Hello,
I'm having a hard time trying to find information related to timer interrupt delivery modes in ¨VMware.
At the moment that a virtual machine should generate a virtual timer interrupt, it might not actually be running. Thus, and according to "Timekeeping in VMware Virtual Machines" document, timer interrupts are buffered in a backlog and are delivered whenever it is possible. Timer interrupts are delivered at a higher rate whenever the backlog grows too large, in order to catch up.
In page 30 of the documented mentioned above, it is stated that there are different modes in which interrupts are delivered:
- Mode 0—aggressive interrupt delivery. This is the normal mode.
- Mode 1—smooth interrupt delivery. This special mode spaces interrupts out more. It is used for certain older guest operating systems that might have fragile interrupt handling code.
- Mode 2—smooth interrupt delivery, with catch-up currently in progress.
- Mode 3—lazy interrupt delivery. This is useful for tickless guest operating systems.
- Mode 4—timer calibration mode. This is used briefly while a Linux guest operating system is calibrating timers during boot
I would like to know if it is possible to force the virtual machine to behave in one of the above modes. If so, which configuration file and how should I modify?
Thanks in advanced.
