lizhanhui commented on issue #5184: URL: https://github.com/apache/rocketmq/issues/5184#issuecomment-1272732514
Hi @nowinkeyy Glad to see your attempts. I advise you to create a RIP, where we can formally define this problem and discuss potential solutions. I am glad to act as shepherd. Actually, we can make writes of consume-queue concurrent since slot of each entry has already been sequentially allocated. We only need to record the position prior to which there would be no empty slots and consumer may consume messages up to. Further, writing to commit log itself may also be made concurrent. Refer MySQL 8.0 which writes to WAL are already concurrent https://dev.mysql.com/blog-archive/mysql-8-0-new-lock-free-scalable-wal-design/ -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: dev-unsubscr...@rocketmq.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
