浅念
0b03c9fb0d
客户列表行内「今日收发」聚合按 channel=?+owner IN+timestamp>= GROUP BY, 两个既有索引把 timestamp 排在 talker/room 后无法 seek——asyncmy 服务端 预编译时优化器弃索引全表扫 86 万含大文本宽行,实测 7.7s/次,前端每次翻页 都撞(用户报微信客户列表加载慢)。补三列窄索引后 owner 前缀直接落入当天 几百行:GROUP BY 0.14s、API 全链 0.032s(78 倍,翻页/WA/员工过滤同测)。 模型+迁移同步声明(防 autogenerate 反向 DROP),inspect 幂等。 Co-Authored-By: Claude <noreply@anthropic.com>
58 lines
2.0 KiB
Python
58 lines
2.0 KiB
Python
"""message 补 (channel, owner_account_id, timestamp) 索引(客户列表 7.7s 回归修复)
|
|
|
|
Revision ID: c53f90b1e6a4
|
|
Revises: b41e8fa0c7d2
|
|
Create Date: 2026-08-27 16:40:00.000000
|
|
|
|
内容
|
|
----
|
|
客户列表行内的「今日发送/接收」聚合(customer.py 的 send_today/receive_today)
|
|
按 ``channel=? AND owner IN (...) AND timestamp>=今日`` GROUP BY owner/talker。
|
|
两个既有索引把 timestamp 排在 talker/room 之后,时间范围无法 seek——字面量
|
|
SQL 时优化器还能忍(索引全扫 92 万项 0.23s),但 asyncmy 走**服务端预编译**,
|
|
优化器弃索引转全表扫 86 万含大文本的宽行:**7.7s/次**,前端客户列表每次翻页
|
|
都撞(2026-08-27 用户报「微信客户列表加载慢」实测 API 7.6s)。
|
|
|
|
本迁移补 (channel, owner_account_id, timestamp) 三列索引:owner 前缀下按
|
|
timestamp 直接落入当天几百行,实测 0.14s → API 全链 0.097s(78 倍)。窄列
|
|
BTREE,86 万行在线建索引实测 16s。
|
|
|
|
幂等:``sa.inspect`` 先查同名索引,存在即跳过。SQLite/MySQL 通用。
|
|
"""
|
|
from collections.abc import Sequence
|
|
|
|
import sqlalchemy as sa
|
|
from alembic import op
|
|
|
|
|
|
# revision identifiers, used by Alembic.
|
|
revision: str = 'c53f90b1e6a4'
|
|
down_revision: str | Sequence[str] | None = 'b41e8fa0c7d2'
|
|
branch_labels: str | Sequence[str] | None = None
|
|
depends_on: str | Sequence[str] | None = None
|
|
|
|
_INDEX_NAME = 'ix_message_channel_owner_time'
|
|
|
|
|
|
def _has_index(table: str, index: str) -> bool:
|
|
insp = sa.inspect(op.get_bind())
|
|
return index in {i['name'] for i in insp.get_indexes(table)}
|
|
|
|
|
|
def upgrade() -> None:
|
|
"""Upgrade schema."""
|
|
if _has_index('message', _INDEX_NAME):
|
|
return # 已建过(或先手工建过),幂等跳过
|
|
op.create_index(
|
|
_INDEX_NAME,
|
|
'message',
|
|
['channel', 'owner_account_id', 'timestamp'],
|
|
)
|
|
|
|
|
|
def downgrade() -> None:
|
|
"""Downgrade schema."""
|
|
if not _has_index('message', _INDEX_NAME):
|
|
return
|
|
op.drop_index(_INDEX_NAME, table_name='message')
|