[ https://issues.apache.org/jira/browse/CASSANDRA-15097?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16886404#comment-16886404 ]
Jay Zhuang commented on CASSANDRA-15097: ---------------------------------------- Add dTest results: | Branch | uTest | jvm-dTest | dTest | dTest vnode | | [15097-3.0|https://github.com/instagram/cassandra/tree/15097-3.0] | [#66 passed |https://circleci.com/gh/Instagram/cassandra/66] | [#67 passed|https://circleci.com/gh/Instagram/cassandra/67] | [#75 failed|https://circleci.com/gh/Instagram/cassandra/75], passed locally: CASSANDRA-14595 | [#74 failed | https://circleci.com/gh/Instagram/cassandra/74], passed locally: CASSANDRA-14595 | | [15097-3.11|https://github.com/instagram/cassandra/tree/15097-3.11] | [#69 passed|https://circleci.com/gh/Instagram/cassandra/69] | [#68 passed|https://circleci.com/gh/Instagram/cassandra/68] | [#77 failed|https://circleci.com/gh/Instagram/cassandra/77], passed locally: CASSANDRA-14595 | [#76 failed|https://circleci.com/gh/Instagram/cassandra/76], passed locally: CASSANDRA-14595 | | [15097-trunk|https://github.com/instagram/cassandra/tree/15097-trunk] | [#72 passed|https://circleci.com/gh/Instagram/cassandra/72] | [#73 passed|https://circleci.com/gh/Instagram/cassandra/73] | [#78 passed|https://circleci.com/gh/Instagram/cassandra/78] | [#79 failed|https://circleci.com/gh/Instagram/cassandra/79], passed locally| All failed dtests are passed locally with 10x run: {{$ pytest --count=10 --cassandra-dir=~/cassandra $TESTS}} > Avoid updating unchanged gossip state > ------------------------------------- > > Key: CASSANDRA-15097 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15097 > Project: Cassandra > Issue Type: Bug > Components: Cluster/Gossip > Reporter: Jay Zhuang > Assignee: Jay Zhuang > Priority: Normal > > The node might get unchanged gossip states, the state might be just updated > after sending a GOSSIP_SYN, then it will get the state that is already up to > date. If the heartbeat in the GOSSIP_ACK message is updated, it will > unnecessary re-apply the same state again, which could be costly like > updating token change. > It's very likely to happen for large cluster when a node startup, as the > first gossip message will sync all endpoints tokens, it could take some time > (in our case about 200 seconds), during that time, it keeps gossip with other > node and get the full token states. Which causes lots of pending gossip tasks. -- This message was sent by Atlassian JIRA (v7.6.14#76016) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org