wave7: 433/194 — kafka/flink/pulsar, spring/micronaut/quarkus, nginx/haproxy/traefik, linux/nomad/consul, numpy/pandas/sklearn, ES/OS/pg/sqlite/rustc/cargo
This commit is contained in:
parent
3735145aa5
commit
5fe6da7cc2
69 changed files with 6793 additions and 32 deletions
|
|
@ -0,0 +1,93 @@
|
|||
# postgresql-0008 — `paraminfo_get_equal_hashops`: O(N²) list_member deduplication in Memoize path planning
|
||||
|
||||
## Status
|
||||
PATCHED
|
||||
|
||||
## Severity
|
||||
MEDIUM (>20× speedup at N=300 join/lateral clauses)
|
||||
|
||||
## Location
|
||||
`src/backend/optimizer/path/joinpath.c`, function `paraminfo_get_equal_hashops()`
|
||||
|
||||
## Description
|
||||
`paraminfo_get_equal_hashops()` builds two parallel lists: `*param_exprs` and
|
||||
`*operators`. While iterating over `ppi_clauses` (join clauses) and
|
||||
`innerrel->lateral_vars` (lateral variable references), it deduplicates entries
|
||||
using `list_member(*param_exprs, expr)` — a full O(|param_exprs|) structural
|
||||
`equal()` walk on every iteration.
|
||||
|
||||
The pattern:
|
||||
|
||||
```c
|
||||
foreach(lc, clauses) {
|
||||
...
|
||||
if (!list_member(*param_exprs, expr)) /* O(|param_exprs|) */
|
||||
*param_exprs = lappend(*param_exprs, expr);
|
||||
}
|
||||
foreach(lc, lateral_vars) {
|
||||
...
|
||||
if (!list_member(*param_exprs, expr)) /* O(|param_exprs|) scan again */
|
||||
*param_exprs = lappend(*param_exprs, expr);
|
||||
}
|
||||
```
|
||||
|
||||
Total cost: O(N²) where N = |ppi_clauses| + |lateral_vars|.
|
||||
|
||||
`expr` is typically a `Var` node (column reference from the outer relation).
|
||||
For Var nodes, deduplication can use Bitmapset O(1) keyed on
|
||||
`varno * 3200 + varattno + 1600` (same encoding as postgresql-0003/0004).
|
||||
Non-Var expressions fall back to a kept `List *seen_nonvar` with `list_member`.
|
||||
|
||||
### Hot path
|
||||
Called from `create_memoize_path()` (line ~844) for every candidate Memoize
|
||||
join path — once per inner relation per parameterized outer path. With K
|
||||
joins in a query of N tables, this is called O(K×P) times where P is the
|
||||
number of parameterized paths.
|
||||
|
||||
## Patch
|
||||
|
||||
```c
|
||||
--- a/src/backend/optimizer/path/joinpath.c
|
||||
+++ b/src/backend/optimizer/path/joinpath.c
|
||||
@@ -480,6 +480,10 @@ paraminfo_get_equal_hashops(...)
|
||||
{
|
||||
List *lateral_vars;
|
||||
ListCell *lc;
|
||||
+ /* CWE-407 fix (postgresql-0008): track seen Var exprs with a Bitmapset so
|
||||
+ * each duplicate check is O(1) instead of O(|param_exprs|).
|
||||
+ * Non-Var exprs fall back to a List for structural equal() comparison. */
|
||||
+ Bitmapset *seen_bms = NULL;
|
||||
+ List *seen_nonvar = NIL;
|
||||
|
||||
*param_exprs = NIL;
|
||||
*operators = NIL;
|
||||
@@ -536,9 +540,21 @@ paraminfo_get_equal_hashops(...)
|
||||
if (!OidIsValid(hasheqoperator))
|
||||
...
|
||||
|
||||
- if (!list_member(*param_exprs, expr))
|
||||
+ /* O(1) Var-path check; O(|seen_nonvar|) fallback for non-Var */
|
||||
+ bool already_seen;
|
||||
+ if (IsA(expr, Var)) {
|
||||
+ Var *v = (Var *) expr;
|
||||
+ int key = v->varno * 3200 + v->varattno + 1600;
|
||||
+ already_seen = bms_is_member(key, seen_bms);
|
||||
+ if (!already_seen) seen_bms = bms_add_member(seen_bms, key);
|
||||
+ } else {
|
||||
+ already_seen = list_member(seen_nonvar, expr);
|
||||
+ if (!already_seen) seen_nonvar = lappend(seen_nonvar, expr);
|
||||
+ }
|
||||
+ if (!already_seen)
|
||||
{
|
||||
*operators = lappend_oid(*operators, hasheqoperator);
|
||||
*param_exprs = lappend(*param_exprs, expr);
|
||||
```
|
||||
|
||||
(Same pattern repeated for the `lateral_vars` loop at line ~593.)
|
||||
|
||||
## Speedup
|
||||
At N=300 lateral vars (all unique Vars): O(N²)=90,000 ops → O(N)=300 ops → **300× speedup**.
|
||||
Realistic scenario (N=50): O(N²)=2,500 ops → O(N)=50 ops → **50× speedup**.
|
||||
|
||||
## Test
|
||||
`defects/postgresql/unit/PostgresqlTest.java` — `postgresql-0008` section.
|
||||
|
|
@ -0,0 +1,83 @@
|
|||
diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c
|
||||
index abcdef..123456 100644
|
||||
--- a/src/backend/optimizer/path/joinpath.c
|
||||
+++ b/src/backend/optimizer/path/joinpath.c
|
||||
@@ -481,6 +481,13 @@ paraminfo_get_equal_hashops(PlannerInfo *root, ParamPathInfo *param_info,
|
||||
{
|
||||
List *lateral_vars;
|
||||
ListCell *lc;
|
||||
+ /*
|
||||
+ * CWE-407 fix (postgresql-0008, joinpath.c):
|
||||
+ * Track seen Var exprs via a Bitmapset (O(1) per check) instead of
|
||||
+ * list_member(*param_exprs, ...) which is O(|param_exprs|) and makes
|
||||
+ * the full deduplication loop O(N²). Non-Var nodes fall back to a
|
||||
+ * kept list and structural equal() — they are rare in practice.
|
||||
+ */
|
||||
+ Bitmapset *seen_bms = NULL;
|
||||
+ List *seen_nonvar = NIL;
|
||||
|
||||
*param_exprs = NIL;
|
||||
*operators = NIL;
|
||||
@@ -534,9 +541,27 @@ paraminfo_get_equal_hashops(PlannerInfo *root, ParamPathInfo *param_info,
|
||||
* 'expr' may already exist as a parameter from a previous item in
|
||||
* ppi_clauses. No need to include it again, however we'd better
|
||||
* ensure we do switch into binary mode if required. See below.
|
||||
*/
|
||||
- if (!list_member(*param_exprs, expr))
|
||||
+ {
|
||||
+ bool already_seen;
|
||||
+
|
||||
+ if (IsA(expr, Var))
|
||||
+ {
|
||||
+ Var *v = (Var *) expr;
|
||||
+ int key = v->varno * 3200 + v->varattno + 1600;
|
||||
+
|
||||
+ already_seen = bms_is_member(key, seen_bms);
|
||||
+ if (!already_seen)
|
||||
+ seen_bms = bms_add_member(seen_bms, key);
|
||||
+ }
|
||||
+ else
|
||||
+ {
|
||||
+ already_seen = list_member(seen_nonvar, expr);
|
||||
+ if (!already_seen)
|
||||
+ seen_nonvar = lappend(seen_nonvar, expr);
|
||||
+ }
|
||||
+ if (!already_seen)
|
||||
{
|
||||
*operators = lappend_oid(*operators, hasheqoperator);
|
||||
*param_exprs = lappend(*param_exprs, expr);
|
||||
}
|
||||
+ }
|
||||
|
||||
/*
|
||||
* When the join operator is not hashable then it's possible that
|
||||
@@ -584,9 +599,24 @@ paraminfo_get_equal_hashops(PlannerInfo *root, ParamPathInfo *param_info,
|
||||
* 'expr' may already exist as a parameter from the ppi_clauses. No
|
||||
* need to include it again, however we'd better ensure we do switch
|
||||
* into binary mode.
|
||||
*/
|
||||
- if (!list_member(*param_exprs, expr))
|
||||
+ {
|
||||
+ bool already_seen;
|
||||
+
|
||||
+ if (IsA(expr, Var))
|
||||
+ {
|
||||
+ Var *v = (Var *) expr;
|
||||
+ int key = v->varno * 3200 + v->varattno + 1600;
|
||||
+
|
||||
+ already_seen = bms_is_member(key, seen_bms);
|
||||
+ if (!already_seen)
|
||||
+ seen_bms = bms_add_member(seen_bms, key);
|
||||
+ }
|
||||
+ else
|
||||
+ {
|
||||
+ already_seen = list_member(seen_nonvar, expr);
|
||||
+ if (!already_seen)
|
||||
+ seen_nonvar = lappend(seen_nonvar, expr);
|
||||
+ }
|
||||
+ if (!already_seen)
|
||||
{
|
||||
*operators = lappend_oid(*operators, typentry->eq_opr);
|
||||
*param_exprs = lappend(*param_exprs, expr);
|
||||
}
|
||||
+ }
|
||||
Loading…
Add table
Add a link
Reference in a new issue