The key to implement VMM protection is the generation of the
page fault events and the detection of their types.
Once the VM is resumed on the target,
page faults would happen when memory access dirtied page; it can be serviced by requesting the referenced page over the network from the source node.
Once the VM resumes at the target, its memory accesses result in
page faults that can be serviced by requesting the referenced page over the network from the source node.
During this
page fault, the home SMP consults the page directory as usual.
The simulation output is composed by total simulation time, number of memory accesses, number of
page faults, and execution space time product.
CVM first vectors
page fault requests to the tape protocol, providing an opportunity to search the queue for a tape that contains the requested page.
For example, in addition to stating that the optimized
Page Fault path must not exceed 8,000 instructions, it might have been beneficial to break this number down into the maximum allowed contribution from the various subsystems used along the
Page Fault path.
Short-running services such as the quick
page fault handler (QUICK-FAULT), where the trap overhead itself is a significant portion of the service, show slowdowns over a factor of 3.
An asterisk (*) indicates that the reference required the page to be fetched into M or M', .i.e., that a
page fault occurred on the reference.
Four bits are used to record program traps (e.g., trace trap, illegal operation), and four more to record system trap types (memory error,
page fault, etc.).
* Memory usage (page files, swap file,
page faults, etc.)
Weighing in at a mere 400Kb, this version also incorporates a full memory-monitoring tool covering everything from virtual memory usage of individual programs to system
page faults. An integrated cache wizard helps to further tune memory performance and make Memory+ the most complete memory management product available.
