[ https://issues.apache.org/jira/browse/FLINK-32213?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Weijie Guo closed FLINK-32213. ------------------------------ Fix Version/s: 1.18.0 Resolution: Done master(1.18) via 81cab8f486997ef666128cce4903c24d44ac7534. > Add get off heap buffer in memory segment > ----------------------------------------- > > Key: FLINK-32213 > URL: https://issues.apache.org/jira/browse/FLINK-32213 > Project: Flink > Issue Type: Improvement > Components: Runtime / Task > Affects Versions: 1.18.0 > Reporter: Fang Yong > Assignee: Fang Yong > Priority: Major > Labels: pull-request-available > Fix For: 1.18.0 > > > When flink job writes data to data lake such as paimon, iceberg and hudi, the > sink will write data to writer buffer first, then flush the data to file > system. To manage the writer buffer better, we'd like to allocate segment > from managed memory in flink and get off heap buffer to create writer buffer -- This message was sent by Atlassian Jira (v8.20.10#820010)