[ https://issues.apache.org/jira/browse/HDFS-6036?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Colin Patrick McCabe updated HDFS-6036: --------------------------------------- Attachment: HDFS-6036.001.patch This patch implements revocation of mlocked areas after enough time has elapsed. Now a misbehaving client can no longer block the munlock indefinitely. I added a new test, TestFsDatasetCacheRevocation. It uses a somewhat different configuration from the other tests, so it needed to be separate (the others have a fixed config set up in the Before sections). > Forcibly timeout misbehaving DFSClients that try to do no-checksum reads that > extend too long > --------------------------------------------------------------------------------------------- > > Key: HDFS-6036 > URL: https://issues.apache.org/jira/browse/HDFS-6036 > Project: Hadoop HDFS > Issue Type: Sub-task > Components: caching, datanode > Affects Versions: 2.5.0 > Reporter: Colin Patrick McCabe > Assignee: Colin Patrick McCabe > Attachments: HDFS-6036.001.patch > > > We should forcibly timeout misbehaving DFSClients that try to do no-checksum > reads that extend too long. -- This message was sent by Atlassian JIRA (v6.2#6252)