ACF
A: Contention for data and index blocks in a single instance database will probably magnify in a RAC environment. C: A typical cause of high latencies is when the LMS process must flush uncommitted changes to the redo log prior to sending the block to the requesting instance.If the application design is such that uncommitted blocks are often in demand across instances in the cluster then these redo log flushes might become common. F: Examining the interconnect - When Global Cache waits are high, we should first determine if the latency is primarily the result of interconnect network waits. References: http://www.toadworld.com/platforms/oracle/w/wiki/10939.optimizing-oracle-rac#rac-tuning-principles