The issue is described bellow:

        When running Windows Vista ultimate in a domain with two vcpus, and then do a heavy disk IO in domain0, the Vista will blue screen with such message "a clock interrupt was not received on a secondary processor within the allocated time interval" with Bug Check 0x101.

This bug can always be reproduced by running the memory testing from Linux Performance Testing suite in domain 0. Note: domain 0 must use the hard disk as swap place.

I need some helps from Linux expert.

1.      Why the system is very slow when you access the hard disk frequently under Linux?

2.      Does it allowed to preempt when do disk i/o access from 2.6.18 Linux kernel?

3.      The detailed process of disk I/O handler under Linux. The interrupt status, the cpu status and buffer lock.