If the number of concurrent established connections is high, the main thread, which polls all the active connections and iterates all the connections, can become a bottleneck.
Investigate alteratives, eg multiple polling threads, event completion frameworks ....
attachment 0001-multi-poll-part-1.patch
attachment 0002-multi-poll-part-2.patch
I did attach a port to current master of a fix provided by Nathan. Just for reference or as a starting point
nunc-stans is part of it - we still need to figure out how to do accept very fast - for the case where the server gets many new connection requests: Ticket #48121 - Accept many new connection requests (milestone - 1.3.5)
Per DS meeting on the 9th of July, closing this ticket as fixed.
Metadata Update from @nhosoi: - Issue assigned to lkrispen - Issue set to the milestone: 1.3.4 backlog
389-ds-base is moving from Pagure to Github. This means that new issues and pull requests will be accepted only in 389-ds-base's github repository.
This issue has been cloned to Github and is available here: - https://github.com/389ds/389-ds-base/issues/661
If you want to receive further updates on the issue, please navigate to the github issue and click on subscribe button.
subscribe
Thank you for understanding. We apologize for all inconvenience.
Metadata Update from @spichugi: - Issue close_status updated to: wontfix (was: Fixed)
Login to comment on this ticket.