Hi, Yong Huang schrieb: > We're using Swingbench to stress test an 8-node 10.2.0.3 RAC running on RH > Linux (2.6.9-55.ELsmp x86_64). The total non-idle active sessions is between > 200 and 300 (select count(*) from gv$session where status = 'ACTIVE' and > wait_class != 'Idle'). At this stress level, we start to see 'gc blocks lost' > statistic going up, sometimes as fast as 10 in 2 hours. > gv$cr_block_server.fail_results also goes up. in load times, my 4-node-RAC (10gR2 64bit on Linux) has between 58 and 140 lost gc blocks. I never had any troble with that. But you can decrease that number by setting the parallel_execution_message_size to a value as large as your architecture supports it. Target: 65535. Regards Martin Klier -- Usn's IT Blog for Linux, Oracle, Asterisk www.usn-it.de -- //www.freelists.org/webpage/oracle-l