Extremely long delay grabbing type info for string array (and likely other types) on CockroachDB

I was having atrocious and unacceptable delays in my production environment that I wasn't seeing locally, using CockroachDB cloud. Found the cause was the introspection of types. I'm using the latest version of the CockroachDB drivers.

I wrote this hack to work around the issue. It caches the result in local memory and also caches it to redis so that new instances don't see it. You can change the key for the redis cache using an environment variable so that new versions aren't locked to old values.

If someone wants to turn it into part of the product, please be my guest. I won't have time for it. In the mean time. here's the hack that does monkey patching:

introspection_result_cache: dict[tuple[str, int, str], Any] = {}

orig_introspection_types = asyncpg.Connection._introspect_types

INTROSPECTION_KEY = os.environ.get(
    "ASYNCPG_INTROSPECTION_CACHE_KEY", "ASYNCPG_INTROSPECTION_CACHE_KEY"
)

introspection_lock = asyncio.Lock()


class FauxResult:
    _binary_fields = ("kind", "elemdelim")
    column_order = [
        "oid",
        "ns",
        "name",
        "kind",
        "basetype",
        "elemtype",
        "elemdelim",
        "range_subtype",
        "attrtypoids",
        "attrnames",
        "depth",
        "basetype_name",
        "elemtype_name",
        "range_subtype_name",
    ]

    def __init__(self, row=None, data: dict | None = None) -> None:
        if row:
            self.data = dict(row)
        else:
            assert data
            self.data = data

    def __getattr__(self, name: str) -> Any:
        return self.data[name]

    def __getitem__(self, idx_or_column_name: int | str) -> Any:
        if isinstance(idx_or_column_name, int):
            return self.data[self.column_order[idx_or_column_name]]
        return self.data[idx_or_column_name]

    def for_serialization(self) -> dict:
        result = copy.copy(self.data)
        for field in self._binary_fields:
            if (value := self.data.get(field)) is not None:
                result[field] = value.decode()
        return result

    @classmethod
    def from_serialization(cls, data: dict) -> Self:
        for field in cls._binary_fields:
            if (value := data.get(field)) is not None:
                data[field] = value.encode()
        return cls(data=data)


class FauxPreparedStatementState:
    def __init__(self, name) -> None:
        self.name = name


async def to_redis_cache(
    host: str, port: int, database: str, inspection_types: tuple[list, Any]
) -> None:
    pss = FauxPreparedStatementState(inspection_types[1].name)
    results = [FauxResult(row) for row in inspection_types[0]]
    await redis_client().set(
        INTROSPECTION_KEY + f"-{host}-{port}-{database}",
        orjson.dumps([[result.for_serialization() for result in results], pss.name]),
    )


async def from_redis_cache(host: str, port: int, database: str) -> tuple[list, Any] | None:
    data = await redis_client().get(INTROSPECTION_KEY + f"-{host}-{port}-{database}")
    if data is None:
        return None
    results, pss_name = orjson.loads(data)
    pss = FauxPreparedStatementState(pss_name)
    return [FauxResult.from_serialization(row) for row in results], pss


def apply_introspection_caching():

    async def new_introspect_types(self, *args, **kwargs) -> Any:
        host: str
        port: int
        database: str
        host, port = self._addr
        database = self._params.database
        if (cached_val := introspection_result_cache.get((host, port, database))) is not None:
            return cached_val
        async with introspection_lock:
            redis_cached_value = await from_redis_cache(host, port, database)
        if redis_cached_value is not None:
            introspection_result_cache[host, port, database] = redis_cached_value
            return redis_cached_value
        result = await orig_introspection_types(self, *args, **kwargs)
        await to_redis_cache(host, port, database, result)
        return result

    asyncpg.Connection._introspect_types = new_introspect_types

Das Issue identifiziert asyncpg.Connection._introspect_types als Einstiegspunkt und berichtet von erheblichen Verzögerungen bei der Typintrospektion von CockroachDB; beginne dort und reproduziere das Verhalten mit CockroachDB. Der vorgeschlagene Caching-Workaround zeigt eine mögliche Richtung auf, aber die beabsichtigte Lösung und die Kriterien für den Abschluss müssen mit den Maintainer:innen abgestimmt werden.