similar to: [RFC, PATCH 0/24] VMI i386 Linux virtualization interface proposal

I''m sure everyone has seen the drop of VMI patches for Linux at this point, but just in case, the link is included below. I''ve read this version of the VMI spec and have made my way through most of the patches. While I wasn''t really that impressed with the first spec wrt Xen, the second version seems to be much more palatable. Specifically, the code inlining and

Hi, We ran a few experiments to compare performance of VMware's paravirtualization technique (VMI) and hardware MMU technologies (HWMMU) on VMware's hypervisor. To give some background, VMI is VMware's paravirtualization specification which tries to optimize CPU and MMU operations of the guest operating system. For more information take a look at this

Hi, We ran a few experiments to compare performance of VMware's paravirtualization technique (VMI) and hardware MMU technologies (HWMMU) on VMware's hypervisor. To give some background, VMI is VMware's paravirtualization specification which tries to optimize CPU and MMU operations of the guest operating system. For more information take a look at this

A NO_IDLE_HZ implementation is provided for i386 VMI builds. When a VCPU enters its idle loop, it disables its periodic alarm and sets up a one shot alarm for the next time event. That way, it does not become ready to run just to service the periodic alarm interrupt. Instead, it can remain halted until there is some real work pending for it. This allows the hypervisor to use the physical

A NO_IDLE_HZ implementation is provided for i386 VMI builds. When a VCPU enters its idle loop, it disables its periodic alarm and sets up a one shot alarm for the next time event. That way, it does not become ready to run just to service the periodic alarm interrupt. Instead, it can remain halted until there is some real work pending for it. This allows the hypervisor to use the physical

Master definition of VMI interface, including calls, constants, and interface version. Signed-off-by: Zachary Amsden <zach@vmware.com> Index: linux-2.6.16-rc5/include/asm-i386/mach-vmi/paravirtualInterface.h =================================================================== --- linux-2.6.16-rc5.orig/include/asm-i386/mach-vmi/paravirtualInterface.h 2006-03-08 10:08:45.000000000 -0800 +++

Master definition of VMI interface, including calls, constants, and interface version. Signed-off-by: Zachary Amsden <zach@vmware.com> Index: linux-2.6.16-rc5/include/asm-i386/mach-vmi/paravirtualInterface.h =================================================================== --- linux-2.6.16-rc5.orig/include/asm-i386/mach-vmi/paravirtualInterface.h 2006-03-08 10:08:45.000000000 -0800 +++

Macros to use VMI calls from assembly and C languages are introduced. The macros are quite complex, but the end result is rather impressive. The result is that when compiling a VMI kernel, the native code is emitted inline, with no function call overhead, and some wiggle room for register allocation. The hypervisor compatibility code is emitted out of line into a separate section, and patched

Macros to use VMI calls from assembly and C languages are introduced. The macros are quite complex, but the end result is rather impressive. The result is that when compiling a VMI kernel, the native code is emitted inline, with no function call overhead, and some wiggle room for register allocation. The hypervisor compatibility code is emitted out of line into a separate section, and patched

SMP bootstrapping support. Just as in the physical platform model, the BSP is responsible for initializing the AP state prior to execution. The dependence on lots of processor state information is a design choice of our implementation. Conceivably, this could be a hypercall that awakens the same start of day state on APs as on the BSP. It is likely the AP startup and the start-of-day model will

SMP bootstrapping support. Just as in the physical platform model, the BSP is responsible for initializing the AP state prior to execution. The dependence on lots of processor state information is a design choice of our implementation. Conceivably, this could be a hypercall that awakens the same start of day state on APs as on the BSP. It is likely the AP startup and the start-of-day model will

(Unless there are complaints, I'll push this as part of the lguest patches for 2.6.24, since there are lguest config changes there too). Andi points out that PARAVIRT is an option best selected when needed. We introduce PARAVIRT_GUEST for the menu itself, and select PARAVIRT if the user turns on anything which needs it. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> ---

(Unless there are complaints, I'll push this as part of the lguest patches for 2.6.24, since there are lguest config changes there too). Andi points out that PARAVIRT is an option best selected when needed. We introduce PARAVIRT_GUEST for the menu itself, and select PARAVIRT if the user turns on anything which needs it. Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> ---

The VMI ROM detection and code patching mechanism is illustrated in setup.c. There ROM is a binary block published by the hypervisor, and and there are certainly implications of this. ROMs certainly have a history of being proprietary, very differently licensed pieces of software, and mostly under non-free licenses. Before jumping to the conclusion that this is a bad thing, let us consider more

The VMI ROM detection and code patching mechanism is illustrated in setup.c. There ROM is a binary block published by the hypervisor, and and there are certainly implications of this. ROMs certainly have a history of being proprietary, very differently licensed pieces of software, and mostly under non-free licenses. Before jumping to the conclusion that this is a bad thing, let us consider more

Introduce the basic VMI sub-arch configuration dependencies. VMI kernels only are designed to run on modern hardware platforms. As such, they require a working APIC, and do not support some legacy functionality, including APM BIOS, ISA and MCA bus systems, PCI BIOS interfaces, or PnP BIOS (by implication of dropping ISA support). They also require a P6 series CPU. Signed-off-by: Zachary Amsden

Introduce the basic VMI sub-arch configuration dependencies. VMI kernels only are designed to run on modern hardware platforms. As such, they require a working APIC, and do not support some legacy functionality, including APM BIOS, ISA and MCA bus systems, PCI BIOS interfaces, or PnP BIOS (by implication of dropping ISA support). They also require a P6 series CPU. Signed-off-by: Zachary Amsden

At OLS I gave a talk on some of the Xen scalability inhibitors, and one of these was writable page tables. We went over why the feature does not scale, but just as important, we found that the uniprocessor case does not provide any advantage either. These tests were done on x86_64, so I wanted to run the 1-way test on 32 bit to show the same problem. So, I have run with writable PTs and

Seems to work OK for native and Xen. I had to play a bit with the paravirt-sched-clock patch to deal with the VMI changes. Zach, can you check that it still works? Thanks, J

Seems to work OK for native and Xen. I had to play a bit with the paravirt-sched-clock patch to deal with the VMI changes. Zach, can you check that it still works? Thanks, J