Meng Zhu created MESOS-9647: ------------------------------- Summary: Improve subscriber scalability. Key: MESOS-9647 URL: https://issues.apache.org/jira/browse/MESOS-9647 Project: Mesos Issue Type: Improvement Reporter: Meng Zhu
Current there is no batching for serving the subscribe requests. And constructing and generating the initial GET_STATE message is very expensive due to evolving and etc. Three perf traces are uploaded: During a scale test, we tested the scalability of concurrent subscribers. Three perf traces are collected: mesos-master_ui_p1.stacks.gz // baseline mesos-master_ui_p10.stacks.gz // added 10 more subscribers mesos-master_ui_p19.stacks.gz // add 19 subscribers At 19, slowness and timeouts are reported: "having a tough time getting a response from /mesos/api/v1?subscribe" "73s/100MB response time, now getting timeouts (504)" -- This message was sent by Atlassian JIRA (v7.6.3#76005)