 41))
(3 rows)

Based on the query plan, retint executed once, but here it should be
executed twice?
maybe we need to use contain_volatile_functions to check through the
other part of the operator expression.

+ if (IsA(leftop, Const))
+ {
+ opno =3D get_commutator(opno);
+
+ if (!OidIsValid(opno))
+ {
+ /* Commuter doesn't exist, we can't reverse the order */
+ or_list =3D lappend(or_list, orqual);
+ continue;
+ }
+
+ nconst_expr =3D get_rightop(orqual);
+ const_expr =3D get_leftop(orqual);
+ }
+ else if (IsA(rightop, Const))
+ {
+ const_expr =3D get_rightop(orqual);
+ nconst_expr =3D get_leftop(orqual);
+ }
+ else
+ {
+ or_list =3D lappend(or_list, orqual);
+ continue;
+ }
do we need to skip this transformation for the const type is anyarray?