Hi Saeid, I think it may be had a long time interval between ScanRequest. Setting the parameter --scanner_ttl_ms(default 60s) larger may solve the problem.
Yao 2018-05-17 17:36 GMT+08:00 Saeid Sattari <saeid.satt...@gmail.com>: > Hi all, > > Lately, I have a critical problem with Kudu cluster (V1.6). For most of > the queries submitted by Impala (even very simple and light one) > regularly encountered with the following error. There are 120 datanode in > my cluster and changed following parameters on datanodes: > > unlock_experimental_flags=true > rpc_service_queue_length=15000 > rpc_acceptor_listen_backlog=1024 > > The error: > >> WARNINGS: Unable to advance iterator: Timed out: Scan RPC to >> 172.18.77.131:7050 timed out after 0.000s (SENT): Not found: Scanner not >> found > > > Any hints and tips are appreciated. Thank you in advance. > > Best, > Saeid >
