zulip/zerver/migrations/0239_usermessage_copy_id_to_bigint_id.py

# Generated by Django 1.11.23 on 2019-08-21 21:43

import time

from django.db import connection, migrations
from django.db.backends.postgresql.schema import BaseDatabaseSchemaEditor
from django.db.migrations.state import StateApps
from django.db.models import Min
from psycopg2.sql import SQL

BATCH_SIZE = 10000


def sql_copy_id_to_bigint_id(id_range_lower_bound: int, id_range_upper_bound: int) -> None:
    query = SQL(
        """
            UPDATE zerver_usermessage
            SET bigint_id = id
            WHERE id BETWEEN %(lower_bound)s AND %(upper_bound)s
    """
    )
    with connection.cursor() as cursor:
        cursor.execute(
            query,
            {
                "lower_bound": id_range_lower_bound,
                "upper_bound": id_range_upper_bound,
            },
        )


def copy_id_to_bigid(apps: StateApps, schema_editor: BaseDatabaseSchemaEditor) -> None:
    UserMessage = apps.get_model("zerver", "UserMessage")
    if not UserMessage.objects.exists():
        # Nothing to do
        return

    #  TODO: is  the below lookup fast enough, considering there's no index on bigint_id?
    first_uncopied_id = UserMessage.objects.filter(bigint_id__isnull=True).aggregate(Min("id"))[
        "id__min"
    ]
    # Note: the below id can fall in a segment
    # where bigint_id = id already, but it's not a big problem
    # this will just do some redundant UPDATEs.
    last_id = UserMessage.objects.latest("id").id

    id_range_lower_bound = first_uncopied_id
    id_range_upper_bound = first_uncopied_id + BATCH_SIZE
    while id_range_upper_bound <= last_id:
        sql_copy_id_to_bigint_id(id_range_lower_bound, id_range_upper_bound)
        id_range_lower_bound = id_range_upper_bound + 1
        id_range_upper_bound = id_range_lower_bound + BATCH_SIZE
        time.sleep(0.1)

    if last_id > id_range_lower_bound:
        # Copy for the last batch.
        sql_copy_id_to_bigint_id(id_range_lower_bound, last_id)


class Migration(migrations.Migration):
    atomic = False
    dependencies = [
        ("zerver", "0238_usermessage_bigint_id"),
    ]

    operations = [
        migrations.RunSQL(
            """
        CREATE FUNCTION zerver_usermessage_bigint_id_to_id_trigger_function()
        RETURNS trigger AS $$
        BEGIN
            NEW.bigint_id = NEW.id;
            RETURN NEW;
        END
        $$ LANGUAGE 'plpgsql';

        CREATE TRIGGER zerver_usermessage_bigint_id_to_id_trigger
        BEFORE INSERT ON zerver_usermessage
        FOR EACH ROW
        EXECUTE PROCEDURE zerver_usermessage_bigint_id_to_id_trigger_function();
        """
        ),
        migrations.RunPython(copy_id_to_bigid, elidable=True),
        migrations.RunSQL(
            """
        CREATE UNIQUE INDEX CONCURRENTLY zerver_usermessage_bigint_id_idx ON zerver_usermessage (bigint_id);
        """
        ),
    ]