codelipenghui commented on PR #21739: URL: https://github.com/apache/pulsar/pull/21739#issuecomment-1873545856
> Yes, because of message skipCondition, one single segment can be spit into segments, such as: entries to be filter-out: [3, 5, 7] entries to read: [1, 10] then, it will be split into: [[1,2],[4], [6], [8,10]], right? In the previous implementation, after read [1,2] finished, then begin to read [4], after read [4] finished, then start to read [6]... I believe it will lead to latency increasing, memory(allocated for entries) will also be retained for a longer period of time, it will affect the throughput of the system. So I tried to read these segments parallel, and it would make changes to ManagedLedgerImpl. @dao-jun Is it better to split them into 2 PRs? The current one is focused on `filter-out deleted entries before reading entries` and the another one for making the reads parallelly. I haven't checked the details yet, but we should be carefully to make this improvement to avoid any regression to the ordering dispatch. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
