Re: Poor performance with large keys using RocksDB and MapState

Cc: user@flink.apache.org Subject: Re: Poor performance with large keys using RocksDB and MapState Thanks Yun!, I used this option, and it greatly helped 2:44<https://xmcyber.slack.com/archives/DP2KLMWUX/p1600947862026600> val be = new RocksDBStateBackend("file:///tmp&qu

Re: Poor performance with large keys using RocksDB and MapState

gt; [1] > https://github.com/dataArtisans/frocksdb/blob/c724d41fab7f9f09f9676dfccc6d210a191da4d6/options/options.cc#L477 > [2] https://issues.apache.org/jira/browse/FLINK-17800 > > Best > Yun Tang > > > -- > *From:* ירון שני > *Sent:* Wednesday, September 23, 2020 23:56 >

Re: Poor performance with large keys using RocksDB and MapState

://issues.apache.org/jira/browse/FLINK-17800 Best Yun Tang From: ירון שני Sent: Wednesday, September 23, 2020 23:56 To: user@flink.apache.org Subject: Poor performance with large keys using RocksDB and MapState Hello, I have a poor throughput issue, and I think I

Poor performance with large keys using RocksDB and MapState

Hello, I have a poor throughput issue, and I think I managed to reproduce it using the following code: val conf = new Configuration() conf.set(TaskManagerOptions.MANAGED_MEMORY_SIZE, MemorySize.ofMebiBytes(6 * 1000)) conf.set(TaskManagerOptions.TOTAL_PROCESS_MEMORY, MemorySize.ofMebiBytes(8 * 1000