VirtualBox

Ticket #4392 (reopened defect) — at Version 10

Opened 9 years ago

Last modified 5 years ago

Huge IO-APIC/guest SMP overhead with 32 bits guests

Reported by: rafael_chang Owned by:
Priority: major Component: VMM/HWACCM
Version: VirtualBox 3.0.6 Keywords:
Cc: Guest type: other
Host type: other

Description (last modified by sandervl73) (diff)

Symptoms are high CPU usage while running e.g. 32 bits Windows XP/2000 guests with IO-APIC enabled.

Current status:

  • fixed for AMD-V in VirtualBox 3.0.6 (requires 3.0.6 guest additions to be installed)
  • still relevant for certain Intel CPUs without the APIC access hardware optimization feature
  • Solaris/OpenSolaris guests have similar issues, but a kernel fix is underway.

Does not apply to:

  • 64 bits guests
  • 32 bits Windows Vista of Windows 7

Change History

comment:1 Changed 9 years ago by rafael_chang

noticed the following, if I disable the IOAPIC and set VCPU to 1, install goes fine and fast ...

comment:2 Changed 9 years ago by sandervl73

  • Summary changed from windows xp VM extremely slow when AMD-v is enable with 2 cpu to huge IO-APIC/guest SMP overhead with 32 bits guests (AMD-V only)

Known problem and mentioned in the manual. 32 bits guests are extremely slow with the IO-APIC enabled on AMD cpus. Will be fixed in a future release.

comment:3 Changed 9 years ago by mike.merrett@…

I can confirm this behavior on 3.0.2 on AMD Phenom, Mandriva 2009.1. I can also confirm that changing the HAL on the guest VM to Advanced Configuration and Power Interface (ACPI) PC, changing the VM properties to disable IO-APIC, single vCPU. The guest then runs quickly and without problems - but of course, single vCPU. Is there any roadmap for a fix?

The exact same VM runs fine with multiple vCPU and IOAPIC on Intel VT-x, what's the problem with AMD-V ?

comment:4 Changed 9 years ago by sandervl73

It's being worked on. Intel provides an optimization feature for APIC TPR access. AMD does not, so I have fix it myself.

comment:5 Changed 9 years ago by mike.merrett@…

Similar statements also apply to VMs running Standard PC HAL compared with MPS Multiprocessor HAL. Switching to Standard speeds it up very much with the IOAPIC turned off in the VM settings.

Do we have a possible timeline for a fix, either a whole new version of VB3 incorporating AMD-friendly technology, or a patch to 3.0.2 ?

comment:6 Changed 9 years ago by sandervl73

  • Summary changed from huge IO-APIC/guest SMP overhead with 32 bits guests (AMD-V only) to huge IO-APIC/guest SMP overhead with 32 bits guests (AMD-V only) -> fixed in SVN/3.0.6

Fixed in 3.0.6, but only after you've installed the 3.0.6 guest additions.

comment:7 Changed 9 years ago by frank

  • Status changed from new to closed
  • Resolution set to fixed

comment:8 Changed 9 years ago by mike.merrett@…

  • Status changed from closed to reopened
  • Resolution fixed deleted

Thanks for the good work on this bug. I will be testing it as soon as I can get my hands on 3.0.6.

Can I please ask you to regression-test this fix against Windows XP 64-bit Edition on AMD-V [3.0.4 crashes when Nested Paging is on, machine occasionally aborts without warning or logging an error when Nested Paging is off]. Host is 32-bit Mandriva 2009 and 2008.

Changed 9 years ago by greerga

Windows 2000 SMP under Ubuntu 9.0.4 64-bit VT-x

comment:9 Changed 9 years ago by greerga

It's not AMD-V only; my VT-x does it too, even with 3.0.6 Guest Additions installed. (See attachment.)

Windows 2000 SMP with Ubuntu 9.0.4 64-bit VT-x.

comment:10 Changed 9 years ago by sandervl73

  • Version changed from VirtualBox 3.0.0 to VirtualBox 3.0.6
  • Description modified (diff)
  • Summary changed from huge IO-APIC/guest SMP overhead with 32 bits guests (AMD-V only) -> fixed in SVN/3.0.6 to Huge IO-APIC/guest SMP overhead with 32 bits guests

mike: please don't mention unrelated problems in this defect. If you still see this xp64 abort with 3.0.6, then open another defect with a proper description and VBox.log.

greerga: your Intel CPU doesn't support the APIC access optimization. I intend to enable the same fix once we get more feedback about AMD-V.

Note: See TracTickets for help on using tickets.

www.oracle.com
ContactPrivacy policyTerms of Use