As RIP-69 has already been assigned, I have changed the number to RIP-73 ---------- Forwarded message --------- 发件人: zhimin li <lizhim...@gmail.com> Date: 2024年12月5日周四 15:20 Subject: [DISCUSS] [RIP‐69] Pop Consumption Improvement Based on RocksDB To: dev <dev@rocketmq.apache.org>
Hi, rocketmq community: Pop 消费是一种全新的消费模式,具有轻量,客户端无状态,无队列独占等优点,目前 Pop 实现代码量大,关闭 buffer 时磁盘写入流量高,开启 buffer 后状态维护较为复杂。 因此我们提出了一个基于 Rocksdb 来存储状态的新实现,优雅的处理了 PopRetry v1 v2 格式兼容和概率重试的问题,其余改进还包括全异步、缓存设计优化、编解码加速以及访问公平性等多个细节。 Pop consumption is a new consumption model with the advantages of being lightweight, stateless on the client side, and non-exclusive queueing in load balance. However, the current pop implementation has a large codebase, high disk write traffic when the buffer is closed, and more complex state maintenance when the buffer is enabled.Therefore, we propose a new implementation based on rocksdb storage to elegantly solve the compatibility issues between pop retry topic v1 and v2 formats and the probabilistic retry access problem. 如果您对这个方案感兴趣,请访问如下链接查看方案细节: Issue: https://github.com/apache/rocketmq/issues/9025 Proposal Link:https://github.com/apache/rocketmq/wiki/%5BRIP%E2%80%9069%5D-Pop-Consumption-Improvement-Based-on-RocksDB 如果有任何疑问,请回复邮件至 dev@rocketmq.apache.org 或在 issue 下评论 If you have any questions, please reply to this email at dev@rocketmq.apache.org Or leave a comment under issue ZHIMIN, LI