From 7457d04d0356dbdffe34f623ef3b80914a6b2b67 Mon Sep 17 00:00:00 2001
From: Claude <noreply@anthropic.com>
Date: Sun, 4 Oct 2026 06:39:00 +0000
Subject: [PATCH] Skip SQL comment stripping for DDL that cannot be a virtual
 table

_virtual_table_module() stripped comments character by character from every
table's DDL. Computing derived-table dependencies for each scanned database
made that 1.4s of event-loop time per 17,500 tables at startup. Removing
comments only ever replaces text with spaces, so DDL without the word
"virtual" cannot declare a virtual table: return early.

Also lock SchemaWatcher.catalog_generation increments, since scans can be
stored from several event loops (threads) at once.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EwkLo2rJWidpkDVT3HkvNv
---
 datasette/schema_watcher.py | 18 +++++++++++++-----
 datasette/utils/sqlite.py   |  7 +++++++
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/datasette/schema_watcher.py b/datasette/schema_watcher.py
index 8a11f48b..ba98f20f 100644
--- a/datasette/schema_watcher.py
+++ b/datasette/schema_watcher.py
@@ -63,6 +63,7 @@ import asyncio
 import json
 import logging
 import os
+import threading
 import time
 
 from .utils import sqlite3
@@ -243,8 +244,11 @@ class SchemaWatcher:
         self._spawned = set()
         self._last_sweep = 0.0
         # Bumped after every write to the catalog tables, so readers can
-        # cache things derived from the catalog (see datasette.utils.catalog)
+        # cache things derived from the catalog (see datasette.utils.catalog).
+        # Locked: several event loops (threads) can store scans at once, and
+        # a lost increment would leave a stale cache in place
         self.catalog_generation = 0
+        self._generation_lock = threading.Lock()
         self.counters = {
             "sweeps": 0,
             "sweep_seconds": 0.0,
@@ -259,6 +263,10 @@ class SchemaWatcher:
             "restored_from_persisted": 0,
         }
 
+    def _bump_catalog_generation(self):
+        with self._generation_lock:
+            self.catalog_generation += 1
+
     # ------------------------------------------------------------------
     # configuration
     # ------------------------------------------------------------------
@@ -886,7 +894,7 @@ class SchemaWatcher:
                 )
             # After the states: a reader that sees the new generation must
             # also see their new catalog versions
-            self.catalog_generation += 1
+            self._bump_catalog_generation()
         if missing:
             for state in missing:
                 if not state.missing:
@@ -910,7 +918,7 @@ class SchemaWatcher:
         await self.ds.get_internal_database().execute_write_fn(_clear)
         for state in states:
             state.catalog_version = None
-        self.catalog_generation += 1
+        self._bump_catalog_generation()
 
     async def _delete_catalog(self, names):
         watcher = self
@@ -924,7 +932,7 @@ class SchemaWatcher:
                     conn.execute(f"DELETE FROM {table} WHERE database_name = ?", [name])
 
         await self.ds.get_internal_database().execute_write_fn(_delete)
-        self.catalog_generation += 1
+        self._bump_catalog_generation()
         for name in names:
             self._pending_removals.discard(name)
 
@@ -952,7 +960,7 @@ class SchemaWatcher:
                 )
 
         await internal.execute_write_fn(_delete_stale)
-        self.catalog_generation += 1
+        self._bump_catalog_generation()
         self._pending_removals.clear()
         states = [s for s in self.states.values() if not s.removed]
         persisted = {}
diff --git a/datasette/utils/sqlite.py b/datasette/utils/sqlite.py
index b5d9cfae..f4b88be9 100644
--- a/datasette/utils/sqlite.py
+++ b/datasette/utils/sqlite.py
@@ -354,6 +354,13 @@ def _quote_identifier(value: str) -> str:
 def _virtual_table_module(sql: str | None) -> str | None:
     if not sql:
         return None
+    if "virtual" not in sql.lower():
+        # Fast path: removing comments only ever replaces text with spaces,
+        # so it cannot produce the VIRTUAL keyword. Skips the
+        # character-by-character comment scan for ordinary tables, which
+        # cost ~1.4s of event loop time per 17,500 tables when the
+        # SchemaWatcher computes derived-table dependencies at startup.
+        return None
     match = _VIRTUAL_TABLE_MODULE_RE.search(_strip_sql_comments(sql))
     if match is None:
         return None