Spacetime 数据库水平扩展方案定档
推荐指数 50.0 NO. 015 · 2026.09.05
发布2026/09/04Score98Comments61
为什么值得看
Spacetime 详细拆解了数据库三维扩展（计算、存储、网络）的底层约束，承认 OLTP 的通用水平扩展常被过度承诺，并公布存储分片将于 2026 年 10 月上线。对正在选型分布式数据库的团队，这是一份难得的"先说不能做什么"的技术诚实。
编辑判断
Spacetime 创始人选择公开讨论"哪些部分不能水平扩展"，这在数据库营销中极为罕见。CockroachDB 和 TiDB 早期也曾因过度承诺通用扩展性而让用户踩过网络协调的坑，Spacetime 显然想避免这条老路。
值得注意的时间点是 2026 年 10 月——存储分片先上，计算和网络的扩展方案未给明确日期。这意味着 Spacetime 目前更适合写少读多、数据量增长快但计算模式相对固定的场景，比如时序数据归档或游戏状态同步，而非高并发 OLTP 交易。
如果你正在 CockroachDB、TiDB 和 Spacetime 之间做选型，建议等存储分片上线后重点压测跨分片事务的 p99 延迟，这是文章暗示的未解决难点。
社区反馈
意见分歧 52 条评论
核心争论：分布式数据库水平扩展是否被过度承诺，以及何时真正需要水平扩展而非单机方案
I had a coworker that would always ask this, like a javelin thrown in the bicycle spokes of every demo. We hoped for tens of users.
I was waiting for a comment like this. It's not like there aren't any projects that should be thinking about "scale", but it's almost a meme at this point. There is even the section there near the beginning about how small web apps without many users 'may have to think about horizontal scaling as we
its substantially worse than that. anytime anyone uses the word 'scale' without even saying what kind of scaling they mean is guilty of eroding the discourse. at this point I don't think we should even be talking about scaling without meaning 'the Amdahl residual'