[ https://issues.apache.org/jira/browse/CASSANDRA-9738?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14709670#comment-14709670 ]
Ariel Weisberg commented on CASSANDRA-9738: ------------------------------------------- For reading a string there is no reason not to use the last bit and allow strings 65k strings. It also doesn't throw if the length is too large. I really would like to get to the one true string reading/writing path if possible. So we can put together one good implementation and also to optimize icache. To allocate or pool temporary buffers is kind of a question of how allocation bound you are. I think the answer for C* right now is very. Is it feasible to share the same pooling buffer for both the key serialization and value serialization? Maybe a little finicky given that size is sometimes retrieved in an order that is different from the order they are serialized in. > Migrate key-cache to be fully off-heap > -------------------------------------- > > Key: CASSANDRA-9738 > URL: https://issues.apache.org/jira/browse/CASSANDRA-9738 > Project: Cassandra > Issue Type: Sub-task > Reporter: Robert Stupp > Assignee: Robert Stupp > Fix For: 3.0 beta 2 > > > Key cache still uses a concurrent map on-heap. This could go to off-heap and > feels doable now after CASSANDRA-8099. > Evaluation should be done in advance based on a POC to prove that pure > off-heap counter cache buys a performance and/or gc-pressure improvement. > In theory, elimination of on-heap management of the map should buy us some > benefit. -- This message was sent by Atlassian JIRA (v6.3.4#6332)